perf vendor events intel: Update sapphirerapids to 1.20

Update events from 1.17 to 1.20 as released in:

  https://github.com/intel/perfmon/commit/6f674057745acf0125395638ca6be36458a59bda

Various description updates. Adds uncore events
UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL,
UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE,
UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL, UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE,
UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL,
UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE,
UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_LOCAL,
UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_REMOTE,
UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_LOCAL,
UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_REMOTE,
UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_LOCAL,
UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_REMOTE and removes core events
AMX_OPS_RETIRED.BF16 and AMX_OPS_RETIRED.INT8.
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Samantha Alt <samantha.alt@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Link: https://lore.kernel.org/r/20240321060016.1464787-8-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/pmu-events/arch/x86/mapfile.csv

@@ -26,7 +26,7 @@ GenuineIntel-6-1[AEF],v4,nehalemep,core
 GenuineIntel-6-2E,v4,nehalemex,core
 GenuineIntel-6-A7,v1.02,rocketlake,core
 GenuineIntel-6-2A,v19,sandybridge,core
-GenuineIntel-6-8F,v1.17,sapphirerapids,core
+GenuineIntel-6-8F,v1.20,sapphirerapids,core
 GenuineIntel-6-AF,v1.01,sierraforest,core
 GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
 GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v58,skylake,core

tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json

@@ -432,6 +432,7 @@
         "BriefDescription": "Retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches.",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM",
+        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.",
         "SampleAfterValue": "100007",
         "UMask": "0x10"

tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json

@@ -267,7 +267,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },

tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json

@@ -264,6 +264,7 @@
         "BriefDescription": "Number of times an RTM execution aborted.",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
+        "PEBS": "1",
         "PublicDescription": "Counts the number of times RTM abort was triggered.",
         "SampleAfterValue": "100003",
         "UMask": "0x4"

tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json

 [
-    {
-        "BriefDescription": "AMX retired arithmetic BF16 operations.",
-        "EventCode": "0xce",
-        "EventName": "AMX_OPS_RETIRED.BF16",
-        "PublicDescription": "Number of AMX-based retired arithmetic bfloat16 (BF16) floating-point operations. Counts TDPBF16PS FP instructions. SW to use operation multiplier of 4",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "AMX retired arithmetic integer 8-bit operations.",
-        "EventCode": "0xce",
-        "EventName": "AMX_OPS_RETIRED.INT8",
-        "PublicDescription": "Number of AMX-based retired arithmetic integer operations of 8-bit width source operands. Counts TDPB[SS,UU,US,SU]D instructions. SW should use operation multiplier of 8.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
     {
         "BriefDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE",
         "CounterMask": "1",
@@ -444,6 +428,7 @@
         "BriefDescription": "INST_RETIRED.MACRO_FUSED",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PEBS": "1",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -451,6 +436,7 @@
         "BriefDescription": "Retired NOP instructions.",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
+        "PEBS": "1",
         "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
@@ -467,6 +453,7 @@
         "BriefDescription": "Iterations of Repeat string retired instructions.",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
+        "PEBS": "1",
         "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"

tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json

@@ -4143,6 +4143,42 @@
         "UMask": "0xcd43ff04",
         "Unit": "CHA"
     },
+    {
+        "BriefDescription": "ItoMCacheNear (partial write) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd42ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoMCacheNear (partial write) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd437f04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoM (write) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc42ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoM (write) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc437f04",
+        "Unit": "CHA"
+    },
     {
         "BriefDescription": "TOR Inserts; Misses from local IO",
         "EventCode": "0x35",
@@ -4153,7 +4189,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "TOR Inserts; ItoM misses from local IO",
+        "BriefDescription": "TOR Inserts : ItoM, indicating a full cacheline write request, from IO Devices that missed the LLC",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM",
         "PerPkg": "1",
@@ -4171,7 +4207,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "TOR Inserts; RdCur and FsRdCur misses from local IO",
+        "BriefDescription": "TOR Inserts; RdCur and FsRdCur requests from local IO that miss LLC",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR",
         "PerPkg": "1",
@@ -4197,6 +4233,24 @@
         "UMask": "0xc8f3ff04",
         "Unit": "CHA"
     },
+    {
+        "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f2ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f37f04",
+        "Unit": "CHA"
+    },
     {
         "BriefDescription": "TOR Inserts; RFO from local IO",
         "EventCode": "0x35",
@@ -5565,6 +5619,42 @@
         "UMask": "0xcd43fe04",
         "Unit": "CHA"
     },
+    {
+        "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd42fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd437e04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; ITOM misses from local IO and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc42fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; ITOM misses from local IO and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc437e04",
+        "Unit": "CHA"
+    },
     {
         "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO",
         "EventCode": "0x36",
@@ -5574,6 +5664,24 @@
         "UMask": "0xc8f3fe04",
         "Unit": "CHA"
     },
+    {
+        "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f2fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f37e04",
+        "Unit": "CHA"
+    },
     {
         "BriefDescription": "TOR Occupancy; RFO misses from local IO",
         "EventCode": "0x36",