arm64: arm_pmu: Add !VHE support for exclude_host/exclude_guest attributes

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 events based
on their event attributes.

With !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. When
using !exclude_hv there is a small blackout window at the guest
entry/exit where host events are not captured.
Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

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>
@@ -528,11 +529,21 @@ 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;
+	u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
 
+	if (armv8pmu_event_is_chained(event))
+		counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+
+	kvm_set_pmu_events(counter_bits, attr);
+
+	/* We rely on the hypervisor switch code to enable guest counters */
+	if (!kvm_pmu_counter_deferred(attr)) {
 		armv8pmu_enable_counter(idx);
 		if (armv8pmu_event_is_chained(event))
 			armv8pmu_enable_counter(idx - 1);
+	}
 }
 
 static inline int armv8pmu_disable_counter(int idx)
@@ -545,11 +556,21 @@ 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))
+		counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+
+	kvm_clr_pmu_events(counter_bits);
+
+	/* We rely on the hypervisor switch code to disable guest counters */
+	if (!kvm_pmu_counter_deferred(attr)) {
 		if (armv8pmu_event_is_chained(event))
 			armv8pmu_disable_counter(idx - 1);
 		armv8pmu_disable_counter(idx);
+	}
 }
 
 static inline int armv8pmu_enable_intens(int idx)
@@ -829,11 +850,16 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 		if (!attr->exclude_kernel)
 			config_base |= ARMV8_PMU_INCLUDE_EL2;
 	} else {
-		if (attr->exclude_kernel)
-			config_base |= ARMV8_PMU_EXCLUDE_EL1;
-		if (!attr->exclude_hv)
+		if (!attr->exclude_hv && !attr->exclude_host)
 			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;
 
@@ -863,6 +889,9 @@ 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().