Series comparison

-[PATCH v1 0/4] Prefer sysfs/JSON events also when no PMU is provided
+[PATCH v6 0/2] Prefer sysfs/JSON events also when no PMU is provided
 ...
 to a more consistent cpu_cycles and avoided the problem. With these
 changes the problematic event will now be skipped, a large warning
 produced, and perf record will continue for the other PMU events. This
 solution was proposed by Arnaldo.
-Two minor changes have been added to help with the error message and
+v6: Rebase of v5 (dropping already merged patches):
-to work around issues occurring with "perf stat metrics (shadow stat)
+    https://lore.kernel.org/lkml/20250109222109.567031-1-irogers@google.com/
-test".
+    that unusually had an RFC posted for it:
     https://lore.kernel.org/lkml/Z7Z5kv75BMML2A1q@google.com/
     Note, this patch conflicts/contradicts:
     https://lore.kernel.org/lkml/20250312211623.2495798-1-irogers@google.com/
     that I posted so that we could either consistently prioritize
     sysfs/json (these patches) or legacy events (the other
     patches). That lack of event printing and encoding inconsistency
     is most prominent in the encoding of events like "instructions"
     which on hybrid are reported as "cpu_core/instructions/" but
     "instructions" before these patches gets a legacy encoding while
     "cpu_core/instructions/" gets a sysfs/json encoding. These patches
     make "instructions" always get a sysfs/json encoding while the
     alternate patches make it always get a legacy encoding.
-The patches have only been tested on my x86 non-hybrid laptop.
+v5: Follow Namhyung's suggestion and ignore the case where command
     line dummy events fail to open alongside other events that all
     fail to open. Note, the Tested-by tags are left on the series as
     v4 and v5 were changing an error case that doesn't occur in
     testing but was manually tested by myself.
-Ian Rogers (4):
+v4: Rework the no events opening change from v3 to make it handle
-  perf evsel: Add pmu_name helper
+    multiple dummy events. Sadly an evlist isn't empty if it just
-  perf stat: Fix find_stat for mixed legacy/non-legacy events
+    contains dummy events as the dummy event may be used with "perf
     record -e dummy .." as a way to determine whether permission
     issues exist. Other software events like cpu-clock would suffice
     for this, but the using dummy genie has left the bottle.
     Another problem is that we appear to have an excessive number of
     dummy events added, for example, we can likely avoid a dummy event
     and add sideband data to the original event. For auxtrace more
     dummy events may be opened too. Anyway, this has led to the
     approach taken in patch 3 where the number of dummy parsed events
     is computed. If the number of removed/failing-to-open non-dummy
     events matches the number of non-dummy events then we want to
     fail, but only if there are no parsed dummy events or if there was
     one then it must have opened. The math here is hard to read, but
     passes my manual testing.
 v3: Make no events opening for perf record a failure as suggested by
     James Clark and Aditya Bodkhe <Aditya.Bodkhe1@ibm.com>. Also,
     rebase.
 v2: Rebase and add tested-by tags from James Clark, Leo Yan and Atish
     Patra who have tested on RISC-V and ARM CPUs, including the
     problem case from before.
 Ian Rogers (2):
   perf record: Skip don't fail for events that don't open
   perf parse-events: Reapply "Prefer sysfs/JSON hardware events over
     legacy"
- tools/perf/builtin-record.c    | 22 +++++++---
+ tools/perf/builtin-record.c    | 47 ++++++++++++++++++---
  tools/perf/util/evsel.c        | 10 +++++
  tools/perf/util/evsel.h        |  1 +
  tools/perf/util/parse-events.c | 26 +++++++++---
  tools/perf/util/parse-events.l | 76 +++++++++++++++++-----------------
  tools/perf/util/parse-events.y | 60 ++++++++++++++++++---------
- tools/perf/util/pmus.c         | 20 +++++++--
+files changed, 139 insertions(+), 70 deletions(-)
  tools/perf/util/stat-shadow.c  |  3 +-
 files changed, 145 insertions(+), 73 deletions(-)
 --
-.47.0.163.g1226f6d8fa-goog
+.49.0.395.g12beb8f557-goog

-[PATCH v1 1/4] perf evsel: Add pmu_name helper
+Deleted patch
-Add helper to get the name of the evsel's PMU. This handles the case
-where there's no sysfs PMU via parse_events event_type helper.
-Signed-off-by: Ian Rogers <irogers@google.com>
----
- tools/perf/util/evsel.c | 10 ++++++++++
- tools/perf/util/evsel.h |  1 +
-files changed, 11 insertions(+)
-diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
-index XXXXXXX..XXXXXXX 100644
---- a/tools/perf/util/evsel.c
-+++ b/tools/perf/util/evsel.c
-@@ -XXX,XX +XXX,XX @@ int evsel__object_config(size_t object_size, int (*init)(struct evsel *evsel),
-     return 0;
- }
-+const char *evsel__pmu_name(const struct evsel *evsel)
-+{
-+    struct perf_pmu *pmu = evsel__find_pmu(evsel);
-+
-+    if (pmu)
-+        return pmu->name;
-+
-+    return event_type(evsel->core.attr.type);
-+}
-+
- #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
- int __evsel__sample_size(u64 sample_type)
-diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
-index XXXXXXX..XXXXXXX 100644
---- a/tools/perf/util/evsel.h
-+++ b/tools/perf/util/evsel.h
-@@ -XXX,XX +XXX,XX @@ int evsel__object_config(size_t object_size,
-              void (*fini)(struct evsel *evsel));
- struct perf_pmu *evsel__find_pmu(const struct evsel *evsel);
-+const char *evsel__pmu_name(const struct evsel *evsel);
- bool evsel__is_aux_event(const struct evsel *evsel);
- struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx);
---
-.47.0.163.g1226f6d8fa-goog

