| 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
| ||
|
Message-Id: <20190916134128.18120-14-kan.liang@linux.intel.com>
Date: Mon, 16 Sep 2019 06:41:27 -0700
From: kan.liang@...ux.intel.com
To: peterz@...radead.org, acme@...nel.org, mingo@...hat.com,
linux-kernel@...r.kernel.org
Cc: tglx@...utronix.de, jolsa@...nel.org, eranian@...gle.com,
alexander.shishkin@...ux.intel.com, ak@...ux.intel.com,
Kan Liang <kan.liang@...ux.intel.com>
Subject: [PATCH V4 13/14] perf, tools, stat: Support new per thread TopDown metrics
From: Andi Kleen <ak@...ux.intel.com>
Icelake has support for reporting per thread TopDown metrics.
These are reported differently than the previous TopDown support,
each metric is standalone, but scaled to pipeline "slots".
We don't need to do anything special for HyperThreading anymore.
Teach perf stat --topdown to handle these new metrics and
print them in the same way as the previous TopDown metrics.
The restrictions of only being able to report information per core is
gone.
Signed-off-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
---
No changes since V3
tools/perf/Documentation/perf-stat.txt | 9 ++-
tools/perf/builtin-stat.c | 24 +++++++
tools/perf/util/stat-shadow.c | 89 ++++++++++++++++++++++++++
tools/perf/util/stat.c | 4 ++
tools/perf/util/stat.h | 8 +++
5 files changed, 132 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 930c51c01201..f90101637c76 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -279,8 +279,13 @@ if the workload is actually bound by the CPU and not by something else.
For best results it is usually a good idea to use it with interval
mode like -I 1000, as the bottleneck of workloads can change often.
-The top down metrics are collected per core instead of per
-CPU thread. Per core mode is automatically enabled
+This enables --metric-only, unless overridden with --no-metric-only.
+
+The following restrictions only apply to older Intel CPUs and Atom,
+on newer CPUs (IceLake and later) TopDown can be collected for any thread:
+
+The top down metrics are collected per core instead of per CPU thread.
+Per core mode is automatically enabled
and -a (global monitoring) is needed, requiring root rights or
perf.perf_event_paranoid=-1.
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7e17bf9f700a..e63f6c06db30 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -124,6 +124,14 @@ static const char * topdown_attrs[] = {
NULL,
};
+static const char *topdown_metric_attrs[] = {
+ "topdown-retiring",
+ "topdown-bad-spec",
+ "topdown-fe-bound",
+ "topdown-be-bound",
+ NULL,
+};
+
static const char *smi_cost_attrs = {
"{"
"msr/aperf/,"
@@ -1331,6 +1339,21 @@ static int add_default_attributes(void)
char *str = NULL;
bool warn = false;
+ if (topdown_filter_events(topdown_metric_attrs, &str, 1) < 0) {
+ pr_err("Out of memory\n");
+ return -1;
+ }
+ if (topdown_metric_attrs[0] && str) {
+ if (!stat_config.interval) {
+ fprintf(stat_config.output,
+ "Topdown accuracy may decreases when measuring long period.\n"
+ "Please print the result regularly, e.g. -I1000\n");
+ }
+ goto setup_metrics;
+ }
+
+ str = NULL;
+
if (stat_config.aggr_mode != AGGR_GLOBAL &&
stat_config.aggr_mode != AGGR_CORE) {
pr_err("top down event configuration requires --per-core mode\n");
@@ -1352,6 +1375,7 @@ static int add_default_attributes(void)
if (topdown_attrs[0] && str) {
if (warn)
arch_topdown_group_warn();
+setup_metrics:
err = parse_events(evsel_list, str, &errinfo);
if (err) {
fprintf(stderr,
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 70c87fdb2a43..0be18b10a96b 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -243,6 +243,18 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
ctx, cpu, count);
+ else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
+ update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
+ ctx, cpu, count);
+ else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
+ update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
+ ctx, cpu, count);
+ else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
+ update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
+ ctx, cpu, count);
+ else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
+ update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
+ ctx, cpu, count);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
ctx, cpu, count);
@@ -694,6 +706,47 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
return sanitize_val(1.0 - sum);
}
+/*
+ * Kernel reports metrics multiplied with slots. To get back
+ * the ratios we need to recreate the sum.
