From:   Thomas Richter <tmricht@linux.ibm.com>
To:     linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
        acme@kernel.org, sumanthk@linux.ibm.com
Cc:     svens@linux.ibm.com, gor@linux.ibm.com, hca@linux.ibm.com,
        Thomas Richter <tmricht@linux.ibm.com>
Subject: [PATCH 6/6] tools/perf/json: Add metric for tlb and cache s390
Date:   Mon, 13 Mar 2023 09:02:01 +0100
Message-Id: <20230313080201.2440201-6-tmricht@linux.ibm.com>
In-Reply-To: <20230313080201.2440201-1-tmricht@linux.ibm.com>
References: <20230313080201.2440201-1-tmricht@linux.ibm.com>
Content-Transfer-Encoding: 8bit
MIME-Version: 1.0
Precedence: bulk

Add metrics for tlb and cache statistics:
- finite_cpi: Cycles per Instructions from Finite cache/memory
- est_cpi: Estimated Instruction Complexity CPI infinite Level 1
- scpl1m: Estimated Sourcing Cycles per Level 1 Miss
- tlb_percent: Estimated TLB CPU percentage of Total CPU
- tlb_miss: Estimated Cycles per TLB Miss

For details about the formulas see this documentation:
https://www.ibm.com/support/pages/system/files/inline-files/CPU%20MF%20Formulas%20including%20z16%20-%20May%202022_1.pdf

Output after:
 # ./perf stat -M tlb_miss -- dd if=/dev/zero of=/dev/null bs=1M count=10K
 ... dd output removed

 Performance counter stats for
 			'dd if=/dev/zero of=/dev/null bs=1M count=10K':

           667,726      DTLB2_MISSES             #   440.96 tlb_miss
               198      ITLB2_WRITES
       795,170,260      L1C_TLB2_MISSES
             9,478      ITLB2_MISSES
               820      DTLB2_WRITES
     1,197,126,869      L1D_PENALTY_CYCLES
         2,457,447      L1I_PENALTY_CYCLES

       1.249342187 seconds time elapsed

       0.001030000 seconds user
       1.248105000 seconds sys

 #

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-By: Sumanth Korikkar <sumanthk@linux.ibm.com>
---
 .../arch/s390/cf_z13/transaction.json         | 30 +++++++++++++++++++
 .../arch/s390/cf_z14/transaction.json         | 25 ++++++++++++++++
 .../arch/s390/cf_z15/transaction.json         | 25 ++++++++++++++++
 .../arch/s390/cf_z16/transaction.json         | 25 ++++++++++++++++
 4 files changed, 105 insertions(+)

diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
index 71e2c7fa734c..b941a7212a4d 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
@@ -43,5 +43,35 @@
     "BriefDescription": "Percentage sourced from memory",
     "MetricName": "memp",
     "MetricExpr": "((L1D_ONNODE_MEM_SOURCED_WRITES + L1D_ONDRAWER_MEM_SOURCED_WRITES + L1D_OFFDRAWER_MEM_SOURCED_WRITES + L1D_ONCHIP_MEM_SOURCED_WRITES + L1I_ONNODE_MEM_SOURCED_WRITES + L1I_ONDRAWER_MEM_SOURCED_WRITES + L1I_OFFDRAWER_MEM_SOURCED_WRITES + L1I_ONCHIP_MEM_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+  },
+  {
+    "BriefDescription": "Cycles per Instructions from Finite cache/memory",
+    "MetricName": "finite_cpi",
+    "MetricExpr": "L1C_TLB1_MISSES / INSTRUCTIONS"
+  },
+  {
+    "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1",
+    "MetricName": "est_cpi",
+    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB1_MISSES / INSTRUCTIONS)"
+  },
+  {
+    "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss",
+    "MetricName": "scpl1m",
+    "MetricExpr": "L1C_TLB1_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)"
+  },
+  {
+    "BriefDescription": "Estimated TLB CPU percentage of Total CPU",
+    "MetricName": "tlb_percent",
+    "MetricExpr": "((DTLB1_MISSES + ITLB1_MISSES) / CPU_CYCLES) * (L1C_TLB1_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100"
+  },
+  {
+    "BriefDescription": "Estimated Cycles per TLB Miss",
+    "MetricName": "tlb_miss",
+    "MetricExpr": "((DTLB1_MISSES + ITLB1_MISSES) / (DTLB1_WRITES + ITLB1_WRITES)) * (L1C_TLB1_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))"
+  },
+  {
+    "BriefDescription": "Page Table Entry misses",
+    "MetricName": "pte_miss",
+    "MetricExpr": "(TLB2_PTE_WRITES / (DTLB1_WRITES + ITLB1_WRITES)) * 100"
   }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
index cca237bdb7ba..ce814ea93396 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
@@ -43,5 +43,30 @@
     "BriefDescription": "Percentage sourced from memory",
     "MetricName": "memp",
     "MetricExpr": "((L1D_ONCHIP_MEMORY_SOURCED_WRITES + L1D_ONCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFDRAWER_MEMORY_SOURCED_WRITES + L1I_ONCHIP_MEMORY_SOURCED_WRITES + L1I_ONCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFDRAWER_MEMORY_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+  },
+  {
+    "BriefDescription": "Cycles per Instructions from Finite cache/memory",
+    "MetricName": "finite_cpi",
+    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS"
+  },
+  {
+    "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1",
+    "MetricName": "est_cpi",
+    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)"
+  },
+  {
+    "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss",
+    "MetricName": "scpl1m",
+    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)"
+  },
+  {
+    "BriefDescription": "Estimated TLB CPU percentage of Total CPU",
+    "MetricName": "tlb_percent",
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100"
+  },
+  {
+    "BriefDescription": "Estimated Cycles per TLB Miss",
+    "MetricName": "tlb_miss",
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))"
   }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
index cca237bdb7ba..ce814ea93396 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
@@ -43,5 +43,30 @@
     "BriefDescription": "Percentage sourced from memory",
     "MetricName": "memp",
     "MetricExpr": "((L1D_ONCHIP_MEMORY_SOURCED_WRITES + L1D_ONCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFDRAWER_MEMORY_SOURCED_WRITES + L1I_ONCHIP_MEMORY_SOURCED_WRITES + L1I_ONCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFDRAWER_MEMORY_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+  },
+  {
+    "BriefDescription": "Cycles per Instructions from Finite cache/memory",
+    "MetricName": "finite_cpi",
+    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS"
+  },
+  {
+    "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1",
+    "MetricName": "est_cpi",
+    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)"
+  },
+  {
+    "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss",
+    "MetricName": "scpl1m",
+    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)"
+  },
+  {
+    "BriefDescription": "Estimated TLB CPU percentage of Total CPU",
+    "MetricName": "tlb_percent",
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100"
+  },
+  {
+    "BriefDescription": "Estimated Cycles per TLB Miss",
+    "MetricName": "tlb_miss",
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))"
   }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
index dde0735a7d22..ec2ff78e2b5f 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
@@ -43,5 +43,30 @@
     "BriefDescription": "Percentage sourced from memory",
     "MetricName": "memp",
     "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+  },
+  {
+    "BriefDescription": "Cycles per Instructions from Finite cache/memory",
+    "MetricName": "finite_cpi",
+    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS"
+  },
+  {
+    "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1",
+    "MetricName": "est_cpi",
+    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)"
+  },
+  {
+    "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss",
+    "MetricName": "scpl1m",
+    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)"
+  },
+  {
+    "BriefDescription": "Estimated TLB CPU percentage of Total CPU",
+    "MetricName": "tlb_percent",
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100"
+  },
+  {
+    "BriefDescription": "Estimated Cycles per TLB Miss",
+    "MetricName": "tlb_miss",
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))"
   }
 ]
-- 
2.39.1