summaryrefslogtreecommitdiff
path: root/tools/perf/builtin-record.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/builtin-record.c')
-rw-r--r--tools/perf/builtin-record.c113
1 files changed, 99 insertions, 14 deletions
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f83252472921..8059bce85a51 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -26,6 +26,7 @@
#include "util/target.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/stat.h"
#include "util/symbol.h"
#include "util/record.h"
#include "util/cpumap.h"
@@ -51,6 +52,7 @@
#include "util/clockid.h"
#include "util/off_cpu.h"
#include "util/bpf-filter.h"
+#include "util/strbuf.h"
#include "asm/bug.h"
#include "perf.h"
#include "cputopo.h"
@@ -161,6 +163,7 @@ struct record {
struct evlist *sb_evlist;
pthread_t thread_id;
int realtime_prio;
+ bool latency;
bool switch_output_event_set;
bool no_buildid;
bool no_buildid_set;
@@ -647,14 +650,27 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
struct record *rec = to;
if (record__comp_enabled(rec)) {
+ struct perf_record_compressed2 *event = map->data;
+ size_t padding = 0;
+ u8 pad[8] = {0};
ssize_t compressed = zstd_compress(rec->session, map, map->data,
mmap__mmap_len(map), bf, size);
if (compressed < 0)
return (int)compressed;
- size = compressed;
- bf = map->data;
+ bf = event;
+ thread->samples++;
+
+ /*
+ * The record from `zstd_compress` is not 8 bytes aligned, which would cause asan
+ * error. We make it aligned here.
+ */
+ event->data_size = compressed - sizeof(struct perf_record_compressed2);
+ event->header.size = PERF_ALIGN(compressed, sizeof(u64));
+ padding = event->header.size - compressed;
+ return record__write(rec, map, bf, compressed) ||
+ record__write(rec, map, &pad, padding);
}
thread->samples++;
@@ -860,7 +876,9 @@ static int record__auxtrace_init(struct record *rec)
if (err)
return err;
- auxtrace_regroup_aux_output(rec->evlist);
+ err = auxtrace_parse_aux_action(rec->evlist);
+ if (err)
+ return err;
return auxtrace_parse_filters(rec->evlist);
}
@@ -1531,7 +1549,7 @@ static void record__adjust_affinity(struct record *rec, struct mmap *map)
static size_t process_comp_header(void *record, size_t increment)
{
- struct perf_record_compressed *event = record;
+ struct perf_record_compressed2 *event = record;
size_t size = sizeof(*event);
if (increment) {
@@ -1539,7 +1557,7 @@ static size_t process_comp_header(void *record, size_t increment)
return increment;
}
- event->header.type = PERF_RECORD_COMPRESSED;
+ event->header.type = PERF_RECORD_COMPRESSED2;
event->header.size = size;
return size;
@@ -1549,7 +1567,7 @@ static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
void *dst, size_t dst_size, void *src, size_t src_size)
{
ssize_t compressed;
- size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
+ size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed2) - 1;
struct zstd_data *zstd_data = &session->zstd_data;
if (map && map->file)
@@ -1748,10 +1766,8 @@ static void record__init_features(struct record *rec)
if (rec->no_buildid)
perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
-#ifdef HAVE_LIBTRACEEVENT
if (!have_tracepoints(&rec->evlist->core.entries))
perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
-#endif
if (!rec->opts.branch_stack)
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
@@ -1917,9 +1933,10 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
u16 misc_flag)
{
struct perf_sample_id *sid;
- struct perf_sample sample = {};
+ struct perf_sample sample;
int id_hdr_size;
+ perf_sample__init(&sample, /*all=*/true);
lost->lost = lost_count;
if (evsel->core.ids) {
sid = xyarray__entry(evsel->core.sample_id, cpu_idx, thread_idx);
@@ -1931,6 +1948,7 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
lost->header.size = sizeof(*lost) + id_hdr_size;
lost->header.misc = misc_flag;
record__write(rec, NULL, lost, lost->header.size);
+ perf_sample__exit(&sample);
}
static void record__read_lost_samples(struct record *rec)
@@ -2480,7 +2498,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
pr_warning("WARNING: --timestamp-filename option is not available in pipe mode.\n");
}
- evlist__uniquify_name(rec->evlist);
+ /*
+ * Use global stat_config that is zero meaning aggr_mode is AGGR_NONE
+ * and hybrid_merge is false.
