Save and restore newly untrapped registers that can be directly
accessed by the guest when the PMU is partitioned.

* PMEVCNTRn_EL0
* PMCCNTR_EL0
* PMSELR_EL0
* PMCR_EL0
* PMCNTEN_EL0
* PMINTEN_EL1

If we know we are not partitioned (that is, using the emulated vPMU),
then return immediately. A later patch will make this lazy so the
context swaps don't happen unless the guest has accessed the PMU.

PMEVTYPER is handled in a following patch since we must apply the KVM
event filter before writing values to hardware.

PMOVS guest counters are cleared to avoid the possibility of
generating spurious interrupts when PMINTEN is written. This is fine
because the virtual register for PMOVS is always the canonical value.

Signed-off-by: Colton Lewis <coltonlewis@google.com>
---
 arch/arm64/kvm/arm.c        |   2 +
 arch/arm64/kvm/pmu-direct.c | 123 ++++++++++++++++++++++++++++++++++++
 include/kvm/arm_pmu.h       |   4 ++
 3 files changed, 129 insertions(+)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 620a465248d1b..adbe79264c032 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -635,6 +635,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		kvm_vcpu_load_vhe(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
 	kvm_vcpu_pmu_restore_guest(vcpu);
+	kvm_pmu_load(vcpu);
 	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
 		kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);
 
@@ -676,6 +677,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
+	kvm_pmu_put(vcpu);
 	if (vcpu_has_nv(vcpu))
 		kvm_vcpu_put_hw_mmu(vcpu);
 	kvm_arm_vmid_clear_active();
diff --git a/arch/arm64/kvm/pmu-direct.c b/arch/arm64/kvm/pmu-direct.c
index f2e6b1eea8bd6..b07b521543478 100644
--- a/arch/arm64/kvm/pmu-direct.c
+++ b/arch/arm64/kvm/pmu-direct.c
@@ -9,6 +9,7 @@
 #include <linux/perf/arm_pmuv3.h>
 
 #include <asm/arm_pmuv3.h>
+#include <asm/kvm_emulate.h>
 
 /**
  * has_host_pmu_partition_support() - Determine if partitioning is possible
@@ -163,3 +164,125 @@ u8 kvm_pmu_hpmn(struct kvm_vcpu *vcpu)
 
