From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/tools/perf/builtin-top.c | 697 ++++++++++++++++++++++++++++++++++++++++------------------
1 files changed, 480 insertions(+), 217 deletions(-)
diff --git a/kernel/tools/perf/builtin-top.c b/kernel/tools/perf/builtin-top.c
index 9caab84..ee30372 100644
--- a/kernel/tools/perf/builtin-top.c
+++ b/kernel/tools/perf/builtin-top.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* builtin-top.c
*
@@ -14,38 +15,45 @@
* Wu Fengguang <fengguang.wu@intel.com>
* Mike Galbraith <efault@gmx.de>
* Paul Mackerras <paulus@samba.org>
- *
- * Released under the GPL v2. (and only v2, not any later version)
*/
#include "builtin.h"
#include "perf.h"
#include "util/annotate.h"
+#include "util/bpf-event.h"
#include "util/config.h"
#include "util/color.h"
-#include "util/drv_configs.h"
+#include "util/dso.h"
#include "util/evlist.h"
#include "util/evsel.h"
+#include "util/evsel_config.h"
#include "util/event.h"
#include "util/machine.h"
+#include "util/map.h"
+#include "util/mmap.h"
#include "util/session.h"
-#include "util/symbol.h"
#include "util/thread.h"
-#include "util/thread_map.h"
+#include "util/symbol.h"
+#include "util/synthetic-events.h"
#include "util/top.h"
+#include "util/util.h"
#include <linux/rbtree.h>
#include <subcmd/parse-options.h>
#include "util/parse-events.h"
+#include "util/callchain.h"
#include "util/cpumap.h"
-#include "util/xyarray.h"
#include "util/sort.h"
+#include "util/string2.h"
#include "util/term.h"
#include "util/intlist.h"
#include "util/parse-branch-options.h"
#include "arch/common.h"
+#include "ui/ui.h"
#include "util/debug.h"
+#include "util/ordered-events.h"
+#include "util/pfm.h"
#include <assert.h>
#include <elf.h>
@@ -73,8 +81,10 @@
#include <linux/stringify.h>
#include <linux/time64.h>
#include <linux/types.h>
+#include <linux/err.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <perf/mmap.h>
static volatile int done;
static volatile int resize;
@@ -99,7 +109,7 @@
static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
struct symbol *sym;
struct annotation *notes;
struct map *map;
@@ -127,7 +137,7 @@
notes = symbol__annotation(sym);
pthread_mutex_lock(¬es->lock);
- if (!symbol__hists(sym, top->evlist->nr_entries)) {
+ if (!symbol__hists(sym, top->evlist->core.nr_entries)) {
pthread_mutex_unlock(¬es->lock);
pr_err("Not enough memory for annotating '%s' symbol!\n",
sym->name);
@@ -135,12 +145,12 @@
return err;
}
- err = symbol__annotate(sym, map, evsel, 0, &top->annotation_opts, NULL);
+ err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL);
if (err == 0) {
top->sym_filter_entry = he;
} else {
char msg[BUFSIZ];
- symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
+ symbol__strerror_disassemble(&he->ms, err, msg, sizeof(msg));
pr_err("Couldn't annotate %s: %s\n", sym->name, msg);
}
@@ -184,7 +194,7 @@
static void perf_top__record_precise_ip(struct perf_top *top,
struct hist_entry *he,
struct perf_sample *sample,
- struct perf_evsel *evsel, u64 ip)
+ struct evsel *evsel, u64 ip)
{
struct annotation *notes;
struct symbol *sym = he->ms.sym;
@@ -226,7 +236,7 @@
static void perf_top__show_details(struct perf_top *top)
{
struct hist_entry *he = top->sym_filter_entry;
- struct perf_evsel *evsel;
+ struct evsel *evsel;
struct annotation *notes;
struct symbol *symbol;
int more;
@@ -246,10 +256,10 @@
if (notes->src == NULL)
goto out_unlock;
- printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name);
+ printf("Showing %s for %s\n", evsel__name(top->sym_evsel), symbol->name);
printf(" Events Pcnt (>=%d%%)\n", top->annotation_opts.min_pcnt);
- more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel, &top->annotation_opts);
+ more = symbol__annotate_printf(&he->ms, top->sym_evsel, &top->annotation_opts);
if (top->evlist->enabled) {
if (top->zero)
@@ -263,20 +273,57 @@
pthread_mutex_unlock(¬es->lock);
}
+static void perf_top__resort_hists(struct perf_top *t)
+{
+ struct evlist *evlist = t->evlist;
+ struct evsel *pos;
+
+ evlist__for_each_entry(evlist, pos) {
+ struct hists *hists = evsel__hists(pos);
+
+ /*
+ * unlink existing entries so that they can be linked
+ * in a correct order in hists__match() below.