+ */
+
+static double td_metric_ratio(int ctx, int cpu,
+ enum stat_type type,
+ struct runtime_stat *stat)
+{
+ double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu);
+ double d = runtime_stat_avg(stat, type, ctx, cpu);
+
+ if (sum)
+ return d / sum;
+ return 0;
+}
+
+/*
+ * ... but only if most of the values are actually available.
+ * We allow two missing.
+ */
+
+static bool full_td(int ctx, int cpu,
+ struct runtime_stat *stat)
+{
+ int c = 0;
+
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) > 0)
+ c++;
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) > 0)
+ c++;
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) > 0)
+ c++;
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu) > 0)
+ c++;
+ return c >= 2;
+}
+
static void print_smi_cost(struct perf_stat_config *config,
int cpu, struct evsel *evsel,
struct perf_stat_output_ctx *out,
@@ -1025,6 +1078,42 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
be_bound * 100.);
else
print_metric(config, ctxp, NULL, NULL, name, 0);
+ } else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
+ full_td(ctx, cpu, st)) {
+ double retiring = td_metric_ratio(ctx, cpu,
+ STAT_TOPDOWN_RETIRING, st);
+
+ if (retiring > 0.7)
+ color = PERF_COLOR_GREEN;
+ print_metric(config, ctxp, color, "%8.1f%%", "retiring",
+ retiring * 100.);
+ } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
+ full_td(ctx, cpu, st)) {
+ double fe_bound = td_metric_ratio(ctx, cpu,
+ STAT_TOPDOWN_FE_BOUND, st);
+
+ if (fe_bound > 0.2)
+ color = PERF_COLOR_RED;
+ print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
+ fe_bound * 100.);
+ } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
+ full_td(ctx, cpu, st)) {
+ double be_bound = td_metric_ratio(ctx, cpu,
+ STAT_TOPDOWN_BE_BOUND, st);
+
+ if (be_bound > 0.2)
+ color = PERF_COLOR_RED;
+ print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
+ be_bound * 100.);
+ } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
+ full_td(ctx, cpu, st)) {
+ double bad_spec = td_metric_ratio(ctx, cpu,
+ STAT_TOPDOWN_BAD_SPEC, st);
+
+ if (bad_spec > 0.1)
+ color = PERF_COLOR_RED;
+ print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
+ bad_spec * 100.);
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
evsel->metric_name, NULL, avg, cpu, out, st);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 8f1ea27f976f..a6201ed26457 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -94,6 +94,10 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
+ ID(TOPDOWN_RETIRING, topdown-retiring),
+ ID(TOPDOWN_BAD_SPEC, topdown-bad-spec),
+ ID(TOPDOWN_FE_BOUND, topdown-fe-bound),
+ ID(TOPDOWN_BE_BOUND, topdown-be-bound),
ID(SMI_NUM, msr/smi/),
ID(APERF, msr/aperf/),
};
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 14fe3e548229..2749b540218b 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -27,6 +27,10 @@ enum perf_stat_evsel_id {
PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
+ PERF_STAT_EVSEL_ID__TOPDOWN_RETIRING,
+ PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC,
+ PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND,
+ PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND,
PERF_STAT_EVSEL_ID__SMI_NUM,
PERF_STAT_EVSEL_ID__APERF,
PERF_STAT_EVSEL_ID__MAX,
@@ -80,6 +84,10 @@ enum stat_type {
STAT_TOPDOWN_SLOTS_RETIRED,
STAT_TOPDOWN_FETCH_BUBBLES,
STAT_TOPDOWN_RECOVERY_BUBBLES,
+ STAT_TOPDOWN_RETIRING,
+ STAT_TOPDOWN_BAD_SPEC,
+ STAT_TOPDOWN_FE_BOUND,
+ STAT_TOPDOWN_BE_BOUND,
STAT_SMI_NUM,
STAT_APERF,
STAT_MAX
--
2.17.1
Powered by blists - more mailing lists