1 files changed, 75 insertions, 58 deletions

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 68fec8c95fee..888f7c7abf54 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -368,6 +368,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_EL1_32BIT:
 		r = cpus_have_final_cap(ARM64_HAS_32BIT_EL1);
 		break;
+	case KVM_CAP_ARM_EL2:
+		r = cpus_have_final_cap(ARM64_HAS_NESTED_VIRT);
+		break;
+	case KVM_CAP_ARM_EL2_E2H0:
+		r = cpus_have_final_cap(ARM64_HAS_HCR_NV1);
+		break;
 	case KVM_CAP_GUEST_DEBUG_HW_BPS:
 		r = get_num_brps();
 		break;
@@ -402,6 +408,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES:
 		r = BIT(0);
 		break;
+	case KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED:
+		if (!kvm)
+			r = -EINVAL;
+		else
+			r = kvm_supports_cacheable_pfnmap();
+		break;
+
 	default:
 		r = 0;
 	}
@@ -515,7 +528,7 @@ static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu)
 		 * Either we're running an L2 guest, and the API/APK bits come
 		 * from L1's HCR_EL2, or API/APK are both set.
 		 */
-		if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) {
+		if (unlikely(is_nested_ctxt(vcpu))) {
 			u64 val;
 
 			val = __vcpu_sys_reg(vcpu, HCR_EL2);
@@ -734,7 +747,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
  */
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF);
+	bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF | HCR_VSE);
+
 	return ((irq_lines || kvm_vgic_vcpu_pending_irq(v))
 		&& !kvm_arm_vcpu_stopped(v) && !v->arch.pause);
 }
@@ -819,10 +833,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (!kvm_arm_vcpu_is_finalized(vcpu))
 		return -EPERM;
 
-	ret = kvm_arch_vcpu_run_map_fp(vcpu);
-	if (ret)
-		return ret;
-
 	if (likely(vcpu_has_run_once(vcpu)))
 		return 0;
 
@@ -843,6 +853,10 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 		return ret;
 
 	if (vcpu_has_nv(vcpu)) {
+		ret = kvm_vcpu_allocate_vncr_tlb(vcpu);
+		if (ret)
+			return ret;
+
 		ret = kvm_vgic_vcpu_nv_init(vcpu);
 		if (ret)
 			return ret;
@@ -1177,6 +1191,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
+		kvm_nested_flush_hwstate(vcpu);
+
 		if (kvm_vcpu_has_pmu(vcpu))
 			kvm_pmu_flush_hwstate(vcpu);
 
@@ -1276,6 +1292,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		/* Exit types that need handling before we can be preempted */
 		handle_exit_early(vcpu, ret);
 
+		kvm_nested_sync_hwstate(vcpu);
+
 		preempt_enable();
 
 		/*
@@ -1914,49 +1932,6 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	}
 }
 
-/* unlocks vcpus from @vcpu_lock_idx and smaller */
-static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
-{
-	struct kvm_vcpu *tmp_vcpu;
-
-	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
-		tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
-		mutex_unlock(&tmp_vcpu->mutex);
-	}
-}
-
-void unlock_all_vcpus(struct kvm *kvm)
-{
-	lockdep_assert_held(&kvm->lock);
-
-	unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
-}
-
-/* Returns true if all vcpus were locked, false otherwise */
-bool lock_all_vcpus(struct kvm *kvm)
-{
-	struct kvm_vcpu *tmp_vcpu;
-	unsigned long c;
-
-	lockdep_assert_held(&kvm->lock);
-
-	/*
-	 * Any time a vcpu is in an ioctl (including running), the
-	 * core KVM code tries to grab the vcpu->mutex.
-	 *
-	 * By grabbing the vcpu->mutex of all VCPUs we ensure that no
-	 * other VCPUs can fiddle with the state while we access it.
-	 */
-	kvm_for_each_vcpu(c, tmp_vcpu, kvm) {
-		if (!mutex_trylock(&tmp_vcpu->mutex)) {
-			unlock_vcpus(kvm, c - 1);
-			return false;
-		}
-	}
-
-	return true;
-}
-
 static unsigned long nvhe_percpu_size(void)
 {
 	return (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_end) -
@@ -2162,7 +2137,7 @@ static void cpu_hyp_init(void *discard)
 
 static void cpu_hyp_uninit(void *discard)
 {
-	if (__this_cpu_read(kvm_hyp_initialized)) {
+	if (!is_protected_kvm_enabled() && __this_cpu_read(kvm_hyp_initialized)) {
 		cpu_hyp_reset();
 		__this_cpu_write(kvm_hyp_initialized, 0);
 	}
@@ -2378,8 +2353,13 @@ static void __init teardown_hyp_mode(void)
 
