kvm/vgic/vgic-init.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2015, 2016 ARM Ltd.
 */

#include <linux/uaccess.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <kvm/arm_vgic.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include "vgic.h"

/*
 * Initialization rules: there are multiple stages to the vgic
 * initialization, both for the distributor and the CPU interfaces.  The basic
 * idea is that even though the VGIC is not functional or not requested from
 * user space, the critical path of the run loop can still call VGIC functions
 * that just won't do anything, without them having to check additional
 * initialization flags to ensure they don't look at uninitialized data
 * structures.
 *
 * Distributor:
 *
 * - kvm_vgic_early_init(): initialization of static data that doesn't
 *   depend on any sizing information or emulation type. No allocation
 *   is allowed there.
 *
 * - vgic_init(): allocation and initialization of the generic data
 *   structures that depend on sizing information (number of CPUs,
 *   number of interrupts). Also initializes the vcpu specific data
 *   structures. Can be executed lazily for GICv2.
 *
 * CPU Interface:
 *
 * - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend
 *   on any sizing information. Private interrupts are allocated if not
 *   already allocated at vgic-creation time.
 */

/* EARLY INIT */

/**
 * kvm_vgic_early_init() - Initialize static VGIC VCPU data structures
 * @kvm: The VM whose VGIC districutor should be initialized
 *
 * Only do initialization of static structures that don't require any
 * allocation or sizing information from userspace.  vgic_init() called
 * kvm_vgic_dist_init() which takes care of the rest.
 */
void kvm_vgic_early_init(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;

	xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ);
}

/* CREATION */

static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type);

/**
 * kvm_vgic_create: triggered by the instantiation of the VGIC device by
 * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only)
 * or through the generic KVM_CREATE_DEVICE API ioctl.
 * irqchip_in_kernel() tells you if this function succeeded or not.
 * @kvm: kvm struct pointer
 * @type: KVM_DEV_TYPE_ARM_VGIC_V[235]
 */
int kvm_vgic_create(struct kvm *kvm, u32 type)
{
	struct kvm_vcpu *vcpu;
	unsigned long i;
	int ret;

	/*
	 * This function is also called by the KVM_CREATE_IRQCHIP handler,
	 * which had no chance yet to check the availability of the GICv2
	 * emulation. So check this here again. KVM_CREATE_DEVICE does
	 * the proper checks already.
	 */
	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 &&
		!kvm_vgic_global_state.can_emulate_gicv2)
		return -ENODEV;

	/*
	 * Ensure mutual exclusion with vCPU creation and any vCPU ioctls by:
	 *
	 *  - Holding kvm->lock to prevent KVM_CREATE_VCPU from reaching
	 *    kvm_arch_vcpu_precreate() and ensuring created_vcpus is stable.
	 *    This alone is insufficient, as kvm_vm_ioctl_create_vcpu() drops
	 *    the kvm->lock before completing the vCPU creation.
	 */
	lockdep_assert_held(&kvm->lock);

	/*
	 *  - Acquiring the vCPU mutex for every *online* vCPU to prevent
	 *    concurrent vCPU ioctls for vCPUs already visible to userspace.
	 */
	ret = -EBUSY;
	if (kvm_trylock_all_vcpus(kvm))
		return ret;

	/*
	 *  - Taking the config_lock which protects VGIC data structures such
	 *    as the per-vCPU arrays of private IRQs (SGIs, PPIs).
	 */
	mutex_lock(&kvm->arch.config_lock);

	/*
	 * - Bailing on the entire thing if a vCPU is in the middle of creation,
	 *   dropped the kvm->lock, but hasn't reached kvm_arch_vcpu_create().
	 *
	 * The whole combination of this guarantees that no vCPU can get into
	 * KVM with a VGIC configuration inconsistent with the VM's VGIC.
	 */
	if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus))
		goto out_unlock;

	if (irqchip_in_kernel(kvm)) {
		ret = -EEXIST;
		goto out_unlock;
	}

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (vcpu_has_run_once(vcpu))
			goto out_unlock;
	}
	ret = 0;