+ */
+ hists__unlink(hists);
+
+ if (evlist->enabled) {
+ if (t->zero) {
+ hists__delete_entries(hists);
+ } else {
+ hists__decay_entries(hists, t->hide_user_symbols,
+ t->hide_kernel_symbols);
+ }
+ }
+
+ hists__collapse_resort(hists, NULL);
+
+ /* Non-group events are considered as leader */
+ if (symbol_conf.event_group && !evsel__is_group_leader(pos)) {
+ struct hists *leader_hists = evsel__hists(pos->leader);
+
+ hists__match(leader_hists, hists);
+ hists__link(leader_hists, hists);
+ }
+ }
+
+ evlist__for_each_entry(evlist, pos) {
+ evsel__output_resort(pos, NULL);
+ }
+}
+
static void perf_top__print_sym_table(struct perf_top *top)
{
char bf[160];
int printed = 0;
const int win_width = top->winsize.ws_col - 1;
- struct perf_evsel *evsel = top->sym_evsel;
+ struct evsel *evsel = top->sym_evsel;
struct hists *hists = evsel__hists(evsel);
puts(CONSOLE_CLEAR);
perf_top__header_snprintf(top, bf, sizeof(bf));
printf("%s\n", bf);
-
- perf_top__reset_sample_counters(top);
printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
@@ -296,17 +343,7 @@
return;
}
- if (top->evlist->enabled) {
- if (top->zero) {
- hists__delete_entries(hists);
- } else {
- hists__decay_entries(hists, top->hide_user_symbols,
- top->hide_kernel_symbols);
- }
- }
-
- hists__collapse_resort(hists, NULL);
- perf_evsel__output_resort(evsel, NULL);
+ perf_top__resort_hists(top);
hists__output_recalc_col_len(hists, top->print_entries - printed);
putchar('\n');
@@ -371,7 +408,7 @@
if (p)
*p = 0;
- next = rb_first(&hists->entries);
+ next = rb_first_cached(&hists->entries);
while (next) {
n = rb_entry(next, struct hist_entry, rb_node);
if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) {
@@ -404,8 +441,8 @@
fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", top->delay_secs);
fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top->print_entries);
- if (top->evlist->nr_entries > 1)
- fprintf(stdout, "\t[E] active event counter. \t(%s)\n", perf_evsel__name(top->sym_evsel));
+ if (top->evlist->core.nr_entries > 1)
+ fprintf(stdout, "\t[E] active event counter. \t(%s)\n", evsel__name(top->sym_evsel));
fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter);
@@ -439,7 +476,7 @@
case 'S':
return 1;
case 'E':
- return top->evlist->nr_entries > 1 ? 1 : 0;
+ return top->evlist->core.nr_entries > 1 ? 1 : 0;
default:
break;
}
@@ -485,20 +522,20 @@
}
break;
case 'E':
- if (top->evlist->nr_entries > 1) {
+ if (top->evlist->core.nr_entries > 1) {
/* Select 0 as the default event: */
int counter = 0;
fprintf(stderr, "\nAvailable events:");
evlist__for_each_entry(top->evlist, top->sym_evsel)
- fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
+ fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, evsel__name(top->sym_evsel));
prompt_integer(&counter, "Enter details event counter");
- if (counter >= top->evlist->nr_entries) {
- top->sym_evsel = perf_evlist__first(top->evlist);
- fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel));
+ if (counter >= top->evlist->core.nr_entries) {
+ top->sym_evsel = evlist__first(top->evlist);
+ fprintf(stderr, "Sorry, no such event, using %s.\n", evsel__name(top->sym_evsel));
sleep(1);
break;
}
@@ -506,7 +543,7 @@
if (top->sym_evsel->idx == counter)
break;
} else
- top->sym_evsel = perf_evlist__first(top->evlist);
+ top->sym_evsel = evlist__first(top->evlist);
break;
case 'f':
prompt_integer(&top->count_filter, "Enter display event count filter");
@@ -554,32 +591,25 @@
static void perf_top__sort_new_samples(void *arg)
{
struct perf_top *t = arg;
- struct perf_evsel *evsel = t->sym_evsel;
- struct hists *hists;
-
- perf_top__reset_sample_counters(t);
if (t->evlist->selected != NULL)
t->sym_evsel = t->evlist->selected;
- hists = evsel__hists(evsel);
+ perf_top__resort_hists(t);
- if (t->evlist->enabled) {
- if (t->zero) {
- hists__delete_entries(hists);
- } else {
- hists__decay_entries(hists, t->hide_user_symbols,
- t->hide_kernel_symbols);
- }
- }
+ if (t->lost || t->drop)
+ pr_warning("Too slow to read ring buffer (change period (-c/-F) or limit CPUs (-C)\n");
+}
- hists__collapse_resort(hists, NULL);
- perf_evsel__output_resort(evsel, NULL);
+static void stop_top(void)
+{
+ session_done = 1;
+ done = 1;
}
static void *display_thread_tui(void *arg)
{
- struct perf_evsel *pos;
+ struct evsel *pos;
struct perf_top *top = arg;
const char *help = "For a higher level overview, try: perf top --sort comm,dso";
struct hist_browser_timer hbt = {
@@ -587,6 +617,7 @@
.arg = top,
.refresh = top->delay_secs,
};
+ int ret;
/* In order to read symbols from other namespaces perf to needs to call
* setns(2). This isn't permitted if the struct_fs has multiple users.