-[PATCH v1 2/4] perf stat: Fix find_stat for mixed legacy/non-legacy events
+Deleted patch
-Legacy events typically don't have a PMU when added leading to
-mismatched legacy/non-legacy cases in find_stat. Use evsel__find_pmu
-to make sure the evsel PMU is looked up. Update the evsel__find_pmu
-code to look for the PMU using the extended config type or, for legacy
-hardware/hw_cache events on non-hybrid systems, just use the core PMU.
-Before:
-```
-$ perf stat -e cycles,cpu/instructions/ -a sleep 1
- Performance counter stats for 'system wide':
-,309,764      cycles
-,326,491      cpu/instructions/
-.002555314 seconds time elapsed
-```
-After:
-```
-$ perf stat -e cycles,cpu/instructions/ -a sleep 1
- Performance counter stats for 'system wide':
-,676,332      cycles
-,235,762,487      cpu/instructions/                #    1.25  insn per cycle
-.002667198 seconds time elapsed
-```
-Fixes: 3612ca8e2935 ("perf stat: Fix the hard-coded metrics
-calculation on the hybrid")
-Signed-off-by: Ian Rogers <irogers@google.com>
----
- tools/perf/util/pmus.c        | 20 +++++++++++++++++---
- tools/perf/util/stat-shadow.c |  3 ++-
-files changed, 19 insertions(+), 4 deletions(-)
-diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
-index XXXXXXX..XXXXXXX 100644
---- a/tools/perf/util/pmus.c
-+++ b/tools/perf/util/pmus.c
-@@ -XXX,XX +XXX,XX @@ char *perf_pmus__default_pmu_name(void)
- struct perf_pmu *evsel__find_pmu(const struct evsel *evsel)
- {
-     struct perf_pmu *pmu = evsel->pmu;
-+    bool legacy_core_type;
--    if (!pmu) {
--        pmu = perf_pmus__find_by_type(evsel->core.attr.type);
--        ((struct evsel *)evsel)->pmu = pmu;
-+    if (pmu)
-+        return pmu;
-+
-+    pmu = perf_pmus__find_by_type(evsel->core.attr.type);
-+    legacy_core_type =
-+        evsel->core.attr.type == PERF_TYPE_HARDWARE ||
-+        evsel->core.attr.type == PERF_TYPE_HW_CACHE;
-+    if (!pmu && legacy_core_type) {
-+        if (perf_pmus__supports_extended_type()) {
-+            u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
-+
-+            pmu = perf_pmus__find_by_type(type);
-+        } else {
-+            pmu = perf_pmus__find_core_pmu();
-+        }
-     }
-+    ((struct evsel *)evsel)->pmu = pmu;
-     return pmu;
- }
-diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
-index XXXXXXX..XXXXXXX 100644
---- a/tools/perf/util/stat-shadow.c
-+++ b/tools/perf/util/stat-shadow.c
-@@ -XXX,XX +XXX,XX @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
- {
-     struct evsel *cur;
-     int evsel_ctx = evsel_context(evsel);
-+    struct perf_pmu *evsel_pmu = evsel__find_pmu(evsel);
-     evlist__for_each_entry(evsel->evlist, cur) {
-         struct perf_stat_aggr *aggr;
-@@ -XXX,XX +XXX,XX @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
-          * Except the SW CLOCK events,
-          * ignore if not the PMU we're looking for.
-          */
--        if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu))
-+        if ((type != STAT_NSECS) && (evsel_pmu != evsel__find_pmu(cur)))
-             continue;
-         aggr = &cur->stats->aggr[aggr_idx];
---
-.47.0.163.g1226f6d8fa-goog

-[PATCH v1 3/4] perf record: Skip don't fail for events that don't open
+[PATCH v6 1/2] perf record: Skip don't fail for events that don't open
 ...
        FINISHED_INIT events:          1  ( 0.0%)
 cycles stats:
               SAMPLE events:         87
 ```
-Note, if all events fail to open then the data file will contain no
+If all events fail to open then the perf record will fail:
-samples. This is deliberate as at the point the events are opened
+```
-there are other events, such as the dummy event for sideband data, and
+$ perf record -e LLC-prefetch-read true
-these events will succeed in opening even if the user specified ones
+Error:
-don't. Having a mix of open and broken events leads to a problem of
+Failure to open event 'LLC-prefetch-read' on PMU 'cpu' which will be removed.
-identifying different sources of events.
+The LLC-prefetch-read event is not supported.
 Error:
 Failure to open any events for recording
 ```
 As an evlist may have dummy events that open when all command line
 events fail we ignore dummy events when detecting if at least some
 events open. This still permits the dummy event on its own to be used
 as a permission check:
 ```
 $ perf record -e dummy true
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.046 MB perf.data ]
 ```
 but allows failure when a dummy event is implicilty inserted or when
 there are insufficient permissions to open it:
 ```
 $ perf record -e LLC-prefetch-read -a true
 Error:
 Failure to open event 'LLC-prefetch-read' on PMU 'cpu' which will be removed.
 The LLC-prefetch-read event is not supported.
 Error:
 Failure to open any events for recording
 ```
 The issue with legacy events is that on RISC-V they want the driver to
 not have mappings from legacy to non-legacy config encodings for each
 vendor/model due to size, complexity and difficulty to update. It was
 reported that on ARM Apple-M? CPUs the legacy mapping in the driver
 ...
 messages like those above because of the uncore PMU advertising legacy
 event names.
 Suggested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
 Signed-off-by: Ian Rogers <irogers@google.com>
+Tested-by: James Clark <james.clark@linaro.org>
+Tested-by: Leo Yan <leo.yan@arm.com>
+Tested-by: Atish Patra <atishp@rivosinc.com>
 ---
- tools/perf/builtin-record.c | 22 +++++++++++++++++-----
+ tools/perf/builtin-record.c | 47 ++++++++++++++++++++++++++++++++-----
-file changed, 17 insertions(+), 5 deletions(-)
+file changed, 41 insertions(+), 6 deletions(-)
 diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
 index XXXXXXX..XXXXXXX 100644
 --- a/tools/perf/builtin-record.c
 +++ b/tools/perf/builtin-record.c
+@@ -XXX,XX +XXX,XX @@ static int record__config_tracking_events(struct record *rec)
+      */
+     if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
+         perf_pmus__num_core_pmus() > 1) {
+-
+         /*
+          * User space tasks can migrate between CPUs, so when tracing
+          * selected CPUs, sideband for all CPUs is still needed.
 @@ -XXX,XX +XXX,XX @@ static int record__open(struct record *rec)
      struct perf_session *session = rec->session;
      struct record_opts *opts = &rec->opts;
      int rc = 0;
 +    bool skipped = false;
 ...
      }
 +    if (skipped) {
 +        struct evsel *tmp;
 +        int idx = 0;
++        bool evlist_empty = true;
 +
++        /* Remove evsels that failed to open and update indices. */
 +        evlist__for_each_entry_safe(evlist, tmp, pos) {
-+            if (pos->skippable)
++            if (pos->skippable) {
 +                evlist__remove(evlist, pos);
++                continue;
++            }
++
++            /*
++             * Note, dummy events may be command line parsed or
++             * added by the tool. We care about supporting `perf
++             * record -e dummy` which may be used as a permission
++             * check. Dummy events that are added to the command
++             * line and opened along with other events that fail,
++             * will still fail as if the dummy events were tool
++             * added events for the sake of code simplicity.
++             */
++            if (!evsel__is_dummy_event(pos))
++                evlist_empty = false;
++        }
++        evlist__for_each_entry(evlist, pos) {
 +            pos->core.idx = idx++;
++        }
++        /* If list is empty then fail. */
++        if (evlist_empty) {
++            ui__error("Failure to open any events for recording.\n");
++            rc = -1;
++            goto out;
 +        }
 +    }
      if (symbol_conf.kptr_restrict && !evlist__exclude_kernel(evlist)) {
          pr_warning(
  "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 --
-.47.0.163.g1226f6d8fa-goog
+.49.0.395.g12beb8f557-goog