+ */
+ evlist__uniquify_evsel_names(rec->evlist, &stat_config);
evlist__config(rec->evlist, opts, &callchain_param);
@@ -2532,6 +2554,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
goto out_free_threads;
}
+ if (!evlist__needs_bpf_sb_event(rec->evlist))
+ opts->no_bpf_event = true;
+
err = record__setup_sb_evlist(rec);
if (err)
goto out_free_threads;
@@ -2563,6 +2588,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
evlist__enable(rec->evlist);
/*
+ * offcpu-time does not call execve, so enable_on_exe wouldn't work
+ * when recording a workload, do it manually
+ */
+ if (rec->off_cpu)
+ evlist__enable_evsel(rec->evlist, (char *)OFFCPU_EVENT);
+
+ /*
* Let the child rip
*/
if (forks) {
@@ -2778,13 +2810,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
record__auxtrace_snapshot_exit(rec);
if (forks && workload_exec_errno) {
- char msg[STRERR_BUFSIZE], strevsels[2048];
+ char msg[STRERR_BUFSIZE];
const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
+ struct strbuf sb = STRBUF_INIT;
- evlist__scnprintf_evsels(rec->evlist, sizeof(strevsels), strevsels);
+ evlist__format_evsels(rec->evlist, &sb, 2048);
pr_err("Failed to collect '%s' for the '%s' workload: %s\n",
- strevsels, argv[0], emsg);
+ sb.buf, argv[0], emsg);
+ strbuf_release(&sb);
err = -1;
goto out_child;
}
@@ -3149,6 +3183,28 @@ out_free:
return ret;
}
+static int record__parse_off_cpu_thresh(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct record_opts *opts = opt->value;
+ char *endptr;
+ u64 off_cpu_thresh_ms;
+
+ if (!str)
+ return -EINVAL;
+
+ off_cpu_thresh_ms = strtoull(str, &endptr, 10);
+
+ /* the threshold isn't string "0", yet strtoull() returns 0, parsing failed */
+ if (*endptr || (off_cpu_thresh_ms == 0 && strcmp(str, "0")))
+ return -EINVAL;
+ else
+ opts->off_cpu_thresh_ns = off_cpu_thresh_ms * NSEC_PER_MSEC;
+
+ return 0;
+}
+
void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused)
{
}
@@ -3342,6 +3398,7 @@ static struct record record = {
.ctl_fd = -1,
.ctl_fd_ack = -1,
.synth = PERF_SYNTH_ALL,
+ .off_cpu_thresh_ns = OFFCPU_THRESH,
},
};
@@ -3371,6 +3428,9 @@ static struct option __record_options[] = {
parse_events_option),
OPT_CALLBACK(0, "filter", &record.evlist, "filter",
"event filter", parse_filter),
+ OPT_BOOLEAN(0, "latency", &record.latency,
+ "Enable data collection for latency profiling.\n"
+ "\t\t\t Use perf report --latency for latency-centric profile."),
OPT_CALLBACK_NOOPT(0, "exclude-perf", &record.evlist,
NULL, "don't record events from perf itself",
exclude_perf),
@@ -3427,6 +3487,8 @@ static struct option __record_options[] = {
"Record the sampled data address data page size"),
OPT_BOOLEAN(0, "code-page-size", &record.opts.sample_code_page_size,
"Record the sampled code address (ip) page size"),
+ OPT_BOOLEAN(0, "sample-mem-info", &record.opts.sample_data_src,
+ "Record the data source for memory operations"),
OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
OPT_BOOLEAN(0, "sample-identifier", &record.opts.sample_identifier,
"Record the sample identifier"),
@@ -3471,7 +3533,7 @@ static struct option __record_options[] = {
"sample selected machine registers on interrupt,"
" use '-I?' to list register names", parse_intr_regs),
OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
- "sample selected machine registers on interrupt,"
+ "sample selected machine registers in user space,"
" use '--user-regs=?' to list register names", parse_user_regs),
OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
"Record running/enabled time of read (:S) events"),
@@ -3564,6 +3626,9 @@ static struct option __record_options[] = {
OPT_BOOLEAN(0, "off-cpu", &record.off_cpu, "Enable off-cpu analysis"),
OPT_STRING(0, "setup-filter", &record.filter_action, "pin|unpin",
"BPF filter action"),
+ OPT_CALLBACK(0, "off-cpu-thresh", &record.opts, "ms",
+ "Dump off-cpu samples if off-cpu time exceeds this threshold (in milliseconds). (Default: 500ms)",
+ record__parse_off_cpu_thresh),
OPT_END()
};
@@ -4017,6 +4082,22 @@ int cmd_record(int argc, const char **argv)
}
+ if (record.latency) {
+ /*
+ * There is no fundamental reason why latency profiling
+ * can't work for system-wide mode, but exact semantics
+ * and details are to be defined.
+ * See the following thread for details:
+ * https://lore.kernel.org/all/Z4XDJyvjiie3howF@google.com/
+ */
+ if (record.opts.target.system_wide) {
+ pr_err("Failed: latency profiling is not supported with system-wide collection.\n");
+ err = -EINVAL;
+ goto out_opts;
+ }
+ record.opts.record_switch_events = true;
+ }
+
if (rec->buildid_mmap) {
if (!perf_can_record_build_id()) {
pr_err("Failed: no support to record build id in mmap events, update your kernel.\n");
@@ -4105,6 +4186,10 @@ int cmd_record(int argc, const char **argv)
goto out_opts;
}
+ /* For backward compatibility, -d implies --mem-info */
+ if (rec->opts.sample_address)
+ rec->opts.sample_data_src = true;
+
/*
* Allow aliases to facilitate the lookup of symbols for address
* filters. Refer to auxtrace_parse_filters().
generated by cgit (git 2.34.1) at 2025-06-07 11:37:41 +0000