Received-SPF: pass (google.com: domain of linux-kernel+bounces-102811-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Date: Wed, 13 Mar 2024 22:50:51 -0700
In-Reply-To: <20240314055051.1960527-1-irogers@google.com>
Message-Id: <20240314055051.1960527-13-irogers@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240314055051.1960527-1-irogers@google.com>
Subject: [PATCH v3 12/12] perf jevents: Add load event json to verify and
 allow fallbacks
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>, 
	John Garry <john.g.garry@oracle.com>, Kan Liang <kan.liang@linux.intel.com>, 
	Jing Zhang <renyu.zj@linux.alibaba.com>, Thomas Richter <tmricht@linux.ibm.com>, 
	James Clark <james.clark@arm.com>, linux-kernel@vger.kernel.org, 
	linux-perf-users@vger.kernel.org, Andi Kleen <ak@linux.intel.com>, 
	Kajol Jain <kjain@linux.ibm.com>, Sandipan Das <sandipan.das@amd.com>, 
	Ravi Bangoria <ravi.bangoria@amd.com>, Perry Taylor <perry.taylor@intel.com>, 
	Samantha Alt <samantha.alt@intel.com>, Caleb Biggers <caleb.biggers@intel.com>, 
	Weilin Wang <weilin.wang@intel.com>, Edward Baker <edward.baker@intel.com>, 
	Stephane Eranian <eranian@google.com>
Content-Type: text/plain; charset="UTF-8"

Add a LoadEvents function that loads all event json files in a
directory. In the Event constructor ensure all events are defined in
the event json except for legacy events like "cycles". If the initial
event isn't found then legacy_event1 is used, and if that isn't found
legacy_event2 is used. This allows a single Event to have multiple
event names as models will often rename the same event over time. If
the event doesn't exist an exception is raised.

So that references to metrics can be added, add the MetricRef
class. This doesn't validate as an event name and so provides an
escape hatch for metrics to refer to each other.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/pmu-events/Build            | 12 ++--
 tools/perf/pmu-events/amd_metrics.py   |  6 +-
 tools/perf/pmu-events/arm64_metrics.py |  6 +-
 tools/perf/pmu-events/intel_metrics.py |  6 +-
 tools/perf/pmu-events/metric.py        | 77 +++++++++++++++++++++++++-
 5 files changed, 95 insertions(+), 12 deletions(-)

diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index e2db33577707..a2c5c04e5c46 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -42,11 +42,11 @@ ZEN_METRICGROUPS = $(foreach x,$(ZENS),$(OUTPUT)$(x)/extra-metricgroups.json)
 
 $(ZEN_METRICS): pmu-events/amd_metrics.py
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,gen)$(PYTHON) $< $(call model_name,$@) arch > $@
+	$(Q)$(call echo-cmd,gen)$(PYTHON) $< $(call model_name,$@) pmu-events/arch > $@
 
 $(ZEN_METRICGROUPS): pmu-events/amd_metrics.py
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,gen)$(PYTHON) $< -metricgroups $(call model_name,$@) arch > $@
+	$(Q)$(call echo-cmd,gen)$(PYTHON) $< -metricgroups $(call model_name,$@) pmu-events/arch > $@
 
 # Generate ARM Json
 ARMS = $(shell ls -d pmu-events/arch/arm64/arm/*)
@@ -55,11 +55,11 @@ ARM_METRICGROUPS = $(foreach x,$(ARMS),$(OUTPUT)$(x)/extra-metricgroups.json)
 
 $(ARM_METRICS): pmu-events/arm64_metrics.py
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,gen)$(PYTHON) $< $(call vendor_name,$@) $(call model_name,$@) arch > $@
+	$(Q)$(call echo-cmd,gen)$(PYTHON) $< $(call vendor_name,$@) $(call model_name,$@) pmu-events/arch > $@
 
 $(ARM_METRICGROUPS): pmu-events/arm64_metrics.py
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,gen)$(PYTHON) $< -metricgroups $(call vendor_name,$@) $(call model_name,$@) arch > $@
+	$(Q)$(call echo-cmd,gen)$(PYTHON) $< -metricgroups $(call vendor_name,$@) $(call model_name,$@) pmu-events/arch > $@
 
 # Generate Intel Json
 INTELS = $(shell ls -d pmu-events/arch/x86/*|grep -v amdzen|grep -v mapfile.csv)
@@ -68,11 +68,11 @@ INTEL_METRICGROUPS = $(foreach x,$(INTELS),$(OUTPUT)$(x)/extra-metricgroups.json
 
 $(INTEL_METRICS): pmu-events/intel_metrics.py
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,gen)$(PYTHON) $< $(call model_name,$@) arch > $@
+	$(Q)$(call echo-cmd,gen)$(PYTHON) $< $(call model_name,$@) pmu-events/arch > $@
 
 $(INTEL_METRICGROUPS): pmu-events/intel_metrics.py
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,gen)$(PYTHON) $< -metricgroups $(call model_name,$@) arch > $@
+	$(Q)$(call echo-cmd,gen)$(PYTHON) $< -metricgroups $(call model_name,$@) pmu-events/arch > $@
 
