perf vendor events: Add POWER9 PMU events

Add POWER9 PMU events.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Link: http://lkml.kernel.org/n/tip-i08irl1x1i914xsikiomvqip@git.kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/pmu-events/arch/powerpc/power9/cache.json

+[
+  {,
+    "EventCode": "0x1002A",
+    "EventName": "PM_CMPLU_STALL_LARX",
+    "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1003C",
+    "EventName": "PM_CMPLU_STALL_DMISS_L2L3",
+    "BriefDescription": "Completion stall by Dcache miss which resolved in L2/L3",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x14048",
+    "EventName": "PM_INST_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to an instruction fetch (not prefetch)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3E054",
+    "EventName": "PM_LD_MISS_L1",
+    "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load.",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x400F0",
+    "EventName": "PM_LD_MISS_L1",
+    "BriefDescription": "Load Missed L1, at execution time (not gated by finish, which means this counter can be greater than loads finished)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1404A",
+    "EventName": "PM_INST_FROM_RL2L3_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1C058",
+    "EventName": "PM_DTLB_MISS_16G",
+    "BriefDescription": "Data TLB Miss page size 16G",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1D15C",
+    "EventName": "PM_MRK_DTLB_MISS_1G",
+    "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M. Implies radix translation was used",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1E056",
+    "EventName": "PM_CMPLU_STALL_FLUSH_ANY_THREAD",
+    "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because any of the 4 threads in the same core suffered a flush, which blocks completion",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x101E6",
+    "EventName": "PM_THRESH_EXC_4096",
+    "BriefDescription": "Threshold counter exceed a count of 4096",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2C01A",
+    "EventName": "PM_CMPLU_STALL_LHS",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that hit on an older store and it was waiting for store data",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2D016",
+    "EventName": "PM_CMPLU_STALL_FXU",
+    "BriefDescription": "Finish stall due to a scalar fixed point or CR instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x24046",
+    "EventName": "PM_INST_FROM_RL2L3_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2404A",
+    "EventName": "PM_INST_FROM_RL4",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2F140",
+    "EventName": "PM_MRK_DPTEG_FROM_L2_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2D15E",
+    "EventName": "PM_MRK_DTLB_MISS_16G",
+    "BriefDescription": "Marked Data TLB Miss page size 16G",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_RMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3D156",
+    "EventName": "PM_MRK_DTLB_MISS_64K",
+    "BriefDescription": "Marked Data TLB Miss page size 64K",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3006C",
+    "EventName": "PM_RUN_CYC_SMT2_MODE",
+    "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT2 mode",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x300F4",
+    "EventName": "PM_THRD_CONC_RUN_INST",
+    "BriefDescription": "PPC Instructions Finished by this thread when all threads in the core had the run-latch set",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4C014",
+    "EventName": "PM_CMPLU_STALL_LMQ_FULL",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that missed in the L1 and the LMQ was unable to accept this load miss request because it was full",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4C016",
+    "EventName": "PM_CMPLU_STALL_DMISS_L2L3_CONFLICT",
+    "BriefDescription": "Completion stall due to cache miss that resolves in the L2 or L3 with a conflict",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4D014",
+    "EventName": "PM_CMPLU_STALL_LOAD_FINISH",
+    "BriefDescription": "Finish stall because the NTF instruction was a load instruction with all its dependencies satisfied just going through the LSU pipe to finish",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4D016",
+    "EventName": "PM_CMPLU_STALL_FXLONG",
+    "BriefDescription": "Completion stall due to a long latency scalar fixed point instruction (division, square root)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4D12A",
+    "EventName": "PM_MRK_DATA_FROM_RL4_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's L4 on the same Node or Group ( Remote) due to a marked load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4C15E",
+    "EventName": "PM_MRK_DTLB_MISS_16M",
+    "BriefDescription": "Marked Data TLB Miss page size 16M",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x401E4",
+    "EventName": "PM_MRK_DTLB_MISS",
+    "BriefDescription": "Marked dtlb miss",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x401EA",
+    "EventName": "PM_THRESH_EXC_128",
+    "BriefDescription": "Threshold counter exceeded a value of 128",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x400F6",
+    "EventName": "PM_BR_MPRED_CMPL",
+    "BriefDescription": "Number of Branch Mispredicts",
+    "PublicDescription": ""
+  }
+]

