[PATCH v7 16/19] KVM: ARM64: Add PMU overflow interrupt routing

[Shannon Zhao]

From: Shannon Zhao <shannon.zhao at linaro.org>

When calling perf_event_create_kernel_counter to create perf_event,
assign a overflow handler. Then when the perf event overflows, set the
corresponding bit of guest PMOVSSET register. If this counter is enabled
and its interrupt is enabled as well, kick the vcpu to sync the
interrupt.

On VM entry, if there is counter overflowed, inject the interrupt with
the level set to 1. Otherwise, inject the interrupt with the level set
to 0.

Signed-off-by: Shannon Zhao <shannon.zhao at linaro.org>
---
 arch/arm/kvm/arm.c    |  2 ++
 include/kvm/arm_pmu.h |  2 ++
 virt/kvm/arm/pmu.c    | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 57 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index e06fd29..cd696ef 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/kvm.h>
 #include <trace/events/kvm.h>
+#include <kvm/arm_pmu.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -569,6 +570,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+		kvm_pmu_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 25b5f98..732ccaf 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -35,6 +35,7 @@ struct kvm_pmu {
 	struct kvm_pmc pmc[ARMV8_MAX_COUNTERS];
 };
 
+void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
 void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
@@ -47,6 +48,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
 struct kvm_pmu {
 };
 
+void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 {
 	return 0;
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index e664721..eff5b19 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -21,6 +21,7 @@
 #include <linux/perf_event.h>
 #include <asm/kvm_emulate.h>
 #include <kvm/arm_pmu.h>
+#include <kvm/arm_vgic.h>
 
 /**
  * kvm_pmu_get_counter_value - get PMU counter value
@@ -75,6 +76,56 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 }
 
 /**
+ * kvm_pmu_flush_hwstate - flush pmu state to cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Inject virtual PMU IRQ if IRQ is pending for this cpu.
+ */
+void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	u64 overflow;
+
+	if (pmu->irq_num == -1)
+		return;
+
+	if (!(vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMCR_E))
+		return;
+
+	overflow = vcpu_sys_reg(vcpu, PMCNTENSET_EL0)
+		   & vcpu_sys_reg(vcpu, PMINTENSET_EL1)
+		   & vcpu_sys_reg(vcpu, PMOVSSET_EL0);
+
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, pmu->irq_num,
+			    overflow ? 1 : 0);
+}
+
+static inline struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu;
+	struct kvm_vcpu_arch *vcpu_arch;
+
+	pmc -= pmc->idx;
+	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
+	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
+	return container_of(vcpu_arch, struct kvm_vcpu, arch);
+}
+
+/**
+ * When perf event overflows, call kvm_pmu_overflow_set to set overflow status.
+ */
+static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
+				  struct perf_sample_data *data,
+				  struct pt_regs *regs)
+{
+	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	int idx = pmc->idx;
+
+	kvm_pmu_overflow_set(vcpu, BIT(idx));
+}
+
+/**
  * kvm_pmu_enable_counter - enable selected PMU counter
  * @vcpu: The vcpu pointer
  * @val: the value guest writes to PMCNTENSET register
@@ -258,7 +309,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	/* The initial sample period (overflow count) of an event. */
 	attr.sample_period = (-counter) & pmc->bitmask;
 
-	event = perf_event_create_kernel_counter(&attr, -1, current, NULL, pmc);
+	event = perf_event_create_kernel_counter(&attr, -1, current,
+						 kvm_pmu_perf_overflow, pmc);
 	if (IS_ERR(event)) {
 		printk_once("kvm: pmu event creation failed %ld\n",
 			    PTR_ERR(event));
-- 
2.0.4