-[PATCH v1 4/4] perf parse-events: Reapply "Prefer sysfs/JSON hardware events over legacy"
+[PATCH v6 2/2] perf parse-events: Reapply "Prefer sysfs/JSON hardware events over legacy"
 ...
 related code simplified.
 Signed-off-by: Ian Rogers <irogers@google.com>
 Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
 Tested-by: Atish Patra <atishp@rivosinc.com>
+Tested-by: James Clark <james.clark@linaro.org>
+Tested-by: Leo Yan <leo.yan@arm.com>
 Cc: Adrian Hunter <adrian.hunter@intel.com>
 Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
 Cc: Beeman Strong <beeman@rivosinc.com>
 Cc: Ingo Molnar <mingo@redhat.com>
-Cc: James Clark <james.clark@arm.com>
 Cc: Jiri Olsa <jolsa@kernel.org>
 Cc: Mark Rutland <mark.rutland@arm.com>
 Cc: Namhyung Kim <namhyung@kernel.org>
 Cc: Peter Zijlstra <peterz@infradead.org>
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 ...
 +    yylval->hardware_event.str = strdup(text);
 +    yylval->hardware_event.num = config;
      return PE_TERM_HW;
  }
-@@ -XXX,XX +XXX,XX @@ percore            { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
+@@ -XXX,XX +XXX,XX @@ aux-output        { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
- aux-output        { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
+ aux-action        { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); }
  aux-sample-size        { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
  metric-id        { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); }
 -cpu-cycles|cycles                { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
 -stalled-cycles-frontend|idle-cycles-frontend    { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
 -stalled-cycles-backend|idle-cycles-backend    { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
 ...
 +                /*head_config=*/NULL, /*wildcard=*/false);
      if (err)
          PE_ABORT(err);
      $$ = list;
 --
-.47.0.163.g1226f6d8fa-goog
+.49.0.395.g12beb8f557-goog

At the RISC-V summit the topic of avoiding event data being in the
RISC-V PMU kernel driver came up. There is a preference for sysfs/JSON
events being the priority when no PMU is provided so that legacy
events maybe supported via json. Originally Mark Rutland also
expressed at LPC 2023 that doing this would resolve bugs on ARM Apple
M? processors, but James Clark more recently tested this and believes
the driver issues there may not have existed or have been resolved. In
any case, it is inconsistent that with a PMU event names avoid legacy
encodings, but when wildcarding PMUs (ie without a PMU with the event
name) the legacy encodings have priority.

The patch doing this work was reverted in a v6.10 release candidate
as, even though the patch was posted for weeks and had been on
linux-next for weeks without issue, Linus was in the habit of using
explicit legacy events with unsupported precision options on his
Neoverse-N1. This machine has SLC PMU events for bus and CPU cycles
where ARM decided to call the events bus_cycles and cycles, the latter
being also a legacy event name. ARM haven't renamed the cycles event
to a more consistent cpu_cycles and avoided the problem. With these
changes the problematic event will now be skipped, a large warning
produced, and perf record will continue for the other PMU events. This
solution was proposed by Arnaldo.

Two minor changes have been added to help with the error message and
to work around issues occurring with "perf stat metrics (shadow stat)
test".

The patches have only been tested on my x86 non-hybrid laptop.

Ian Rogers (4):
  perf evsel: Add pmu_name helper
  perf stat: Fix find_stat for mixed legacy/non-legacy events
  perf record: Skip don't fail for events that don't open
  perf parse-events: Reapply "Prefer sysfs/JSON hardware events over
    legacy"

tools/perf/builtin-record.c    | 22 +++++++---
 tools/perf/util/evsel.c        | 10 +++++
 tools/perf/util/evsel.h        |  1 +
 tools/perf/util/parse-events.c | 26 +++++++++---
 tools/perf/util/parse-events.l | 76 +++++++++++++++++-----------------
 tools/perf/util/parse-events.y | 60 ++++++++++++++++++---------
 tools/perf/util/pmus.c         | 20 +++++++--
 tools/perf/util/stat-shadow.c  |  3 +-
 8 files changed, 145 insertions(+), 73 deletions(-)

-- 
2.47.0.163.g1226f6d8fa-goog

Add helper to get the name of the evsel's PMU. This handles the case
where there's no sysfs PMU via parse_events event_type helper.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/evsel.c | 10 ++++++++++
 tools/perf/util/evsel.h |  1 +
 2 files changed, 11 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -XXX,XX +XXX,XX @@ int evsel__object_config(size_t object_size, int (*init)(struct evsel *evsel),
 	return 0;
 }
 
+const char *evsel__pmu_name(const struct evsel *evsel)
+{
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
+
+	if (pmu)
+		return pmu->name;
+
+	return event_type(evsel->core.attr.type);
+}
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
 
 int __evsel__sample_size(u64 sample_type)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -XXX,XX +XXX,XX @@ int evsel__object_config(size_t object_size,
 			 void (*fini)(struct evsel *evsel));
 
 struct perf_pmu *evsel__find_pmu(const struct evsel *evsel);
+const char *evsel__pmu_name(const struct evsel *evsel);
 bool evsel__is_aux_event(const struct evsel *evsel);
 
 struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx);
-- 
2.47.0.163.g1226f6d8fa-goog

Legacy events typically don't have a PMU when added leading to
mismatched legacy/non-legacy cases in find_stat. Use evsel__find_pmu
to make sure the evsel PMU is looked up. Update the evsel__find_pmu
code to look for the PMU using the extended config type or, for legacy
hardware/hw_cache events on non-hybrid systems, just use the core PMU.

