perf jevents: Add ports metric group giving utilization on Intel

The ports metric group contains a metric for each port giving its
utilization as a ratio of cycles.

The metrics are created by looking for UOPS_DISPATCHED.PORT events.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
index 919a058c343a63ddfca9268eed1dcb997da23175..7fcc0a1c544d84f8d607da5ee6e11bfc35ae7236 100755 (executable)
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -1,12 +1,14 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 import argparse
+import json
 import math
 import os
+import re
 from typing import Optional
 from metric import (d_ratio, has_event, max, CheckPmu, Event, JsonEncodeMetric,
-                    JsonEncodeMetricGroupDescriptions, LoadEvents, Metric,
-                    MetricGroup, MetricRef, Select)
+                    JsonEncodeMetricGroupDescriptions, Literal, LoadEvents,
+                    Metric, MetricGroup, MetricRef, Select)
 
 # Global command line arguments.
 _args = None
@@ -261,6 +263,34 @@ def IntelBr():
                        description="breakdown of retired branch instructions")
 
 
+def IntelPorts() -> Optional[MetricGroup]:
+    pipeline_events = json.load(
+        open(f"{_args.events_path}/x86/{_args.model}/pipeline.json"))
+
+    core_cycles = Event("CPU_CLK_UNHALTED.THREAD_P_ANY",
+                        "CPU_CLK_UNHALTED.DISTRIBUTED",
+                        "cycles")
+    # Number of CPU cycles scaled for SMT.
+    smt_cycles = Select(core_cycles / 2, Literal("#smt_on"), core_cycles)
+
+    metrics = []
+    for x in pipeline_events:
+        if "EventName" in x and re.search("^UOPS_DISPATCHED.PORT", x["EventName"]):
+            name = x["EventName"]
+            port = re.search(r"(PORT_[0-9].*)", name).group(0).lower()
+            if name.endswith("_CORE"):
+                cyc = core_cycles
+            else:
+                cyc = smt_cycles
+            metrics.append(Metric(f"lpm_{port}", f"{port} utilization (higher is better)",
+                                  d_ratio(Event(name), cyc), "100%"))
+    if len(metrics) == 0:
+        return None
+
+    return MetricGroup("lpm_ports", metrics, "functional unit (port) utilization -- "
+                       "fraction of cycles each port is utilized (higher is better)")
+
+
 def IntelSwpf() -> Optional[MetricGroup]:
     ins = Event("instructions")
     try:
@@ -356,6 +386,7 @@ def main() -> None:
         Smi(),
         Tsx(),
         IntelBr(),
+        IntelPorts(),
         IntelSwpf(),
     ])