perf vendor events intel: Broadwellx v20 events

Updates descriptions and encodings. Adds BR_MISP_EXEC.INDIRECT events.
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Dan Williams <dan.j.williams@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>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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

@@ -8,7 +8,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.",
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
@@ -16,7 +16,7 @@
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "L1D miss oustandings duration in cycles",
+        "BriefDescription": "L1D miss outstandings duration in cycles",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
         "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
@@ -454,22 +454,22 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "All retired load uops.",
+        "BriefDescription": "Retired load uops.",
         "Data_LA": "1",
         "EventCode": "0xD0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "PEBS": "1",
-        "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
+        "PublicDescription": "Counts all retired load uops. This event accounts for SW prefetch uops of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
         "SampleAfterValue": "2000003",
         "UMask": "0x81"
     },
     {
-        "BriefDescription": "All retired store uops.",
+        "BriefDescription": "Retired store uops.",
         "Data_LA": "1",
         "EventCode": "0xD0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "PEBS": "1",
-        "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
+        "PublicDescription": "Counts all retired store uops.",
         "SampleAfterValue": "2000003",
         "UMask": "0x82"
     },
@@ -541,10 +541,10 @@
         "UMask": "0x80"
     },
     {
-        "BriefDescription": "Cacheable and noncachaeble code read requests",
+        "BriefDescription": "Cacheable and non-cacheable code read requests",
         "EventCode": "0xB0",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "This event counts both cacheable and noncachaeble code read requests.",
+        "PublicDescription": "This event counts both cacheable and non-cacheable code read requests.",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },

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

@@ -125,16 +125,16 @@
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES",
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
         "SampleAfterValue": "2000003",
         "UMask": "0x30"
     },
     {
-        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_DSB_CYCLES",
@@ -143,7 +143,7 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy",
         "CounterMask": "1",
         "EdgeDetect": "1",
         "EventCode": "0x79",
@@ -153,7 +153,7 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_DSB_UOPS",
         "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
@@ -161,10 +161,10 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_MITE_UOPS",
-        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
+        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -178,10 +178,10 @@
         "UMask": "0x30"
     },
     {
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
         "SampleAfterValue": "2000003",
         "UMask": "0x30"
     },

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

@@ -214,6 +214,14 @@
         "SampleAfterValue": "200003",
         "UMask": "0xc4"
     },
+    {
+        "BriefDescription": "Speculative mispredicted indirect branches",
+        "EventCode": "0x89",
+        "EventName": "BR_MISP_EXEC.INDIRECT",
+        "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).",
+        "SampleAfterValue": "200003",
+        "UMask": "0xe4"
+    },
     {
         "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches",
         "EventCode": "0x89",
@@ -500,7 +508,7 @@
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "EventCode": "0x87",
         "EventName": "ILD_STALL.LCP",
-        "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+        "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -909,7 +917,7 @@
     },
     {
         "AnyThread": "1",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
+        "BriefDescription": "Cycles per core when uops are executed in port 0.",
         "EventCode": "0xA1",
         "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
         "SampleAfterValue": "2000003",
@@ -925,7 +933,7 @@
     },
     {
         "AnyThread": "1",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
+        "BriefDescription": "Cycles per core when uops are executed in port 1.",
         "EventCode": "0xA1",
         "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
         "SampleAfterValue": "2000003",
@@ -973,7 +981,7 @@
     },
     {
         "AnyThread": "1",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
+        "BriefDescription": "Cycles per core when uops are executed in port 4.",
         "EventCode": "0xA1",
         "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
         "SampleAfterValue": "2000003",
@@ -989,7 +997,7 @@
     },
     {
         "AnyThread": "1",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
+        "BriefDescription": "Cycles per core when uops are executed in port 5.",
         "EventCode": "0xA1",
         "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
         "SampleAfterValue": "2000003",
@@ -1005,7 +1013,7 @@
     },
     {
         "AnyThread": "1",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
+        "BriefDescription": "Cycles per core when uops are executed in port 6.",
         "EventCode": "0xA1",
         "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
         "SampleAfterValue": "2000003",

tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json

@@ -395,7 +395,7 @@
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "PerPkg": "1",
-        "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
     },
     {
@@ -403,7 +403,7 @@
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "PerPkg": "1",
-        "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
     },
     {
@@ -411,7 +411,7 @@
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "PerPkg": "1",
-        "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
     },
     {
@@ -427,7 +427,7 @@
         "EventCode": "0x9",
         "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles that we are in Interal PROCHOT mode.  This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.",
+        "PublicDescription": "Counts the number of cycles that we are in Internal PROCHOT mode.  This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.",
         "Unit": "PCU"
     },
     {
@@ -451,7 +451,7 @@
         "EventCode": "0x42",
         "EventName": "UNC_P_VR_HOT_CYCLES",
         "PerPkg": "1",
-        "PublicDescription": "UNC_P_VR_HOT_CYCLES",
+        "PublicDescription": "VR Hot : Number of cycles that a CPU SVID VR is hot.  Does not cover DRAM VRs",
         "Unit": "PCU"
     }
 ]

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

@@ -4,7 +4,7 @@ GenuineIntel-6-BE,v1.19,alderlaken,core
 GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core
 GenuineIntel-6-(3D|47),v27,broadwell,core
 GenuineIntel-6-56,v9,broadwellde,core
-GenuineIntel-6-4F,v19,broadwellx,core
+GenuineIntel-6-4F,v20,broadwellx,core
 GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core
 GenuineIntel-6-9[6C],v1.03,elkhartlake,core
 GenuineIntel-6-5[CF],v13,goldmont,core