@@ -595,11 +626,14 @@
*/
unshare(CLONE_FS);
+ prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0);
+
+repeat:
perf_top__sort_new_samples(top);
/*
* Initialize the uid_filter_str, in the future the TUI will allow
- * Zooming in/out UIDs. For now juse use whatever the user passed
+ * Zooming in/out UIDs. For now just use whatever the user passed
* via --uid.
*/
evlist__for_each_entry(top->evlist, pos) {
@@ -607,19 +641,24 @@
hists->uid_filter_str = top->record_opts.target.uid_str;
}
- perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+ ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
top->min_percent,
&top->session->header.env,
!top->record_opts.overwrite,
&top->annotation_opts);
- done = 1;
+ if (ret == K_RELOAD) {
+ top->zero = true;
+ goto repeat;
+ } else
+ stop_top();
+
return NULL;
}
static void display_sig(int sig __maybe_unused)
{
- done = 1;
+ stop_top();
}
static void display_setup_sig(void)
@@ -644,6 +683,8 @@
* that we're observing.
*/
unshare(CLONE_FS);
+
+ prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0);
display_setup_sig();
pthread__unblock_sigwinch();
@@ -674,7 +715,7 @@
if (perf_top__handle_keypress(top, c))
goto repeat;
- done = 1;
+ stop_top();
}
}
@@ -688,19 +729,20 @@
{
struct perf_top *top = arg;
struct hist_entry *he = iter->he;
- struct perf_evsel *evsel = iter->evsel;
+ struct evsel *evsel = iter->evsel;
if (perf_hpp_list.sym && single)
perf_top__record_precise_ip(top, he, iter->sample, evsel, al->addr);
hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
- !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY));
+ !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY),
+ NULL);
return 0;
}
static void perf_event__process_sample(struct perf_tool *tool,
const union perf_event *event,
- struct perf_evsel *evsel,
+ struct evsel *evsel,
struct perf_sample *sample,
struct machine *machine)
{
@@ -734,13 +776,16 @@
if (machine__resolve(machine, &al, sample) < 0)
return;
+ if (top->stitch_lbr)
+ al.thread->lbr_stitch_enable = true;
+
if (!machine->kptr_restrict_warned &&
symbol_conf.kptr_restrict &&
al.cpumode == PERF_RECORD_MISC_KERNEL) {
if (!perf_evlist__exclude_kernel(top->session->evlist)) {
ui__warning(
"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
-"Check /proc/sys/kernel/kptr_restrict.\n\n"
+"Check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n"
"Kernel%s samples will not be resolved.\n",
al.map && map__has_symbols(al.map) ?
" modules" : "");
@@ -806,108 +851,82 @@
addr_location__put(&al);
}
+static void
+perf_top__process_lost(struct perf_top *top, union perf_event *event,
+ struct evsel *evsel)
+{
+ struct hists *hists = evsel__hists(evsel);
+
+ top->lost += event->lost.lost;
+ top->lost_total += event->lost.lost;
+ hists->stats.total_lost += event->lost.lost;
+}
+
+static void
+perf_top__process_lost_samples(struct perf_top *top,
+ union perf_event *event,
+ struct evsel *evsel)
+{
+ struct hists *hists = evsel__hists(evsel);
+
+ top->lost += event->lost_samples.lost;
+ top->lost_total += event->lost_samples.lost;
+ hists->stats.total_lost_samples += event->lost_samples.lost;
+}
+
+static u64 last_timestamp;
+
static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
{
struct record_opts *opts = &top->record_opts;
- struct perf_evlist *evlist = top->evlist;
- struct perf_sample sample;
- struct perf_evsel *evsel;
- struct perf_mmap *md;
- struct perf_session *session = top->session;
+ struct evlist *evlist = top->evlist;
+ struct mmap *md;
union perf_event *event;
- struct machine *machine;
- int ret;
md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
- if (perf_mmap__read_init(md) < 0)
+ if (perf_mmap__read_init(&md->core) < 0)
return;
- while ((event = perf_mmap__read_event(md)) != NULL) {
- ret = perf_evlist__parse_sample(evlist, event, &sample);
- if (ret) {
- pr_err("Can't parse sample, err = %d\n", ret);
- goto next_event;
+ while ((event = perf_mmap__read_event(&md->core)) != NULL) {
+ int ret;
+
+ ret = perf_evlist__parse_sample_timestamp(evlist, event, &last_timestamp);
+ if (ret && ret != -1)
+ break;
+
+ ret = ordered_events__queue(top->qe.in, event, last_timestamp, 0);
+ if (ret)
+ break;
+
+ perf_mmap__consume(&md->core);
+
+ if (top->qe.rotate) {
+ pthread_mutex_lock(&top->qe.mutex);
+ top->qe.rotate = false;
+ pthread_cond_signal(&top->qe.cond);
+ pthread_mutex_unlock(&top->qe.mutex);
}
-
- evsel = perf_evlist__id2evsel(session->evlist, sample.id);
- assert(evsel != NULL);
-
- if (event->header.type == PERF_RECORD_SAMPLE)
- ++top->samples;
-
- switch (sample.cpumode) {
- case PERF_RECORD_MISC_USER:
- ++top->us_samples;
- if (top->hide_user_symbols)
- goto next_event;
- machine = &session->machines.host;
- break;
- case PERF_RECORD_MISC_KERNEL:
- ++top->kernel_samples;
- if (top->hide_kernel_symbols)
- goto next_event;
- machine = &session->machines.host;
- break;
- case PERF_RECORD_MISC_GUEST_KERNEL:
- ++top->guest_kernel_samples;
- machine = perf_session__find_machine(session,
- sample.pid);
- break;
- case PERF_RECORD_MISC_GUEST_USER:
- ++top->guest_us_samples;
- /*
- * TODO: we don't process guest user from host side
- * except simple counting.