tools/perf/pmu-events/arch/powerpc/power9/floating-point.json

+[
+  {,
+    "EventCode": "0x10058",
+    "EventName": "PM_MEM_LOC_THRESH_IFU",
+    "BriefDescription": "Local Memory above threshold for IFU speculation control",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4505E",
+    "EventName": "PM_FLOP_CMPL",
+    "BriefDescription": "Floating Point Operation Finished",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1415A",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 with load hit store conflict due to a marked load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2D028",
+    "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L2",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L2 data cache",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2D154",
+    "EventName": "PM_MRK_DERAT_MISS_64K",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 64K",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x30012",
+    "EventName": "PM_FLUSH_COMPLETION",
+    "BriefDescription": "The instruction that was next to complete did not complete because it suffered a flush",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4016E",
+    "EventName": "PM_THRESH_NOT_MET",
+    "BriefDescription": "Threshold counter did not meet threshold",
+    "PublicDescription": ""
+  }
+]

tools/perf/pmu-events/arch/powerpc/power9/memory.json

+[
+  {,
+    "EventCode": "0x10008",
+    "EventName": "PM_RUN_SPURR",
+    "BriefDescription": "Run SPURR",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1000A",
+    "EventName": "PM_PMC3_REWIND",
+    "BriefDescription": "PMC3 rewind event. A rewind happens when a speculative event (such as latency or CPI stack) is selected on PMC3 and the stall reason or reload source did not match the one programmed in PMC3. When this occurs, the count in PMC3 will not change.",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1C040",
+    "EventName": "PM_DATA_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a demand load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1C050",
+    "EventName": "PM_DATA_CHIP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for a demand load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1D15E",
+    "EventName": "PM_MRK_RUN_CYC",
+    "BriefDescription": "Run cycles in which a marked instruction is in the pipeline",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x15158",
+    "EventName": "PM_SYNC_MRK_L2HIT",
+    "BriefDescription": "Marked L2 Hits that can throw a synchronous interrupt",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x20010",
+    "EventName": "PM_PMC1_OVERFLOW",
+    "BriefDescription": "Overflow from counter 1",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2C040",
+    "EventName": "PM_DATA_FROM_L2_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state due to a demand load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2005A",
+    "EventName": "PM_DARQ1_7_9_ENTRIES",
+    "BriefDescription": "Cycles in which 7 to 9 DARQ1 entries (out of 12) are in use",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2C05C",
+    "EventName": "PM_INST_GRP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for an instruction fetch (demand only)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2D156",
+    "EventName": "PM_MRK_DTLB_MISS_4K",
+    "BriefDescription": "Marked Data TLB Miss page size 4k",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2E05A",
+    "EventName": "PM_LRQ_REJECT",
+    "BriefDescription": "Internal LSU reject from LRQ. Rejects cause the load to go back to LRQ, but it stays contained within the LSU once it gets issued. This event counts the number of times the LRQ attempts to relaunch an instruction after a reject. Any load can suffer multiple rejects",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2E05C",
+    "EventName": "PM_LSU_REJECT_ERAT_MISS",
+    "BriefDescription": "LSU Reject due to ERAT (up to 4 per cycles)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x200F6",
+    "EventName": "PM_LSU_DERAT_MISS",
+    "BriefDescription": "DERAT Reloaded due to a DERAT miss",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3C048",
+    "EventName": "PM_DATA_FROM_DL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3404A",
+    "EventName": "PM_INST_FROM_RMEM",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3C058",
+    "EventName": "PM_LARX_FIN",
+    "BriefDescription": "Larx finished",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3E050",
+    "EventName": "PM_DARQ1_4_6_ENTRIES",
+    "BriefDescription": "Cycles in which 4, 5, or 6 DARQ1 entries (out of 12) are in use",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3006E",
+    "EventName": "PM_NEST_REF_CLK",
+    "BriefDescription": "Multiply by 4 to obtain the number of PB cycles",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x301E2",
+    "EventName": "PM_MRK_ST_CMPL",
+    "BriefDescription": "Marked store completed and sent to nest",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4D02C",
+    "EventName": "PM_PMC1_REWIND",
+    "BriefDescription": "",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4003E",
+    "EventName": "PM_LD_CMPL",
+    "BriefDescription": "count of Loads completed",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4C040",
+    "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_OTHER",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a demand load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4C042",
+    "EventName": "PM_DATA_FROM_L3",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4C048",
+    "EventName": "PM_DATA_FROM_DL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4D056",
+    "EventName": "PM_NON_FMA_FLOP_CMPL",
+    "BriefDescription": "Non FMA instruction completed",
+    "PublicDescription": ""
+  }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/powerpc/power9/pmc.json