Before:
```
$ perf stat -e cycles,cpu/instructions/ -a sleep 1
 Performance counter stats for 'system wide':

215,309,764      cycles
        44,326,491      cpu/instructions/

1.002555314 seconds time elapsed
```
After:
```
$ perf stat -e cycles,cpu/instructions/ -a sleep 1

Performance counter stats for 'system wide':

990,676,332      cycles
     1,235,762,487      cpu/instructions/                #    1.25  insn per cycle

1.002667198 seconds time elapsed
```

Fixes: 3612ca8e2935 ("perf stat: Fix the hard-coded metrics
calculation on the hybrid")
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/pmus.c        | 20 +++++++++++++++++---
 tools/perf/util/stat-shadow.c |  3 ++-
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -XXX,XX +XXX,XX @@ char *perf_pmus__default_pmu_name(void)
 struct perf_pmu *evsel__find_pmu(const struct evsel *evsel)
 {
 	struct perf_pmu *pmu = evsel->pmu;
+	bool legacy_core_type;
 
-	if (!pmu) {
-		pmu = perf_pmus__find_by_type(evsel->core.attr.type);
-		((struct evsel *)evsel)->pmu = pmu;
+	if (pmu)
+		return pmu;
+
+	pmu = perf_pmus__find_by_type(evsel->core.attr.type);
+	legacy_core_type =
+		evsel->core.attr.type == PERF_TYPE_HARDWARE ||
+		evsel->core.attr.type == PERF_TYPE_HW_CACHE;
+	if (!pmu && legacy_core_type) {
+		if (perf_pmus__supports_extended_type()) {
+			u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+
+			pmu = perf_pmus__find_by_type(type);
+		} else {
+			pmu = perf_pmus__find_core_pmu();
+		}
 	}
+	((struct evsel *)evsel)->pmu = pmu;
 	return pmu;
 }
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -XXX,XX +XXX,XX @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
 {
 	struct evsel *cur;
 	int evsel_ctx = evsel_context(evsel);
+	struct perf_pmu *evsel_pmu = evsel__find_pmu(evsel);
 
 	evlist__for_each_entry(evsel->evlist, cur) {
 		struct perf_stat_aggr *aggr;
@@ -XXX,XX +XXX,XX @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
 		 * Except the SW CLOCK events,
 		 * ignore if not the PMU we're looking for.
 		 */
-		if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu))
+		if ((type != STAT_NSECS) && (evsel_pmu != evsel__find_pmu(cur)))
 			continue;
 
 		aggr = &cur->stats->aggr[aggr_idx];
-- 
2.47.0.163.g1226f6d8fa-goog

Whilst for many tools it is an expected behavior that failure to open
a perf event is a failure, ARM decided to name PMU events the same as
legacy events and then failed to rename such events on a server uncore
SLC PMU. As perf's default behavior when no PMU is specified is to
open the event on all PMUs that advertise/"have" the event, this
yielded failures when trying to make the priority of legacy and
sysfs/json events uniform - something requested by RISC-V and ARM. A
legacy event user on ARM hardware may find their event opened on an
uncore PMU which for perf record will fail. Arnaldo suggested skipping
such events which this patch implements. Rather than have the skipping
conditional on running on ARM, the skipping is done on all
architectures as such a fundamental behavioral difference could lead
to problems with tools built/depending on perf.

An example of perf record failing to open events on x86 is:
```
$ perf record -e data_read,cycles,LLC-prefetch-read -a sleep 0.1
Error:
Failure to open event 'data_read' on PMU 'uncore_imc_free_running_0' which will be removed.
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (data_read).
"dmesg | grep -i perf" may provide additional information.

Error:
Failure to open event 'data_read' on PMU 'uncore_imc_free_running_1' which will be removed.
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (data_read).
"dmesg | grep -i perf" may provide additional information.

Error:
Failure to open event 'LLC-prefetch-read' on PMU 'cpu' which will be removed.
The LLC-prefetch-read event is not supported.
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 2.188 MB perf.data (87 samples) ]

$ perf report --stats
Aggregated stats:
               TOTAL events:      17255
                MMAP events:        284  ( 1.6%)
                COMM events:       1961  (11.4%)
                EXIT events:          1  ( 0.0%)
                FORK events:       1960  (11.4%)
              SAMPLE events:         87  ( 0.5%)
               MMAP2 events:      12836  (74.4%)
             KSYMBOL events:         83  ( 0.5%)
           BPF_EVENT events:         36  ( 0.2%)
      FINISHED_ROUND events:          2  ( 0.0%)
            ID_INDEX events:          1  ( 0.0%)
          THREAD_MAP events:          1  ( 0.0%)
             CPU_MAP events:          1  ( 0.0%)
           TIME_CONV events:          1  ( 0.0%)
       FINISHED_INIT events:          1  ( 0.0%)
cycles stats:
              SAMPLE events:         87
```

Note, if all events fail to open then the data file will contain no
samples. This is deliberate as at the point the events are opened
there are other events, such as the dummy event for sideband data, and
these events will succeed in opening even if the user specified ones
don't. Having a mix of open and broken events leads to a problem of
identifying different sources of events.

The issue with legacy events is that on RISC-V they want the driver to
not have mappings from legacy to non-legacy config encodings for each
vendor/model due to size, complexity and difficulty to update. It was
reported that on ARM Apple-M? CPUs the legacy mapping in the driver
was broken and the sysfs/json events should always take precedent,
however, it isn't clear this is still the case. It is the case that
without working around this issue a legacy event like cycles without a
PMU can encode differently than when specified with a PMU - the
non-PMU version favoring legacy encodings, the PMU one avoiding legacy
encodings.

The patch removes events and then adjusts the idx value for each
evsel. This is done so that the dense xyarrays used for file
descriptors, etc. don't contain broken entries. As event opening
happens relatively late in the record process, use of the idx value
before the open will have become corrupted, so it is expected there
are latent bugs hidden behind this change - the change is best
effort. As the only vendor that has broken event names is ARM, this
will principally effect ARM users. They will also experience warning
messages like those above because of the uncore PMU advertising legacy
event names.

Suggested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/builtin-record.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -XXX,XX +XXX,XX @@ static int record__open(struct record *rec)
 	struct perf_session *session = rec->session;
 	struct record_opts *opts = &rec->opts;
 	int rc = 0;
+	bool skipped = false;
 
 	evlist__for_each_entry(evlist, pos) {
 try_again:
@@ -XXX,XX +XXX,XX @@ static int record__open(struct record *rec)
 			        pos = evlist__reset_weak_group(evlist, pos, true);
 				goto try_again;
 			}
-			rc = -errno;
 			evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg));
-			ui__error("%s\n", msg);
-			goto out;
+			ui__error("Failure to open event '%s' on PMU '%s' which will be removed.\n%s\n",
+				  evsel__name(pos), evsel__pmu_name(pos), msg);
+			pos->skippable = true;
+			skipped = true;
+		} else {
+			pos->supported = true;
 		}
-
-		pos->supported = true;
 	}
 
+	if (skipped) {
+		struct evsel *tmp;
+		int idx = 0;
+
+		evlist__for_each_entry_safe(evlist, tmp, pos) {
+			if (pos->skippable)
+				evlist__remove(evlist, pos);
+			pos->core.idx = idx++;
+		}
+	}
 	if (symbol_conf.kptr_restrict && !evlist__exclude_kernel(evlist)) {
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
-- 
2.47.0.163.g1226f6d8fa-goog

Originally posted and merged from:
https://lore.kernel.org/r/20240416061533.921723-10-irogers@google.com
This reverts commit 4f1b067359ac8364cdb7f9fda41085fa85789d0f although
the patch is now smaller due to related fixes being applied in commit
22a4db3c3603 ("perf evsel: Add alternate_hw_config and use in
evsel__match").
The original commit message was:

It was requested that RISC-V be able to add events to the perf tool so
the PMU driver didn't need to map legacy events to config encodings:
https://lore.kernel.org/lkml/20240217005738.3744121-1-atishp@rivosinc.com/

This change makes the priority of events specified without a PMU the
same as those specified with a PMU, namely sysfs and JSON events are
checked first before using the legacy encoding.

