Hi Leo,
在 2023/8/14 18:01, Leo Yan 写道:
Hi Shijie,
On Mon, Aug 14, 2023 at 05:29:54PM +0800, Shijie Huang wrote:
[...]
Seems to me, based on Marc's patch, we need to apply below change. In
below code, we don't need to change the perf core code and we can
resolve it as a common issue for Arm PMU drivers.
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 121f1a14c829..8f9673cdadec 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -38,14 +38,20 @@ struct kvm_pmu_events *kvm_get_pmu_events(void)
void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr)
{
struct kvm_pmu_events *pmu = kvm_get_pmu_events();
+ int resync;
if (!kvm_arm_support_pmu_v3() || !pmu || !kvm_pmu_switch_needed(attr))
return;
+ resync = pmu->events_guest != set;
If we set two events in guest, the resync will set
For example:
perf stat -e cycles:Gu, cycles:Gk
If so, this is not reasonble...
You mean if set two guest events, the kvm_vcpu_pmu_resync_el0() will
be invoked twice, and the second calling is not reasonable, right?
IMHO, even the first time is not reasonable. why call
kvm_vcpu_pmu_resync_el0() when event rotation
does not happen?
I can accept this since I personally think this should not introduce
much performance penalty.
I understand your preference to call kvm_vcpu_pmu_resync_el0() from
perf core layer, but this is not a common issue for all PMU events and
crossing arches. Furthermore, even perf core rotates events, it's not
If we can find a better way to fix it in PMU code, I am okay too. :)
I tried to fix it in PMU code, but I am not satified with it.
necessarily mean we must restore events for guest in the case there
have no event is enabled for guest.
Not only for events in guest, but also for the events in the host too.
In the kvm_vcpu_pmu_restore_guest(), it also disable the EL0 for host
events.
Thanks
Huang Shijie
Thanks,
Leo
