[PATCH v1 08/20] perf jevents: Add L2 metrics for Intel

[Ian Rogers <irogers@google.com>]

Give a breakdown of various L2 counters as metrics, including totals,
reads, hardware prefetcher, RFO, code and evictions.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/pmu-events/intel_metrics.py | 158 +++++++++++++++++++++++++
 1 file changed, 158 insertions(+)

diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
index 63d46ee1dca9..d22a1abca8d9 100755
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -271,6 +271,163 @@ def IntelBr():
                      description="breakdown of retired branch instructions")
 
 
+def IntelL2() -> Optional[MetricGroup]:
+  try:
+    DC_HIT = Event("L2_RQSTS.DEMAND_DATA_RD_HIT")
+  except:
+    return None
+  try:
+    DC_MISS = Event("L2_RQSTS.DEMAND_DATA_RD_MISS")
+    l2_dmnd_miss = DC_MISS
+    l2_dmnd_rd_all = DC_MISS + DC_HIT
+  except:
+    DC_ALL = Event("L2_RQSTS.ALL_DEMAND_DATA_RD")
+    l2_dmnd_miss = DC_ALL - DC_HIT
+    l2_dmnd_rd_all = DC_ALL
+  l2_dmnd_mrate = d_ratio(l2_dmnd_miss, interval_sec)
+  l2_dmnd_rrate = d_ratio(l2_dmnd_rd_all, interval_sec)
+
+  DC_PFH = None
+  DC_PFM = None
+  l2_pf_all = None
+  l2_pf_mrate = None
+  l2_pf_rrate = None
+  try:
+    DC_PFH = Event("L2_RQSTS.PF_HIT")
+    DC_PFM = Event("L2_RQSTS.PF_MISS")
+    l2_pf_all = DC_PFH + DC_PFM
+    l2_pf_mrate = d_ratio(DC_PFM, interval_sec)
+    l2_pf_rrate = d_ratio(l2_pf_all, interval_sec)
+  except:
+    pass
+
+  DC_RFOH = Event("L2_RQSTS.RFO_HIT")
+  DC_RFOM = Event("L2_RQSTS.RFO_MISS")
+  l2_rfo_all = DC_RFOH + DC_RFOM
+  l2_rfo_mrate  = d_ratio(DC_RFOM, interval_sec)
+  l2_rfo_rrate  = d_ratio(l2_rfo_all, interval_sec)
+
+  DC_CH = Event("L2_RQSTS.CODE_RD_HIT")
+  DC_CM = Event("L2_RQSTS.CODE_RD_MISS")
+  DC_IN = Event("L2_LINES_IN.ALL")
+  DC_OUT_NS = None
+  DC_OUT_S = None
+  l2_lines_out = None
+  l2_out_rate = None
+  wbn = None
+  isd = None
+  try:
+    DC_OUT_NS = Event("L2_LINES_OUT.NON_SILENT",
+                      "L2_LINES_OUT.DEMAND_DIRTY",
+                      "L2_LINES_IN.S")
+    DC_OUT_S = Event("L2_LINES_OUT.SILENT",
+                     "L2_LINES_OUT.DEMAND_CLEAN",
+                     "L2_LINES_IN.I")
+    if DC_OUT_S.name == "L2_LINES_OUT.SILENT" and (
+        args.model.startswith("skylake") or
+        args.model == "cascadelakex"):
+      DC_OUT_S.name = "L2_LINES_OUT.SILENT/any/"
+    # bring is back to per-CPU
+    l2_s  = Select(DC_OUT_S / 2, Literal("#smt_on"), DC_OUT_S)
+    l2_ns = DC_OUT_NS
+    l2_lines_out = l2_s + l2_ns;
+    l2_out_rate = d_ratio(l2_lines_out, interval_sec);
+    nlr = max(l2_ns - DC_WB_U - DC_WB_D, 0)
+    wbn = d_ratio(nlr, interval_sec)
+    isd = d_ratio(l2_s, interval_sec)
+  except:
+    pass
+  DC_OUT_U = None
+  l2_pf_useless = None
+  l2_useless_rate = None
+  try:
+    DC_OUT_U = Event("L2_LINES_OUT.USELESS_HWPF")
+    l2_pf_useless = DC_OUT_U
+    l2_useless_rate = d_ratio(l2_pf_useless, interval_sec)
+  except:
+    pass
+  DC_WB_U = None
+  DC_WB_D = None
+  wbu = None
+  wbd = None
+  try:
+    DC_WB_U = Event("IDI_MISC.WB_UPGRADE")
+    DC_WB_D = Event("IDI_MISC.WB_DOWNGRADE")
+    wbu = d_ratio(DC_WB_U, interval_sec)
+    wbd = d_ratio(DC_WB_D, interval_sec)
+  except:
+    pass
+
+  l2_lines_in = DC_IN
+  l2_code_all = DC_CH + DC_CM
+  l2_code_rate = d_ratio(l2_code_all, interval_sec)
+  l2_code_miss_rate = d_ratio(DC_CM, interval_sec)
+  l2_in_rate = d_ratio(l2_lines_in, interval_sec)
+
+  return MetricGroup("l2", [
+    MetricGroup("l2_totals", [
+      Metric("l2_totals_in", "L2 cache total in per second",