	if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
		kvm->max_vcpus = VGIC_V2_MAX_CPUS;
	else if (type == KVM_DEV_TYPE_ARM_VGIC_V3)
		kvm->max_vcpus = VGIC_V3_MAX_CPUS;
	else if (type == KVM_DEV_TYPE_ARM_VGIC_V5)
		kvm->max_vcpus = min(VGIC_V5_MAX_CPUS,
				     kvm_vgic_global_state.max_gic_vcpus);

	if (atomic_read(&kvm->online_vcpus) > kvm->max_vcpus) {
		ret = -E2BIG;
		goto out_unlock;
	}

	kvm->arch.vgic.in_kernel = true;
	kvm->arch.vgic.vgic_model = type;
	kvm->arch.vgic.implementation_rev = KVM_VGIC_IMP_REV_LATEST;
	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;

	switch (type) {
	case KVM_DEV_TYPE_ARM_VGIC_V2:
		kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
		break;
	case KVM_DEV_TYPE_ARM_VGIC_V3:
		INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
		break;
	}

	/*
	 * We've now created the GIC. Update the system register state
	 * to accurately reflect what we've created.
	 */
	kvm_vgic_finalize_idregs(kvm);

	kvm_for_each_vcpu(i, vcpu, kvm) {
		ret = vgic_allocate_private_irqs_locked(vcpu, type);
		if (ret)
			break;
	}

	if (ret) {
		kvm_for_each_vcpu(i, vcpu, kvm) {
			struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
			kfree(vgic_cpu->private_irqs);
			vgic_cpu->private_irqs = NULL;
		}

		kvm->arch.vgic.vgic_model = 0;
		kvm->arch.vgic.in_kernel = false;
		goto out_unlock;
	}

	if (type == KVM_DEV_TYPE_ARM_VGIC_V3)
		kvm->arch.vgic.nassgicap = system_supports_direct_sgis();

	/*
	 * We now know that we have a GICv5. The Arch Timer PPI interrupts may
	 * have been initialised at this stage, but will have done so assuming
	 * that we have an older GIC, meaning that the IntIDs won't be
	 * correct. We init them again, and this time they will be correct.
	 */
	if (type == KVM_DEV_TYPE_ARM_VGIC_V5)
		kvm_timer_init_vm(kvm);

out_unlock:
	mutex_unlock(&kvm->arch.config_lock);
	kvm_unlock_all_vcpus(kvm);
	return ret;
}

/* INIT/DESTROY */

/**
 * kvm_vgic_dist_init: initialize the dist data structures
 * @kvm: kvm struct pointer
 * @nr_spis: number of spis, frozen by caller
 */
static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
	int i;

	if (dist->spis)
		return 0;

	dist->active_spis = (atomic_t)ATOMIC_INIT(0);
	dist->spis = kzalloc_objs(struct vgic_irq, nr_spis, GFP_KERNEL_ACCOUNT);
	if (!dist->spis)
		return  -ENOMEM;

	/*
	 * In the following code we do not take the irq struct lock since
	 * no other action on irq structs can happen while the VGIC is
	 * not initialized yet:
	 * If someone wants to inject an interrupt or does a MMIO access, we
	 * require prior initialization in case of a virtual GICv3 or trigger
	 * initialization when using a virtual GICv2.
	 */
	for (i = 0; i < nr_spis; i++) {
		struct vgic_irq *irq = &dist->spis[i];

		irq->intid = i + VGIC_NR_PRIVATE_IRQS;
		INIT_LIST_HEAD(&irq->ap_list);
		raw_spin_lock_init(&irq->irq_lock);
		irq->vcpu = NULL;
		irq->target_vcpu = vcpu0;
		refcount_set(&irq->refcount, 0);
		switch (dist->vgic_model) {
		case KVM_DEV_TYPE_ARM_VGIC_V2:
			irq->targets = 0;
			irq->group = 0;
			break;
		case KVM_DEV_TYPE_ARM_VGIC_V3:
			irq->mpidr = 0;
			irq->group = 1;
			break;
		default:
			kfree(dist->spis);
			dist->spis = NULL;
			return -EINVAL;
		}
	}
	return 0;
}

