[PATCH v2 11/23] KVM: arm64: Set up FGT for Partitioned PMU

[Colton Lewis]

In order to gain the best performance benefit from partitioning the
PMU, utilize fine grain traps (FEAT_FGT and FEAT_FGT2) to avoid
trapping common PMU register accesses by the guest to remove that
overhead.

There should be no information leaks between guests as all these
registers are context swapped by a later patch in this series.

Untrapped:
* PMCR_EL0
* PMUSERENR_EL0
* PMSELR_EL0
* PMCCNTR_EL0
* PMINTEN_EL0
* PMEVCNTRn_EL0

Trapped:
* PMOVS_EL0
* PMEVTYPERn_EL0
* PMCCFILTR_EL0
* PMICNTR_EL0
* PMICFILTR_EL0

PMOVS remains trapped so KVM can track overflow IRQs that will need to
be injected into the guest.

PMICNTR remains trapped because KVM is not handling that yet.

PMEVTYPERn remains trapped so KVM can limit which events guests can
count, such as disallowing counting at EL2. PMCCFILTR and PMCIFILTR
are the same.

Signed-off-by: Colton Lewis <coltonlewis at google.com>
---
 arch/arm64/include/asm/kvm_pmu.h        | 13 ++++++
 arch/arm64/kvm/hyp/include/hyp/switch.h | 58 +++++++++++++++++++++++++
 arch/arm64/kvm/pmu-part.c               | 32 ++++++++++++++
 3 files changed, 103 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_pmu.h b/arch/arm64/include/asm/kvm_pmu.h
index 151e5b6793f2..02984cfeb446 100644
--- a/arch/arm64/include/asm/kvm_pmu.h
+++ b/arch/arm64/include/asm/kvm_pmu.h
@@ -93,7 +93,20 @@ u64 kvm_pmu_guest_counter_mask(struct arm_pmu *pmu);
 void kvm_pmu_host_counters_enable(void);
 void kvm_pmu_host_counters_disable(void);
 
+#if !defined(__KVM_NVHE_HYPERVISOR__)
+bool kvm_vcpu_pmu_is_partitioned(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_pmu_use_fgt(struct kvm_vcpu *vcpu);
 #else
+static inline bool kvm_vcpu_pmu_is_partitioned(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
+static inline bool kvm_vcpu_pmu_use_fgt(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+#endif
 
 /*
  * Updates the vcpu's view of the pmu events for this cpu.
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 825b81749972..47d2db8446df 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -191,6 +191,61 @@ static inline bool cpu_has_amu(void)
                ID_AA64PFR0_EL1_AMU_SHIFT);
 }
 
