linux-kernel - [PATCH 9/9] perf script: Support Retire Latency

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:   Thu,  1 Dec 2022 11:57:04 -0800
From:   kan.liang@...ux.intel.com
To:     peterz@...radead.org, mingo@...hat.com, acme@...nel.org,
        linux-kernel@...r.kernel.org
Cc:     ak@...ux.intel.com, eranian@...gle.com, irogers@...gle.com,
        Kan Liang <kan.liang@...ux.intel.com>
Subject: [PATCH 9/9] perf script: Support Retire Latency

From: Kan Liang <kan.liang@...ux.intel.com>

The Retire Latency field is added in the var3_w of the
PERF_SAMPLE_WEIGHT_STRUCT. The Retire Latency reports the number of
elapsed core clocks between the retirement of the instruction
indicated by the Instruction Pointer field of the PEBS record and the
retirement of the prior instruction. That's quite useful to display
the information with perf script.

Add a new field retire_lat for the Retire Latency information.

Reviewed-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
---
 tools/perf/builtin-script.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7ca238277d83..071ffdff1980 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -127,6 +127,7 @@ enum perf_output_field {
 	PERF_OUTPUT_BRSTACKINSNLEN  = 1ULL << 36,
 	PERF_OUTPUT_MACHINE_PID     = 1ULL << 37,
 	PERF_OUTPUT_VCPU            = 1ULL << 38,
+	PERF_OUTPUT_RETIRE_LAT      = 1ULL << 39,
 };
 
 struct perf_script {
@@ -197,6 +198,7 @@ struct output_option {
 	{.str = "brstackinsnlen", .field = PERF_OUTPUT_BRSTACKINSNLEN},
 	{.str = "machine_pid", .field = PERF_OUTPUT_MACHINE_PID},
 	{.str = "vcpu", .field = PERF_OUTPUT_VCPU},
+	{.str = "retire_lat", .field = PERF_OUTPUT_RETIRE_LAT},
 };
 
 enum {
@@ -272,7 +274,7 @@ static struct {
 			      PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
 			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR |
 			      PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE |
-			      PERF_OUTPUT_INS_LAT,
+			      PERF_OUTPUT_INS_LAT | PERF_OUTPUT_RETIRE_LAT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -539,6 +541,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 	    evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_STRUCT, "WEIGHT_STRUCT", PERF_OUTPUT_INS_LAT))
 		return -EINVAL;
 
+	if (PRINT_FIELD(RETIRE_LAT) &&
+	    evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_STRUCT, "WEIGHT_STRUCT", PERF_OUTPUT_RETIRE_LAT))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -2175,6 +2181,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(INS_LAT))
 		fprintf(fp, "%16" PRIu16, sample->ins_lat);
 
+	if (PRINT_FIELD(RETIRE_LAT))
+		fprintf(fp, "%16" PRIu16, sample->retire_lat);
+
 	if (PRINT_FIELD(IP)) {
 		struct callchain_cursor *cursor = NULL;
 
@@ -3849,7 +3858,7 @@ int cmd_script(int argc, const char **argv)
 		     "brstacksym,flags,data_src,weight,bpf-output,brstackinsn,"
 		     "brstackinsnlen,brstackoff,callindent,insn,insnlen,synth,"
 		     "phys_addr,metric,misc,srccode,ipc,tod,data_page_size,"
-		     "code_page_size,ins_lat",
+		     "code_page_size,ins_lat,retire_lat",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
-- 
2.35.1