+             l2_in_rate, "In/s"),
+      Metric("l2_totals_out", "L2 cache total out per second",
+             l2_out_rate, "Out/s") if l2_out_rate else None,
+    ]),
+    MetricGroup("l2_rd", [
+      Metric("l2_rd_hits", "L2 cache data read hits",
+             d_ratio(DC_HIT, l2_dmnd_rd_all), "100%"),
+      Metric("l2_rd_hits", "L2 cache data read hits",
+             d_ratio(l2_dmnd_miss, l2_dmnd_rd_all), "100%"),
+      Metric("l2_rd_requests", "L2 cache data read requests per second",
+             l2_dmnd_rrate, "requests/s"),
+      Metric("l2_rd_misses", "L2 cache data read misses per second",
+             l2_dmnd_mrate, "misses/s"),
+    ]),
+    MetricGroup("l2_hwpf", [
+      Metric("l2_hwpf_hits", "L2 cache hardware prefetcher hits",
+             d_ratio(DC_PFH, l2_pf_all), "100%"),
+      Metric("l2_hwpf_misses", "L2 cache hardware prefetcher misses",
+             d_ratio(DC_PFM, l2_pf_all), "100%"),
+      Metric("l2_hwpf_useless", "L2 cache hardware prefetcher useless prefetches per second",
+             l2_useless_rate, "100%") if l2_useless_rate else None,
+      Metric("l2_hwpf_requests", "L2 cache hardware prefetcher requests per second",
+             l2_pf_rrate, "100%"),
+      Metric("l2_hwpf_misses", "L2 cache hardware prefetcher misses per second",
+             l2_pf_mrate, "100%"),
+    ]) if DC_PFH else None,
+    MetricGroup("l2_rfo", [
+      Metric("l2_rfo_hits", "L2 cache request for ownership (RFO) hits",
+             d_ratio(DC_RFOH, l2_rfo_all), "100%"),
+      Metric("l2_rfo_misses", "L2 cache request for ownership (RFO) misses",
+             d_ratio(DC_RFOM, l2_rfo_all), "100%"),
+      Metric("l2_rfo_requests", "L2 cache request for ownership (RFO) requests per second",
+             l2_rfo_rrate, "requests/s"),
+      Metric("l2_rfo_misses", "L2 cache request for ownership (RFO) misses per second",
+             l2_rfo_mrate, "misses/s"),
+    ]),
+    MetricGroup("l2_code", [
+      Metric("l2_code_hits", "L2 cache code hits",
+             d_ratio(DC_CH, l2_code_all), "100%"),
+      Metric("l2_code_misses", "L2 cache code misses",
+             d_ratio(DC_CM, l2_code_all), "100%"),
+      Metric("l2_code_requests", "L2 cache code requests per second",
+             l2_code_rate, "requests/s"),
+      Metric("l2_code_misses", "L2 cache code misses per second",
+             l2_code_miss_rate, "misses/s"),
+    ]),
+    MetricGroup("l2_evict", [
+      MetricGroup("l2_evict_mef_lines", [
+        Metric("l2_evict_mef_lines_l3_hot_lru", "L2 evictions M/E/F lines L3 hot LRU per second",
+               wbu, "HotLRU/s") if wbu else None,
+        Metric("l2_evict_mef_lines_l3_norm_lru", "L2 evictions M/E/F lines L3 normal LRU per second",
+               wbn, "NormLRU/s") if wbn else None,
+        Metric("l2_evict_mef_lines_dropped", "L2 evictions M/E/F lines dropped per second",
+               wbd, "dropped/s") if wbd else None,
+        Metric("l2_evict_is_lines_dropped", "L2 evictions I/S lines dropped per second",
+               isd, "dropped/s") if isd else None,
+      ]),
+    ]),
+  ], description = "L2 data cache analysis")
+
+
 def IntelPorts() -> Optional[MetricGroup]:
   pipeline_events = json.load(open(f"{os.path.dirname(os.path.realpath(__file__))}"
                                    f"/arch/x86/{args.model}/pipeline.json"))
@@ -363,6 +520,7 @@ all_metrics = MetricGroup("", [
     Smi(),
     Tsx(),
     IntelBr(),
+    IntelL2(),
     IntelPorts(),
     IntelSwpf(),
 ])
-- 
2.44.0.278.ge034bb2e1d-goog