From f4929bd37208540c2c6f416e9035ff1938f2dbc6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Apr 2011 13:39:56 +0200 Subject: [PATCH] perf, x86: Update/fix Intel Nehalem cache events Change the Nehalem cache events to use retired memory instruction counters (similar to Westmere), this greatly improves the provided stats. Using: main () { int i; for (i = 0; i < 1000000000; i++) { asm("mov (%%rsp), %%rbx;" "mov %%rbx, (%%rsp);" : : : "rbx"); } } We find: $ perf stat --repeat 10 -e instructions:u -e l1-dcache-loads:u -e l1-dcache-stores:u ./loop_1b_loads+stores Performance counter stats for './loop_1b_loads+stores' (10 runs): 4,000,081,056 instructions:u # 0.000 IPC ( +- 0.000% ) 4,999,502,846 l1-dcache-loads:u ( +- 0.008% ) 1,000,034,832 l1-dcache-stores:u ( +- 0.000% ) 1.565184942 seconds time elapsed ( +- 0.005% ) The 5b is surprising - we'd expect 1b: $ perf stat --repeat 10 -e instructions:u -e r10b:u -e l1-dcache-stores:u ./loop_1b_loads+stores Performance counter stats for './loop_1b_loads+stores' (10 runs): 4,000,081,054 instructions:u # 0.000 IPC ( +- 0.000% ) 1,000,021,961 r10b:u ( +- 0.000% ) 1,000,030,951 l1-dcache-stores:u ( +- 0.000% ) 1.565055422 seconds time elapsed ( +- 0.003% ) Which this patch thus fixes. Signed-off-by: Peter Zijlstra Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt Cc: Stephane Eranian Cc: Lin Ming Cc: Cyrill Gorcunov Link: http://lkml.kernel.org/n/tip-q9rtru7b7840tws75xzboapv@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 586cced12d1f..43fa20b13817 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -391,12 +391,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids { [ C(L1D) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */ - [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */ + [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */ + [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */ }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */ - [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */ + [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */ + [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */ }, [ C(OP_PREFETCH) ] = { [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */