vgic-v3-sr.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2012-2015 - ARM Ltd
 * Author: Marc Zyngier <[email protected]>
 */

#include <hyp/adjust_pc.h>

#include <linux/compiler.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <linux/kvm_host.h>

#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>

#include "../../vgic/vgic.h"

#define vtr_to_max_lr_idx(v)		((v) & 0xf)
#define vtr_to_nr_pre_bits(v)		((((u32)(v) >> 26) & 7) + 1)
#define vtr_to_nr_apr_regs(v)		(1 << (vtr_to_nr_pre_bits(v) - 5))

u64 __gic_v3_get_lr(unsigned int lr)
{
	switch (lr & 0xf) {
	case 0:
		return read_gicreg(ICH_LR0_EL2);
	case 1:
		return read_gicreg(ICH_LR1_EL2);
	case 2:
		return read_gicreg(ICH_LR2_EL2);
	case 3:
		return read_gicreg(ICH_LR3_EL2);
	case 4:
		return read_gicreg(ICH_LR4_EL2);
	case 5:
		return read_gicreg(ICH_LR5_EL2);
	case 6:
		return read_gicreg(ICH_LR6_EL2);
	case 7:
		return read_gicreg(ICH_LR7_EL2);
	case 8:
		return read_gicreg(ICH_LR8_EL2);
	case 9:
		return read_gicreg(ICH_LR9_EL2);
	case 10:
		return read_gicreg(ICH_LR10_EL2);
	case 11:
		return read_gicreg(ICH_LR11_EL2);
	case 12:
		return read_gicreg(ICH_LR12_EL2);
	case 13:
		return read_gicreg(ICH_LR13_EL2);
	case 14:
		return read_gicreg(ICH_LR14_EL2);
	case 15:
		return read_gicreg(ICH_LR15_EL2);
	}

	unreachable();
}

void __gic_v3_set_lr(u64 val, int lr)
{
	switch (lr & 0xf) {
	case 0:
		write_gicreg(val, ICH_LR0_EL2);
		break;
	case 1:
		write_gicreg(val, ICH_LR1_EL2);
		break;
	case 2:
		write_gicreg(val, ICH_LR2_EL2);
		break;
	case 3:
		write_gicreg(val, ICH_LR3_EL2);
		break;
	case 4:
		write_gicreg(val, ICH_LR4_EL2);
		break;
	case 5:
		write_gicreg(val, ICH_LR5_EL2);
		break;
	case 6:
		write_gicreg(val, ICH_LR6_EL2);
		break;
	case 7:
		write_gicreg(val, ICH_LR7_EL2);
		break;
	case 8:
		write_gicreg(val, ICH_LR8_EL2);
		break;
	case 9:
		write_gicreg(val, ICH_LR9_EL2);
		break;
	case 10:
		write_gicreg(val, ICH_LR10_EL2);
		break;
	case 11:
		write_gicreg(val, ICH_LR11_EL2);
		break;
	case 12:
		write_gicreg(val, ICH_LR12_EL2);
		break;
	case 13:
		write_gicreg(val, ICH_LR13_EL2);
		break;
	case 14:
		write_gicreg(val, ICH_LR14_EL2);
		break;
	case 15:
		write_gicreg(val, ICH_LR15_EL2);
		break;
	}
}

static void __vgic_v3_write_ap0rn(u32 val, int n)
{
	switch (n) {
	case 0:
		write_gicreg(val, ICH_AP0R0_EL2);
		break;
	case 1:
		write_gicreg(val, ICH_AP0R1_EL2);
		break;
	case 2:
		write_gicreg(val, ICH_AP0R2_EL2);
		break;
	case 3:
		write_gicreg(val, ICH_AP0R3_EL2);
		break;
	}
}

static void __vgic_v3_write_ap1rn(u32 val, int n)
{
	switch (n) {
	case 0:
		write_gicreg(val, ICH_AP1R0_EL2);
		break;
	case 1:
		write_gicreg(val, ICH_AP1R1_EL2);
		break;
	case 2:
		write_gicreg(val, ICH_AP1R2_EL2);
		break;
	case 3:
		write_gicreg(val, ICH_AP1R3_EL2);
		break;
	}
}