+[
+  {,
+    "EventCode": "0x0",
+    "EventName": "PM_SUSPENDED",
+    "BriefDescription": "Counter OFF",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x10026",
+    "EventName": "PM_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when an instruction tablewalk is active",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1E04C",
+    "EventName": "PM_DPTEG_FROM_LL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x1F14E",
+    "EventName": "PM_MRK_DPTEG_FROM_L2MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x10060",
+    "EventName": "PM_TM_TRANS_RUN_CYC",
+    "BriefDescription": "run cycles in transactional state",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2C012",
+    "EventName": "PM_CMPLU_STALL_DCACHE_MISS",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that missed the L1 and was waiting for the data to return from the nest",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2E04C",
+    "EventName": "PM_DPTEG_FROM_MEMORY",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x2C056",
+    "EventName": "PM_DTLB_MISS_4K",
+    "BriefDescription": "Data TLB Miss page size 4k",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3000C",
+    "EventName": "PM_FREQ_DOWN",
+    "BriefDescription": "Power Management: Below Threshold B",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3D142",
+    "EventName": "PM_MRK_DATA_FROM_LMEM",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a marked load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x3F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x301E8",
+    "EventName": "PM_THRESH_EXC_64",
+    "BriefDescription": "Threshold counter exceeded a value of 64",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x40118",
+    "EventName": "PM_MRK_DCACHE_RELOAD_INTV",
+    "BriefDescription": "Combined Intervention event",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4C01E",
+    "EventName": "PM_CMPLU_STALL_CRYPTO",
+    "BriefDescription": "Finish stall because the NTF instruction was routed to the crypto execution pipe and was waiting to finish",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4D018",
+    "EventName": "PM_CMPLU_STALL_BRU",
+    "BriefDescription": "Completion stall due to a Branch Unit",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4D128",
+    "EventName": "PM_MRK_DATA_FROM_LMEM_CYC",
+    "BriefDescription": "Duration in cycles to reload from the local chip's Memory due to a marked load",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4E04E",
+    "EventName": "PM_DPTEG_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L3",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4F148",
+    "EventName": "PM_MRK_DPTEG_FROM_DL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x40050",
+    "EventName": "PM_SYS_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x40056",
+    "EventName": "PM_MEM_LOC_THRESH_LSU_HIGH",
+    "BriefDescription": "Local memory above threshold for LSU medium",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x4D054",
+    "EventName": "PM_8FLOP_CMPL",
+    "BriefDescription": "8 FLOP instruction completed",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x45050",
+    "EventName": "PM_1FLOP_CMPL",
+    "BriefDescription": "one flop (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg) operation completed",
+    "PublicDescription": ""
+  },
+  {,
+    "EventCode": "0x45052",
+    "EventName": "PM_4FLOP_CMPL",
+    "BriefDescription": "4 FLOP instruction completed",
+    "PublicDescription": ""
+  }
+]