perf vendor events intel: Update meteorlake events

Update from 1.00 to 1.01. Event description updates. Addition of
IDQ_BUBBLES.CORE, TOPDOWN.BACKEND_BOUND_SLOTS, UOPS_RETIRED.SLOTS.
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.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: Peter Zijlstra <peterz@infradead.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230314053312.3237390-2-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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

@@ -18,7 +18,7 @@ GenuineIntel-6-3A,v23,ivybridge,core
 GenuineIntel-6-3E,v22,ivytown,core
 GenuineIntel-6-2D,v22,jaketown,core
 GenuineIntel-6-(57|85),v10,knightslanding,core
-GenuineIntel-6-A[AC],v1.00,meteorlake,core
+GenuineIntel-6-A[AC],v1.01,meteorlake,core
 GenuineIntel-6-1[AEF],v3,nehalemep,core
 GenuineIntel-6-2E,v3,nehalemex,core
 GenuineIntel-6-2A,v18,sandybridge,core

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

@@ -3,6 +3,7 @@
         "BriefDescription": "L2 code requests",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "PublicDescription": "Counts the total number of L2 code requests.",
         "SampleAfterValue": "200003",
         "UMask": "0xe4",
         "Unit": "cpu_core"
@@ -11,6 +12,7 @@
         "BriefDescription": "Demand Data Read access L2 cache",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
         "SampleAfterValue": "200003",
         "UMask": "0xe1",
         "Unit": "cpu_core"
@@ -19,6 +21,7 @@
         "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
         "SampleAfterValue": "200003",
         "UMask": "0x41",
         "Unit": "cpu_atom"
@@ -27,6 +30,7 @@
         "BriefDescription": "Core-originated cacheable requests that missed L3  (Except hardware prefetches to the L3)",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -35,6 +39,7 @@
         "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
         "SampleAfterValue": "200003",
         "UMask": "0x4f",
         "Unit": "cpu_atom"
@@ -43,6 +48,7 @@
         "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
         "SampleAfterValue": "100003",
         "UMask": "0x4f",
         "Unit": "cpu_core"
@@ -53,6 +59,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
         "SampleAfterValue": "1000003",
         "UMask": "0x81",
         "Unit": "cpu_core"
@@ -63,6 +70,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
         "PEBS": "1",
+        "PublicDescription": "Counts all retired store instructions.",
         "SampleAfterValue": "1000003",
         "UMask": "0x82",
         "Unit": "cpu_core"

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

@@ -14,5 +14,14 @@
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_atom"
+    },
+    {
+        "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.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
     }
 ]

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

@@ -7,6 +7,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
         "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "1009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -19,6 +20,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
         "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -31,6 +33,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
         "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "503",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -43,6 +46,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
         "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -55,6 +59,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
         "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -67,6 +72,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
         "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "101",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -79,6 +85,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
         "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "2003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -91,6 +98,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
         "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "50021",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -101,12 +109,13 @@
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
         "PEBS": "2",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts cacheable demand data reads were not supplied by the L3 cache.",
+        "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",
@@ -126,7 +135,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO were not supplied by the L3 cache.",
+        "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",

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

 [
     {
-        "BriefDescription": "Counts cacheable demand data reads Catch all value for any response types - this includes response types not define in the OCR.  If this is set all other response types will be ignored",
+        "BriefDescription": "Counts demand data reads that have any type of response.",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
@@ -20,7 +20,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO Catch all value for any response types - this includes response types not define in the OCR.  If this is set all other response types will be ignored",
+        "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",

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

@@ -3,6 +3,7 @@
         "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -11,6 +12,7 @@
         "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -19,6 +21,7 @@
         "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.",
         "EventCode": "0x85",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size.  Includes page walks that page fault.",
         "SampleAfterValue": "200003",
         "UMask": "0xe",
         "Unit": "cpu_atom"
@@ -27,6 +30,7 @@
         "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"