static u32 __vgic_v3_read_ap0rn(int n)
{
	u32 val;

	switch (n) {
	case 0:
		val = read_gicreg(ICH_AP0R0_EL2);
		break;
	case 1:
		val = read_gicreg(ICH_AP0R1_EL2);
		break;
	case 2:
		val = read_gicreg(ICH_AP0R2_EL2);
		break;
	case 3:
		val = read_gicreg(ICH_AP0R3_EL2);
		break;
	default:
		unreachable();
	}

	return val;
}

static u32 __vgic_v3_read_ap1rn(int n)
{
	u32 val;

	switch (n) {
	case 0:
		val = read_gicreg(ICH_AP1R0_EL2);
		break;
	case 1:
		val = read_gicreg(ICH_AP1R1_EL2);
		break;
	case 2:
		val = read_gicreg(ICH_AP1R2_EL2);
		break;
	case 3:
		val = read_gicreg(ICH_AP1R3_EL2);
		break;
	default:
		unreachable();
	}

	return val;
}

static u64 compute_ich_hcr(struct vgic_v3_cpu_if *cpu_if)
{
	return cpu_if->vgic_hcr | vgic_ich_hcr_trap_bits();
}

void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
{
	u64 used_lrs = cpu_if->used_lrs;

	/*
	 * Make sure stores to the GIC via the memory mapped interface
	 * are now visible to the system register interface when reading the
	 * LRs, and when reading back the VMCR on non-VHE systems.
	 */
	if (used_lrs || !has_vhe()) {
		if (!cpu_if->vgic_sre) {
			dsb(sy);
			isb();
		}
	}

	if (used_lrs) {
		int i;
		u32 elrsr;

		elrsr = read_gicreg(ICH_ELRSR_EL2);

		for (i = 0; i < used_lrs; i++) {
			if (elrsr & (1 << i))
				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
			else
				cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);

			__gic_v3_set_lr(0, i);
		}
	}

	cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2);

	if (cpu_if->vgic_hcr & ICH_HCR_EL2_LRENPIE) {
		u64 val = read_gicreg(ICH_HCR_EL2);
		cpu_if->vgic_hcr &= ~ICH_HCR_EL2_EOIcount;
		cpu_if->vgic_hcr |= val & ICH_HCR_EL2_EOIcount;
	}

	write_gicreg(0, ICH_HCR_EL2);

	/*
	 * Hack alert: On NV, this results in a trap so that the above write
	 * actually takes effect... No synchronisation is necessary, as we
	 * only care about the effects when this traps.
	 */
	read_gicreg(ICH_MISR_EL2);
}

void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
{
	u64 used_lrs = cpu_if->used_lrs;
	int i;

	write_gicreg(compute_ich_hcr(cpu_if), ICH_HCR_EL2);

	for (i = 0; i < used_lrs; i++)
		__gic_v3_set_lr(cpu_if->vgic_lr[i], i);

	/*
	 * Ensure that writes to the LRs, and on non-VHE systems ensure that
	 * the write to the VMCR in __vgic_v3_activate_traps(), will have
	 * reached the (re)distributors. This ensure the guest will read the
	 * correct values from the memory-mapped interface.
	 */
	if (used_lrs || !has_vhe()) {
		if (!cpu_if->vgic_sre) {
			isb();
			dsb(sy);
		}
	}
}

void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
{
	/*
	 * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
	 * Group0 interrupt (as generated in GICv2 mode) to be
	 * delivered as a FIQ to the guest, with potentially fatal
	 * consequences. So we must make sure that ICC_SRE_EL1 has
	 * been actually programmed with the value we want before
	 * starting to mess with the rest of the GIC, and VMCR_EL2 in
	 * particular.  This logic must be called before
	 * __vgic_v3_restore_state().
	 *
	 * However, if the vgic is disabled (ICH_HCR_EL2.EN==0), no GIC is
	 * provisioned at all. In order to prevent illegal accesses to the
	 * system registers to trap to EL1 (duh), force ICC_SRE_EL1.SRE to 1
	 * so that the trap bits can take effect. Yes, we *loves* the GIC.
	 */
	if (!(cpu_if->vgic_hcr & ICH_HCR_EL2_En)) {
		write_gicreg(ICC_SRE_EL1_SRE, ICC_SRE_EL1);
		isb();
	} else if (!cpu_if->vgic_sre) {
		write_gicreg(0, ICC_SRE_EL1);
		isb();
		write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);


		if (has_vhe()) {
			/*
			 * Ensure that the write to the VMCR will have reached
			 * the (re)distributors. This ensure the guest will
			 * read the correct values from the memory-mapped
			 * interface.
			 */
			isb();
			dsb(sy);
		}
	}

