perf vendor events: Update broadwellx metrics add event counter information

Add counter information necessary for optimizing event grouping the
perf tool.

The most recent RFC patch set using this information:
https://lore.kernel.org/lkml/20240412210756.309828-1-weilin.wang@intel.com/

The information was added in:
https://github.com/intel/perfmon/commit/475892a9690cb048949e593fe39cee65cd4765e1
and later patches.

The TMA 4.8 information was updated in:
https://github.com/intel/perfmon/commit/59194d4d90ca50a3fcb2de0d82b9f6fc0c9a5736Co-authored-by: Weilin Wang <weilin.wang@intel.com>
Co-authored-by: Caleb Biggers <caleb.biggers@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Alexandre Torgue <alexandre.torgue@foss.st.com>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240620181752.3945845-7-irogers@google.com

tools/perf/pmu-events/arch/x86/broadwellx/counter.json

+[
+    {
+        "Unit": "core",
+        "CountersNumFixed": "3",
+        "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "CBOX",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "HA",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "IRP",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "2"
+    },
+    {
+        "Unit": "PCU",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "QPI",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "R2PCIe",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "R3QPI",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "3"
+    },
+    {
+        "Unit": "SBOX",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "UBOX",
+        "CountersNumFixed": "1",
+        "CountersNumGeneric": "2"
+    },
+    {
+        "Unit": "iMC",
+        "CountersNumFixed": "1",
+        "CountersNumGeneric": "4"
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json

@@ -5,7 +5,18 @@
     "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",

tools/perf/pmu-events/arch/x86/broadwellx/other.json

 [
     {
         "BriefDescription": "Unhalted core cycles when the thread is in ring 0",
+        "Counter": "0,1,2,3",
         "EventCode": "0x5C",
         "EventName": "CPL_CYCLES.RING0",
         "PublicDescription": "This event counts the unhalted core cycles during which the thread is in the ring 0 privileged mode.",
@@ -9,6 +10,7 @@
     },
     {
         "BriefDescription": "Number of intervals between processor halts while thread is in ring 0",
+        "Counter": "0,1,2,3",
         "CounterMask": "1",
         "EdgeDetect": "1",
         "EventCode": "0x5C",
@@ -19,6 +21,7 @@
     },
     {
         "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
+        "Counter": "0,1,2,3",
         "EventCode": "0x5C",
         "EventName": "CPL_CYCLES.RING123",
         "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
@@ -27,6 +30,7 @@
     },
     {
         "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
+        "Counter": "0,1,2,3",
         "EventCode": "0x63",
         "EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
         "PublicDescription": "This event counts cycles in which the L1 and L2 are locked due to a UC lock or split lock. A lock is asserted in case of locked memory access, due to noncacheable memory, locked operation that spans two cache lines, or a page walk from the noncacheable page table. L1D and L2 locks have a very high performance penalty and it is highly recommended to avoid such access.",