1 files changed, 136 insertions, 45 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ba20bf7c011d..7ea3a11aca70 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"
@@ -169,10 +171,12 @@ struct record {
 	bool			no_buildid_cache_set;
 	bool			buildid_all;
 	bool			buildid_mmap;
+	bool			buildid_mmap_set;
 	bool			timestamp_filename;
 	bool			timestamp_boundary;
 	bool			off_cpu;
 	const char		*filter_action;
+	const char		*uid_str;
 	struct switch_output	switch_output;
 	unsigned long long	samples;
 	unsigned long		output_max_size;	/* = 0: unlimited */
@@ -648,14 +652,27 @@ 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++;
@@ -758,7 +775,9 @@ static int record__auxtrace_mmap_read(struct record *rec,
 {
 	int ret;
 
-	ret = auxtrace_mmap__read(map, rec->itr, &rec->tool,
+	ret = auxtrace_mmap__read(map, rec->itr,
+				  perf_session__env(rec->session),
+				  &rec->tool,
 				  record__process_auxtrace);
 	if (ret < 0)
 		return ret;
@@ -774,7 +793,9 @@ static int record__auxtrace_mmap_read_snapshot(struct record *rec,
 {
 	int ret;
 
-	ret = auxtrace_mmap__read_snapshot(map, rec->itr, &rec->tool,
+	ret = auxtrace_mmap__read_snapshot(map, rec->itr,
+					   perf_session__env(rec->session),
+					   &rec->tool,
 					   record__process_auxtrace,
 					   rec->opts.auxtrace_snapshot_size);
 	if (ret < 0)
@@ -1534,7 +1555,7 @@ 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) {
@@ -1542,7 +1563,7 @@ 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;
@@ -1552,7 +1573,7 @@ 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)
@@ -1795,6 +1816,7 @@ record__finish_output(struct record *rec)
 			data->dir.files[i].size = lseek(data->dir.files[i].fd, 0, SEEK_CUR);
 	}
 
+	/* Buildid scanning disabled or build ID in kernel and synthesized map events. */
 	if (!rec->no_buildid) {
 		process_buildids(rec);
 
@@ -2146,6 +2168,14 @@ out:
 	return err;
 }
 
+static void record__synthesize_final_bpf_metadata(struct record *rec __maybe_unused)
+{
+#ifdef HAVE_LIBBPF_SUPPORT
+	perf_event__synthesize_final_bpf_metadata(rec->session,
+						  process_synthesized_event);
+#endif
+}
+
 static int record__process_signal_event(union perf_event *event __maybe_unused, void *data)
 {
 	struct record *rec = data;
@@ -2177,7 +2207,7 @@ static int record__setup_sb_evlist(struct record *rec)
 			}
 		}
 
-		if (evlist__add_bpf_sb_event(rec->sb_evlist, &rec->session->header.env)) {
+		if (evlist__add_bpf_sb_event(rec->sb_evlist, perf_session__env(rec->session))) {
 			pr_err("Couldn't ask for PERF_RECORD_BPF_EVENT side band events.\n.");
 			return -1;
 		}
@@ -2196,15 +2226,16 @@ static int record__init_clock(struct record *rec)
 	struct perf_session *session = rec->session;
 	struct timespec ref_clockid;
 	struct timeval ref_tod;
+	struct perf_env *env = perf_session__env(session);
 	u64 ref;
 
 	if (!rec->opts.use_clockid)
 		return 0;
 
 	if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
-		session->header.env.clock.clockid_res_ns = rec->opts.clockid_res_ns;
+		env->clock.clockid_res_ns = rec->opts.clockid_res_ns;
 
-	session->header.env.clock.clockid = rec->opts.clockid;
+	env->clock.clockid = rec->opts.clockid;
 
 	if (gettimeofday(&ref_tod, NULL) != 0) {
 		pr_err("gettimeofday failed, cannot set reference time.\n");
@@ -2219,12 +2250,12 @@ static int record__init_clock(struct record *rec)
 	ref = (u64) ref_tod.tv_sec * NSEC_PER_SEC +
 	      (u64) ref_tod.tv_usec * NSEC_PER_USEC;
 
-	session->header.env.clock.tod_ns = ref;
+	env->clock.tod_ns = ref;
 
 	ref = (u64) ref_clockid.tv_sec * NSEC_PER_SEC +
 	      (u64) ref_clockid.tv_nsec;
 
-	session->header.env.clock.clockid_ns = ref;
+	env->clock.clockid_ns = ref;
 	return 0;
 }
 
@@ -2370,6 +2401,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	int fd;
 	float ratio = 0;
 	enum evlist_ctl_cmd cmd = EVLIST_CTL_CMD_UNSUPPORTED;
+	struct perf_env *env;
 
 	atexit(record__sig_exit);
 	signal(SIGCHLD, sig_handler);
@@ -2411,7 +2443,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		pr_err("Perf session creation failed.\n");
 		return PTR_ERR(session);
 	}
-
+	env = perf_session__env(session);
 	if (record__threads_enabled(rec)) {
 		if (perf_data__is_pipe(&rec->data)) {
 			pr_err("Parallel trace streaming is not available in pipe mode.\n");
@@ -2445,8 +2477,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 #endif // HAVE_EVENTFD_SUPPORT
 
-	session->header.env.comp_type  = PERF_COMP_ZSTD;
-	session->header.env.comp_level = rec->opts.comp_level;
+	env->comp_type  = PERF_COMP_ZSTD;
+	env->comp_level = rec->opts.comp_level;
 
 	if (rec->opts.kcore &&
 	    !record__kcore_readable(&session->machines.host)) {
@@ -2483,7 +2515,11 @@ 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);
 