	/* Only disable SRE if the host implements the GICv2 interface */
	if (static_branch_unlikely(&vgic_v3_has_v2_compat)) {
		/*
		 * Prevent the guest from touching the ICC_SRE_EL1 system
		 * register. Note that this may not have any effect, as
		 * ICC_SRE_EL2.Enable being RAO/WI is a valid implementation.
		 */
		write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
			     ICC_SRE_EL2);
	}

	/*
	 * If we need to trap system registers, we must write ICH_HCR_EL2
	 * anyway, even if no interrupts are being injected. Note that this
	 * also applies if we don't expect any system register access (no
	 * vgic at all). In any case, no need to provide MI configuration.
	 */
	if (static_branch_unlikely(&vgic_v3_cpuif_trap) ||
	    cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre)
		write_gicreg(vgic_ich_hcr_trap_bits() | ICH_HCR_EL2_En, ICH_HCR_EL2);
}

void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
{
	u64 val;

	/* Only restore SRE if the host implements the GICv2 interface */
	if (static_branch_unlikely(&vgic_v3_has_v2_compat)) {
		val = read_gicreg(ICC_SRE_EL2);
		write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2);

		if (!cpu_if->vgic_sre) {
			/* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
			isb();
			write_gicreg(1, ICC_SRE_EL1);
		}
	}

	/*
	 * If we were trapping system registers, we enabled the VGIC even if
	 * no interrupts were being injected, and we disable it again here.
	 */
	if (static_branch_unlikely(&vgic_v3_cpuif_trap) ||
	    cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre)
		write_gicreg(0, ICH_HCR_EL2);
}

void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
{
	u64 val;
	u32 nr_pre_bits;

	val = read_gicreg(ICH_VTR_EL2);
	nr_pre_bits = vtr_to_nr_pre_bits(val);

	switch (nr_pre_bits) {
	case 7:
		cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3);
		cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2);
		fallthrough;
	case 6:
		cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1);
		fallthrough;
	default:
		cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0);
	}

	switch (nr_pre_bits) {
	case 7:
		cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3);
		cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2);
		fallthrough;
	case 6:
		cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1);
		fallthrough;
	default:
		cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0);
	}
}

static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
{
	u64 val;
	u32 nr_pre_bits;

	val = read_gicreg(ICH_VTR_EL2);
	nr_pre_bits = vtr_to_nr_pre_bits(val);

	switch (nr_pre_bits) {
	case 7:
		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3);
		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2);
		fallthrough;
	case 6:
		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1);
		fallthrough;
	default:
		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0);
	}

	switch (nr_pre_bits) {
	case 7:
		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3);
		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2);
		fallthrough;
	case 6:
		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1);
		fallthrough;
	default:
		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0);
	}
}

void __vgic_v3_init_lrs(void)
{
	int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
	int i;

	for (i = 0; i <= max_lr_idx; i++)
		__gic_v3_set_lr(0, i);
}

/*
 * Return the GIC CPU configuration:
 * - [31:0]  ICH_VTR_EL2
 * - [62:32] RES0
 * - [63]    MMIO (GICv2) capable
 */
u64 __vgic_v3_get_gic_config(void)
{
	u64 val, sre;
	unsigned long flags = 0;

	/*
	 * In compat mode, we cannot access ICC_SRE_EL1 at any EL
	 * other than EL1 itself; just return the
	 * ICH_VTR_EL2. ICC_IDR0_EL1 is only implemented on a GICv5
	 * system, so we first check if we have GICv5 support.
	 */
	if (cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF))
		return read_gicreg(ICH_VTR_EL2);

	sre = read_gicreg(ICC_SRE_EL1);
	/*
	 * To check whether we have a MMIO-based (GICv2 compatible)
	 * CPU interface, we need to disable the system register
	 * view.
	 *
	 * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
	 * that to be able to set ICC_SRE_EL1.SRE to 0, all the
	 * interrupt overrides must be set. You've got to love this.
	 *
	 * As we always run VHE with HCR_xMO set, no extra xMO
	 * manipulation is required in that case.
	 *
	 * To safely disable SRE, we have to prevent any interrupt
	 * from firing (which would be deadly). This only makes sense
	 * on VHE, as interrupts are already masked for nVHE as part
	 * of the exception entry to EL2.
	 */
	if (has_vhe()) {
		flags = local_daif_save();
	} else {
		sysreg_clear_set_hcr(0, HCR_AMO | HCR_FMO | HCR_IMO);
		isb();
	}

	write_gicreg(0, ICC_SRE_EL1);
	isb();

	val = read_gicreg(ICC_SRE_EL1);

	write_gicreg(sre, ICC_SRE_EL1);
	isb();

	if (has_vhe()) {
		local_daif_restore(flags);
	} else {
		sysreg_clear_set_hcr(HCR_AMO | HCR_FMO | HCR_IMO, 0);
		isb();
	}

	val  = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
	val |= read_gicreg(ICH_VTR_EL2);

	return val;
}

static void __vgic_v3_compat_mode_enable(void)
{
	if (!cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF))
		return;

	sysreg_clear_set_s(SYS_ICH_VCTLR_EL2, 0, ICH_VCTLR_EL2_V3);
	/* Wait for V3 to become enabled */
	isb();
}

static u64 __vgic_v3_read_vmcr(void)
{
	return read_gicreg(ICH_VMCR_EL2);
}

static void __vgic_v3_write_vmcr(u32 vmcr)
{
	write_gicreg(vmcr, ICH_VMCR_EL2);
}

void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if)
{
	__vgic_v3_compat_mode_enable();

	/*
	 * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
	 * is dependent on ICC_SRE_EL1.SRE, and we have to perform the
	 * VMCR_EL2 save/restore in the world switch.
	 */
	if (cpu_if->vgic_sre)
		__vgic_v3_write_vmcr(cpu_if->vgic_vmcr);
	__vgic_v3_restore_aprs(cpu_if);
}

static int __vgic_v3_bpr_min(void)
{
	/* See Pseudocode for VPriorityGroup */
	return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2));
}

static int __vgic_v3_get_group(struct kvm_vcpu *vcpu)
{
	u64 esr = kvm_vcpu_get_esr(vcpu);
	u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;

	return crm != 8;
}

#define GICv3_IDLE_PRIORITY	0xff

static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr,
					 u64 *lr_val)
{
	unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
	u8 priority = GICv3_IDLE_PRIORITY;
	int i, lr = -1;

	for (i = 0; i < used_lrs; i++) {
		u64 val = __gic_v3_get_lr(i);
		u8 lr_prio = (val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT;

		/* Not pending in the state? */
		if ((val & ICH_LR_STATE) != ICH_LR_PENDING_BIT)
			continue;

		/* Group-0 interrupt, but Group-0 disabled? */
		if (!(val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_EL2_VENG0_MASK))
			continue;

		/* Group-1 interrupt, but Group-1 disabled? */
		if ((val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_EL2_VENG1_MASK))
			continue;

		/* Not the highest priority? */
		if (lr_prio >= priority)
			continue;

		/* This is a candidate */
		priority = lr_prio;
		*lr_val = val;
		lr = i;
	}

	if (lr == -1)
		*lr_val = ICC_IAR1_EL1_SPURIOUS;

	return lr;
}

static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid,
				    u64 *lr_val)
{
	unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
	int i;

	for (i = 0; i < used_lrs; i++) {
		u64 val = __gic_v3_get_lr(i);

		if ((val & ICH_LR_VIRTUAL_ID_MASK) == intid &&
		    (val & ICH_LR_ACTIVE_BIT)) {
			*lr_val = val;
			return i;
		}
	}

	*lr_val = ICC_IAR1_EL1_SPURIOUS;
	return -1;
}

static int __vgic_v3_get_highest_active_priority(void)
{
	u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
	u32 hap = 0;
	int i;

	for (i = 0; i < nr_apr_regs; i++) {
		u32 val;