- */
- goto next_event;
- default:
- if (event->header.type == PERF_RECORD_SAMPLE)
- goto next_event;
- machine = &session->machines.host;
- break;
- }
-
-
- if (event->header.type == PERF_RECORD_SAMPLE) {
- perf_event__process_sample(&top->tool, event, evsel,
- &sample, machine);
- } else if (event->header.type < PERF_RECORD_MAX) {
- hists__inc_nr_events(evsel__hists(evsel), event->header.type);
- machine__process_event(machine, event, &sample);
- } else
- ++session->evlist->stats.nr_unknown_events;
-next_event:
- perf_mmap__consume(md);
}
- perf_mmap__read_done(md);
+ perf_mmap__read_done(&md->core);
}
static void perf_top__mmap_read(struct perf_top *top)
{
bool overwrite = top->record_opts.overwrite;
- struct perf_evlist *evlist = top->evlist;
- unsigned long long start, end;
+ struct evlist *evlist = top->evlist;
int i;
- start = rdclock();
if (overwrite)
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING);
- for (i = 0; i < top->evlist->nr_mmaps; i++)
+ for (i = 0; i < top->evlist->core.nr_mmaps; i++)
perf_top__mmap_read_idx(top, i);
if (overwrite) {
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
}
- end = rdclock();
-
- if ((end - start) > (unsigned long long)top->delay_secs * NSEC_PER_SEC)
- ui__warning("Too slow to read ring buffer.\n"
- "Please try increasing the period (-c) or\n"
- "decreasing the freq (-F) or\n"
- "limiting the number of CPUs (-C)\n");
}
/*
@@ -930,17 +949,17 @@
static int perf_top__overwrite_check(struct perf_top *top)
{
struct record_opts *opts = &top->record_opts;
- struct perf_evlist *evlist = top->evlist;
- struct perf_evsel_config_term *term;
+ struct evlist *evlist = top->evlist;
+ struct evsel_config_term *term;
struct list_head *config_terms;
- struct perf_evsel *evsel;
+ struct evsel *evsel;
int set, overwrite = -1;
evlist__for_each_entry(evlist, evsel) {
set = -1;
config_terms = &evsel->config_terms;
list_for_each_entry(term, config_terms, list) {
- if (term->type == PERF_EVSEL__CONFIG_TERM_OVERWRITE)
+ if (term->type == EVSEL__CONFIG_TERM_OVERWRITE)
set = term->val.overwrite ? 1 : 0;
}
@@ -959,7 +978,7 @@
/* has term for current event */
if ((overwrite < 0) && (set >= 0)) {
/* if it's first event, set overwrite */
- if (evsel == perf_evlist__first(evlist))
+ if (evsel == evlist__first(evlist))
overwrite = set;
else
return -1;
@@ -973,21 +992,21 @@
}
static int perf_top_overwrite_fallback(struct perf_top *top,
- struct perf_evsel *evsel)
+ struct evsel *evsel)
{
struct record_opts *opts = &top->record_opts;
- struct perf_evlist *evlist = top->evlist;
- struct perf_evsel *counter;
+ struct evlist *evlist = top->evlist;
+ struct evsel *counter;
if (!opts->overwrite)
return 0;
/* only fall back when first event fails */
- if (evsel != perf_evlist__first(evlist))
+ if (evsel != evlist__first(evlist))
return 0;
evlist__for_each_entry(evlist, counter)
- counter->attr.write_backward = false;
+ counter->core.attr.write_backward = false;
opts->overwrite = false;
pr_debug2("fall back to non-overwrite mode\n");
return 1;
@@ -996,8 +1015,8 @@
static int perf_top__start_counters(struct perf_top *top)
{
char msg[BUFSIZ];
- struct perf_evsel *counter;
- struct perf_evlist *evlist = top->evlist;
+ struct evsel *counter;
+ struct evlist *evlist = top->evlist;
struct record_opts *opts = &top->record_opts;
if (perf_top__overwrite_check(top)) {
@@ -1010,8 +1029,8 @@
evlist__for_each_entry(evlist, counter) {
try_again:
- if (perf_evsel__open(counter, top->evlist->cpus,
- top->evlist->threads) < 0) {
+ if (evsel__open(counter, top->evlist->core.cpus,
+ top->evlist->core.threads) < 0) {
/*
* Specially handle overwrite fall back.
