perf vendor events intel: Update meteorlake to 1.08

Update events from 1.07 to 1.08 as released in:

  f0f8f3e163

Various description updates. Adds topdown, offcore and uncore events
OCR.DEMAND_DATA_RD.L3_HIT, OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD,
OCR.DEMAND_RFO.L3_HIT, OCR.DEMAND_DATA_RD.L3_MISS,
OCR.DEMAND_RFO.L3_MISS, OCR.DEMAND_DATA_RD.ANY_RESPONSE,
OCR.DEMAND_DATA_RD.DRAM, OCR.DEMAND_RFO.ANY_RESPONSE,
OCR.DEMAND_RFO.DRAM, TOPDOWN_BAD_SPECULATION.ALL_P,
TOPDOWN_BE_BOUND.ALL_P, TOPDOWN_FE_BOUND.ALL_P,
TOPDOWN_RETIRING.ALL_P, UNC_ARB_DAT_OCCUPANCY.RD and
UNC_HAC_ARB_COH_TRK_REQUESTS.ALL.

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/20240321060016.1464787-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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

@@ -21,7 +21,7 @@ GenuineIntel-6-3E,v24,ivytown,core
 GenuineIntel-6-2D,v24,jaketown,core
 GenuineIntel-6-(57|85),v16,knightslanding,core
 GenuineIntel-6-BD,v1.01,lunarlake,core
-GenuineIntel-6-A[AC],v1.07,meteorlake,core
+GenuineIntel-6-A[AC],v1.08,meteorlake,core
 GenuineIntel-6-1[AEF],v4,nehalemep,core
 GenuineIntel-6-2E,v4,nehalemex,core
 GenuineIntel-6-A7,v1.02,rocketlake,core

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

@@ -966,6 +966,16 @@
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F803C0001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
         "EventCode": "0xB7",
@@ -986,6 +996,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x4003C0001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.",
         "EventCode": "0xB7",
@@ -1006,6 +1026,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.L3_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F803C0002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
         "EventCode": "0xB7",

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

@@ -378,7 +378,7 @@
         "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",
         "Unit": "cpu_core"
@@ -455,7 +455,7 @@
         "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nThe count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"

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

@@ -296,6 +296,16 @@
         "UMask": "0x4",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FBFC00001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
         "EventCode": "0x2A,0x2B",
@@ -306,6 +316,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FBFC00002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
         "EventCode": "0x2A,0x2B",

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

@@ -17,6 +17,16 @@
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand data reads that have any type of response.",
         "EventCode": "0x2A,0x2B",
@@ -27,6 +37,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
         "EventCode": "0x2A,0x2B",
@@ -37,6 +57,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
         "EventCode": "0x2A,0x2B",
@@ -47,6 +77,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "EventCode": "0xB7",
@@ -97,7 +137,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
         "EventCode": "0x75",
         "EventName": "SERIALIZATION.C01_MS_SCB",
         "SampleAfterValue": "200003",

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

@@ -1067,7 +1067,7 @@
         "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.\nThe count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "10000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1116,10 +1116,18 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
         "EventCode": "0x73",
         "EventName": "TOPDOWN_BAD_SPECULATION.ALL",
-        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
+        "EventCode": "0x73",
+        "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_atom"
     },
@@ -1156,7 +1164,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]",
         "EventCode": "0x74",
         "EventName": "TOPDOWN_BE_BOUND.ALL",
         "SampleAfterValue": "1000003",
@@ -1170,6 +1178,13 @@
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]",
+        "EventCode": "0x74",
+        "EventName": "TOPDOWN_BE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop).  This could be caused by RSV full or load/store buffer block.",
         "EventCode": "0x74",
@@ -1211,12 +1226,19 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL_P]",
         "EventCode": "0x71",
         "EventName": "TOPDOWN_FE_BOUND.ALL",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL]",
+        "EventCode": "0x71",
+        "EventName": "TOPDOWN_FE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear",
         "EventCode": "0x71",
@@ -1299,13 +1321,21 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL",
+        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL_P]",
         "EventCode": "0x72",
         "EventName": "TOPDOWN_RETIRING.ALL",
         "PEBS": "1",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL]",
+        "EventCode": "0x72",
+        "EventName": "TOPDOWN_RETIRING.ALL_P",
+        "PEBS": "1",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Number of non dec-by-all uops decoded by decoder",
         "EventCode": "0x76",
@@ -1591,7 +1621,7 @@
         "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric.",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric.\nSoftware can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"

tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json

@@ -1,4 +1,20 @@
 [
+    {
+        "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.",
+        "EventCode": "0x85",
+        "EventName": "UNC_ARB_DAT_OCCUPANCY.RD",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "ARB"
+    },
+    {
+        "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop,  etc.",
+        "EventCode": "0x84",
+        "EventName": "UNC_HAC_ARB_COH_TRK_REQUESTS.ALL",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "HAC_ARB"
+    },
     {
         "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches",
         "EventCode": "0x81",
@@ -9,7 +25,7 @@
     },
     {
         "BriefDescription": "Number of all CMI transactions",
-        "EventCode": "0x8a",
+        "EventCode": "0x8A",
         "EventName": "UNC_HAC_ARB_TRANSACTIONS.ALL",
         "PerPkg": "1",
         "UMask": "0x1",
@@ -17,7 +33,7 @@
     },
     {
         "BriefDescription": "Number of all CMI reads",
-        "EventCode": "0x8a",
+        "EventCode": "0x8A",
         "EventName": "UNC_HAC_ARB_TRANSACTIONS.READS",
         "PerPkg": "1",
         "UMask": "0x2",
@@ -25,7 +41,7 @@
     },
     {
         "BriefDescription": "Number of all CMI writes not including Mflush",
-        "EventCode": "0x8a",
+        "EventCode": "0x8A",
         "EventName": "UNC_HAC_ARB_TRANSACTIONS.WRITES",
         "PerPkg": "1",
         "UMask": "0x4",