		/*
		 * The ICH_AP0Rn_EL2 and ICH_AP1Rn_EL2 registers
		 * contain the active priority levels for this VCPU
		 * for the maximum number of supported priority
		 * levels, and we return the full priority level only
		 * if the BPR is programmed to its minimum, otherwise
		 * we return a combination of the priority level and
		 * subpriority, as determined by the setting of the
		 * BPR, but without the full subpriority.
		 */
		val  = __vgic_v3_read_ap0rn(i);
		val |= __vgic_v3_read_ap1rn(i);
		if (!val) {
			hap += 32;
			continue;
		}

		return (hap + __ffs(val)) << __vgic_v3_bpr_min();
	}

	return GICv3_IDLE_PRIORITY;
}

static unsigned int __vgic_v3_get_bpr0(u32 vmcr)
{
	return FIELD_GET(ICH_VMCR_EL2_VBPR0, vmcr);
}

static unsigned int __vgic_v3_get_bpr1(u32 vmcr)
{
	unsigned int bpr;

	if (vmcr & ICH_VMCR_EL2_VCBPR_MASK) {
		bpr = __vgic_v3_get_bpr0(vmcr);
		if (bpr < 7)
			bpr++;
	} else {
		bpr = FIELD_GET(ICH_VMCR_EL2_VBPR1, vmcr);
	}

	return bpr;
}

/*
 * Convert a priority to a preemption level, taking the relevant BPR
 * into account by zeroing the sub-priority bits.
 */
static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
{
	unsigned int bpr;

	if (!grp)
		bpr = __vgic_v3_get_bpr0(vmcr) + 1;
	else
		bpr = __vgic_v3_get_bpr1(vmcr);

	return pri & (GENMASK(7, 0) << bpr);
}

/*
 * The priority value is independent of any of the BPR values, so we
 * normalize it using the minimal BPR value. This guarantees that no
 * matter what the guest does with its BPR, we can always set/get the
 * same value of a priority.
 */
static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
{
	u8 pre, ap;
	u32 val;
	int apr;

	pre = __vgic_v3_pri_to_pre(pri, vmcr, grp);
	ap = pre >> __vgic_v3_bpr_min();
	apr = ap / 32;

	if (!grp) {
		val = __vgic_v3_read_ap0rn(apr);
		__vgic_v3_write_ap0rn(val | BIT(ap % 32), apr);
	} else {
		val = __vgic_v3_read_ap1rn(apr);
		__vgic_v3_write_ap1rn(val | BIT(ap % 32), apr);
	}
}

static int __vgic_v3_clear_highest_active_priority(void)
{
	u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
	u32 hap = 0;
	int i;

	for (i = 0; i < nr_apr_regs; i++) {
		u32 ap0, ap1;
		int c0, c1;

		ap0 = __vgic_v3_read_ap0rn(i);
		ap1 = __vgic_v3_read_ap1rn(i);
		if (!ap0 && !ap1) {
			hap += 32;
			continue;
		}

		c0 = ap0 ? __ffs(ap0) : 32;
		c1 = ap1 ? __ffs(ap1) : 32;

		/* Always clear the LSB, which is the highest priority */
		if (c0 < c1) {
			ap0 &= ~BIT(c0);
			__vgic_v3_write_ap0rn(ap0, i);
			hap += c0;
		} else {
			ap1 &= ~BIT(c1);
			__vgic_v3_write_ap1rn(ap1, i);
			hap += c1;
		}

		/* Rescale to 8 bits of priority */
		return hap << __vgic_v3_bpr_min();
	}

	return GICv3_IDLE_PRIORITY;
}

static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u64 lr_val;
	u8 lr_prio, pmr;
	int lr, grp;

	grp = __vgic_v3_get_group(vcpu);

	lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val);
	if (lr < 0)
		goto spurious;

	if (grp != !!(lr_val & ICH_LR_GROUP))
		goto spurious;

	pmr = FIELD_GET(ICH_VMCR_EL2_VPMR, vmcr);
	lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT;
	if (pmr <= lr_prio)
		goto spurious;

	if (__vgic_v3_get_highest_active_priority() <= __vgic_v3_pri_to_pre(lr_prio, vmcr, grp))
		goto spurious;