@@ -1027,20 +1046,19 @@
perf_top_overwrite_fallback(top, counter))
goto try_again;
- if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+ if (evsel__fallback(counter, errno, msg, sizeof(msg))) {
if (verbose > 0)
ui__warning("%s\n", msg);
goto try_again;
}
- perf_evsel__open_strerror(counter, &opts->target,
- errno, msg, sizeof(msg));
+ evsel__open_strerror(counter, &opts->target, errno, msg, sizeof(msg));
ui__error("%s\n", msg);
goto out_err;
}
}
- if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
+ if (evlist__mmap(evlist, opts->mmap_pages) < 0) {
ui__error("Failed to mmap with %d (%s)\n",
errno, str_error_r(errno, msg, sizeof(msg)));
goto out_err;
@@ -1054,12 +1072,7 @@
static int callchain_param__setup_sample_type(struct callchain_param *callchain)
{
- if (!perf_hpp_list.sym) {
- if (callchain->enabled) {
- ui__error("Selected -g but \"sym\" not present in --sort/-s.");
- return -EINVAL;
- }
- } else if (callchain->mode != CHAIN_NONE) {
+ if (callchain->mode != CHAIN_NONE) {
if (callchain_register_param(callchain) < 0) {
ui__error("Can't register callchain params.\n");
return -EINVAL;
@@ -1069,40 +1082,202 @@
return 0;
}
+static struct ordered_events *rotate_queues(struct perf_top *top)
+{
+ struct ordered_events *in = top->qe.in;
+
+ if (top->qe.in == &top->qe.data[1])
+ top->qe.in = &top->qe.data[0];
+ else
+ top->qe.in = &top->qe.data[1];
+
+ return in;
+}
+
+static void *process_thread(void *arg)
+{
+ struct perf_top *top = arg;
+
+ while (!done) {
+ struct ordered_events *out, *in = top->qe.in;
+
+ if (!in->nr_events) {
+ usleep(100);
+ continue;
+ }
+
+ out = rotate_queues(top);
+
+ pthread_mutex_lock(&top->qe.mutex);
+ top->qe.rotate = true;
+ pthread_cond_wait(&top->qe.cond, &top->qe.mutex);
+ pthread_mutex_unlock(&top->qe.mutex);
+
+ if (ordered_events__flush(out, OE_FLUSH__TOP))
+ pr_err("failed to process events\n");
+ }
+
+ return NULL;
+}
+
+/*
+ * Allow only 'top->delay_secs' seconds behind samples.
+ */
+static int should_drop(struct ordered_event *qevent, struct perf_top *top)
+{
+ union perf_event *event = qevent->event;
+ u64 delay_timestamp;
+
+ if (event->header.type != PERF_RECORD_SAMPLE)
+ return false;
+
+ delay_timestamp = qevent->timestamp + top->delay_secs * NSEC_PER_SEC;
+ return delay_timestamp < last_timestamp;
+}
+
+static int deliver_event(struct ordered_events *qe,
+ struct ordered_event *qevent)
+{
+ struct perf_top *top = qe->data;
+ struct evlist *evlist = top->evlist;
+ struct perf_session *session = top->session;
+ union perf_event *event = qevent->event;
+ struct perf_sample sample;
+ struct evsel *evsel;
+ struct machine *machine;
+ int ret = -1;
+
+ if (should_drop(qevent, top)) {
+ top->drop++;
+ top->drop_total++;
+ return 0;
+ }
+
+ ret = perf_evlist__parse_sample(evlist, event, &sample);
+ if (ret) {
+ pr_err("Can't parse sample, err = %d\n", ret);
+ goto next_event;
+ }
+
+ evsel = perf_evlist__id2evsel(session->evlist, sample.id);
+ assert(evsel != NULL);
+
+ if (event->header.type == PERF_RECORD_SAMPLE) {
+ if (evswitch__discard(&top->evswitch, evsel))
+ return 0;
+ ++top->samples;
+ }
+
+ switch (sample.cpumode) {
+ case PERF_RECORD_MISC_USER:
+ ++top->us_samples;
+ if (top->hide_user_symbols)
+ goto next_event;
+ machine = &session->machines.host;
+ break;
+ case PERF_RECORD_MISC_KERNEL:
+ ++top->kernel_samples;
+ if (top->hide_kernel_symbols)
+ goto next_event;
+ machine = &session->machines.host;
+ break;
+ case PERF_RECORD_MISC_GUEST_KERNEL:
+ ++top->guest_kernel_samples;
+ machine = perf_session__find_machine(session,
+ sample.pid);
+ break;
+ case PERF_RECORD_MISC_GUEST_USER:
+ ++top->guest_us_samples;
+ /*
+ * TODO: we don't process guest user from host side
+ * except simple counting.