/* Default GICv3 Maintenance Interrupt INTID, as per SBSA */
#define DEFAULT_MI_INTID	25

int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu)
{
	int ret;

	guard(mutex)(&vcpu->kvm->arch.config_lock);

	/*
	 * Matching the tradition established with the timers, provide
	 * a default PPI for the maintenance interrupt. It makes
	 * things easier to reason about.
	 */
	if (vcpu->kvm->arch.vgic.mi_intid == 0)
		vcpu->kvm->arch.vgic.mi_intid = DEFAULT_MI_INTID;
	ret = kvm_vgic_set_owner(vcpu, vcpu->kvm->arch.vgic.mi_intid, vcpu);

	return ret;
}

static void vgic_setup_private_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
				   u32 type)
{
	irq->intid = irq - &vcpu->arch.vgic_cpu.private_irqs[0];

	if (vgic_irq_is_sgi(irq->intid)) {
		/* SGIs */
		irq->enabled = 1;
		irq->config = VGIC_CONFIG_EDGE;
	} else {
		/* PPIs */
		irq->config = VGIC_CONFIG_LEVEL;
	}

	switch (type) {
	case KVM_DEV_TYPE_ARM_VGIC_V3:
		irq->group = 1;
		irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
		break;
	case KVM_DEV_TYPE_ARM_VGIC_V2:
		irq->group = 0;
		irq->targets = BIT(vcpu->vcpu_id);
		break;
	}
}

static void vgic_v5_setup_private_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
{
	int i = irq - &vcpu->arch.vgic_cpu.private_irqs[0];

	irq->intid = vgic_v5_make_ppi(i);

	/* The only Edge architected PPI is the SW_PPI */
	if (i == GICV5_ARCH_PPI_SW_PPI)
		irq->config = VGIC_CONFIG_EDGE;
	else
		irq->config = VGIC_CONFIG_LEVEL;

	/* Register the GICv5-specific PPI ops */
	vgic_v5_set_ppi_ops(vcpu, irq->intid);
}

static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	u32 num_private_irqs;
	int i;

	lockdep_assert_held(&vcpu->kvm->arch.config_lock);

	if (vgic_cpu->private_irqs)
		return 0;

	if (vgic_is_v5(vcpu->kvm))
		num_private_irqs = VGIC_V5_NR_PRIVATE_IRQS;
	else
		num_private_irqs = VGIC_NR_PRIVATE_IRQS;

	vgic_cpu->private_irqs = kzalloc_objs(struct vgic_irq,
					      num_private_irqs,
					      GFP_KERNEL_ACCOUNT);

	if (!vgic_cpu->private_irqs)
		return -ENOMEM;

	for (i = 0; i < num_private_irqs; i++) {
		struct vgic_irq *irq = &vcpu->arch.vgic_cpu.private_irqs[i];

		INIT_LIST_HEAD(&irq->ap_list);
		raw_spin_lock_init(&irq->irq_lock);
		irq->vcpu = NULL;
		irq->target_vcpu = vcpu;
		refcount_set(&irq->refcount, 0);

		if (vgic_is_v5(vcpu->kvm))
			vgic_v5_setup_private_irq(vcpu, irq);
		else
			vgic_setup_private_irq(vcpu, irq, type);
	}

	return 0;
}

static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type)
{
	int ret;

	mutex_lock(&vcpu->kvm->arch.config_lock);
	ret = vgic_allocate_private_irqs_locked(vcpu, type);
	mutex_unlock(&vcpu->kvm->arch.config_lock);

	return ret;
}

/**
 * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data
 * structures and register VCPU-specific KVM iodevs
 *
 * @vcpu: pointer to the VCPU being created and initialized
 *
 * Only do initialization, but do not actually enable the
 * VGIC CPU interface
 */
int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	int ret = 0;

	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;

	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
	raw_spin_lock_init(&vgic_cpu->ap_list_lock);
	atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0);

	if (!irqchip_in_kernel(vcpu->kvm))
		return 0;

	ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model);
	if (ret)
		return ret;