	lr_val &= ~ICH_LR_STATE;
	lr_val |= ICH_LR_ACTIVE_BIT;
	__gic_v3_set_lr(lr_val, lr);
	__vgic_v3_set_active_priority(lr_prio, vmcr, grp);
	vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK);
	return;

spurious:
	vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS);
}

static void __vgic_v3_clear_active_lr(int lr, u64 lr_val)
{
	lr_val &= ~ICH_LR_ACTIVE_BIT;
	if (lr_val & ICH_LR_HW) {
		u32 pid;

		pid = (lr_val & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT;
		gic_write_dir(pid);
	}

	__gic_v3_set_lr(lr_val, lr);
}

static void __vgic_v3_bump_eoicount(void)
{
	u32 hcr;

	hcr = read_gicreg(ICH_HCR_EL2);
	hcr += 1 << ICH_HCR_EL2_EOIcount_SHIFT;
	write_gicreg(hcr, ICH_HCR_EL2);
}

static int ___vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u32 vid = vcpu_get_reg(vcpu, rt);
	u64 lr_val;
	int lr;

	/* EOImode == 0, nothing to be done here */
	if (!(vmcr & ICH_VMCR_EL2_VEOIM_MASK))
		return 1;

	/* No deactivate to be performed on an LPI */
	if (vid >= VGIC_MIN_LPI)
		return 1;

	lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val);
	if (lr != -1) {
		__vgic_v3_clear_active_lr(lr, lr_val);
		return 1;
	}

	return 0;
}

static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	if (!___vgic_v3_write_dir(vcpu, vmcr, rt))
		__vgic_v3_bump_eoicount();
}

static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u32 vid = vcpu_get_reg(vcpu, rt);
	u64 lr_val;
	u8 lr_prio, act_prio;
	int lr, grp;

	grp = __vgic_v3_get_group(vcpu);

	/* Drop priority in any case */
	act_prio = __vgic_v3_clear_highest_active_priority();

	lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val);
	if (lr == -1) {
		/* Do not bump EOIcount for LPIs that aren't in the LRs */
		if (!(vid >= VGIC_MIN_LPI))
			__vgic_v3_bump_eoicount();
		return;
	}

	/* EOImode == 1 and not an LPI, nothing to be done here */
	if ((vmcr & ICH_VMCR_EL2_VEOIM_MASK) && !(vid >= VGIC_MIN_LPI))
		return;

	lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT;

	/* If priorities or group do not match, the guest has fscked-up. */
	if (grp != !!(lr_val & ICH_LR_GROUP) ||
	    __vgic_v3_pri_to_pre(lr_prio, vmcr, grp) != act_prio)
		return;

	/* Let's now perform the deactivation */
	__vgic_v3_clear_active_lr(lr, lr_val);
}

static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VENG0, vmcr));
}

static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VENG1, vmcr));
}

static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u64 val = vcpu_get_reg(vcpu, rt);

	FIELD_MODIFY(ICH_VMCR_EL2_VENG0, &vmcr, val & 1);

	__vgic_v3_write_vmcr(vmcr);
}

static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u64 val = vcpu_get_reg(vcpu, rt);

	FIELD_MODIFY(ICH_VMCR_EL2_VENG1, &vmcr, val & 1);

	__vgic_v3_write_vmcr(vmcr);
}

static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr));
}

static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr));
}

static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u64 val = vcpu_get_reg(vcpu, rt);
	u8 bpr_min = __vgic_v3_bpr_min() - 1;

	/* Enforce BPR limiting */
	if (val < bpr_min)
		val = bpr_min;

	FIELD_MODIFY(ICH_VMCR_EL2_VBPR0, &vmcr, val);

	__vgic_v3_write_vmcr(vmcr);
}

static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u64 val = vcpu_get_reg(vcpu, rt);
	u8 bpr_min = __vgic_v3_bpr_min();

	if (FIELD_GET(ICH_VMCR_EL2_VCBPR, val))
		return;

	/* Enforce BPR limiting */
	if (val < bpr_min)
		val = bpr_min;

	FIELD_MODIFY(ICH_VMCR_EL2_VBPR1, &vmcr, val);

