summaryrefslogtreecommitdiff
path: root/tools/perf/util/stat-shadow.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util/stat-shadow.c')
-rw-r--r--tools/perf/util/stat-shadow.c117
1 files changed, 104 insertions, 13 deletions
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index e1ba6c1b916a..901265127e36 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -241,6 +241,18 @@ 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 (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
ctx, cpu, count);
@@ -517,7 +529,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache accesses", ratio);
}
static void print_l1_icache_misses(struct perf_stat_config *config,
@@ -538,7 +550,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache accesses", ratio);
}
static void print_dtlb_cache_misses(struct perf_stat_config *config,
@@ -558,7 +570,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache accesses", ratio);
}
static void print_itlb_cache_misses(struct perf_stat_config *config,
@@ -578,7 +590,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache accesses", ratio);
}
static void print_ll_cache_misses(struct perf_stat_config *config,
@@ -598,7 +610,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio);
}
/*
@@ -705,6 +717,47 @@ 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,
@@ -853,14 +906,16 @@ static void generic_metric(struct perf_stat_config *config,
double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
{
struct expr_parse_ctx pctx;
- double ratio;
+ double ratio = 0.0;
if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0)
- return 0.;
+ goto out;
if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1))
- return 0.;
+ ratio = 0.0;
+out:
+ expr__ctx_clear(&pctx);
return ratio;
}
@@ -918,7 +973,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
} else if (
evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1I |
@@ -928,7 +983,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
print_l1_icache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
} else if (
evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
@@ -938,7 +993,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
} else if (
evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
@@ -948,7 +1003,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
} else if (
evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_LL |
@@ -958,7 +1013,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
print_ll_cache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
@@ -1071,6 +1126,42 @@ 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, NULL,
evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-01 19:20:28 +0000