Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more kvm updates from Paolo Bonzini:

 - ARM fixes

 - RISC-V Svade and Svadu (accessed and dirty bit) extension support for
   host and guest

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: riscv: selftests: Add Svade and Svadu Extension to get-reg-list test
  RISC-V: KVM: Add Svade and Svadu Extensions Support for Guest/VM
  dt-bindings: riscv: Add Svade and Svadu Entries
  RISC-V: Add Svade and Svadu Extensions Support
  KVM: arm64: Use MDCR_EL2.HPME to evaluate overflow of hyp counters
  KVM: arm64: Ignore PMCNTENSET_EL0 while checking for overflow status
  KVM: arm64: Mark set_sysreg_masks() as inline to avoid build failure
  KVM: arm64: vgic-its: Add stronger type-checking to the ITS entry sizes
  KVM: arm64: vgic: Kill VGIC_MAX_PRIVATE definition
  KVM: arm64: vgic: Make vgic_get_irq() more robust
  KVM: arm64: vgic-v3: Sanitise guest writes to GICR_INVLPIR

Author: torvalds

Documentation/devicetree/bindings/riscv/extensions.yaml

@@ -171,6 +171,34 @@ properties:
             ratified at commit 3f9ed34 ("Add ability to manually trigger
             workflow. (#2)") of riscv-time-compare.
 
+        - const: svade
+          description: |
+            The standard Svade supervisor-level extension for SW-managed PTE A/D
+            bit updates as ratified in the 20240213 version of the privileged
+            ISA specification.
+
+            Both Svade and Svadu extensions control the hardware behavior when
+            the PTE A/D bits need to be set. The default behavior for the four
+            possible combinations of these extensions in the device tree are:
+            1) Neither Svade nor Svadu present in DT => It is technically
+               unknown whether the platform uses Svade or Svadu. Supervisor
+               software should be prepared to handle either hardware updating
+               of the PTE A/D bits or page faults when they need updated.
+            2) Only Svade present in DT => Supervisor must assume Svade to be
+               always enabled.
+            3) Only Svadu present in DT => Supervisor must assume Svadu to be
+               always enabled.
+            4) Both Svade and Svadu present in DT => Supervisor must assume
+               Svadu turned-off at boot time. To use Svadu, supervisor must
+               explicitly enable it using the SBI FWFT extension.
+
+        - const: svadu
+          description: |
+            The standard Svadu supervisor-level extension for hardware updating
+            of PTE A/D bits as ratified in the 20240528 version of the
+            privileged ISA specification. Please refer to Svade dt-binding
+            description for more details.
+
         - const: svinval
           description:
             The standard Svinval supervisor-level extension for fine-grained

arch/arm64/kvm/nested.c

@@ -951,7 +951,7 @@ u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu,
 	return v;
 }
 
-static void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1)
+static __always_inline void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1)
 {
 	int i = sr - __SANITISED_REG_START__;
 

arch/arm64/kvm/pmu-emul.c

@@ -274,12 +274,23 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 	irq_work_sync(&vcpu->arch.pmu.overflow_work);
 }
 
-bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx)
+static u64 kvm_pmu_hyp_counter_mask(struct kvm_vcpu *vcpu)
 {
-	unsigned int hpmn;
+	unsigned int hpmn, n;
 
-	if (!vcpu_has_nv(vcpu) || idx == ARMV8_PMU_CYCLE_IDX)
-		return false;
+	if (!vcpu_has_nv(vcpu))
+		return 0;
+
+	hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
+	n = vcpu->kvm->arch.pmcr_n;
+
+	/*
+	 * Programming HPMN to a value greater than PMCR_EL0.N is
+	 * CONSTRAINED UNPREDICTABLE. Make the implementation choice that an
+	 * UNKNOWN number of counters (in our case, zero) are reserved for EL2.
+	 */
+	if (hpmn >= n)
+		return 0;
 
 	/*
 	 * Programming HPMN=0 is CONSTRAINED UNPREDICTABLE if FEAT_HPMN0 isn't
@@ -288,20 +299,22 @@ bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx)
 	 * implementation choice that all counters are included in the second
 	 * range reserved for EL2/EL3.
 	 */
-	hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
-	return idx >= hpmn;
+	return GENMASK(n - 1, hpmn);
+}
+
+bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx)
+{
+	return kvm_pmu_hyp_counter_mask(vcpu) & BIT(idx);
 }
 
 u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu)
 {
 	u64 mask = kvm_pmu_implemented_counter_mask(vcpu);
-	u64 hpmn;
 
 	if (!vcpu_has_nv(vcpu) || vcpu_is_el2(vcpu))
 		return mask;
 
-	hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
-	return mask & ~GENMASK(vcpu->kvm->arch.pmcr_n - 1, hpmn);
+	return mask & ~kvm_pmu_hyp_counter_mask(vcpu);
 }
 
 u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu)
@@ -375,15 +388,30 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 	}
 }
 
-static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
+/*
+ * Returns the PMU overflow state, which is true if there exists an event
+ * counter where the values of the global enable control, PMOVSSET_EL0[n], and
+ * PMINTENSET_EL1[n] are all 1.
+ */
+static bool kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
 {
-	u64 reg = 0;
+	u64 reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
 
-	if ((kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) {
-		reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
-		reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
-		reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
-	}
+	reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
+
+	/*
+	 * PMCR_EL0.E is the global enable control for event counters available
+	 * to EL0 and EL1.
+	 */
+	if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E))
+		reg &= kvm_pmu_hyp_counter_mask(vcpu);
+
+	/*
+	 * Otherwise, MDCR_EL2.HPME is the global enable control for event
+	 * counters reserved for EL2.
+	 */
+	if (!(vcpu_read_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HPME))
+		reg &= ~kvm_pmu_hyp_counter_mask(vcpu);
 
 	return reg;
 }
@@ -396,7 +424,7 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return;
 
-	overflow = !!kvm_pmu_overflow_status(vcpu);
+	overflow = kvm_pmu_overflow_status(vcpu);
 	if (pmu->irq_level == overflow)
 		return;
 

arch/arm64/kvm/vgic/vgic-debug.c

@@ -287,7 +287,10 @@ static int vgic_debug_show(struct seq_file *s, void *v)
 	 * Expect this to succeed, as iter_mark_lpis() takes a reference on
 	 * every LPI to be visited.
 	 */
-	irq = vgic_get_irq(kvm, vcpu, iter->intid);
+	if (iter->intid < VGIC_NR_PRIVATE_IRQS)
+		irq = vgic_get_vcpu_irq(vcpu, iter->intid);
+	else
+		irq = vgic_get_irq(kvm, iter->intid);
 	if (WARN_ON_ONCE(!irq))
 		return -EINVAL;
 

arch/arm64/kvm/vgic/vgic-init.c

@@ -322,7 +322,7 @@ int vgic_init(struct kvm *kvm)
 			goto out;
 
 		for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
-			struct vgic_irq *irq = vgic_get_irq(kvm, vcpu, i);
+			struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i);
 
 			switch (dist->vgic_model) {
 			case KVM_DEV_TYPE_ARM_VGIC_V3: