From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Kan Liang <kan.liang@linux.intel.com>,
James Clark <james.clark@arm.com>,
linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
bpf@vger.kernel.org, Atish Patra <atishp@rivosinc.com>,
linux-riscv@lists.infradead.org,
Beeman Strong <beeman@rivosinc.com>
Subject: [PATCH v2 06/16] perf parse-events: Legacy cache names on all PMUs and lower priority
Date: Mon, 15 Apr 2024 23:15:22 -0700 [thread overview]
Message-ID: <20240416061533.921723-7-irogers@google.com> (raw)
In-Reply-To: <20240416061533.921723-1-irogers@google.com>
Prior behavior is to not look for legacy cache names in sysfs/json and
to create events on all core PMUs. New behavior is to look for
sysfs/json events first on all PMUs, for core PMUs add a legacy event
if the sysfs/json event isn't present.
This is done so that there is consistency with how event names in
terms are handled and their prioritization of sysfs/json over
legacy. It may make sense to use a legacy cache event name as an event
name on a non-core PMU so we should allow it.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/parse-events.c | 39 +++++++++++++++++++++++++++-------
tools/perf/util/parse-events.h | 2 +-
2 files changed, 32 insertions(+), 9 deletions(-)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 39548ec645ec..1440a3b4b674 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -442,17 +442,21 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
return strcmp(parse_state->pmu_filter, pmu->name) != 0;
}
+static int parse_events_add_pmu(struct parse_events_state *parse_state,
+ struct list_head *list, struct perf_pmu *pmu,
+ const struct parse_events_terms *const_parsed_terms,
+ bool auto_merge_stats);
+
int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
struct parse_events_state *parse_state,
- struct parse_events_terms *head_config)
+ struct parse_events_terms *parsed_terms)
{
struct perf_pmu *pmu = NULL;
bool found_supported = false;
- const char *config_name = get_config_name(head_config);
- const char *metric_id = get_config_metric_id(head_config);
+ const char *config_name = get_config_name(parsed_terms);
+ const char *metric_id = get_config_metric_id(parsed_terms);
- /* Legacy cache events are only supported by core PMUs. */
- while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+ while ((pmu = perf_pmus__scan(pmu)) != NULL) {
LIST_HEAD(config_terms);
struct perf_event_attr attr;
int ret;
@@ -460,6 +464,24 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
if (parse_events__filter_pmu(parse_state, pmu))
continue;
+ if (perf_pmu__have_event(pmu, name)) {
+ /*
+ * The PMU has the event so add as not a legacy cache
+ * event.
+ */
+ ret = parse_events_add_pmu(parse_state, list, pmu,
+ parsed_terms,
+ perf_pmu__auto_merge_stats(pmu));
+ if (ret)
+ return ret;
+ continue;
+ }
+
+ if (!pmu->is_core) {
+ /* Legacy cache events are only supported by core PMUs. */
+ continue;
+ }
+
memset(&attr, 0, sizeof(attr));
attr.type = PERF_TYPE_HW_CACHE;
@@ -469,11 +491,12 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
found_supported = true;
- if (head_config) {
- if (config_attr(&attr, head_config, parse_state->error, config_term_common))
+ if (parsed_terms) {
+ if (config_attr(&attr, parsed_terms, parse_state->error,
+ config_term_common))
return -EINVAL;
- if (get_config_terms(head_config, &config_terms))
+ if (get_config_terms(parsed_terms, &config_terms))
return -ENOMEM;
}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index a331b9f0da2b..db47913e54bc 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -203,7 +203,7 @@ int parse_events_add_tool(struct parse_events_state *parse_state,
int tool_event);
int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
struct parse_events_state *parse_state,
- struct parse_events_terms *head_config);
+ struct parse_events_terms *parsed_terms);
int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config);
int parse_events_add_breakpoint(struct parse_events_state *parse_state,
struct list_head *list,
--
2.44.0.683.g7961c838ac-goog
next prev parent reply other threads:[~2024-04-16 6:15 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-16 6:15 [PATCH v2 00/16] Consistently prefer sysfs/json events Ian Rogers
2024-04-16 6:15 ` [PATCH v2 01/16] perf parse-events: Factor out '<event_or_pmu>/.../' parsing Ian Rogers
2024-04-16 6:15 ` [PATCH v2 02/16] perf parse-events: Directly pass PMU to parse_events_add_pmu Ian Rogers
2024-04-16 6:15 ` [PATCH v2 03/16] perf parse-events: Avoid copying an empty list Ian Rogers
2024-04-16 6:15 ` [PATCH v2 04/16] perf pmu: Refactor perf_pmu__match Ian Rogers
2024-04-16 6:15 ` [PATCH v2 05/16] perf tests parse-events: Use branches rather than cache-references Ian Rogers
2024-04-16 6:15 ` Ian Rogers [this message]
2024-04-16 6:15 ` [PATCH v2 07/16] perf parse-events: Handle PE_TERM_HW in name_or_raw Ian Rogers
2024-04-16 6:15 ` [PATCH v2 08/16] perf parse-events: Constify parse_events_add_numeric Ian Rogers
2024-04-16 6:15 ` [PATCH v2 09/16] perf parse-events: Prefer sysfs/json hardware events over legacy Ian Rogers
2024-04-16 6:15 ` [PATCH v2 10/16] perf parse-events: Inline parse_events_update_lists Ian Rogers
2024-04-16 6:15 ` [PATCH v2 11/16] perf parse-events: Improve error message for bad numbers Ian Rogers
2024-04-18 20:27 ` Liang, Kan
2024-04-18 21:07 ` Ian Rogers
2024-04-19 13:29 ` Liang, Kan
2024-04-27 1:35 ` Arnaldo Carvalho de Melo
2024-04-27 1:36 ` Arnaldo Carvalho de Melo
2024-04-27 22:05 ` Ian Rogers
2024-04-16 6:15 ` [PATCH v2 12/16] perf parse-events: Inline parse_events_evlist_error Ian Rogers
2024-04-16 6:15 ` [PATCH v2 13/16] perf parse-events: Improvements to modifier parsing Ian Rogers
2024-04-18 20:32 ` Liang, Kan
2024-04-19 6:22 ` Ian Rogers
2024-04-19 13:20 ` Liang, Kan
2024-04-24 15:18 ` Ian Rogers
2024-04-24 15:30 ` Liang, Kan
2024-04-16 6:15 ` [PATCH v2 14/16] perf parse-event: Constify event_symbol arrays Ian Rogers
2024-04-16 6:15 ` [PATCH v2 15/16] perf parse-events: Minor grouping tidy up Ian Rogers
2024-04-16 6:15 ` [PATCH v2 16/16] perf parse-events: Tidy the setting of the default event name Ian Rogers
2024-04-24 0:28 ` [PATCH v2 00/16] Consistently prefer sysfs/json events Atish Kumar Patra
2024-04-24 15:14 ` Ian Rogers
2024-04-24 15:34 ` Liang, Kan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240416061533.921723-7-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=atishp@rivosinc.com \
--cc=beeman@rivosinc.com \
--cc=bpf@vger.kernel.org \
--cc=james.clark@arm.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).