perf jevents: Add local/remote "mem" breakdown metrics for Intel

Breakdown local and remote memory bandwidth, read and writes.

The implementation uses the HA and CHA PMUs present in server models
broadwellde, broadwellx cascadelakex, emeraldrapids, haswellx, icelakex,
ivytown, sapphirerapids and skylakex.

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 f671d6e4fd6721added9475d4b85d3062d4c91fa..983e5021f3d3cff76def99ca5b60990ac0e1f11e 100755 (executable)
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -815,6 +815,36 @@ def IntelLdSt() -> Optional[MetricGroup]:
     ], description="Breakdown of load/store instructions")
 
 
+def UncoreMem() -> Optional[MetricGroup]:
+    try:
+        loc_rds = Event("UNC_CHA_REQUESTS.READS_LOCAL",
+                        "UNC_H_REQUESTS.READS_LOCAL")
+        rem_rds = Event("UNC_CHA_REQUESTS.READS_REMOTE",
+                        "UNC_H_REQUESTS.READS_REMOTE")
+        loc_wrs = Event("UNC_CHA_REQUESTS.WRITES_LOCAL",
+                        "UNC_H_REQUESTS.WRITES_LOCAL")
+        rem_wrs = Event("UNC_CHA_REQUESTS.WRITES_REMOTE",
+                        "UNC_H_REQUESTS.WRITES_REMOTE")
+    except:
+        return None
+
+    scale = 64 / 1_000_000
+    return MetricGroup("lpm_mem", [
+        MetricGroup("lpm_mem_local", [
+            Metric("lpm_mem_local_read", "Local memory read bandwidth not including directory updates",
+                   d_ratio(loc_rds, interval_sec), f"{scale}MB/s"),
+            Metric("lpm_mem_local_write", "Local memory write bandwidth not including directory updates",
+                   d_ratio(loc_wrs, interval_sec), f"{scale}MB/s"),
+        ]),
+        MetricGroup("lpm_mem_remote", [
+            Metric("lpm_mem_remote_read", "Remote memory read bandwidth not including directory updates",
+                   d_ratio(rem_rds, interval_sec), f"{scale}MB/s"),
+            Metric("lpm_mem_remote_write", "Remote memory write bandwidth not including directory updates",
+                   d_ratio(rem_wrs, interval_sec), f"{scale}MB/s"),
+        ]),
+    ], description="Memory Bandwidth breakdown local vs. remote (remote requests in). directory updates not included")
+
+
 def UncoreMemBw() -> Optional[MetricGroup]:
     mem_events = []
     try:
@@ -914,6 +944,7 @@ def main() -> None:
         IntelMlp(),
         IntelPorts(),
         IntelSwpf(),
+        UncoreMem(),
         UncoreMemBw(),
     ])