Currently, jevents.py parses hundreds of JSON event and metric files
sequentially across all CPU architectures during Kbuild startup, taking
~3.3 seconds of pure single-core execution time.

Refactor jevents.py to pre-populate its internal JSON AST cache in parallel
across all available CPU cores using ProcessPoolExecutor. Configure worker
process initializers to guarantee standard event mapping inheritance under
spawn multiprocessing semantics, and apply depth filtering to prevent
redundant worker tasks. This accelerates jevents.py execution by over 11x
(from 3.3s down to ~290ms), fully reclaiming multi-core concurrency during
the build generation phase.

Tested-by: James Clark <james.clark@linaro.org>
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/pmu-events/jevents.py | 36 ++++++++++++++++++++++++++++----
 1 file changed, 32 insertions(+), 4 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 70a45e62f5d1..eb72c154f946 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -457,8 +457,8 @@ class JsonEvent:
     return f'{{ { _bcs.offsets[s] } }}, /* {fix_comment(s)} */\n'
 
 
-@lru_cache(maxsize=None)
-def read_json_events(path: str, topic: str) -> Sequence[JsonEvent]:
+_json_cache = {}
+def _read_json_events_impl(path: str, topic: str) -> Sequence[JsonEvent]:
   """Read json events from the specified file."""
   try:
     events = json.load(open(path), object_hook=JsonEvent)
@@ -474,12 +474,16 @@ def read_json_events(path: str, topic: str) -> Sequence[JsonEvent]:
   if updates:
     for event in events:
       if event.metric_name in updates:
-        # print(f'Updated {event.metric_name} from\n"{event.metric_expr}"\n'
-        #       f'to\n"{updates[event.metric_name]}"')
         event.metric_expr = updates[event.metric_name]
 
   return events
 
+def read_json_events(path: str, topic: str) -> Sequence[JsonEvent]:
+  key = (path, topic)
+  if key not in _json_cache:
+    _json_cache[key] = _read_json_events_impl(path, topic)
+  return _json_cache[key]
+
 def preprocess_arch_std_files(archpath: str) -> None:
   """Read in all architecture standard events."""
   global _arch_std_events
@@ -1381,6 +1385,10 @@ const char *describe_metricgroup(const char *group)
 }
 """)
 
+def _parallel_read_json_events(task: Tuple[str, str]) -> Tuple[str, str, Sequence[JsonEvent]]:
+  path, topic = task
+  return path, topic, _read_json_events_impl(path, topic)
+
 def main() -> None:
   global _args
 
@@ -1459,9 +1467,29 @@ struct pmu_table_entry {
     raise IOError(f'Missing architecture directory \'{_args.arch}\'')
 
   archs.sort()
+  import concurrent.futures
+  tasks = []
+  def collect_json(parents: Sequence[str], item: os.DirEntry) -> None:
+    if len(parents) == 0:
+      return
+    if item.is_file() and item.name.endswith('.json') and not item.name.endswith('metricgroups.json'):
+      tasks.append((item.path, get_topic(item.name)))
+
   for arch in archs:
     arch_path = f'{_args.starting_dir}/{arch}'
     preprocess_arch_std_files(arch_path)
+    ftw(arch_path, [], collect_json)
+
+  def _init_worker(std_events: dict) -> None:
+    global _arch_std_events
+    _arch_std_events = std_events
+
+  with concurrent.futures.ProcessPoolExecutor(initializer=_init_worker, initargs=(_arch_std_events,)) as executor:
+    for path, topic, events in executor.map(_parallel_read_json_events, tasks):
+      _json_cache[(path, topic)] = events
+
+  for arch in archs:
+    arch_path = f'{_args.starting_dir}/{arch}'
     ftw(arch_path, [], preprocess_one_file)
 
   _bcs.compute()
-- 
2.54.0.563.g4f69b47b94-goog