	/*
	 * If we are creating a VCPU with a GICv3 we must also register the
	 * KVM io device for the redistributor that belongs to this VCPU.
	 */
	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
		mutex_lock(&vcpu->kvm->slots_lock);
		ret = vgic_register_redist_iodev(vcpu);
		mutex_unlock(&vcpu->kvm->slots_lock);
	}
	return ret;
}

static void kvm_vgic_vcpu_reset(struct kvm_vcpu *vcpu)
{
	const struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V5)
		vgic_v5_reset(vcpu);
	else if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_reset(vcpu);
	else
		vgic_v3_reset(vcpu);
}

/*
 * vgic_init: allocates and initializes dist and vcpu data structures
 * depending on two dimensioning parameters:
 * - the number of spis
 * - the number of vcpus
 * The function is generally called when nr_spis has been explicitly set
 * by the guest through the KVM DEVICE API. If not nr_spis is set to 256.
 * vgic_initialized() returns true when this function has succeeded.
 */
int vgic_init(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu;
	int ret = 0;
	unsigned long idx;

	lockdep_assert_held(&kvm->arch.config_lock);

	if (vgic_initialized(kvm))
		return 0;

	/* Are we also in the middle of creating a VCPU? */
	if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus))
		return -EBUSY;

	if (!vgic_is_v5(kvm)) {
		/* freeze the number of spis */
		if (!dist->nr_spis)
			dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS;

		ret = kvm_vgic_dist_init(kvm, dist->nr_spis);
		if (ret)
			return ret;

		/*
		 * Ensure vPEs are allocated if direct IRQ injection (e.g. vSGIs,
		 * vLPIs) is supported.
		 */
		if (vgic_supports_direct_irqs(kvm)) {
			ret = vgic_v4_init(kvm);
			if (ret)
				return ret;
		}
	} else {
		ret = vgic_v5_init(kvm);
		if (ret)
			return ret;
	}

	kvm_for_each_vcpu(idx, vcpu, kvm)
		kvm_vgic_vcpu_reset(vcpu);

	ret = kvm_vgic_setup_default_irq_routing(kvm);
	if (ret)
		return ret;

	vgic_debug_init(kvm);
	dist->initialized = true;

	return 0;
}

static void kvm_vgic_dist_destroy(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct vgic_redist_region *rdreg, *next;

	dist->ready = false;
	dist->initialized = false;

	kfree(dist->spis);
	dist->spis = NULL;
	dist->nr_spis = 0;
	dist->vgic_dist_base = VGIC_ADDR_UNDEF;

	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
		list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list)
			vgic_v3_free_redist_region(kvm, rdreg);
		INIT_LIST_HEAD(&dist->rd_regions);
	} else {
		dist->vgic_cpu_base = VGIC_ADDR_UNDEF;
	}

	if (vgic_supports_direct_irqs(kvm))
		vgic_v4_teardown(kvm);

	xa_destroy(&dist->lpi_xa);
}

static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

	/*
	 * Retire all pending LPIs on this vcpu anyway as we're
	 * going to destroy it.
	 */
	vgic_flush_pending_lpis(vcpu);

	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
	kfree(vgic_cpu->private_irqs);
	vgic_cpu->private_irqs = NULL;

	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
		/*
		 * If this vCPU is being destroyed because of a failed creation
		 * then unregister the redistributor to avoid leaving behind a
		 * dangling pointer to the vCPU struct.
		 *
		 * vCPUs that have been successfully created (i.e. added to
		 * kvm->vcpu_array) get unregistered in kvm_vgic_destroy(), as
		 * this function gets called while holding kvm->arch.config_lock
		 * in the VM teardown path and would otherwise introduce a lock
		 * inversion w.r.t. kvm->srcu.
		 *
		 * vCPUs that failed creation are torn down outside of the
		 * kvm->arch.config_lock and do not get unregistered in
		 * kvm_vgic_destroy(), meaning it is both safe and necessary to
		 * do so here.
		 */
		if (kvm_get_vcpu_by_id(vcpu->kvm, vcpu->vcpu_id) != vcpu)
			vgic_unregister_redist_iodev(vcpu);

		vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
	}
}

void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;