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
+		if (per_cpu(kvm_hyp_initialized, cpu))
+			continue;
+
 		free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT);
-		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
+		if (!kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu])
+			continue;
 
 		if (free_sve) {
 			struct cpu_sve_state *sve_state;
@@ -2387,6 +2367,9 @@ static void __init teardown_hyp_mode(void)
 			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
 			free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
 		}
+
+		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
 	}
 }
 
@@ -2450,6 +2433,19 @@ static void kvm_hyp_init_symbols(void)
 	kvm_nvhe_sym(__icache_flags) = __icache_flags;
 	kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
 
+	/* Propagate the FGT state to the the nVHE side */
+	kvm_nvhe_sym(hfgrtr_masks)  = hfgrtr_masks;
+	kvm_nvhe_sym(hfgwtr_masks)  = hfgwtr_masks;
+	kvm_nvhe_sym(hfgitr_masks)  = hfgitr_masks;
+	kvm_nvhe_sym(hdfgrtr_masks) = hdfgrtr_masks;
+	kvm_nvhe_sym(hdfgwtr_masks) = hdfgwtr_masks;
+	kvm_nvhe_sym(hafgrtr_masks) = hafgrtr_masks;
+	kvm_nvhe_sym(hfgrtr2_masks) = hfgrtr2_masks;
+	kvm_nvhe_sym(hfgwtr2_masks) = hfgwtr2_masks;
+	kvm_nvhe_sym(hfgitr2_masks) = hfgitr2_masks;
+	kvm_nvhe_sym(hdfgrtr2_masks)= hdfgrtr2_masks;
+	kvm_nvhe_sym(hdfgwtr2_masks)= hdfgwtr2_masks;
+
 	/*
 	 * Flush entire BSS since part of its data containing init symbols is read
 	 * while the MMU is off.
@@ -2604,6 +2600,13 @@ static int __init init_hyp_mode(void)
 		goto out_err;
 	}
 
+	err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_start),
+				  kvm_ksym_ref(__hyp_data_end), PAGE_HYP);
+	if (err) {
+		kvm_err("Cannot map .hyp.data section\n");
+		goto out_err;
+	}
+
 	err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start),
 				  kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO);
 	if (err) {
@@ -2743,11 +2746,6 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
 	return irqchip_in_kernel(kvm);
 }
 
-bool kvm_arch_has_irq_bypass(void)
-{
-	return true;
-}
-
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
@@ -2765,6 +2763,7 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 	return kvm_vgic_v4_set_forwarding(irqfd->kvm, prod->irq,
 					  &irqfd->irq_entry);
 }
+
 void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
@@ -2775,8 +2774,26 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	if (irq_entry->type != KVM_IRQ_ROUTING_MSI)
 		return;
 
-	kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq,
-				     &irqfd->irq_entry);
+	kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq);
+}
+
+void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+				   struct kvm_kernel_irq_routing_entry *old,
+				   struct kvm_kernel_irq_routing_entry *new)
+{
+	if (old->type == KVM_IRQ_ROUTING_MSI &&
+	    new->type == KVM_IRQ_ROUTING_MSI &&
+	    !memcmp(&old->msi, &new->msi, sizeof(new->msi)))
+		return;
+
+	/*
+	 * Remapping the vLPI requires taking the its_lock mutex to resolve
+	 * the new translation. We're in spinlock land at this point, so no
+	 * chance of resolving the translation.
+	 *
+	 * Unmap the vLPI and fall back to software LPI injection.
+	 */
+	return kvm_vgic_v4_unset_forwarding(irqfd->kvm, irqfd->producer->irq);
 }
 
 void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons)