From 7639dae0ca11038286bbbcda05f2bef601c1eb8d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 14 Dec 2010 21:26:40 +0100 Subject: [PATCH] perf, x86: Provide a PEBS capable cycle event Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index c8f5c08..24e390e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -816,6 +816,32 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; + if (event->attr.precise_ip && + (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { + /* + * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P + * (0x003c) so that we can use it with PEBS. + * + * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't + * PEBS capable. However we can use INST_RETIRED.ANY_P + * (0x00c0), which is a PEBS capable event, to get the same + * count. + * + * INST_RETIRED.ANY_P counts the number of cycles that retires + * CNTMASK instructions. By setting CNTMASK to a value (16) + * larger than the maximum number of instructions that can be + * retired per cycle (4) and then inverting the condition, we + * count all cycles that retire 16 or less instructions, which + * is every cycle. + * + * Thereby we gain a PEBS capable cycle counter. + */ + u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */ + + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); + event->hw.config = alt_config; + } + if (event->attr.type != PERF_TYPE_RAW) return 0; -- 2.7.4