| 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
| ||
|
Date: Tue, 30 Nov 2021 09:49:45 -0800
From: Ian Rogers <irogers@...gle.com>
To: Andi Kleen <ak@...ux.intel.com>, Jiri Olsa <jolsa@...hat.com>,
Namhyung Kim <namhyung@...nel.org>,
John Garry <john.garry@...wei.com>,
Kajol Jain <kjain@...ux.ibm.com>,
"Paul A . Clarke" <pc@...ibm.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Riccardo Mancini <rickyman7@...il.com>,
Kan Liang <kan.liang@...ux.intel.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
Vineet Singh <vineet.singh@...el.com>
Cc: eranian@...gle.com, Ian Rogers <irogers@...gle.com>
Subject: [PATCH v3 2/2] perf parse-events: Architecture specific leader override
Currently topdown events must appear after a slots event:
$ perf stat -e '{slots,topdown-fe-bound}' /bin/true
Performance counter stats for '/bin/true':
3,183,090 slots
986,133 topdown-fe-bound
Reversing the events yields:
$ perf stat -e '{topdown-fe-bound,slots}' /bin/true
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (topdown-fe-bound).
For metrics the order of events is determined by iterating over a
hashmap, and so slots isn't guaranteed to be first which can yield this
error.
Change the set_leader in parse-events, called when a group is closed, so
that rather than always making the first event the leader, if the slots
event exists then it is made the leader. It is then moved to the head of
the evlist otherwise it won't be opened in the correct order.
The result is:
$ perf stat -e '{topdown-fe-bound,slots}' /bin/true
Performance counter stats for '/bin/true':
3,274,795 slots
1,001,702 topdown-fe-bound
A problem with this approach is the slots event is identified by name,
names can be overwritten like 'cpu/slots,name=foo/' and this causes the
leader change to fail.
The change also modifies and fixes mixed groups like, with the change:
$ perf stat -e '{instructions,slots,topdown-fe-bound}' -a -- sleep 2
Performance counter stats for 'system wide':
5574985410 slots
971981616 instructions
1348461887 topdown-fe-bound
2.001263120 seconds time elapsed
Without the change:
$ perf stat -e '{instructions,slots,topdown-fe-bound}' -a -- sleep 2
Performance counter stats for 'system wide':
<not counted> instructions
<not counted> slots
<not supported> topdown-fe-bound
2.006247990 seconds time elapsed
Something that may be undesirable here is that the events are reordered
in the output.
v2. Move the list_move operation into parse_events__set_leader as
suggested by Jiri Olsa <jolsa@...hat.com>.
v3. Switched list_entry to list_first_entry as suggested by Arnaldo
Carvalho de Melo <acme@...nel.org>.
Reviewed-by: Kajol Jain<kjain@...ux.ibm.com>
Acked-by: Jiri Olsa <jolsa@...hat.com>
Signed-off-by: Ian Rogers <irogers@...gle.com>
---
tools/perf/arch/x86/util/evlist.c | 17 +++++++++++++++++
tools/perf/util/evlist.h | 1 +
tools/perf/util/parse-events.c | 8 +++++++-
3 files changed, 25 insertions(+), 1 deletion(-)
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 0b0951030a2f..f924246eff78 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -17,3 +17,20 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
else
return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL);
}
+
+struct evsel *arch_evlist__leader(struct list_head *list)
+{
+ struct evsel *evsel, *first;
+
+ first = list_first_entry(list, struct evsel, core.node);
+
+ if (!pmu_have_event("cpu", "slots"))
+ return first;
+
+ __evlist__for_each_entry(list, evsel) {
+ if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
+ evsel->name && strstr(evsel->name, "slots"))
+ return evsel;
+ }
+ return first;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 97bfb8d0be4f..993437ffe429 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -110,6 +110,7 @@ int __evlist__add_default_attrs(struct evlist *evlist,
__evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
int arch_evlist__add_default_attrs(struct evlist *evlist);
+struct evsel *arch_evlist__leader(struct list_head *list);
int evlist__add_dummy(struct evlist *evlist);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c2935aca4b67..1faf3c19430b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1821,6 +1821,11 @@ parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list,
return ret;
}
+__weak struct evsel *arch_evlist__leader(struct list_head *list)
+{
+ return list_first_entry(list, struct evsel, core.node);
+}
+
void parse_events__set_leader(char *name, struct list_head *list,
struct parse_events_state *parse_state)
{
@@ -1834,9 +1839,10 @@ void parse_events__set_leader(char *name, struct list_head *list,
if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
return;
- leader = list_first_entry(list, struct evsel, core.node);
+ leader = arch_evlist__leader(list);
__perf_evlist__set_leader(list, &leader->core);
leader->group_name = name ? strdup(name) : NULL;
+ list_move(&leader->core.node, list);
}
/* list_event is assumed to point to malloc'ed memory */
--
2.34.0.rc2.393.gf8c9666880-goog
Powered by blists - more mailing lists