@@ -2495,7 +2531,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 	/* Debug message used by test scripts */
 	pr_debug3("perf record done opening and mmapping events\n");
-	session->header.env.comp_mmap_len = session->evlist->core.mmap_len;
+	env->comp_mmap_len = session->evlist->core.mmap_len;
 
 	if (rec->opts.kcore) {
 		err = record__kcore_copy(&session->machines.host, data);
@@ -2569,6 +2605,13 @@ 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) {
@@ -2780,17 +2823,21 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	trigger_off(&auxtrace_snapshot_trigger);
 	trigger_off(&switch_output_trigger);
 
+	record__synthesize_final_bpf_metadata(rec);
+
 	if (opts->auxtrace_snapshot_on_exit)
 		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;
 	}
@@ -2814,7 +2861,7 @@ out_free_threads:
 
 	if (rec->session->bytes_transferred && rec->session->bytes_compressed) {
 		ratio = (float)rec->session->bytes_transferred/(float)rec->session->bytes_compressed;
-		session->header.env.comp_ratio = ratio + 0.5;
+		env->comp_ratio = ratio + 0.5;
 	}
 
 	if (forks) {
@@ -2966,6 +3013,8 @@ static int perf_record_config(const char *var, const char *value, void *cb)
 			rec->no_buildid = true;
 		else if (!strcmp(value, "mmap"))
 			rec->buildid_mmap = true;
+		else if (!strcmp(value, "no-mmap"))
+			rec->buildid_mmap = false;
 		else
 			return -1;
 		return 0;
@@ -3155,6 +3204,28 @@ 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)
 {
 }
@@ -3348,7 +3419,9 @@ static struct record record = {
 		.ctl_fd              = -1,
 		.ctl_fd_ack          = -1,
 		.synth               = PERF_SYNTH_ALL,
+		.off_cpu_thresh_ns   = OFFCPU_THRESH,
 	},
+	.buildid_mmap = true,
 };
 
 const char record_callchain_help[] = CALLCHAIN_RECORD_HELP
@@ -3436,6 +3509,8 @@ 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"),
@@ -3460,8 +3535,7 @@ static struct option __record_options[] = {
 		     "or ranges of time to enable events e.g. '-D 10-20,30-40'",
 		     record__parse_event_enable_time),
 	OPT_BOOLEAN(0, "kcore", &record.opts.kcore, "copy /proc/kcore"),
-	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
-		   "user to profile"),
+	OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"),
 
 	OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
 		     "branch any", "sample any taken branches",
@@ -3480,7 +3554,7 @@ 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"),
@@ -3514,8 +3588,8 @@ static struct option __record_options[] = {
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN(0, "buildid-all", &record.buildid_all,
 		    "Record build-id of all DSOs regardless of hits"),
-	OPT_BOOLEAN(0, "buildid-mmap", &record.buildid_mmap,
-		    "Record build-id in map events"),
+	OPT_BOOLEAN_SET(0, "buildid-mmap", &record.buildid_mmap, &record.buildid_mmap_set,
+			"Record build-id in mmap events and skip build-id processing."),
 	OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
 		    "append timestamp to output filename"),
 	OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary,
@@ -3573,6 +3647,9 @@ 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()
 };
 
@@ -4042,19 +4119,24 @@ int cmd_record(int argc, const char **argv)
 		record.opts.record_switch_events = true;
 	}
 
+	if (!rec->buildid_mmap) {
+		pr_debug("Disabling build id in synthesized mmap2 events.\n");
+		symbol_conf.no_buildid_mmap2 = true;
+	} else if (rec->buildid_mmap_set) {
+		/*
+		 * Explicitly passing --buildid-mmap disables buildid processing
+		 * and cache generation.
+		 */
+		rec->no_buildid = true;
+	}
+	if (rec->buildid_mmap && !perf_can_record_build_id()) {
+		pr_warning("Missing support for build id in kernel mmap events.\n"
+			   "Disable this warning with --no-buildid-mmap\n");
+		rec->buildid_mmap = false;
+	}
 	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");
-			err = -EINVAL;
-			goto out_opts;
-		}
-		pr_debug("Enabling build id in mmap2 events.\n");
-		/* Enable mmap build id synthesizing. */
-		symbol_conf.buildid_mmap2 = true;
 		/* Enable perf_event_attr::build_id bit. */
 		rec->opts.build_id = true;
-		/* Disable build id cache. */
-		rec->no_buildid = true;
 	}
 
 	if (rec->opts.record_cgroup && !perf_can_record_cgroup()) {
@@ -4130,6 +4212,10 @@ 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().
@@ -4196,19 +4282,24 @@ int cmd_record(int argc, const char **argv)
 		ui__warning("%s\n", errbuf);
 	}
 
-	err = target__parse_uid(&rec->opts.target);
-	if (err) {
-		int saved_errno = errno;
+	if (rec->uid_str) {
+		uid_t uid = parse_uid(rec->uid_str);
 
-		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
-		ui__error("%s", errbuf);
+		if (uid == UINT_MAX) {
+			ui__error("Invalid User: %s", rec->uid_str);
+			err = -EINVAL;
+			goto out;
+		}
+		err = parse_uid_filter(rec->evlist, uid);
+		if (err)
+			goto out;
 
-		err = -saved_errno;
-		goto out;
+		/* User ID filtering implies system wide. */
+		rec->opts.target.system_wide = true;
 	}
 
-	/* Enable ignoring missing threads when -u/-p option is defined. */
-	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid;
+	/* Enable ignoring missing threads when -p option is defined. */
+	rec->opts.ignore_missing_thread = rec->opts.target.pid;
 
 	evlist__warn_user_requested_cpus(rec->evlist, rec->opts.target.cpu_list);