The hw_term is made more generic as a hardware_event that encodes a
pair of string and int value, allowing parse_events_multi_pmu_add to
fall back on a known encoding when the sysfs/JSON adding fails for
core events. As this covers PE_VALUE_SYM_HW, that token is removed and
related code simplified.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Atish Patra <atishp@rivosinc.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Beeman Strong <beeman@rivosinc.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 26 +++++++++---
 tools/perf/util/parse-events.l | 76 +++++++++++++++++-----------------
 tools/perf/util/parse-events.y | 60 ++++++++++++++++++---------
 3 files changed, 98 insertions(+), 64 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -XXX,XX +XXX,XX @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	struct list_head *list = NULL;
 	struct perf_pmu *pmu = NULL;
 	YYLTYPE *loc = loc_;
-	int ok = 0;
-	const char *config;
+	int ok = 0, core_ok = 0;
+	const char *tmp;
 	struct parse_events_terms parsed_terms;
 
 	*listp = NULL;
@@ -XXX,XX +XXX,XX @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			return ret;
 	}
 
-	config = strdup(event_name);
-	if (!config)
+	tmp = strdup(event_name);
+	if (!tmp)
 		goto out_err;
 
 	if (parse_events_term__num(&term,
 				   PARSE_EVENTS__TERM_TYPE_USER,
-				   config, /*num=*/1, /*novalue=*/true,
+				   tmp, /*num=*/1, /*novalue=*/true,
 				   loc, /*loc_val=*/NULL) < 0) {
-		zfree(&config);
+		zfree(&tmp);
 		goto out_err;
 	}
 	list_add_tail(&term->list, &parsed_terms.terms);
@@ -XXX,XX +XXX,XX @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			pr_debug("%s -> %s/%s/\n", event_name, pmu->name, sb.buf);
 			strbuf_release(&sb);
 			ok++;
+			if (pmu->is_core)
+				core_ok++;
 		}
 	}
 
@@ -XXX,XX +XXX,XX @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 		}
 	}
 
+	if (hw_config != PERF_COUNT_HW_MAX && !core_ok) {
+		/*
+		 * The event wasn't found on core PMUs but it has a hardware
+		 * config version to try.
+		 */
+		if (!parse_events_add_numeric(parse_state, list,
+						PERF_TYPE_HARDWARE, hw_config,
+						const_parsed_terms,
+						/*wildcard=*/true))
+			ok++;
+	}
+
 out_err:
 	parse_events_terms__exit(&parsed_terms);
 	if (ok)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -XXX,XX +XXX,XX @@ do {								\
 	yyless(0);						\
 } while (0)
 
-static int sym(yyscan_t scanner, int type, int config)
+static int sym(yyscan_t scanner, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 
-	yylval->num = (type << 16) + config;
-	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
+	yylval->num = config;
+	return PE_VALUE_SYM_SW;
 }
 
 static int term(yyscan_t scanner, enum parse_events__term_type type)
@@ -XXX,XX +XXX,XX @@ static int term(yyscan_t scanner, enum parse_events__term_type type)
 	return PE_TERM;
 }
 
-static int hw_term(yyscan_t scanner, int config)
+static int hw(yyscan_t scanner, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 	char *text = parse_events_get_text(scanner);
 
-	yylval->hardware_term.str = strdup(text);
-	yylval->hardware_term.num = PERF_TYPE_HARDWARE + config;
+	yylval->hardware_event.str = strdup(text);
+	yylval->hardware_event.num = config;
 	return PE_TERM_HW;
 }
 
@@ -XXX,XX +XXX,XX @@ percore			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
 aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 aux-sample-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
 metric-id		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); }
-cpu-cycles|cycles				{ return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
-stalled-cycles-frontend|idle-cycles-frontend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
-stalled-cycles-backend|idle-cycles-backend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
-instructions					{ return hw_term(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
-cache-references				{ return hw_term(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
-cache-misses					{ return hw_term(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
-branch-instructions|branches			{ return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
-branch-misses					{ return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
-bus-cycles					{ return hw_term(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
-ref-cycles					{ return hw_term(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-cycles|cycles				{ return hw(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return hw(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return hw(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return hw(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return hw(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return hw(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
 r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
 r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 ,			{ return ','; }
@@ -XXX,XX +XXX,XX @@ r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 <<EOF>>			{ BEGIN(INITIAL); }
 }
 
-cpu-cycles|cycles				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
-stalled-cycles-frontend|idle-cycles-frontend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
-stalled-cycles-backend|idle-cycles-backend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
-instructions					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
-cache-references				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
-cache-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
-branch-instructions|branches			{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
-branch-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
-bus-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
-ref-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
-cpu-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
-task-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
-page-faults|faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
-minor-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
-major-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
-context-switches|cs				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
-cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
-alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
-emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
-dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
-bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
-cgroup-switches					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); }
+cpu-cycles|cycles				{ return hw(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return hw(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return hw(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return hw(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return hw(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return hw(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-clock					{ return sym(yyscanner, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock					{ return sym(yyscanner, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults				{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults					{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults					{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs				{ return sym(yyscanner, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations			{ return sym(yyscanner, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults				{ return sym(yyscanner, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults				{ return sym(yyscanner, PERF_COUNT_SW_EMULATION_FAULTS); }
+dummy						{ return sym(yyscanner, PERF_COUNT_SW_DUMMY); }
+bpf-output					{ return sym(yyscanner, PERF_COUNT_SW_BPF_OUTPUT); }
+cgroup-switches					{ return sym(yyscanner, PERF_COUNT_SW_CGROUP_SWITCHES); }
 
 {lc_type}			{ return str(yyscanner, PE_LEGACY_CACHE); }
 {lc_type}-{lc_op_result}	{ return str(yyscanner, PE_LEGACY_CACHE); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 %}
 
