lkml.org 
[lkml]   [2016]   [Dec]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH V2 03/13] perf/x86: output sampling overhead
Date
From: Kan Liang <kan.liang@intel.com>

On x86, NMI handler is the most important part which brings overhead
for sampling. Adding a pmu specific overhead type
PERF_PMU_SAMPLE_OVERHEAD for it.

For other architectures which may don't have NMI, the overhead type can
be reused.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
arch/x86/events/core.c | 17 ++++++++++++++++-
arch/x86/events/perf_event.h | 2 ++
include/uapi/linux/perf_event.h | 1 +
3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9d4bf3a..de40f96 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1397,6 +1397,9 @@ static void x86_pmu_del(struct perf_event *event, int flags)

perf_event_update_userpage(event);

+ if ((flags & PERF_EF_LOG) && cpuc->nmi_overhead.nr)
+ perf_log_overhead(event, PERF_PMU_SAMPLE_OVERHEAD, &cpuc->nmi_overhead);
+
do_del:
if (x86_pmu.del) {
/*
@@ -1475,11 +1478,21 @@ void perf_events_lapic_init(void)
apic_write(APIC_LVTPC, APIC_DM_NMI);
}

+static void
+perf_calculate_nmi_overhead(u64 time)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ cpuc->nmi_overhead.nr++;
+ cpuc->nmi_overhead.time += time;
+}
+
static int
perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
{
u64 start_clock;
u64 finish_clock;
+ u64 clock;
int ret;

/*
@@ -1492,8 +1505,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
start_clock = sched_clock();
ret = x86_pmu.handle_irq(regs);
finish_clock = sched_clock();
+ clock = finish_clock - start_clock;

- perf_sample_event_took(finish_clock - start_clock);
+ perf_calculate_nmi_overhead(clock);
+ perf_sample_event_took(clock);

return ret;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a77ee02..7a03384 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -230,6 +230,8 @@ struct cpu_hw_events {
struct intel_excl_cntrs *excl_cntrs;
int excl_thread_id; /* 0 or 1 */

+ struct perf_overhead_entry nmi_overhead;
+
/*
* AMD specific bits
*/
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index bb0ecf0..fe7b1fb 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1001,6 +1001,7 @@ enum perf_record_overhead_type {
PERF_CORE_OVERHEAD = 0,

PERF_PMU_OVERHEAD = 20,
+ PERF_PMU_SAMPLE_OVERHEAD = 20,

PERF_OVERHEAD_MAX,
};
--
2.5.5
\
 
 \ /
  Last update: 2016-12-02 22:24    [W:0.375 / U:1.300 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site