Add support for the :G and :H attributes in perf by handling the
exclude_host/exclude_guest event attributes.
We notify KVM of counters that we wish to be enabled or disabled on
guest entry/exit and thus defer from starting or stopping :G events
as per the events exclude_host attribute.
With both VHE and non-VHE we switch the counters between host/guest
at EL2. We are able to eliminate counters counting host events on
the boundaries of guest entry/exit when using :G by filtering out
EL2 for exclude_host. However when using :H unless exclude_hv is set
on non-VHE then there is a small blackout window at the guest
entry/exit where host events are not captured.
Signed-off-by: Andrew Murray <andrew.mur...@arm.com>
---
arch/arm64/kernel/perf_event.c | 51 ++++++++++++++++++++++++++++++++++++------
1 file changed, 44 insertions(+), 7 deletions(-)
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index de564ae..4a3c73d 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -26,6 +26,7 @@
#include <linux/acpi.h>
#include <linux/clocksource.h>
+#include <linux/kvm_host.h>
#include <linux/of.h>
#include <linux/perf/arm_pmu.h>
#include <linux/platform_device.h>
@@ -647,11 +648,26 @@ static inline int armv8pmu_enable_counter(int idx)
static inline void armv8pmu_enable_event_counter(struct perf_event *event)
{
+ struct perf_event_attr *attr = &event->attr;
int idx = event->hw.idx;
+ int flags = 0;
+ u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
- armv8pmu_enable_counter(idx);
if (armv8pmu_event_is_chained(event))
- armv8pmu_enable_counter(idx - 1);
+ counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+
+ if (!attr->exclude_host)
+ flags |= KVM_PMU_EVENTS_HOST;
+ if (!attr->exclude_guest)
+ flags |= KVM_PMU_EVENTS_GUEST;
+
+ kvm_set_pmu_events(counter_bits, flags);
+
+ if (!attr->exclude_host) {
+ armv8pmu_enable_counter(idx);
+ if (armv8pmu_event_is_chained(event))
+ armv8pmu_enable_counter(idx - 1);
+ }
}
static inline int armv8pmu_disable_counter(int idx)
@@ -664,11 +680,20 @@ static inline int armv8pmu_disable_counter(int idx)
static inline void armv8pmu_disable_event_counter(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
+ struct perf_event_attr *attr = &event->attr;
int idx = hwc->idx;
+ u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
if (armv8pmu_event_is_chained(event))
- armv8pmu_disable_counter(idx - 1);
- armv8pmu_disable_counter(idx);
+ counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+
+ kvm_clr_pmu_events(counter_bits);
+
+ if (!attr->exclude_host) {
+ if (armv8pmu_event_is_chained(event))
+ armv8pmu_disable_counter(idx - 1);
+ armv8pmu_disable_counter(idx);
+ }
}
static inline int armv8pmu_enable_intens(int idx)
@@ -943,16 +968,25 @@ static int armv8pmu_set_event_filter(struct hw_perf_event
*event,
* Therefore we ignore exclude_hv in this configuration, since
* there's no hypervisor to sample anyway. This is consistent
* with other architectures (x86 and Power).
+ *
+ * To eliminate counting host events on the boundaries of
+ * guest entry/exit we ensure EL2 is not included in hyp mode
+ * with !exclude_host.
*/
if (is_kernel_in_hyp_mode()) {
- if (!attr->exclude_kernel)
+ if (!attr->exclude_kernel && !attr->exclude_host)
config_base |= ARMV8_PMU_INCLUDE_EL2;
} else {
- if (attr->exclude_kernel)
- config_base |= ARMV8_PMU_EXCLUDE_EL1;
if (!attr->exclude_hv)
config_base |= ARMV8_PMU_INCLUDE_EL2;
}
+
+ /*
+ * Filter out !VHE kernels and guest kernels
+ */
+ if (attr->exclude_kernel)
+ config_base |= ARMV8_PMU_EXCLUDE_EL1;
+
if (attr->exclude_user)
config_base |= ARMV8_PMU_EXCLUDE_EL0;
@@ -976,6 +1010,9 @@ static void armv8pmu_reset(void *info)
armv8pmu_disable_intens(idx);
}
+ /* Clear the counters we flip at guest entry/exit */
+ kvm_clr_pmu_events(U32_MAX);
+
/*
* Initialize & Reset PMNC. Request overflow interrupt for
* 64 bit cycle counter but cheat in armv8pmu_write_counter().
--
2.7.4
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
