Merge branch kvm-arm64/misc into kvmarm/next

* kvm-arm64/misc:
  : Miscellaneous updates
  :
  :  - Drop useless check against vgic state in ICC_CLTR_EL1.SEIS read
  :    emulation
  :
  :  - Fix trap configuration for pKVM
  :
  :  - Close the door on initialization bugs surrounding userspace irqchip
  :    static key by removing it.
  KVM: selftests: Don't bother deleting memslots in KVM when freeing VMs
  KVM: arm64: Get rid of userspace_irqchip_in_use
  KVM: arm64: Initialize trap register values in hyp in pKVM
  KVM: arm64: Initialize the hypervisor's VM state at EL2
  KVM: arm64: Refactor kvm_vcpu_enable_ptrauth() for hyp use
  KVM: arm64: Move pkvm_vcpu_init_traps() to init_pkvm_hyp_vcpu()
  KVM: arm64: Don't map 'kvm_vgic_global_state' at EL2 with pKVM
  KVM: arm64: Just advertise SEIS as 0 when emulating ICC_CTLR_EL1

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

arch/arm64/include/asm/kvm_asm.h

@@ -76,7 +76,6 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_save_vmcr_aprs,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_restore_vmcr_aprs,
-	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
 	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,

arch/arm64/include/asm/kvm_emulate.h

@@ -693,4 +693,8 @@ static inline bool guest_hyp_sve_traps_enabled(const struct kvm_vcpu *vcpu)
 	return __guest_hyp_cptr_xen_trap_enabled(vcpu, ZEN);
 }
 
+static inline void kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
+{
+	vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH);
+}
 #endif /* __ARM64_KVM_EMULATE_H__ */

arch/arm64/include/asm/kvm_host.h

@@ -74,8 +74,6 @@ enum kvm_mode kvm_get_mode(void);
 static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; };
 #endif
 
-DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
-
 extern unsigned int __ro_after_init kvm_sve_max_vl;
 extern unsigned int __ro_after_init kvm_host_sve_max_vl;
 int __init kvm_arm_init_sve(void);

arch/arm64/kvm/arch_timer.c

@@ -206,8 +206,7 @@ void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map)
 
 static inline bool userspace_irqchip(struct kvm *kvm)
 {
-	return static_branch_unlikely(&userspace_irqchip_in_use) &&
-		unlikely(!irqchip_in_kernel(kvm));
+	return unlikely(!irqchip_in_kernel(kvm));
 }
 
 static void soft_timer_start(struct hrtimer *hrt, u64 ns)

arch/arm64/kvm/arm.c

@@ -69,7 +69,6 @@ DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 static bool vgic_present, kvm_arm_initialised;
 
 static DEFINE_PER_CPU(unsigned char, kvm_hyp_initialized);
-DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
 bool is_kvm_arm_initialised(void)
 {
@@ -503,9 +502,6 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	if (vcpu_has_run_once(vcpu) && unlikely(!irqchip_in_kernel(vcpu->kvm)))
-		static_branch_dec(&userspace_irqchip_in_use);
-
 	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
@@ -848,22 +844,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
-	if (!irqchip_in_kernel(kvm)) {
-		/*
-		 * Tell the rest of the code that there are userspace irqchip
-		 * VMs in the wild.
-		 */
-		static_branch_inc(&userspace_irqchip_in_use);
-	}
-
-	/*
-	 * Initialize traps for protected VMs.
-	 * NOTE: Move to run in EL2 directly, rather than via a hypercall, once
-	 * the code is in place for first run initialization at EL2.
-	 */
-	if (kvm_vm_is_protected(kvm))
-		kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu);
-
 	mutex_lock(&kvm->arch.config_lock);
 	set_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags);
 	mutex_unlock(&kvm->arch.config_lock);
@@ -1077,7 +1057,7 @@ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret)
 	 * state gets updated in kvm_timer_update_run and
 	 * kvm_pmu_update_run below).
 	 */
-	if (static_branch_unlikely(&userspace_irqchip_in_use)) {
+	if (unlikely(!irqchip_in_kernel(vcpu->kvm))) {
 		if (kvm_timer_should_notify_user(vcpu) ||
 		    kvm_pmu_should_notify_user(vcpu)) {
 			*ret = -EINTR;
@@ -1199,7 +1179,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			isb(); /* Ensure work in x_flush_hwstate is committed */
 			kvm_pmu_sync_hwstate(vcpu);
-			if (static_branch_unlikely(&userspace_irqchip_in_use))
+			if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
 				kvm_timer_sync_user(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			local_irq_enable();
@@ -1245,7 +1225,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * we don't want vtimer interrupts to race with syncing the
 		 * timer virtual interrupt state.
 		 */
-		if (static_branch_unlikely(&userspace_irqchip_in_use))
+		if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
 			kvm_timer_sync_user(vcpu);
 
 		kvm_arch_vcpu_ctxsync_fp(vcpu);

arch/arm64/kvm/hyp/include/nvhe/trap_handler.h

@@ -15,6 +15,4 @@
 #define DECLARE_REG(type, name, ctxt, reg)	\
 				type name = (type)cpu_reg(ctxt, (reg))
 