 	return *host_data_ptr(nr_event_counters);
 }
+
+/**
+ * kvm_pmu_load() - Load untrapped PMU registers
+ * @vcpu: Pointer to struct kvm_vcpu
+ *
+ * Load all untrapped PMU registers from the VCPU into the PCPU. Mask
+ * to only bits belonging to guest-reserved counters and leave
+ * host-reserved counters alone in bitmask registers.
+ */
+void kvm_pmu_load(struct kvm_vcpu *vcpu)
+{
+	struct arm_pmu *pmu;
+	unsigned long guest_counters;
+	u64 mask;
+	u8 i;
+	u64 val;
+
+	/*
+	 * If we aren't guest-owned then we know the guest isn't using
+	 * the PMU anyway, so no need to bother with the swap.
+	 */
+	if (!kvm_vcpu_pmu_is_partitioned(vcpu))
+		return;
+
+	preempt_disable();
+
+	pmu = vcpu->kvm->arch.arm_pmu;
+	guest_counters = kvm_pmu_guest_counter_mask(pmu);
+
+	for_each_set_bit(i, &guest_counters, ARMPMU_MAX_HWEVENTS) {
+		val = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i);
+
+		write_sysreg(i, pmselr_el0);
+		write_sysreg(val, pmxevcntr_el0);
+	}
+
+	val = __vcpu_sys_reg(vcpu, PMSELR_EL0);
+	write_sysreg(val, pmselr_el0);
+
+	/* Save only the stateful writable bits. */
+	val = __vcpu_sys_reg(vcpu, PMCR_EL0);
+	mask = ARMV8_PMU_PMCR_MASK &
+		~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
+	write_sysreg(val & mask, pmcr_el0);
+
+	/*
+	 * When handling these:
+	 * 1. Apply only the bits for guest counters (indicated by mask)
+	 * 2. Use the different registers for set and clear
+	 */
+	mask = kvm_pmu_guest_counter_mask(pmu);
+
+	/* Clear the hardware overflow flags so there is no chance of
+	 * creating spurious interrupts. The hardware here is never
+	 * the canonical version anyway.
+	 */
+	write_sysreg(mask, pmovsclr_el0);
+
+	val = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+	write_sysreg(val & mask, pmcntenset_el0);
+	write_sysreg(~val & mask, pmcntenclr_el0);
+
+	val = __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
+	write_sysreg(val & mask, pmintenset_el1);
+	write_sysreg(~val & mask, pmintenclr_el1);
+
+	preempt_enable();
+}
+
+/**
+ * kvm_pmu_put() - Put untrapped PMU registers
+ * @vcpu: Pointer to struct kvm_vcpu
+ *
+ * Put all untrapped PMU registers from the VCPU into the PCPU. Mask
+ * to only bits belonging to guest-reserved counters and leave
+ * host-reserved counters alone in bitmask registers.
+ */
+void kvm_pmu_put(struct kvm_vcpu *vcpu)
+{
+	struct arm_pmu *pmu;
+	unsigned long guest_counters;
+	u64 mask;
+	u8 i;
+	u64 val;
+
+	/*
+	 * If we aren't guest-owned then we know the guest is not
+	 * accessing the PMU anyway, so no need to bother with the
+	 * swap.
+	 */
+	if (!kvm_vcpu_pmu_is_partitioned(vcpu))
+		return;
+
+	preempt_disable();
+
+	pmu = vcpu->kvm->arch.arm_pmu;
+	guest_counters = kvm_pmu_guest_counter_mask(pmu);
+
+	for_each_set_bit(i, &guest_counters, ARMPMU_MAX_HWEVENTS) {
+		write_sysreg(i, pmselr_el0);
+		val = read_sysreg(pmxevcntr_el0);
+
+		__vcpu_assign_sys_reg(vcpu, PMEVCNTR0_EL0 + i, val);
+	}
+
+	val = read_sysreg(pmselr_el0);
+	__vcpu_assign_sys_reg(vcpu, PMSELR_EL0, val);
+
+	val = read_sysreg(pmcr_el0);
+	__vcpu_assign_sys_reg(vcpu, PMCR_EL0, val);
+
+	/* Mask these to only save the guest relevant bits. */
+	mask = kvm_pmu_guest_counter_mask(pmu);
+
+	val = read_sysreg(pmcntenset_el0);
+	__vcpu_assign_sys_reg(vcpu, PMCNTENSET_EL0, val & mask);
+
+	val = read_sysreg(pmintenset_el1);
+	__vcpu_assign_sys_reg(vcpu, PMINTENSET_EL1, val & mask);
+
+	preempt_enable();
+}
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 8fab533fa3ebc..93ccda941aa46 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -100,6 +100,8 @@ void kvm_pmu_host_counters_disable(void);
 
 u8 kvm_pmu_guest_num_counters(struct kvm_vcpu *vcpu);
 u8 kvm_pmu_hpmn(struct kvm_vcpu *vcpu);
+void kvm_pmu_load(struct kvm_vcpu *vcpu);
+void kvm_pmu_put(struct kvm_vcpu *vcpu);
 
 #if !defined(__KVM_NVHE_HYPERVISOR__)
 bool kvm_vcpu_pmu_is_partitioned(struct kvm_vcpu *vcpu);
@@ -173,6 +175,8 @@ static inline u8 kvm_pmu_hpmn(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }
+static inline void kvm_pmu_load(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_put(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu,
 					     u64 select_idx, u64 val) {}
 static inline void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu,
-- 
2.53.0.rc2.204.g2597b5adb4-goog