[PATCH v1 19/20] perf jevents: Add local/remote miss latency metrics for Intel

[Ian Rogers <irogers@google.com>]

Derive from CBOX/CHA occupancy and inserts the average latency as is
provided in Intel's uncore performance monitoring reference.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/pmu-events/intel_metrics.py | 59 ++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
index 1b9f7cd3b789..cdeb58e17c5e 100755
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -617,6 +617,64 @@ def IntelL2() -> Optional[MetricGroup]:
   ], description = "L2 data cache analysis")
 
 
+def IntelMissLat() -> Optional[MetricGroup]:
+  try:
+    ticks = Event("UNC_CHA_CLOCKTICKS", "UNC_C_CLOCKTICKS")
+    data_rd_loc_occ = Event("UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL",
+                            "UNC_CHA_TOR_OCCUPANCY.IA_MISS",
+                            "UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE",
+                            "UNC_C_TOR_OCCUPANCY.MISS_OPCODE")
+    data_rd_loc_ins = Event("UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL",
+                            "UNC_CHA_TOR_INSERTS.IA_MISS",
+                            "UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE",
+                            "UNC_C_TOR_INSERTS.MISS_OPCODE")
+    data_rd_rem_occ = Event("UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE",
+                            "UNC_CHA_TOR_OCCUPANCY.IA_MISS",
+                            "UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE",
+                            "UNC_C_TOR_OCCUPANCY.NID_MISS_OPCODE")
+    data_rd_rem_ins = Event("UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE",
+                            "UNC_CHA_TOR_INSERTS.IA_MISS",
+                            "UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE",
+                            "UNC_C_TOR_INSERTS.NID_MISS_OPCODE")
+  except:
+    return None
+
+  if (data_rd_loc_occ.name == "UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE" or
+      data_rd_loc_occ.name == "UNC_C_TOR_OCCUPANCY.MISS_OPCODE"):
+    data_rd = 0x182
+    for e in [data_rd_loc_occ, data_rd_loc_ins, data_rd_rem_occ, data_rd_rem_ins]:
+      e.name += f"/filter_opc={hex(data_rd)}/"
+  elif data_rd_loc_occ.name == "UNC_CHA_TOR_OCCUPANCY.IA_MISS":
+    # Demand Data Read - Full cache-line read requests from core for
+    # lines to be cached in S or E, typically for data
+    demand_data_rd = 0x202
+    #  LLC Prefetch Data - Uncore will first look up the line in the
+    #  LLC; for a cache hit, the LRU will be updated, on a miss, the
+    #  DRd will be initiated
+    llc_prefetch_data = 0x25a
+    local_filter = (f"/filter_opc0={hex(demand_data_rd)},"
+                    f"filter_opc1={hex(llc_prefetch_data)},"
+                    "filter_loc,filter_nm,filter_not_nm/")
+    remote_filter = (f"/filter_opc0={hex(demand_data_rd)},"
+                     f"filter_opc1={hex(llc_prefetch_data)},"
+                     "filter_rem,filter_nm,filter_not_nm/")
+    for e in [data_rd_loc_occ, data_rd_loc_ins]:
+      e.name += local_filter
+    for e in [data_rd_rem_occ, data_rd_rem_ins]:
+      e.name += remote_filter
+  else:
+    assert data_rd_loc_occ.name == "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL", data_rd_loc_occ
+
+  loc_lat = interval_sec * 1e9 * data_rd_loc_occ / (ticks * data_rd_loc_ins)
+  rem_lat = interval_sec * 1e9 * data_rd_rem_occ / (ticks * data_rd_rem_ins)
+  return MetricGroup("miss_lat", [
+      Metric("miss_lat_loc", "Local to a socket miss latency in nanoseconds",
+             loc_lat, "ns"),
+      Metric("miss_lat_rem", "Remote to a socket miss latency in nanoseconds",
+             rem_lat, "ns"),
+  ])
+
+
 def IntelMlp() -> Optional[Metric]:
   try:
     l1d = Event("L1D_PEND_MISS.PENDING")
@@ -960,6 +1018,7 @@ all_metrics = MetricGroup("", [
     IntelIlp(),
     IntelL2(),
     IntelLdSt(),
+    IntelMissLat(),
     IntelMlp(),
     IntelPorts(),
     IntelSwpf(),
-- 
2.44.0.278.ge034bb2e1d-goog