	__vgic_v3_write_vmcr(vmcr);
}

static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
{
	u32 val;

	if (!__vgic_v3_get_group(vcpu))
		val = __vgic_v3_read_ap0rn(n);
	else
		val = __vgic_v3_read_ap1rn(n);

	vcpu_set_reg(vcpu, rt, val);
}

static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
{
	u32 val = vcpu_get_reg(vcpu, rt);

	if (!__vgic_v3_get_group(vcpu))
		__vgic_v3_write_ap0rn(val, n);
	else
		__vgic_v3_write_ap1rn(val, n);
}

static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu,
					    u32 vmcr, int rt)
{
	__vgic_v3_read_apxrn(vcpu, rt, 0);
}

static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu,
					    u32 vmcr, int rt)
{
	__vgic_v3_read_apxrn(vcpu, rt, 1);
}

static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	__vgic_v3_read_apxrn(vcpu, rt, 2);
}

static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	__vgic_v3_read_apxrn(vcpu, rt, 3);
}

static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	__vgic_v3_write_apxrn(vcpu, rt, 0);
}

static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	__vgic_v3_write_apxrn(vcpu, rt, 1);
}

static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	__vgic_v3_write_apxrn(vcpu, rt, 2);
}

static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	__vgic_v3_write_apxrn(vcpu, rt, 3);
}

static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u64 lr_val;
	int lr, lr_grp, grp;

	grp = __vgic_v3_get_group(vcpu);

	lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val);
	if (lr == -1)
		goto spurious;

	lr_grp = !!(lr_val & ICH_LR_GROUP);
	if (lr_grp != grp)
		lr_val = ICC_IAR1_EL1_SPURIOUS;

spurious:
	vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK);
}

static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VPMR, vmcr));
}

static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u32 val = vcpu_get_reg(vcpu, rt);

	FIELD_MODIFY(ICH_VMCR_EL2_VPMR, &vmcr, val);

	write_gicreg(vmcr, ICH_VMCR_EL2);
}

static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u32 val = __vgic_v3_get_highest_active_priority();
	vcpu_set_reg(vcpu, rt, val);
}

static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u32 vtr, val;

	vtr = read_gicreg(ICH_VTR_EL2);
	/* PRIbits */
	val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT;
	/* IDbits */
	val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT;
	/* A3V */
	val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT;
	/* EOImode */
	val |= FIELD_PREP(ICC_CTLR_EL1_EOImode_MASK,
			  FIELD_GET(ICH_VMCR_EL2_VEOIM, vmcr));
	/* CBPR */
	val |= FIELD_PREP(ICC_CTLR_EL1_CBPR_MASK,
			FIELD_GET(ICH_VMCR_EL2_VCBPR, vmcr));

	vcpu_set_reg(vcpu, rt, val);
}

static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
	u32 val = vcpu_get_reg(vcpu, rt);

	FIELD_MODIFY(ICH_VMCR_EL2_VCBPR, &vmcr,
		     FIELD_GET(ICC_CTLR_EL1_CBPR_MASK, val));

	FIELD_MODIFY(ICH_VMCR_EL2_VEOIM, &vmcr,
		     FIELD_GET(ICC_CTLR_EL1_EOImode_MASK, val));

	write_gicreg(vmcr, ICH_VMCR_EL2);
}

static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
					    u32 sysreg, bool is_read)
{
	u64 ich_hcr;

	if (!is_nested_ctxt(vcpu))
		return false;

	ich_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);

	switch (sysreg) {
	case SYS_ICC_IGRPEN0_EL1:
		if (is_read &&
		    (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1))
			return true;

		if (!is_read &&
		    (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1))
			return true;

		fallthrough;

	case SYS_ICC_AP0Rn_EL1(0):
	case SYS_ICC_AP0Rn_EL1(1):
	case SYS_ICC_AP0Rn_EL1(2):
	case SYS_ICC_AP0Rn_EL1(3):
	case SYS_ICC_BPR0_EL1:
	case SYS_ICC_EOIR0_EL1:
	case SYS_ICC_HPPIR0_EL1:
	case SYS_ICC_IAR0_EL1:
		return ich_hcr & ICH_HCR_EL2_TALL0;

	case SYS_ICC_IGRPEN1_EL1:
		if (is_read &&
		    (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1))
			return true;

