File perf-evlist-Keep-topdown-counters-in-weak-group.patch of Package perf.35610
From: Ian Rogers <irogers@google.com>
Date: Mon, 16 May 2022 22:27:23 -0700
Subject: perf evlist: Keep topdown counters in weak group
Git-commit: d98079c05b5a5411c6030c47b6256cbeeeff77d0
References: jsc#SLE-24578 (dependent patch)
X-Info: adjust for context, no 9aba0adae8c773ba0c0adc7c4d97768e044166cb (perf expr: Add source_count for aggregating events)
X-Info: adjust for context, no 63c12ae2f246dcdc30895ec7c980365a5133433d (perf evsel: Add bitfield_swap() to handle branch_stack endian issue)
Signed-off-by: Tony Jones <tonyj@suse.de>
On Intel Icelake, topdown events must always be grouped with a slots
event as leader. When a metric is parsed a weak group is formed and
retried if perf_event_open fails. The retried events aren't grouped
breaking the slots leader requirement. This change modifies the weak
group "reset" behavior so that topdown events aren't broken from the
group for the retry.
$ perf stat -e '{slots,topdown-bad-spec,topdown-be-bound,topdown-fe-bound,topdown-retiring,branch-instructions,branch-misses,bus-cycles,cache-misses,cache-references,cpu-cycles,instructions,mem-loads,mem-stores,ref-cycles,baclears.any,ARITH.DIVIDER_ACTIVE}:W' -a sleep 1
Performance counter stats for 'system wide':
47,867,188,483 slots (92.27%)
<not supported> topdown-bad-spec
<not supported> topdown-be-bound
<not supported> topdown-fe-bound
<not supported> topdown-retiring
2,173,346,937 branch-instructions (92.27%)
10,540,253 branch-misses # 0.48% of all branches (92.29%)
96,291,140 bus-cycles (92.29%)
6,214,202 cache-misses # 20.120 % of all cache refs (92.29%)
30,886,082 cache-references (76.91%)
11,773,726,641 cpu-cycles (84.62%)
11,807,585,307 instructions # 1.00 insn per cycle (92.31%)
0 mem-loads (92.32%)
2,212,928,573 mem-stores (84.69%)
10,024,403,118 ref-cycles (92.35%)
16,232,978 baclears.any (92.35%)
23,832,633 ARITH.DIVIDER_ACTIVE (84.59%)
0.981070734 seconds time elapsed
After:
$ perf stat -e '{slots,topdown-bad-spec,topdown-be-bound,topdown-fe-bound,topdown-retiring,branch-instructions,branch-misses,bus-cycles,cache-misses,cache-references,cpu-cycles,instructions,mem-loads,mem-stores,ref-cycles,baclears.any,ARITH.DIVIDER_ACTIVE}:W' -a sleep 1
Performance counter stats for 'system wide':
31040189283 slots (92.27%)
8997514811 topdown-bad-spec # 28.2% bad speculation (92.27%)
10997536028 topdown-be-bound # 34.5% backend bound (92.27%)
4778060526 topdown-fe-bound # 15.0% frontend bound (92.27%)
7086628768 topdown-retiring # 22.2% retiring (92.27%)
1417611942 branch-instructions (92.26%)
5285529 branch-misses # 0.37% of all branches (92.28%)
62922469 bus-cycles (92.29%)
1440708 cache-misses # 8.292 % of all cache refs (92.30%)
17374098 cache-references (76.94%)
8040889520 cpu-cycles (84.63%)
7709992319 instructions # 0.96 insn per cycle (92.32%)
0 mem-loads (92.32%)
1515669558 mem-stores (84.68%)
6542411177 ref-cycles (92.35%)
4154149 baclears.any (92.35%)
20556152 ARITH.DIVIDER_ACTIVE (84.59%)
1.010799593 seconds time elapsed
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Florian Fischer <florian.fischer@muhq.space>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20220517052724.283874-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Tony Jones <tonyj@suse.de>
---
tools/perf/arch/x86/util/evsel.c | 12 ++++++++++++
tools/perf/util/evlist.c | 16 ++++++++++++++--
tools/perf/util/evsel.c | 10 ++++++++++
tools/perf/util/evsel.h | 3 +++
4 files changed, 39 insertions(+), 2 deletions(-)
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index ac2899a25b7a..00cb4466b4ca 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -3,6 +3,7 @@
#include <stdlib.h>
#include "util/evsel.h"
#include "util/env.h"
+#include "util/pmu.h"
#include "linux/string.h"
void arch_evsel__set_sample_weight(struct evsel *evsel)
@@ -29,3 +30,14 @@ void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr)
free(env.cpuid);
}
+
+bool arch_evsel__must_be_in_group(const struct evsel *evsel)
+{
+ if ((evsel->pmu_name && strcmp(evsel->pmu_name, "cpu")) ||
+ !pmu_have_event("cpu", "slots"))
+ return false;
+
+ return evsel->name &&
+ (!strcasecmp(evsel->name, "slots") ||
+ strcasestr(evsel->name, "topdown"));
+}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7ae56b062f44..91bbe4c069eb 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1742,8 +1742,17 @@ struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel *
if (evsel__has_leader(c2, leader)) {
if (is_open && close)
perf_evsel__close(&c2->core);
- evsel__set_leader(c2, c2);
- c2->core.nr_members = 0;
+ /*
+ * We want to close all members of the group and reopen
+ * them. Some events, like Intel topdown, require being
+ * in a group and so keep these in the group.
+ */
+ if (!evsel__must_be_in_group(c2) && c2 != leader) {
+ evsel__set_leader(c2, c2);
+ c2->core.nr_members = 0;
+ leader->core.nr_members--;
+ }
+
/*
* Set this for all former members of the group
* to indicate they get reopened.
@@ -1751,6 +1760,9 @@ struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel *
c2->reset_group = true;
}
}
+ /* Reset the leader count if all entries were removed. */
+ if (leader->core.nr_members == 1)
+ leader->core.nr_members = 0;
return leader;
}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5fd7924f8eb3..1cf967d689aa 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3103,3 +3103,13 @@ void evsel__set_leader(struct evsel *evsel, struct evsel *leader)
{
evsel->core.leader = &leader->core;
}
+
+bool __weak arch_evsel__must_be_in_group(const struct evsel *evsel __maybe_unused)
+{
+ return false;
+}
+
+bool evsel__must_be_in_group(const struct evsel *evsel)
+{
+ return arch_evsel__must_be_in_group(evsel);
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 52dc5fd106b1..84755fabc544 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -499,6 +499,9 @@ bool evsel__has_leader(struct evsel *evsel, struct evsel *leader);
bool evsel__has_leader(struct evsel *evsel, struct evsel *leader);
bool evsel__is_leader(struct evsel *evsel);
void evsel__set_leader(struct evsel *evsel, struct evsel *leader);
+bool evsel__must_be_in_group(const struct evsel *evsel);
+
+bool arch_evsel__must_be_in_group(const struct evsel *evsel);
/*
* Macro to swap the bit-field postition and size.