 GEN_JSON = $(patsubst %,$(OUTPUT)%,$(JSON)) \
             $(ZEN_METRICS) $(ZEN_METRICGROUPS) \
diff --git a/tools/perf/pmu-events/amd_metrics.py b/tools/perf/pmu-events/amd_metrics.py
index 7ab2ee4fdb17..4f728e7aae4a 100755
--- a/tools/perf/pmu-events/amd_metrics.py
+++ b/tools/perf/pmu-events/amd_metrics.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, MetricGroup)
+from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, LoadEvents,
+                    MetricGroup)
 import argparse
 import json
 import os
@@ -27,6 +28,9 @@ def main() -> None:
   )
   _args = parser.parse_args()
 
+  directory = f"{_args.events_path}/x86/{_args.model}/"
+  LoadEvents(directory)
+
   all_metrics = MetricGroup("",[])
 
   if _args.metricgroups:
diff --git a/tools/perf/pmu-events/arm64_metrics.py b/tools/perf/pmu-events/arm64_metrics.py
index a9f0e6bc751b..c9aa2d827a82 100755
--- a/tools/perf/pmu-events/arm64_metrics.py
+++ b/tools/perf/pmu-events/arm64_metrics.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, MetricGroup)
+from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, LoadEvents,
+                    MetricGroup)
 import argparse
 import json
 import os
@@ -30,6 +31,9 @@ def main() -> None:
 
   all_metrics = MetricGroup("",[])
 
+  directory = f"{_args.events_path}/arm64/{_args.vendor}/{_args.model}/"
+  LoadEvents(directory)
+
   if _args.metricgroups:
     print(JsonEncodeMetricGroupDescriptions(all_metrics))
   else:
diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
index f004c27640d2..04a19d05c6c1 100755
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, MetricGroup)
+from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, LoadEvents,
+                    MetricGroup)
 import argparse
 import json
 import os
@@ -27,6 +28,9 @@ def main() -> None:
   )
   _args = parser.parse_args()
 
+  directory = f"{_args.events_path}/x86/{_args.model}/"
+  LoadEvents(directory)
+
   all_metrics = MetricGroup("",[])
 
   if _args.metricgroups:
diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py
index dd8fd06940e6..03312cd6d491 100644
--- a/tools/perf/pmu-events/metric.py
+++ b/tools/perf/pmu-events/metric.py
@@ -3,10 +3,50 @@
 import ast
 import decimal
 import json
+import os
 import re
 from enum import Enum
 from typing import Dict, List, Optional, Set, Tuple, Union
 
+all_events = set()
+
+def LoadEvents(directory: str) -> None:
+  """Populate a global set of all known events for the purpose of validating Event names"""
+  global all_events
+  all_events = {
+      "context\-switches",
+      "cycles",
+      "duration_time",
+      "instructions",
+      "l2_itlb_misses",
+  }
+  for file in os.listdir(os.fsencode(directory)):
+    filename = os.fsdecode(file)
+    if filename.endswith(".json"):
+      for x in json.load(open(f"{directory}/{filename}")):
+        if "EventName" in x:
+          all_events.add(x["EventName"])
+        elif "ArchStdEvent" in x:
+          all_events.add(x["ArchStdEvent"])
+
+
+def CheckEvent(name: str) -> bool:
+  """Check the event name exists in the set of all loaded events"""
+  global all_events
+  if len(all_events) == 0:
+    # No events loaded so assume any event is good.
+    return True
+
+  if ':' in name:
+    # Remove trailing modifier.
+    name = name[:name.find(':')]
+  elif '/' in name:
+    # Name could begin with a PMU or an event, for now assume it is good.
+    return True
+
+  return name in all_events
+
+
 class MetricConstraint(Enum):
   GROUPED_EVENTS = 0
   NO_GROUP_EVENTS = 1
@@ -317,9 +357,18 @@ def _FixEscapes(s: str) -> str:
 class Event(Expression):
   """An event in an expression."""
 
-  def __init__(self, name: str, legacy_name: str = ''):
-    self.name = _FixEscapes(name)
-    self.legacy_name = _FixEscapes(legacy_name)
+  def __init__(self, *args: str):
+    error = ""
+    for name in args:
+      if CheckEvent(name):
+        self.name = _FixEscapes(name)
+        return
+      if error:
+        error += " or " + name
+      else:
+        error = name
+    global all_events
+    raise Exception(f"No event {error} in:\n{all_events}")
 
   def ToPerfJson(self):
     result = re.sub('/', '@', self.name)
@@ -338,6 +387,28 @@ class Event(Expression):
     return self
 
 
+class MetricRef(Expression):
+  """A metric reference in an expression."""
+
+  def __init__(self, name: str):
+    self.name = _FixEscapes(name)
+
+  def ToPerfJson(self):
+    return self.name
+
+  def ToPython(self):
+    return f'MetricRef(r"{self.name}")'
+
+  def Simplify(self) -> Expression:
+    return self
+
+  def Equals(self, other: Expression) -> bool:
+    return isinstance(other, MetricRef) and self.name == other.name
+
+  def Substitute(self, name: str, expression: Expression) -> Expression:
+    return self
+
+
 class Constant(Expression):
   """A constant within the expression tree."""
 
-- 
2.44.0.278.ge034bb2e1d-goog