perf vendor events intel: Update CascadelakeX events to v1.08

- Update CascadelakeX events to v1.08.
- Update CascadelakeX JSON metrics from TMAM 4.0.

Other fixes:

- Add NO_NMI_WATCHDOG metric constraint to Backend_Bound
- Change 'MB/sec' to 'MB' in UNC_M_PMM_BANDWIDTH.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Link: https://lore.kernel.org/lkml/20200922031918.3723-1-yao.jin@linux.intel.com/Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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

@@ -8063,6 +8063,20 @@
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020004",
+        "Offcore": "1",
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "This event is deprecated. Refer to new event OCR.ALL_PF_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD",
         "Counter": "0,1,2,3",
@@ -9255,20 +9269,6 @@
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "Counter": "0,1,2,3",
-        "CounterHTOff": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000020004",
-        "Offcore": "1",
-        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
     {
         "BriefDescription": "This event is deprecated. Refer to new event OCR.ALL_PF_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
         "Counter": "0,1,2,3",

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

@@ -246,6 +246,30 @@
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
+    {
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xAB",
+        "EventName": "DSB2MITE_SWITCHES.COUNT",
+        "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x400106",
+        "PEBS": "2",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "SampleAfterValue": "100007",
+        "TakenAlone": "1",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
         "Counter": "0,1,2,3",
@@ -359,6 +383,16 @@
         "SampleAfterValue": "2000003",
         "UMask": "0x24"
     },
+    {
+        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xE6",
+        "EventName": "BACLEARS.ANY",
+        "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",

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

@@ -826,16 +826,6 @@
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
-    {
-        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
-        "Counter": "0,1,2,3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xE6",
-        "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
     {
         "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.",
         "Counter": "0,1,2,3",

tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json

@@ -90,32 +90,32 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Intel Optane DC persistent memory bandwidth read (MB/sec). Derived from unc_m_pmm_rpq_inserts",
+        "BriefDescription": "Intel Optane DC persistent memory bandwidth read (MB). Derived from unc_m_pmm_rpq_inserts",
         "Counter": "0,1,2,3",
         "EventCode": "0xE3",
         "EventName": "UNC_M_PMM_BANDWIDTH.READ",
         "PerPkg": "1",
-        "ScaleUnit": "6.103515625E-5MB/sec",
+        "ScaleUnit": "6.103515625E-5MB",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Intel Optane DC persistent memory bandwidth write (MB/sec). Derived from unc_m_pmm_wpq_inserts",
+        "BriefDescription": "Intel Optane DC persistent memory bandwidth write (MB). Derived from unc_m_pmm_wpq_inserts",
         "Counter": "0,1,2,3",
         "EventCode": "0xE7",
         "EventName": "UNC_M_PMM_BANDWIDTH.WRITE",
         "PerPkg": "1",
-        "ScaleUnit": "6.103515625E-5MB/sec",
+        "ScaleUnit": "6.103515625E-5MB",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Intel Optane DC persistent memory bandwidth total (MB/sec). Derived from unc_m_pmm_rpq_inserts",
+        "BriefDescription": "Intel Optane DC persistent memory bandwidth total (MB). Derived from unc_m_pmm_rpq_inserts",
         "Counter": "0,1,2,3",
         "EventCode": "0xE3",
         "EventName": "UNC_M_PMM_BANDWIDTH.TOTAL",
         "MetricExpr": "UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS",
         "MetricName": "UNC_M_PMM_BANDWIDTH.TOTAL",
         "PerPkg": "1",
-        "ScaleUnit": "6.103515625E-5MB/sec",
+        "ScaleUnit": "6.103515625E-5MB",
         "Unit": "iMC"
     },
     {

tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json

@@ -537,6 +537,27 @@
         "UMask": "0x10",
         "Unit": "CHA"
     },
+    {
+        "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD",
+        "Filter": "config1=0x40433",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : DRds issued by iA Cores 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": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD",
+        "Filter": "config1=0x40433",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : 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": "0x21",
+        "Unit": "CHA"
+    },
     {
         "BriefDescription": "Clockticks of the IIO Traffic Controller",
         "Counter": "0,1,2,3",