	mutex_lock(&kvm->slots_lock);
	__kvm_vgic_vcpu_destroy(vcpu);
	mutex_unlock(&kvm->slots_lock);
}

void kvm_vgic_destroy(struct kvm *kvm)
{
	struct kvm_vcpu *vcpu;
	unsigned long i;

	mutex_lock(&kvm->slots_lock);
	mutex_lock(&kvm->arch.config_lock);

	vgic_debug_destroy(kvm);

	kvm_for_each_vcpu(i, vcpu, kvm)
		__kvm_vgic_vcpu_destroy(vcpu);

	kvm_vgic_dist_destroy(kvm);

	mutex_unlock(&kvm->arch.config_lock);

	if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
		kvm_for_each_vcpu(i, vcpu, kvm)
			vgic_unregister_redist_iodev(vcpu);

	mutex_unlock(&kvm->slots_lock);
}

/**
 * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest
 * is a GICv2. A GICv3 must be explicitly initialized by userspace using the
 * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group.
 * @kvm: kvm struct pointer
 */
int vgic_lazy_init(struct kvm *kvm)
{
	int ret = 0;

	if (unlikely(!vgic_initialized(kvm))) {
		/*
		 * We only provide the automatic initialization of the VGIC
		 * for the legacy case of a GICv2. Any other type must
		 * be explicitly initialized once setup with the respective
		 * KVM device call.
		 */
		if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2)
			return -EBUSY;

		mutex_lock(&kvm->arch.config_lock);
		ret = vgic_init(kvm);
		mutex_unlock(&kvm->arch.config_lock);
	}

	return ret;
}

/* RESOURCE MAPPING */

/**
 * kvm_vgic_map_resources - map the MMIO regions
 * @kvm: kvm struct pointer
 *
 * Map the MMIO regions depending on the VGIC model exposed to the guest
 * called on the first VCPU run.
 * Also map the virtual CPU interface into the VM.
 * v2 calls vgic_init() if not already done.
 * v3 and derivatives return an error if the VGIC is not initialized.
 */
int kvm_vgic_map_resources(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	bool needs_dist = true;
	enum vgic_type type;
	gpa_t dist_base;
	int ret = 0;

	if (likely(smp_load_acquire(&dist->ready)))
		return 0;

	mutex_lock(&kvm->slots_lock);
	mutex_lock(&kvm->arch.config_lock);
	if (dist->ready)
		goto out;

	if (!irqchip_in_kernel(kvm))
		goto out;

	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) {
		ret = vgic_v2_map_resources(kvm);
		type = VGIC_V2;
	} else if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
		ret = vgic_v3_map_resources(kvm);
		type = VGIC_V3;
	} else {
		ret = vgic_v5_map_resources(kvm);
		type = VGIC_V5;
		needs_dist = false;
	}

	if (ret)
		goto out;

	if (needs_dist) {
		dist_base = dist->vgic_dist_base;
		mutex_unlock(&kvm->arch.config_lock);

		ret = vgic_register_dist_iodev(kvm, dist_base, type);
		if (ret) {
			kvm_err("Unable to register VGIC dist MMIO regions\n");
			goto out_slots;
		}
	} else {
		mutex_unlock(&kvm->arch.config_lock);
	}

	smp_store_release(&dist->ready, true);
	goto out_slots;
out:
	mutex_unlock(&kvm->arch.config_lock);
out_slots:
	if (ret)
		kvm_vm_dead(kvm);

	mutex_unlock(&kvm->slots_lock);

	return ret;
}

void kvm_vgic_finalize_idregs(struct kvm *kvm)
{
	u32 type = kvm->arch.vgic.vgic_model;
	u64 aa64pfr0, aa64pfr2, pfr1;

	aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC;
	aa64pfr2 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR2_EL1) & ~ID_AA64PFR2_EL1_GCIE;
	pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC;

	switch (type) {
	case KVM_DEV_TYPE_ARM_VGIC_V2:
		break;
	case KVM_DEV_TYPE_ARM_VGIC_V3:
		aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP);
		if (kvm_supports_32bit_el0())
			pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3);
		break;
	case KVM_DEV_TYPE_ARM_VGIC_V5:
		aa64pfr2 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR2_EL1, GCIE, IMP);
		break;
	default:
		WARN_ONCE(1, "Unknown VGIC type!!!\n");
	}