-void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu);
-
 #endif /* __ARM64_KVM_NVHE_TRAP_HANDLER_H__ */

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -105,8 +105,10 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;
 
-	hyp_vcpu->vcpu.arch.hcr_el2	= host_vcpu->arch.hcr_el2;
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
+	hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
+	hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &
+						 (HCR_TWI | HCR_TWE);
 
 	hyp_vcpu->vcpu.arch.iflags	= host_vcpu->arch.iflags;
 
@@ -349,13 +351,6 @@ static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize();
 }
 
-static void handle___pkvm_vcpu_init_traps(struct kvm_cpu_context *host_ctxt)
-{
-	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
-
-	__pkvm_vcpu_init_traps(kern_hyp_va(vcpu));
-}
-
 static void handle___pkvm_init_vm(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm *, host_kvm, host_ctxt, 1);
@@ -411,7 +406,6 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__vgic_v3_save_vmcr_aprs),
 	HANDLE_FUNC(__vgic_v3_restore_vmcr_aprs),
-	HANDLE_FUNC(__pkvm_vcpu_init_traps),
 	HANDLE_FUNC(__pkvm_init_vm),
 	HANDLE_FUNC(__pkvm_init_vcpu),
 	HANDLE_FUNC(__pkvm_teardown_vm),

arch/arm64/kvm/hyp/nvhe/pkvm.c

@@ -6,6 +6,9 @@
 
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
+
+#include <asm/kvm_emulate.h>
+
 #include <nvhe/fixed_config.h>
 #include <nvhe/mem_protect.h>
 #include <nvhe/memory.h>
@@ -201,11 +204,46 @@ static void pvm_init_trap_regs(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+
+	if (has_hvhe())
+		vcpu->arch.hcr_el2 |= HCR_E2H;
+
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) {
+		/* route synchronous external abort exceptions to EL2 */
+		vcpu->arch.hcr_el2 |= HCR_TEA;
+		/* trap error record accesses */
+		vcpu->arch.hcr_el2 |= HCR_TERR;
+	}
+
+	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
+		vcpu->arch.hcr_el2 |= HCR_FWB;
+
+	if (cpus_have_final_cap(ARM64_HAS_EVT) &&
+	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE))
+		vcpu->arch.hcr_el2 |= HCR_TID4;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TID2;
+
+	if (vcpu_has_ptrauth(vcpu))
+		vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK);
+}
+
 /*
  * Initialize trap register values in protected mode.
  */
-void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu)
+static void pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.cptr_el2 = kvm_get_reset_cptr_el2(vcpu);
+	vcpu->arch.mdcr_el2 = 0;
+
+	pkvm_vcpu_reset_hcr(vcpu);
+
+	if ((!vcpu_is_protected(vcpu)))
+		return;
+
 	pvm_init_trap_regs(vcpu);
 	pvm_init_traps_aa64pfr0(vcpu);
 	pvm_init_traps_aa64pfr1(vcpu);
@@ -289,6 +327,65 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	hyp_spin_unlock(&vm_table_lock);
 }
 
