perf_counter: Accurate period data
We currently log hw.sample_period for PERF_SAMPLE_PERIOD, however this is
incorrect. When we adjust the period, it will only take effect the next
cycle but report it for the current cycle. So when we adjust the period
for every cycle, we're always wrong.
Solve this by keeping track of the last_period.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
index 5e0bf399..4990ce2 100644
--- a/arch/powerpc/kernel/perf_counter.c
+++ b/arch/powerpc/kernel/perf_counter.c
@@ -767,6 +767,7 @@
perf_disable();
power_pmu_read(counter);
left = counter->hw.sample_period;
+ counter->hw.last_period = left;
val = 0;
if (left < 0x80000000L)
val = 0x80000000L - left;
@@ -937,7 +938,8 @@
counter->hw.config = events[n];
counter->hw.counter_base = cflags[n];
- atomic64_set(&counter->hw.period_left, counter->hw.sample_period);
+ counter->hw.last_period = counter->hw.sample_period;
+ atomic64_set(&counter->hw.period_left, counter->hw.last_period);
/*
* See if we need to reserve the PMU.
@@ -1002,8 +1004,9 @@
*/
if (record) {
struct perf_sample_data data = {
- .regs = regs,
- .addr = 0,
+ .regs = regs,
+ .addr = 0,
+ .period = counter->hw.last_period,
};
if (counter->attr.sample_type & PERF_SAMPLE_ADDR) {