lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 21 Feb 2024 02:20:56 -0500
From: weilin.wang@...el.com
To: weilin.wang@...el.com,
	Ian Rogers <irogers@...gle.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...hat.com>,
	Arnaldo Carvalho de Melo <acme@...nel.org>,
	Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
	Jiri Olsa <jolsa@...nel.org>,
	Namhyung Kim <namhyung@...nel.org>,
	Adrian Hunter <adrian.hunter@...el.com>,
	Kan Liang <kan.liang@...ux.intel.com>
Cc: linux-perf-users@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Perry Taylor <perry.taylor@...el.com>,
	Samantha Alt <samantha.alt@...el.com>,
	Caleb Biggers <caleb.biggers@...el.com>
Subject: [RFC PATCH v1 2/5] perf stat: Fork and launch perf record when perf stat needs to get retire latency value for a metric.

From: Weilin Wang <weilin.wang@...el.com>

Signed-off-by: Weilin Wang <weilin.wang@...el.com>
---
 tools/perf/builtin-stat.c     | 179 +++++++++++++++++++++++++++++++++-
 tools/perf/util/data.c        |   4 +
 tools/perf/util/data.h        |   1 +
 tools/perf/util/metricgroup.c |  11 ++-
 tools/perf/util/metricgroup.h |   7 ++
 tools/perf/util/stat.h        |   3 +
 6 files changed, 201 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 93a7cba30f12..e03665af9da2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -94,8 +94,13 @@
 #include <perf/evlist.h>
 #include <internal/threadmap.h>
 
+#include "util/sample.h"
+#include <sys/param.h>
+#include <subcmd/run-command.h>
+
 #define DEFAULT_SEPARATOR	" "
 #define FREEZE_ON_SMI_PATH	"devices/cpu/freeze_on_smi"
+#define PERF_DATA		"-"
 
 static void print_counters(struct timespec *ts, int argc, const char **argv);
 
@@ -162,7 +167,8 @@ static struct perf_stat_config stat_config = {
 	.ctl_fd			= -1,
 	.ctl_fd_ack		= -1,
 	.iostat_run		= false,
-	.tpebs_event_size = 0,
+	.tpebs_event_size       = 0,
+	.tpebs_pid              = -1,
 };
 
 static bool cpus_map_matched(struct evsel *a, struct evsel *b)
@@ -687,12 +693,163 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 	return COUNTER_FATAL;
 }
 
-static int __run_perf_record(void)
+static int __run_perf_record(const char **record_argv)
 {
+	int i = 0;
+	struct tpebs_event *e;
 	pr_debug("Prepare perf record for retire_latency\n");
+
+
+	record_argv[i++] = "perf";
+	record_argv[i++] = "record";
+	record_argv[i++] = "-W";
+
+	if (stat_config.user_requested_cpu_list) {
+		record_argv[i++] = "-C";
+		record_argv[i++] = stat_config.user_requested_cpu_list;
+	}
+
+	if (stat_config.system_wide)
+		record_argv[i++] = "-a";
+
+	list_for_each_entry(e, &stat_config.tpebs_events, nd) {
+		record_argv[i++] = "-e";
+		record_argv[i++] = e->name;
+	}
+
+	record_argv[i++] = "-o";
+	record_argv[i++] = PERF_DATA;
+
 	return 0;
 }
 
+static void prepare_run_command(struct child_process *cmd,
+			       const char **argv)
+{
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->argv = argv;
+	cmd->out = -1;
+}
+static int prepare_perf_record(struct child_process *cmd)
+{
+	const char **record_argv;
+
+	record_argv = calloc(10 + 2 * stat_config.tpebs_event_size, sizeof(char *));
+	if (!record_argv)
+		return -1;
+	__run_perf_record(record_argv);
+
+	prepare_run_command(cmd, record_argv);
+	return start_command(cmd);
+}
+
+struct perf_script {
+	struct perf_tool	tool;
+	struct perf_session	*session;
+	struct evswitch		evswitch;
+	struct perf_cpu_map	*cpus;
+	struct perf_thread_map *threads;
+	int			name_width;
+};
+
+static void tpebs_data__delete(void)
+{
+	struct tpebs_retire_lat *r, *rtmp;
+	struct tpebs_event *e, *etmp;
+	list_for_each_entry_safe(r, rtmp, &stat_config.tpebs_results, nd) {
+		list_del_init(&r->nd);
+		free(r);
+	}
+	list_for_each_entry_safe(e, etmp, &stat_config.tpebs_events, nd) {
+		list_del_init(&e->nd);
+		free(e);
+	}
+}
+
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event __maybe_unused,
+				struct perf_sample *sample,
+				struct evsel *evsel,
+				struct machine *machine __maybe_unused)
+{
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	int ret = 0;
+	const char *evname;
+	struct tpebs_retire_lat *t;
+
+	pr_debug("entering function %s\n ", __func__);
+	evname = evsel__name(evsel);
+
+	pr_debug("[%03d] ", sample->cpu);
+	pr_debug("%*s: ", script->name_width, evname ?: "[unknown]");
+	pr_debug("%16" PRIu16, sample->retire_lat);
+	pr_debug("\n");
+
+	// Need to handle per core results?
+	// We are assuming average retire latency value will be used. Save the number of
+	// samples and the sum of retire latency value for each event.
+	list_for_each_entry(t, &stat_config.tpebs_results, nd) {
+		if (!strcmp(evname, t->name)) {
+			t->count += 1;
+			t->sum += sample->retire_lat;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(session, event);
+	return 0;
+}
+
+static int __cmd_script(struct child_process *cmd __maybe_unused)
+{
+	int err = 0;
+	struct perf_session *session;
+	struct perf_data data = {
+		.mode = PERF_DATA_MODE_READ,
+		.path = PERF_DATA,
+		.fd   = cmd->out,
+	};
+	struct perf_script script = {
+		.tool = {
+		.sample		 = process_sample_event,
+		.ordered_events	 = true,
+		.ordering_requires_timestamps = true,
+		.feature	 = process_feature_event,
+		.attr		 = perf_event__process_attr,
+		},
+	};
+	struct tpebs_event *e;
+
+	list_for_each_entry(e, &stat_config.tpebs_events, nd) {
+		struct tpebs_retire_lat *new = malloc(sizeof(struct tpebs_retire_lat));
+
+		if (!new)
+			return -1;
+		new->name = strdup(e->name);
+		new->tpebs_name = strdup(e->tpebs_name);
+		new->count = 0;
+		new->sum = 0;
+		list_add_tail(&new->nd, &stat_config.tpebs_results);
+	}
+
+	kill(cmd->pid, SIGTERM);
+	session = perf_session__new(&data, &script.tool);
+	if (IS_ERR(session))
+		return PTR_ERR(session);
+	script.session = session;
+	err = perf_session__process_events(session);
+	perf_session__delete(session);
+
+	return err;
+}
+
 static int __run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int interval = stat_config.interval;
@@ -709,12 +866,14 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	struct affinity saved_affinity, *affinity = NULL;
 	int err;
 	bool second_pass = false;
+	struct child_process cmd;
 