	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0);
	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR2_EL1, aa64pfr2);
	kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1);
}

/* GENERIC PROBE */

void kvm_vgic_cpu_up(void)
{
	enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0);
}


void kvm_vgic_cpu_down(void)
{
	disable_percpu_irq(kvm_vgic_global_state.maint_irq);
}

static irqreturn_t vgic_maintenance_handler(int irq, void *data)
{
	struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)data;

	/*
	 * We cannot rely on the vgic maintenance interrupt to be
	 * delivered synchronously. This means we can only use it to
	 * exit the VM, and we perform the handling of EOIed
	 * interrupts on the exit path (see vgic_fold_lr_state).
	 *
	 * Of course, NV throws a wrench in this plan, and needs
	 * something special.
	 */
	if (vcpu && vgic_state_is_nested(vcpu))
		vgic_v3_handle_nested_maint_irq(vcpu);

	return IRQ_HANDLED;
}

static struct gic_kvm_info *gic_kvm_info;

void __init vgic_set_kvm_info(const struct gic_kvm_info *info)
{
	BUG_ON(gic_kvm_info != NULL);
	gic_kvm_info = kmalloc_obj(*gic_kvm_info);
	if (gic_kvm_info)
		*gic_kvm_info = *info;
}

/**
 * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware
 *
 * For a specific CPU, initialize the GIC VE hardware.
 */
void kvm_vgic_init_cpu_hardware(void)
{
	BUG_ON(preemptible());

	/*
	 * We want to make sure the list registers start out clear so that we
	 * only have the program the used registers.
	 */
	if (kvm_vgic_global_state.type == VGIC_V2) {
		vgic_v2_init_lrs();
	} else if (kvm_vgic_global_state.type == VGIC_V3 ||
		   kvm_vgic_global_state.has_gcie_v3_compat) {
		kvm_call_hyp(__vgic_v3_init_lrs);
	}
}

/**
 * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable
 * according to the host GIC model. Accordingly calls either
 * vgic_v2/v3_probe which registers the KVM_DEVICE that can be
 * instantiated by a guest later on .
 */
int kvm_vgic_hyp_init(void)
{
	bool has_mask;
	int ret;

	if (!gic_kvm_info)
		return -ENODEV;

	has_mask = !gic_kvm_info->no_maint_irq_mask;

	if (has_mask && !gic_kvm_info->maint_irq) {
		kvm_err("No vgic maintenance irq\n");
		ret = -ENXIO;
		goto out_free;
	}

	/*
	 * If we get one of these oddball non-GICs, taint the kernel,
	 * as we have no idea of how they *really* behave.
	 */
	if (gic_kvm_info->no_hw_deactivation) {
		kvm_info("Non-architectural vgic, tainting kernel\n");
		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
		kvm_vgic_global_state.no_hw_deactivation = true;
	}

	switch (gic_kvm_info->type) {
	case GIC_V2:
		ret = vgic_v2_probe(gic_kvm_info);
		break;
	case GIC_V3:
		ret = vgic_v3_probe(gic_kvm_info);
		if (!ret) {
			static_branch_enable(&kvm_vgic_global_state.gicv3_cpuif);
			kvm_info("GIC system register CPU interface enabled\n");
		}
		break;
	case GIC_V5:
		ret = vgic_v5_probe(gic_kvm_info);
		break;
	default:
		ret = -ENODEV;
	}

	kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq;

out_free:
	kfree(gic_kvm_info);
	gic_kvm_info = NULL;

	if (ret)
		return ret;

	if (!has_mask && !kvm_vgic_global_state.maint_irq)
		return 0;

	ret = request_percpu_irq(kvm_vgic_global_state.maint_irq,
				 vgic_maintenance_handler,
				 "vgic", kvm_get_running_vcpus());
	if (ret) {
		kvm_err("Cannot register interrupt %d\n",
			kvm_vgic_global_state.maint_irq);
		return ret;
	}

	kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq);
	return 0;
}