+/**
+ * __activate_pmu_fgt() - Activate fine grain traps for partitioned PMU
+ * @vcpu: Pointer to struct kvm_vcpu
+ *
+ * Clear the most commonly accessed registers for a partitioned
+ * PMU. Trap the rest.
+ */
+static inline void __activate_pmu_fgt(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	u64 set;
+	u64 clr;
+
+	set = HDFGRTR_EL2_PMOVS
+		| HDFGRTR_EL2_PMCCFILTR_EL0
+		| HDFGRTR_EL2_PMEVTYPERn_EL0;
+	clr = HDFGRTR_EL2_PMUSERENR_EL0
+		| HDFGRTR_EL2_PMSELR_EL0
+		| HDFGRTR_EL2_PMINTEN
+		| HDFGRTR_EL2_PMCNTEN
+		| HDFGRTR_EL2_PMCCNTR_EL0
+		| HDFGRTR_EL2_PMEVCNTRn_EL0;
+
+	update_fgt_traps_cs(hctxt, vcpu, kvm, HDFGRTR_EL2, clr, set);
+
+	set = HDFGWTR_EL2_PMOVS
+		| HDFGWTR_EL2_PMCCFILTR_EL0
+		| HDFGWTR_EL2_PMEVTYPERn_EL0;
+	clr = HDFGWTR_EL2_PMUSERENR_EL0
+		| HDFGWTR_EL2_PMCR_EL0
+		| HDFGWTR_EL2_PMSELR_EL0
+		| HDFGWTR_EL2_PMINTEN
+		| HDFGWTR_EL2_PMCNTEN
+		| HDFGWTR_EL2_PMCCNTR_EL0
+		| HDFGWTR_EL2_PMEVCNTRn_EL0;
+
+	update_fgt_traps_cs(hctxt, vcpu, kvm, HDFGWTR_EL2, clr, set);
+
+	if (!cpus_have_final_cap(ARM64_HAS_FGT2))
+		return;
+
+	set = HDFGRTR2_EL2_nPMICFILTR_EL0
+		| HDFGRTR2_EL2_nPMICNTR_EL0;
+	clr = 0;
+
+	update_fgt_traps_cs(hctxt, vcpu, kvm, HDFGRTR2_EL2, clr, set);
+
+	set = HDFGWTR2_EL2_nPMICFILTR_EL0
+		| HDFGWTR2_EL2_nPMICNTR_EL0;
+	clr = 0;
+
+	update_fgt_traps_cs(hctxt, vcpu, kvm, HDFGWTR2_EL2, clr, set);
+}
+
 static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
@@ -210,6 +265,9 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	if (cpu_has_amu())
 		update_fgt_traps(hctxt, vcpu, kvm, HAFGRTR_EL2);
 
+	if (kvm_vcpu_pmu_use_fgt(vcpu))
+		__activate_pmu_fgt(vcpu);
+
 	if (!cpus_have_final_cap(ARM64_HAS_FGT2))
 	    return;
 
diff --git a/arch/arm64/kvm/pmu-part.c b/arch/arm64/kvm/pmu-part.c
index 340f8d334efd..269397a1fcbc 100644
--- a/arch/arm64/kvm/pmu-part.c
+++ b/arch/arm64/kvm/pmu-part.c
@@ -26,6 +26,38 @@ bool kvm_pmu_is_partitioned(struct arm_pmu *pmu)
 	return pmu->hpmn_max <= *host_data_ptr(nr_event_counters);
 }
 
+/**
+ * kvm_vcpu_pmu_is_partitioned() - Determine if given VCPU has a partitioned PMU
+ * @vcpu: Pointer to kvm_vcpu struct
+ *
+ * Determine if given VCPU has a partitioned PMU by extracting that
+ * field and passing it to :c:func:`kvm_pmu_is_partitioned`
+ *
+ * Return: True if the VCPU PMU is partitioned, false otherwise
+ */
+bool kvm_vcpu_pmu_is_partitioned(struct kvm_vcpu *vcpu)
+{
+	return kvm_pmu_is_partitioned(vcpu->kvm->arch.arm_pmu);
+}
+
+/**
+ * kvm_vcpu_pmu_use_fgt() - Determine if we can use FGT
+ * @vcpu: Pointer to struct kvm_vcpu
+ *
+ * Determine if we can use FGT for direct access to registers. We can
+ * if capabilities permit the number of guest counters requested.
+ *
+ * Return: True if we can use FGT, false otherwise
+ */
+bool kvm_vcpu_pmu_use_fgt(struct kvm_vcpu *vcpu)
+{
+	u8 hpmn = vcpu->kvm->arch.nr_pmu_counters;
+
+	return kvm_vcpu_pmu_is_partitioned(vcpu) &&
+		cpus_have_final_cap(ARM64_HAS_FGT) &&
+		(hpmn != 0 || cpus_have_final_cap(ARM64_HAS_HPMN0));
+}
+
 /**
  * kvm_pmu_host_counter_mask() - Compute bitmask of host-reserved counters
  * @pmu: Pointer to arm_pmu struct
-- 
2.50.0.714.g196bf9f422-goog