 	//Prepare perf record for sampling event retire_latency before fork and prepare workload
 	if (stat_config.tpebs_event_size > 0) {
 		int ret;
 
-		ret = __run_perf_record();
+		pr_debug("perf stat pid = %d\n", getpid());
+		ret = prepare_perf_record(&cmd);
 		if (ret)
 			return ret;
 	}
@@ -924,6 +1083,17 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 	t1 = rdclock();
 
+	if (stat_config.tpebs_event_size > 0) {
+		int ret;
+
+		pr_debug("pid = %d\n", getpid());
+		pr_debug("cmd.pid = %d\n", cmd.pid);
+
+		ret = __cmd_script(&cmd);
+		close(cmd.out);
+		pr_debug("%d\n", ret);
+	}
+
 	if (stat_config.walltime_run_table)
 		stat_config.walltime_run[run_idx] = t1 - t0;
 
@@ -2714,6 +2884,7 @@ int cmd_stat(int argc, const char **argv)
 	}
 
 	INIT_LIST_HEAD(&stat_config.tpebs_events);
+	INIT_LIST_HEAD(&stat_config.tpebs_results);
 
 	/*
 	 * Metric parsing needs to be delayed as metrics may optimize events
@@ -2921,5 +3092,7 @@ int cmd_stat(int argc, const char **argv)
 	metricgroup__rblist_exit(&stat_config.metric_events);
 	evlist__close_control(stat_config.ctl_fd, stat_config.ctl_fd_ack, &stat_config.ctl_fd_close);
 
+	tpebs_data__delete();
+
 	return status;
 }
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index fc16299c915f..2298ca3b370b 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -173,6 +173,10 @@ static bool check_pipe(struct perf_data *data)
 	int fd = perf_data__is_read(data) ?
 		 STDIN_FILENO : STDOUT_FILENO;
 
+	if (data->fd > 0) {
+		fd = data->fd;
+	}
+
 	if (!data->path) {
 		if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
 			is_pipe = true;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index effcc195d7e9..5554d46ad212 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -28,6 +28,7 @@ struct perf_data_file {
 
 struct perf_data {
 	const char		*path;
+	int			 fd;
 	struct perf_data_file	 file;
 	bool			 is_pipe;
 	bool			 is_dir;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 6c16e5a0b1fc..8518e2b3e5be 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -691,8 +691,17 @@ static int metricgroup__build_event_string(struct strbuf *events,
 
 		if (p) {
 			struct tpebs_event *new_event = malloc(sizeof(struct tpebs_event));
-			*p = '\0';
+			char *name;
+
 			new_event->tpebs_name = strdup(id);
+			*p = '\0';
+			name = malloc(strlen(id) + 2);
+			if (!name)
+				return -ENOMEM;
+
+			strcpy(name, id);
+			strcat(name, ":p");
+			new_event->name = name;
 			*tpebs_event_size += 1;
 			pr_debug("retire_latency required, tpebs_event_size=%lu, new_event=%s\n",
 			*tpebs_event_size, new_event->name);
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 7c24ed768ff3..1fa12cc3294e 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -71,6 +71,13 @@ struct tpebs_event {
 	const char *name;
 	const char *tpebs_name;
 };
+struct tpebs_retire_lat {
+	struct list_head nd;
+	const char *name;
+	const char *tpebs_name;
+	size_t count;
+	int sum;
+};
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 					 struct evsel *evsel,
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 9d0186316b29..8e180f13aa2d 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -111,6 +111,9 @@ struct perf_stat_config {
 	struct rblist		 metric_events;
 	struct list_head	 tpebs_events;
 	size_t			 tpebs_event_size;
+	struct list_head	 tpebs_results;
+	pid_t			 tpebs_pid;
+	int			 tpebs_pipe;
 	int			 ctl_fd;
 	int			 ctl_fd_ack;
 	bool			 ctl_fd_close;
-- 
2.43.0


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