+ */
+ goto next_event;
+ default:
+ if (event->header.type == PERF_RECORD_SAMPLE)
+ goto next_event;
+ machine = &session->machines.host;
+ break;
+ }
+
+ if (event->header.type == PERF_RECORD_SAMPLE) {
+ perf_event__process_sample(&top->tool, event, evsel,
+ &sample, machine);
+ } else if (event->header.type == PERF_RECORD_LOST) {
+ perf_top__process_lost(top, event, evsel);
+ } else if (event->header.type == PERF_RECORD_LOST_SAMPLES) {
+ perf_top__process_lost_samples(top, event, evsel);
+ } else if (event->header.type < PERF_RECORD_MAX) {
+ hists__inc_nr_events(evsel__hists(evsel), event->header.type);
+ machine__process_event(machine, event, &sample);
+ } else
+ ++session->evlist->stats.nr_unknown_events;
+
+ ret = 0;
+next_event:
+ return ret;
+}
+
+static void init_process_thread(struct perf_top *top)
+{
+ ordered_events__init(&top->qe.data[0], deliver_event, top);
+ ordered_events__init(&top->qe.data[1], deliver_event, top);
+ ordered_events__set_copy_on_queue(&top->qe.data[0], true);
+ ordered_events__set_copy_on_queue(&top->qe.data[1], true);
+ top->qe.in = &top->qe.data[0];
+ pthread_mutex_init(&top->qe.mutex, NULL);
+ pthread_cond_init(&top->qe.cond, NULL);
+}
+
static int __cmd_top(struct perf_top *top)
{
- char msg[512];
- struct perf_evsel *pos;
- struct perf_evsel_config_term *err_term;
- struct perf_evlist *evlist = top->evlist;
struct record_opts *opts = &top->record_opts;
- pthread_t thread;
+ pthread_t thread, thread_process;
int ret;
-
- top->session = perf_session__new(NULL, false, NULL);
- if (top->session == NULL)
- return -1;
if (!top->annotation_opts.objdump_path) {
ret = perf_env__lookup_objdump(&top->session->header.env,
&top->annotation_opts.objdump_path);
if (ret)
- goto out_delete;
+ return ret;
}
ret = callchain_param__setup_sample_type(&callchain_param);
if (ret)
- goto out_delete;
+ return ret;
if (perf_session__register_idle_thread(top->session) < 0)
- goto out_delete;
+ return ret;
if (top->nr_threads_synthesize > 1)
perf_set_multithreaded();
+ init_process_thread(top);
+
+ if (opts->record_namespaces)
+ top->tool.namespace_events = true;
+ if (opts->record_cgroup) {
+#ifdef HAVE_FILE_HANDLE
+ top->tool.cgroup_events = true;
+#else
+ pr_err("cgroup tracking is not supported.\n");
+ return -1;
+#endif
+ }
+
+ ret = perf_event__synthesize_bpf_events(top->session, perf_event__process,
+ &top->session->machines.host,
+ &top->record_opts);
+ if (ret < 0)
+ pr_debug("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n");
+
+ ret = perf_event__synthesize_cgroups(&top->tool, perf_event__process,
+ &top->session->machines.host);
+ if (ret < 0)
+ pr_debug("Couldn't synthesize cgroup events.\n");
+
machine__synthesize_threads(&top->session->machines.host, &opts->target,
- top->evlist->threads, false,
- opts->proc_map_timeout,
+ top->evlist->core.threads, false,
top->nr_threads_synthesize);
if (top->nr_threads_synthesize > 1)
@@ -1110,21 +1285,18 @@
if (perf_hpp_list.socket) {
ret = perf_env__read_cpu_topology_map(&perf_env);
- if (ret < 0)
- goto out_err_cpu_topo;
+ if (ret < 0) {
+ char errbuf[BUFSIZ];
+ const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
+
+ ui__error("Could not read the CPU topology map: %s\n", err);
+ return ret;
+ }
}
ret = perf_top__start_counters(top);
if (ret)
- goto out_delete;
-
- ret = perf_evlist__apply_drv_configs(evlist, &pos, &err_term);
- if (ret) {
- pr_err("failed to set config \"%s\" on event %s with %d (%s)\n",
- err_term->val.drv_cfg, perf_evsel__name(pos), errno,
- str_error_r(errno, msg, sizeof(msg)));
- goto out_delete;
- }
+ return ret;
top->session->evlist = top->evlist;
perf_session__set_id_hdr_size(top->session);
@@ -1138,18 +1310,18 @@
* so leave the check here.
