From 2c95afc1e83d93fac3be6923465e1753c2c53b0a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 9 Jun 2016 06:14:38 -0700 Subject: [PATCH] perf/x86/intel, watchdog: Switch NMI watchdog to ref cycles on x86 The NMI watchdog uses either the fixed cycles or a generic cycles counter. This causes a lot of conflicts with users of the PMU who want to run a full group including the cycles fixed counter, for example the --topdown support recently added to perf stat. The code needs to fall back to not use groups, which can cause measurement inaccuracy due to multiplexing errors. This patch switches the NMI watchdog to use reference cycles on Intel systems. This is actually more accurate than cycles, because cycles can tick faster than the measured CPU Frequency due to Turbo mode. The ref cycles always tick at their frequency, or slower when the system is idling. That means the NMI watchdog can never expire too early, unlike with cycles. The reference cycles tick roughly at the frequency of the TSC, so the same period computation can be used. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: jolsa@kernel.org Link: http://lkml.kernel.org/r/1465478079-19993-1-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/hw_nmi.c | 8 ++++++++ include/linux/nmi.h | 1 + kernel/watchdog.c | 7 +++++++ 3 files changed, 16 insertions(+) diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 7788ce643bf4..016f4263fad4 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -18,8 +18,16 @@ #include #include #include +#include #ifdef CONFIG_HARDLOCKUP_DETECTOR +int hw_nmi_get_event(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + return PERF_COUNT_HW_REF_CPU_CYCLES; + return PERF_COUNT_HW_CPU_CYCLES; +} + u64 hw_nmi_get_sample_period(int watchdog_thresh) { return (u64)(cpu_khz) * 1000 * watchdog_thresh; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 4630eeae18e0..79858af27209 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -66,6 +66,7 @@ static inline bool trigger_allbutself_cpu_backtrace(void) #ifdef CONFIG_LOCKUP_DETECTOR u64 hw_nmi_get_sample_period(int watchdog_thresh); +int hw_nmi_get_event(void); extern int nmi_watchdog_enabled; extern int soft_watchdog_enabled; extern int watchdog_user_enabled; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 9acb29f280ec..8dd30fcd91be 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -315,6 +315,12 @@ static int is_softlockup(unsigned long touch_ts) #ifdef CONFIG_HARDLOCKUP_DETECTOR +/* Can be overriden by architecture */ +__weak int hw_nmi_get_event(void) +{ + return PERF_COUNT_HW_CPU_CYCLES; +} + static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, @@ -604,6 +610,7 @@ static int watchdog_nmi_enable(unsigned int cpu) wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); + wd_attr->config = hw_nmi_get_event(); /* Try to register using hardware perf events */ event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); -- 2.20.1