+static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struct kvm *host_kvm)
+{
+	struct kvm *kvm = &hyp_vm->kvm;
+	DECLARE_BITMAP(allowed_features, KVM_VCPU_MAX_FEATURES);
+
+	/* No restrictions for non-protected VMs. */
+	if (!kvm_vm_is_protected(kvm)) {
+		bitmap_copy(kvm->arch.vcpu_features,
+			    host_kvm->arch.vcpu_features,
+			    KVM_VCPU_MAX_FEATURES);
+		return;
+	}
+
+	bitmap_zero(allowed_features, KVM_VCPU_MAX_FEATURES);
+
+	/*
+	 * For protected VMs, always allow:
+	 * - CPU starting in poweroff state
+	 * - PSCI v0.2
+	 */
+	set_bit(KVM_ARM_VCPU_POWER_OFF, allowed_features);
+	set_bit(KVM_ARM_VCPU_PSCI_0_2, allowed_features);
+
+	/*
+	 * Check if remaining features are allowed:
+	 * - Performance Monitoring
+	 * - Scalable Vectors
+	 * - Pointer Authentication
+	 */
+	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), PVM_ID_AA64DFR0_ALLOW))
+		set_bit(KVM_ARM_VCPU_PMU_V3, allowed_features);
+
+	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), PVM_ID_AA64PFR0_ALLOW))
+		set_bit(KVM_ARM_VCPU_SVE, allowed_features);
+
+	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API), PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED) &&
+	    FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA), PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED))
+		set_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, allowed_features);
+
+	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI), PVM_ID_AA64ISAR1_ALLOW) &&
+	    FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA), PVM_ID_AA64ISAR1_ALLOW))
+		set_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, allowed_features);
+
+	bitmap_and(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features,
+		   allowed_features, KVM_VCPU_MAX_FEATURES);
+}
+
+static void pkvm_vcpu_init_ptrauth(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu;
+
+	if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) ||
+	    vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC)) {
+		kvm_vcpu_enable_ptrauth(vcpu);
+	} else {
+		vcpu_clear_flag(&hyp_vcpu->vcpu, GUEST_HAS_PTRAUTH);
+	}
+}
+
 static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu)
 {
 	if (host_vcpu)
@@ -310,6 +407,18 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
 	hyp_vm->host_kvm = host_kvm;
 	hyp_vm->kvm.created_vcpus = nr_vcpus;
 	hyp_vm->kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr;
+	hyp_vm->kvm.arch.pkvm.enabled = READ_ONCE(host_kvm->arch.pkvm.enabled);
+	pkvm_init_features_from_host(hyp_vm, host_kvm);
+}
+
+static void pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu)
+{
+	struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu;
+
+	if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) {
+		vcpu_clear_flag(vcpu, GUEST_HAS_SVE);
+		vcpu_clear_flag(vcpu, VCPU_SVE_FINALIZED);
+	}
 }
 
 static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
@@ -335,6 +444,11 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 
 	hyp_vcpu->vcpu.arch.hw_mmu = &hyp_vm->kvm.arch.mmu;
 	hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags);
+	hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED;
+
+	pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu);
+	pkvm_vcpu_init_ptrauth(hyp_vcpu);
+	pkvm_vcpu_init_traps(&hyp_vcpu->vcpu);
 done:
 	if (ret)
 		unpin_host_vcpu(host_vcpu);

arch/arm64/kvm/hyp/nvhe/setup.c

@@ -95,7 +95,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 {
 	void *start, *end, *virt = hyp_phys_to_virt(phys);
 	unsigned long pgt_size = hyp_s1_pgtable_pages() << PAGE_SHIFT;
-	enum kvm_pgtable_prot prot;
 	int ret, i;
 
 	/* Recreate the hyp page-table using the early page allocator */
@@ -148,22 +147,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 	}
 
 	pkvm_create_host_sve_mappings();
-
-	/*
-	 * Map the host sections RO in the hypervisor, but transfer the
-	 * ownership from the host to the hypervisor itself to make sure they
-	 * can't be donated or shared with another entity.
-	 *
-	 * The ownership transition requires matching changes in the host
-	 * stage-2. This will be done later (see finalize_host_mappings()) once
-	 * the hyp_vmemmap is addressable.
-	 */
-	prot = pkvm_mkstate(PAGE_HYP_RO, PKVM_PAGE_SHARED_OWNED);
-	ret = pkvm_create_mappings(&kvm_vgic_global_state,
-				   &kvm_vgic_global_state + 1, prot);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 

arch/arm64/kvm/hyp/vgic-v3-sr.c

@@ -1012,9 +1012,6 @@ static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 	val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT;
 	/* IDbits */
 	val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT;
-	/* SEIS */
-	if (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK)
-		val |= BIT(ICC_CTLR_EL1_SEIS_SHIFT);
 	/* A3V */
 	val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT;
 	/* EOImode */

arch/arm64/kvm/reset.c

@@ -167,11 +167,6 @@ static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
 		memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu));
 }
 
-static void kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
-{
-	vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH);
-}
-
 /**
  * kvm_reset_vcpu - sets core registers and sys_regs to reset value
  * @vcpu: The VCPU pointer

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -720,9 +720,6 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 	rb_erase(&region->hva_node, &vm->regions.hva_tree);
 	hash_del(&region->slot_node);
 
-	region->region.memory_size = 0;
-	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
-
 	sparsebit_free(&region->unused_phy_pages);
 	sparsebit_free(&region->protected_phy_pages);
 	ret = munmap(region->mmap_start, region->mmap_size);
@@ -1197,7 +1194,12 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
  */
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
 {
-	__vm_mem_region_delete(vm, memslot2region(vm, slot));
+	struct userspace_mem_region *region = memslot2region(vm, slot);
+
+	region->region.memory_size = 0;
+	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
+
+	__vm_mem_region_delete(vm, region);
 }
 
 void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,