 %token PE_START_EVENTS PE_START_TERMS
-%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_TERM
+%token PE_VALUE PE_VALUE_SYM_SW PE_TERM
 %token PE_EVENT_NAME
 %token PE_RAW PE_NAME
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP PE_BP_COLON PE_BP_SLASH
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_DRV_CFG_TERM
 %token PE_TERM_HW
 %type <num> PE_VALUE
-%type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
 %type <mod> PE_MODIFIER_EVENT
 %type <term_type> PE_TERM
-%type <num> value_sym
 %type <str> PE_RAW
 %type <str> PE_NAME
 %type <str> PE_LEGACY_CACHE
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <list_terms> opt_pmu_config
 %destructor { parse_events_terms__delete ($$); } <list_terms>
 %type <list_evsel> event_pmu
+%type <list_evsel> event_legacy_hardware
 %type <list_evsel> event_legacy_symbol
 %type <list_evsel> event_legacy_cache
 %type <list_evsel> event_legacy_mem
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 %destructor { free_list_evsel ($$); } <list_evsel>
 %type <tracepoint_name> tracepoint_name
 %destructor { free ($$.sys); free ($$.event); } <tracepoint_name>
-%type <hardware_term> PE_TERM_HW
-%destructor { free ($$.str); } <hardware_term>
+%type <hardware_event> PE_TERM_HW
+%destructor { free ($$.str); } <hardware_event>
 
 %union
 {
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 		char *sys;
 		char *event;
 	} tracepoint_name;
-	struct hardware_term {
+	struct hardware_event {
 		char *str;
 		u64 num;
-	} hardware_term;
+	} hardware_event;
 }
 %%
 
@@ -XXX,XX +XXX,XX @@ PE_EVENT_NAME event_def
 event_def
 
 event_def: event_pmu |
+	   event_legacy_hardware |
 	   event_legacy_symbol |
 	   event_legacy_cache sep_dc |
 	   event_legacy_mem sep_dc |
@@ -XXX,XX +XXX,XX @@ PE_NAME sep_dc
 	$$ = list;
 }
 
-value_sym:
-PE_VALUE_SYM_HW
+event_legacy_hardware:
+PE_TERM_HW opt_pmu_config
+{
+	/* List of created evsels. */
+	struct list_head *list = NULL;
+	int err = parse_events_multi_pmu_add(_parse_state, $1.str, $1.num, $2, &list, &@1);
+
+	free($1.str);
+	parse_events_terms__delete($2);
+	if (err)
+		PE_ABORT(err);
+
+	$$ = list;
+}
 |
-PE_VALUE_SYM_SW
+PE_TERM_HW sep_dc
+{
+	struct list_head *list;
+	int err;
+
+	err = parse_events_multi_pmu_add(_parse_state, $1.str, $1.num, NULL, &list, &@1);
+	free($1.str);
+	if (err)
+		PE_ABORT(err);
+	$$ = list;
+}
 
 event_legacy_symbol:
-value_sym '/' event_config '/'
+PE_VALUE_SYM_SW '/' event_config '/'
 {
 	struct list_head *list;
-	int type = $1 >> 16;
-	int config = $1 & 255;
 	int err;
-	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard);
+	err = parse_events_add_numeric(_parse_state, list,
+				/*type=*/PERF_TYPE_SOFTWARE, /*config=*/$1,
+				$3, /*wildcard=*/false);
 	parse_events_terms__delete($3);
 	if (err) {
 		free_list_evsel(list);
@@ -XXX,XX +XXX,XX @@ value_sym '/' event_config '/'
 	$$ = list;
 }
 |
-value_sym sep_slash_slash_dc
+PE_VALUE_SYM_SW sep_slash_slash_dc
 {
 	struct list_head *list;
-	int type = $1 >> 16;
-	int config = $1 & 255;
-	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 	int err;
 
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard);
+	err = parse_events_add_numeric(_parse_state, list,
+				/*type=*/PERF_TYPE_SOFTWARE, /*config=*/$1,
+				/*head_config=*/NULL, /*wildcard=*/false);
 	if (err)
 		PE_ABORT(err);
 	$$ = list;
-- 
2.47.0.163.g1226f6d8fa-goog

v6: Rebase of v5 (dropping already merged patches):
    https://lore.kernel.org/lkml/20250109222109.567031-1-irogers@google.com/
    that unusually had an RFC posted for it:
    https://lore.kernel.org/lkml/Z7Z5kv75BMML2A1q@google.com/
    Note, this patch conflicts/contradicts:
    https://lore.kernel.org/lkml/20250312211623.2495798-1-irogers@google.com/
    that I posted so that we could either consistently prioritize
    sysfs/json (these patches) or legacy events (the other
    patches). That lack of event printing and encoding inconsistency
    is most prominent in the encoding of events like "instructions"
    which on hybrid are reported as "cpu_core/instructions/" but
    "instructions" before these patches gets a legacy encoding while
    "cpu_core/instructions/" gets a sysfs/json encoding. These patches
    make "instructions" always get a sysfs/json encoding while the
    alternate patches make it always get a legacy encoding.

v5: Follow Namhyung's suggestion and ignore the case where command
    line dummy events fail to open alongside other events that all
    fail to open. Note, the Tested-by tags are left on the series as
    v4 and v5 were changing an error case that doesn't occur in
    testing but was manually tested by myself.

v4: Rework the no events opening change from v3 to make it handle
    multiple dummy events. Sadly an evlist isn't empty if it just
    contains dummy events as the dummy event may be used with "perf
    record -e dummy .." as a way to determine whether permission
    issues exist. Other software events like cpu-clock would suffice
    for this, but the using dummy genie has left the bottle.

Another problem is that we appear to have an excessive number of
    dummy events added, for example, we can likely avoid a dummy event
    and add sideband data to the original event. For auxtrace more
    dummy events may be opened too. Anyway, this has led to the
    approach taken in patch 3 where the number of dummy parsed events
    is computed. If the number of removed/failing-to-open non-dummy
    events matches the number of non-dummy events then we want to
    fail, but only if there are no parsed dummy events or if there was
    one then it must have opened. The math here is hard to read, but
    passes my manual testing.

v3: Make no events opening for perf record a failure as suggested by
    James Clark and Aditya Bodkhe <Aditya.Bodkhe1@ibm.com>. Also,
    rebase.

v2: Rebase and add tested-by tags from James Clark, Leo Yan and Atish
    Patra who have tested on RISC-V and ARM CPUs, including the
    problem case from before.

Ian Rogers (2):
  perf record: Skip don't fail for events that don't open
  perf parse-events: Reapply "Prefer sysfs/JSON hardware events over
    legacy"

tools/perf/builtin-record.c    | 47 ++++++++++++++++++---
 tools/perf/util/parse-events.c | 26 +++++++++---
 tools/perf/util/parse-events.l | 76 +++++++++++++++++-----------------
 tools/perf/util/parse-events.y | 60 ++++++++++++++++++---------
 4 files changed, 139 insertions(+), 70 deletions(-)

-- 
2.49.0.395.g12beb8f557-goog

If all events fail to open then the perf record will fail:
```
$ perf record -e LLC-prefetch-read true
Error:
Failure to open event 'LLC-prefetch-read' on PMU 'cpu' which will be removed.
The LLC-prefetch-read event is not supported.
Error:
Failure to open any events for recording
```

As an evlist may have dummy events that open when all command line
events fail we ignore dummy events when detecting if at least some
events open. This still permits the dummy event on its own to be used
as a permission check:
```
$ perf record -e dummy true
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.046 MB perf.data ]
```
but allows failure when a dummy event is implicilty inserted or when
there are insufficient permissions to open it:
```
$ perf record -e LLC-prefetch-read -a true
Error:
Failure to open event 'LLC-prefetch-read' on PMU 'cpu' which will be removed.
The LLC-prefetch-read event is not supported.
Error:
Failure to open any events for recording
```

Suggested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Tested-by: Atish Patra <atishp@rivosinc.com>
---
 tools/perf/builtin-record.c | 47 ++++++++++++++++++++++++++++++++-----
 1 file changed, 41 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -XXX,XX +XXX,XX @@ static int record__config_tracking_events(struct record *rec)
 	 */
 	if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
 	    perf_pmus__num_core_pmus() > 1) {
-
 		/*
 		 * User space tasks can migrate between CPUs, so when tracing
 		 * selected CPUs, sideband for all CPUs is still needed.
@@ -XXX,XX +XXX,XX @@ static int record__open(struct record *rec)
 	struct perf_session *session = rec->session;
 	struct record_opts *opts = &rec->opts;
 	int rc = 0;
+	bool skipped = false;
 
 	evlist__for_each_entry(evlist, pos) {
 try_again:
@@ -XXX,XX +XXX,XX @@ static int record__open(struct record *rec)
 			        pos = evlist__reset_weak_group(evlist, pos, true);
 				goto try_again;
 			}
-			rc = -errno;
 			evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg));
-			ui__error("%s\n", msg);
-			goto out;
+			ui__error("Failure to open event '%s' on PMU '%s' which will be removed.\n%s\n",
+				  evsel__name(pos), evsel__pmu_name(pos), msg);
+			pos->skippable = true;
+			skipped = true;
+		} else {
+			pos->supported = true;
 		}
-
-		pos->supported = true;
 	}
 
+	if (skipped) {
+		struct evsel *tmp;
+		int idx = 0;
+		bool evlist_empty = true;
+
+		/* Remove evsels that failed to open and update indices. */
+		evlist__for_each_entry_safe(evlist, tmp, pos) {
+			if (pos->skippable) {
+				evlist__remove(evlist, pos);
+				continue;
+			}
+
+			/*
+			 * Note, dummy events may be command line parsed or
+			 * added by the tool. We care about supporting `perf
+			 * record -e dummy` which may be used as a permission
+			 * check. Dummy events that are added to the command
+			 * line and opened along with other events that fail,
+			 * will still fail as if the dummy events were tool
+			 * added events for the sake of code simplicity.
+			 */
+			if (!evsel__is_dummy_event(pos))
+				evlist_empty = false;
+		}
+		evlist__for_each_entry(evlist, pos) {
+			pos->core.idx = idx++;
+		}
+		/* If list is empty then fail. */
+		if (evlist_empty) {
+			ui__error("Failure to open any events for recording.\n");
+			rc = -1;
+			goto out;
+		}
+	}
 	if (symbol_conf.kptr_restrict && !evlist__exclude_kernel(evlist)) {
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
-- 
2.49.0.395.g12beb8f557-goog

This change makes the priority of events specified without a PMU the
same as those specified with a PMU, namely sysfs and JSON events are
checked first before using the legacy encoding.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Atish Patra <atishp@rivosinc.com>
Tested-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Beeman Strong <beeman@rivosinc.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 26 +++++++++---
 tools/perf/util/parse-events.l | 76 +++++++++++++++++-----------------
 tools/perf/util/parse-events.y | 60 ++++++++++++++++++---------
 3 files changed, 98 insertions(+), 64 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -XXX,XX +XXX,XX @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	struct list_head *list = NULL;
 	struct perf_pmu *pmu = NULL;
 	YYLTYPE *loc = loc_;
-	int ok = 0;
-	const char *config;
+	int ok = 0, core_ok = 0;
+	const char *tmp;
 	struct parse_events_terms parsed_terms;
 
 	*listp = NULL;
@@ -XXX,XX +XXX,XX @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			return ret;
 	}
 
-	config = strdup(event_name);
-	if (!config)
+	tmp = strdup(event_name);
+	if (!tmp)
 		goto out_err;
 
 	if (parse_events_term__num(&term,
 				   PARSE_EVENTS__TERM_TYPE_USER,
-				   config, /*num=*/1, /*novalue=*/true,
+				   tmp, /*num=*/1, /*novalue=*/true,
 				   loc, /*loc_val=*/NULL) < 0) {
-		zfree(&config);
+		zfree(&tmp);
 		goto out_err;
 	}
 	list_add_tail(&term->list, &parsed_terms.terms);
@@ -XXX,XX +XXX,XX @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			pr_debug("%s -> %s/%s/\n", event_name, pmu->name, sb.buf);
 			strbuf_release(&sb);
 			ok++;
+			if (pmu->is_core)
+				core_ok++;
 		}
 	}
 
@@ -XXX,XX +XXX,XX @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 		}
 	}
 
+	if (hw_config != PERF_COUNT_HW_MAX && !core_ok) {
+		/*
+		 * The event wasn't found on core PMUs but it has a hardware
+		 * config version to try.
+		 */
+		if (!parse_events_add_numeric(parse_state, list,
+						PERF_TYPE_HARDWARE, hw_config,
+						const_parsed_terms,
+						/*wildcard=*/true))
+			ok++;
+	}
+
 out_err:
 	parse_events_terms__exit(&parsed_terms);
 	if (ok)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -XXX,XX +XXX,XX @@ do {								\
 	yyless(0);						\
 } while (0)
 
-static int sym(yyscan_t scanner, int type, int config)
+static int sym(yyscan_t scanner, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 
-	yylval->num = (type << 16) + config;
-	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
+	yylval->num = config;
+	return PE_VALUE_SYM_SW;
 }
 
 static int term(yyscan_t scanner, enum parse_events__term_type type)
@@ -XXX,XX +XXX,XX @@ static int term(yyscan_t scanner, enum parse_events__term_type type)
 	return PE_TERM;
 }
 
-static int hw_term(yyscan_t scanner, int config)
+static int hw(yyscan_t scanner, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 	char *text = parse_events_get_text(scanner);
 
-	yylval->hardware_term.str = strdup(text);
-	yylval->hardware_term.num = PERF_TYPE_HARDWARE + config;
+	yylval->hardware_event.str = strdup(text);
+	yylval->hardware_event.num = config;
 	return PE_TERM_HW;
 }
 
@@ -XXX,XX +XXX,XX @@ aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 aux-action		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); }
 aux-sample-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
 metric-id		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); }
-cpu-cycles|cycles				{ return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
-stalled-cycles-frontend|idle-cycles-frontend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
-stalled-cycles-backend|idle-cycles-backend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
-instructions					{ return hw_term(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
-cache-references				{ return hw_term(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
-cache-misses					{ return hw_term(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
-branch-instructions|branches			{ return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
-branch-misses					{ return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
-bus-cycles					{ return hw_term(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
-ref-cycles					{ return hw_term(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-cycles|cycles				{ return hw(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return hw(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return hw(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return hw(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return hw(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return hw(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
 r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
 r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 ,			{ return ','; }
@@ -XXX,XX +XXX,XX @@ r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 <<EOF>>			{ BEGIN(INITIAL); }
 }
 
-cpu-cycles|cycles				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
-stalled-cycles-frontend|idle-cycles-frontend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
-stalled-cycles-backend|idle-cycles-backend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
-instructions					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
-cache-references				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
-cache-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
-branch-instructions|branches			{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
-branch-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
-bus-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
-ref-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
-cpu-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
-task-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
-page-faults|faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
-minor-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
-major-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
-context-switches|cs				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
-cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
-alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
-emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
-dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
-bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
-cgroup-switches					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); }
+cpu-cycles|cycles				{ return hw(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return hw(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return hw(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return hw(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return hw(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return hw(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-clock					{ return sym(yyscanner, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock					{ return sym(yyscanner, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults				{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults					{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults					{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs				{ return sym(yyscanner, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations			{ return sym(yyscanner, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults				{ return sym(yyscanner, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults				{ return sym(yyscanner, PERF_COUNT_SW_EMULATION_FAULTS); }
+dummy						{ return sym(yyscanner, PERF_COUNT_SW_DUMMY); }
+bpf-output					{ return sym(yyscanner, PERF_COUNT_SW_BPF_OUTPUT); }
+cgroup-switches					{ return sym(yyscanner, PERF_COUNT_SW_CGROUP_SWITCHES); }
 
 {lc_type}			{ return str(yyscanner, PE_LEGACY_CACHE); }
 {lc_type}-{lc_op_result}	{ return str(yyscanner, PE_LEGACY_CACHE); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index XXXXXXX..XXXXXXX 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 %}
 
 %token PE_START_EVENTS PE_START_TERMS
-%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_TERM
+%token PE_VALUE PE_VALUE_SYM_SW PE_TERM
 %token PE_EVENT_NAME
 %token PE_RAW PE_NAME
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP PE_BP_COLON PE_BP_SLASH
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_DRV_CFG_TERM
 %token PE_TERM_HW
 %type <num> PE_VALUE
-%type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
 %type <mod> PE_MODIFIER_EVENT
 %type <term_type> PE_TERM
-%type <num> value_sym
 %type <str> PE_RAW
 %type <str> PE_NAME
 %type <str> PE_LEGACY_CACHE
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <list_terms> opt_pmu_config
 %destructor { parse_events_terms__delete ($$); } <list_terms>
 %type <list_evsel> event_pmu
+%type <list_evsel> event_legacy_hardware
 %type <list_evsel> event_legacy_symbol
 %type <list_evsel> event_legacy_cache
 %type <list_evsel> event_legacy_mem
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 %destructor { free_list_evsel ($$); } <list_evsel>
 %type <tracepoint_name> tracepoint_name
 %destructor { free ($$.sys); free ($$.event); } <tracepoint_name>
-%type <hardware_term> PE_TERM_HW
-%destructor { free ($$.str); } <hardware_term>
+%type <hardware_event> PE_TERM_HW
+%destructor { free ($$.str); } <hardware_event>
 
 %union
 {
@@ -XXX,XX +XXX,XX @@ static void free_list_evsel(struct list_head* list_evsel)
 		char *sys;
 		char *event;
 	} tracepoint_name;
-	struct hardware_term {
+	struct hardware_event {
 		char *str;
 		u64 num;
-	} hardware_term;
+	} hardware_event;
 }
 %%
 
@@ -XXX,XX +XXX,XX @@ PE_EVENT_NAME event_def
 event_def
 
 event_def: event_pmu |
+	   event_legacy_hardware |
 	   event_legacy_symbol |
 	   event_legacy_cache sep_dc |
 	   event_legacy_mem sep_dc |
@@ -XXX,XX +XXX,XX @@ PE_NAME sep_dc
 	$$ = list;
 }
 
-value_sym:
-PE_VALUE_SYM_HW
+event_legacy_hardware:
+PE_TERM_HW opt_pmu_config
+{
+	/* List of created evsels. */
+	struct list_head *list = NULL;
+	int err = parse_events_multi_pmu_add(_parse_state, $1.str, $1.num, $2, &list, &@1);
+
+	free($1.str);
+	parse_events_terms__delete($2);
+	if (err)
+		PE_ABORT(err);
+
+	$$ = list;
+}
 |
-PE_VALUE_SYM_SW
+PE_TERM_HW sep_dc
+{
+	struct list_head *list;
+	int err;
+
+	err = parse_events_multi_pmu_add(_parse_state, $1.str, $1.num, NULL, &list, &@1);
+	free($1.str);
+	if (err)
+		PE_ABORT(err);
+	$$ = list;
+}
 
 event_legacy_symbol:
-value_sym '/' event_config '/'
+PE_VALUE_SYM_SW '/' event_config '/'
 {
 	struct list_head *list;
-	int type = $1 >> 16;
-	int config = $1 & 255;
 	int err;
-	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard);
+	err = parse_events_add_numeric(_parse_state, list,
+				/*type=*/PERF_TYPE_SOFTWARE, /*config=*/$1,
+				$3, /*wildcard=*/false);
 	parse_events_terms__delete($3);
 	if (err) {
 		free_list_evsel(list);
@@ -XXX,XX +XXX,XX @@ value_sym '/' event_config '/'
 	$$ = list;
 }
 |
-value_sym sep_slash_slash_dc
+PE_VALUE_SYM_SW sep_slash_slash_dc
 {
 	struct list_head *list;
-	int type = $1 >> 16;
-	int config = $1 & 255;
-	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 	int err;
 
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard);
+	err = parse_events_add_numeric(_parse_state, list,
+				/*type=*/PERF_TYPE_SOFTWARE, /*config=*/$1,
+				/*head_config=*/NULL, /*wildcard=*/false);
 	if (err)
 		PE_ABORT(err);
 	$$ = list;
-- 
2.49.0.395.g12beb8f557-goog