*/
if (!target__none(&opts->target))
- perf_evlist__enable(top->evlist);
-
- /* Wait for a minimal set of events before starting the snapshot */
- perf_evlist__poll(top->evlist, 100);
-
- perf_top__mmap_read(top);
+ evlist__enable(top->evlist);
ret = -1;
+ if (pthread_create(&thread_process, NULL, process_thread, top)) {
+ ui__error("Could not create process thread.\n");
+ return ret;
+ }
+
if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
display_thread), top)) {
ui__error("Could not create display thread.\n");
- goto out_delete;
+ goto out_join_thread;
}
if (top->realtime_prio) {
@@ -1162,13 +1334,18 @@
}
}
+ /* Wait for a minimal set of events before starting the snapshot */
+ evlist__poll(top->evlist, 100);
+
+ perf_top__mmap_read(top);
+
while (!done) {
u64 hits = top->samples;
perf_top__mmap_read(top);
if (opts->overwrite || (hits == top->samples))
- ret = perf_evlist__poll(top->evlist, 100);
+ ret = evlist__poll(top->evlist, 100);
if (resize) {
perf_top__resize(top);
@@ -1179,19 +1356,10 @@
ret = 0;
out_join:
pthread_join(thread, NULL);
-out_delete:
- perf_session__delete(top->session);
- top->session = NULL;
-
+out_join_thread:
+ pthread_cond_signal(&top->qe.cond);
+ pthread_join(thread_process, NULL);
return ret;
-
-out_err_cpu_topo: {
- char errbuf[BUFSIZ];
- const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
-
- ui__error("Could not read the CPU topology map: %s\n", err);
- goto out_delete;
-}
}
static int
@@ -1262,8 +1430,16 @@
.target = {
.uses_mmap = true,
},
- .proc_map_timeout = 500,
- .overwrite = 1,
+ /*
+ * FIXME: This will lose PERF_RECORD_MMAP and other metadata
+ * when we pause, fix that and reenable. Probably using a
+ * separate evlist with a dummy event, i.e. a non-overwrite
+ * ring buffer just for metadata events, while PERF_RECORD_SAMPLE
+ * stays in overwrite mode. -acme
+ * */
+ .overwrite = 0,
+ .sample_time = true,
+ .sample_time_set = true,
},
.max_stack = sysctl__max_stack(),
.annotation_opts = annotation__default_options,
@@ -1288,6 +1464,8 @@
"file", "vmlinux pathname"),
OPT_BOOLEAN(0, "ignore-vmlinux", &symbol_conf.ignore_vmlinux,
"don't load vmlinux even if found"),
+ OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
+ "file", "kallsyms pathname"),
OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
"hide kernel symbols"),
OPT_CALLBACK('m', "mmap-pages", &opts->mmap_pages, "pages",
@@ -1354,10 +1532,15 @@
"Display raw encoding of assembly instructions (default)"),
OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
"Enable kernel symbol demangling"),
+ OPT_BOOLEAN(0, "no-bpf-event", &top.record_opts.no_bpf_event, "do not record bpf events"),
OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path",
"objdump binary to use for disassembly and annotations"),
OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style",
"Specify disassembler style (e.g. -M intel for intel syntax)"),
+ OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix",
+ "Add prefix to source file path names in programs (with --prefix-strip)"),
+ OPT_STRING(0, "prefix-strip", &top.annotation_opts.prefix_strip, "N",
+ "Strip first N entries of source file path name in programs (with --prefix)"),
OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
OPT_CALLBACK(0, "percent-limit", &top, "percent",
"Don't show entries under that percent", parse_percent_limit),
@@ -1366,7 +1549,7 @@
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_UINTEGER(0, "proc-map-timeout", &opts->proc_map_timeout,
+ OPT_UINTEGER(0, "proc-map-timeout", &proc_map_timeout,
"per thread proc mmap processing timeout in ms"),
OPT_CALLBACK_NOOPT('b', "branch-any", &opts->branch_stack,
"branch any", "sample any taken branches",
@@ -1378,9 +1561,27 @@
"Show raw trace event output (do not use print fmt or plugins)"),
OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
"Show entries in a hierarchy"),
+ OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite,
+ "Use a backward ring buffer, default: no"),
OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
"number of thread to run event synthesize"),
+ OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces,
+ "Record namespaces events"),
+ OPT_BOOLEAN(0, "all-cgroups", &opts->record_cgroup,
+ "Record cgroup events"),
+ OPT_INTEGER(0, "group-sort-idx", &symbol_conf.group_sort_idx,
+ "Sort the output by the event at the index n in group. "
+ "If n is invalid, sort by the first event. "
+ "WARNING: should be used on grouped events."),
+ OPT_BOOLEAN(0, "stitch-lbr", &top.stitch_lbr,
+ "Enable LBR callgraph stitching approach"),
+#ifdef HAVE_LIBPFM
+ OPT_CALLBACK(0, "pfm-events", &top.evlist, "event",
+ "libpfm4 event selector. use 'perf list' to list available events",
+ parse_libpfm_events_option),
+#endif
+ OPTS_EVSWITCH(&top.evswitch),
OPT_END()
};
const char * const top_usage[] = {
@@ -1395,23 +1596,45 @@
top.annotation_opts.min_pcnt = 5;
top.annotation_opts.context = 4;
- top.evlist = perf_evlist__new();
+ top.evlist = evlist__new();
if (top.evlist == NULL)
return -ENOMEM;
status = perf_config(perf_top_config, &top);
if (status)
return status;
+ /*
+ * Since the per arch annotation init routine may need the cpuid, read
+ * it here, since we are not getting this from the perf.data header.
