On Wed, Nov 21, 2018 at 03:58:14PM +0000, Mark Rutland wrote: > On Tue, Nov 20, 2018 at 02:15:19PM +0000, Andrew Murray wrote: > > The armv8pmu_enable_event_counter function issues an isb instruction > > after enabling a pair of counters - this doesn't provide any value > > and is inconsistent with the armv8pmu_disable_event_counter. > > > > In any case armv8pmu_enable_event_counter is always called with the > > PMU stopped. Starting the PMU with armv8pmu_start results in an isb > > instruction being issued. > > > > Let's remove the unnecessary isb instruction. > > > > Signed-off-by: Andrew Murray <andrew.mur...@arm.com> > > Acked-by: Mark Rutland <mark.rutl...@arm.com> > > ... though it would be nice to explicitly point out that the ISB in > armv8pmu_start() is before the write to PMCR_EL1, if you happen to > respin this patch.
Thanks, I'm respining so I'll update the log and preserve your ack. Andrew Murray > > Mark. > > > --- > > arch/arm64/kernel/perf_event.c | 1 - > > 1 file changed, 1 deletion(-) > > > > diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c > > index 8e38d52..de564ae 100644 > > --- a/arch/arm64/kernel/perf_event.c > > +++ b/arch/arm64/kernel/perf_event.c > > @@ -652,7 +652,6 @@ static inline void armv8pmu_enable_event_counter(struct > > perf_event *event) > > armv8pmu_enable_counter(idx); > > if (armv8pmu_event_is_chained(event)) > > armv8pmu_enable_counter(idx - 1); > > - isb(); > > } > > > > static inline int armv8pmu_disable_counter(int idx) > > -- > > 2.7.4 > > _______________________________________________ kvmarm mailing list kvmarm@lists.cs.columbia.edu https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