+ */
+ status = perf_env__read_cpuid(&perf_env);
+ if (status) {
+ /*
+ * Some arches do not provide a get_cpuid(), so just use pr_debug, otherwise
+ * warn the user explicitely.
+ */
+ eprintf(status == ENOSYS ? 1 : 0, verbose,
+ "Couldn't read the cpuid for this machine: %s\n",
+ str_error_r(errno, errbuf, sizeof(errbuf)));
+ }
+ top.evlist->env = &perf_env;
argc = parse_options(argc, argv, options, top_usage, 0);
if (argc)
usage_with_options(top_usage, options);
- if (!top.evlist->nr_entries &&
- perf_evlist__add_default(top.evlist) < 0) {
+ if (annotate_check_args(&top.annotation_opts) < 0)
+ goto out_delete_evlist;
+
+ if (!top.evlist->core.nr_entries &&
+ evlist__add_default(top.evlist) < 0) {
pr_err("Not enough memory for event selector list\n");
goto out_delete_evlist;
}
+
+ status = evswitch__init(&top.evswitch, top.evlist, stderr);
+ if (status)
+ goto out_delete_evlist;
if (symbol_conf.report_hierarchy) {
/* disable incompatible options */
@@ -1425,6 +1648,14 @@
goto out_delete_evlist;
}
}
+
+ if (top.stitch_lbr && !(callchain_param.record_mode == CALLCHAIN_LBR)) {
+ pr_err("Error: --stitch-lbr must be used with --call-graph lbr\n");
+ goto out_delete_evlist;
+ }
+
+ if (opts->branch_stack && callchain_param.enabled)
+ symbol_conf.show_branchflag_count = true;
sort__mode = SORT_MODE__TOP;
/* display thread wants entries to be collapsed in a different tree */
@@ -1480,7 +1711,7 @@
goto out_delete_evlist;
}
- top.sym_evsel = perf_evlist__first(top.evlist);
+ top.sym_evsel = evlist__first(top.evlist);
if (!callchain_param.enabled) {
symbol_conf.cumulate_callchain = false;
@@ -1494,7 +1725,7 @@
if (status < 0)
goto out_delete_evlist;
- annotation_config__init();
+ annotation_config__init(&top.annotation_opts);
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
status = symbol__init(NULL);
@@ -1509,10 +1740,42 @@
signal(SIGWINCH, winch_sig);
}
+ top.session = perf_session__new(NULL, false, NULL);
+ if (IS_ERR(top.session)) {
+ status = PTR_ERR(top.session);
+ top.session = NULL;
+ goto out_delete_evlist;
+ }
+
+#ifdef HAVE_LIBBPF_SUPPORT
+ if (!top.record_opts.no_bpf_event) {
+ top.sb_evlist = evlist__new();
+
+ if (top.sb_evlist == NULL) {
+ pr_err("Couldn't create side band evlist.\n.");
+ goto out_delete_evlist;
+ }
+
+ if (evlist__add_bpf_sb_event(top.sb_evlist, &perf_env)) {
+ pr_err("Couldn't ask for PERF_RECORD_BPF_EVENT side band events.\n.");
+ goto out_delete_evlist;
+ }
+ }
+#endif
+
+ if (perf_evlist__start_sb_thread(top.sb_evlist, target)) {
+ pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+ opts->no_bpf_event = true;
+ }
+
status = __cmd_top(&top);
+ if (!opts->no_bpf_event)
+ perf_evlist__stop_sb_thread(top.sb_evlist);
+
out_delete_evlist:
- perf_evlist__delete(top.evlist);
+ evlist__delete(top.evlist);
+ perf_session__delete(top.session);
return status;
}
--
Gitblit v1.6.2