		if (!is_read &&
		    (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1))
			return true;

		fallthrough;

	case SYS_ICC_AP1Rn_EL1(0):
	case SYS_ICC_AP1Rn_EL1(1):
	case SYS_ICC_AP1Rn_EL1(2):
	case SYS_ICC_AP1Rn_EL1(3):
	case SYS_ICC_BPR1_EL1:
	case SYS_ICC_EOIR1_EL1:
	case SYS_ICC_HPPIR1_EL1:
	case SYS_ICC_IAR1_EL1:
		return ich_hcr & ICH_HCR_EL2_TALL1;

	case SYS_ICC_DIR_EL1:
		if (ich_hcr & ICH_HCR_EL2_TDIR)
			return true;

		fallthrough;

	case SYS_ICC_RPR_EL1:
	case SYS_ICC_CTLR_EL1:
	case SYS_ICC_PMR_EL1:
		return ich_hcr & ICH_HCR_EL2_TC;

	default:
		return false;
	}
}

int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
{
	int rt;
	u64 esr;
	u32 vmcr;
	void (*fn)(struct kvm_vcpu *, u32, int);
	bool is_read;
	u32 sysreg;

	if (kern_hyp_va(vcpu->kvm)->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3)
		return 0;

	esr = kvm_vcpu_get_esr(vcpu);
	if (vcpu_mode_is_32bit(vcpu)) {
		if (!kvm_condition_valid(vcpu)) {
			__kvm_skip_instr(vcpu);
			return 1;
		}

		sysreg = esr_cp15_to_sysreg(esr);
	} else {
		sysreg = esr_sys64_to_sysreg(esr);
	}

	is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ;

	if (__vgic_v3_check_trap_forwarding(vcpu, sysreg, is_read))
		return 0;

	switch (sysreg) {
	case SYS_ICC_IAR0_EL1:
	case SYS_ICC_IAR1_EL1:
		if (unlikely(!is_read))
			return 0;
		fn = __vgic_v3_read_iar;
		break;
	case SYS_ICC_EOIR0_EL1:
	case SYS_ICC_EOIR1_EL1:
		if (unlikely(is_read))
			return 0;
		fn = __vgic_v3_write_eoir;
		break;
	case SYS_ICC_IGRPEN1_EL1:
		if (is_read)
			fn = __vgic_v3_read_igrpen1;
		else
			fn = __vgic_v3_write_igrpen1;
		break;
	case SYS_ICC_BPR1_EL1:
		if (is_read)
			fn = __vgic_v3_read_bpr1;
		else
			fn = __vgic_v3_write_bpr1;
		break;
	case SYS_ICC_AP0Rn_EL1(0):
	case SYS_ICC_AP1Rn_EL1(0):
		if (is_read)
			fn = __vgic_v3_read_apxr0;
		else
			fn = __vgic_v3_write_apxr0;
		break;
	case SYS_ICC_AP0Rn_EL1(1):
	case SYS_ICC_AP1Rn_EL1(1):
		if (is_read)
			fn = __vgic_v3_read_apxr1;
		else
			fn = __vgic_v3_write_apxr1;
		break;
	case SYS_ICC_AP0Rn_EL1(2):
	case SYS_ICC_AP1Rn_EL1(2):
		if (is_read)
			fn = __vgic_v3_read_apxr2;
		else
			fn = __vgic_v3_write_apxr2;
		break;
	case SYS_ICC_AP0Rn_EL1(3):
	case SYS_ICC_AP1Rn_EL1(3):
		if (is_read)
			fn = __vgic_v3_read_apxr3;
		else
			fn = __vgic_v3_write_apxr3;
		break;
	case SYS_ICC_HPPIR0_EL1:
	case SYS_ICC_HPPIR1_EL1:
		if (unlikely(!is_read))
			return 0;
		fn = __vgic_v3_read_hppir;
		break;
	case SYS_ICC_IGRPEN0_EL1:
		if (is_read)
			fn = __vgic_v3_read_igrpen0;
		else
			fn = __vgic_v3_write_igrpen0;
		break;
	case SYS_ICC_BPR0_EL1:
		if (is_read)
			fn = __vgic_v3_read_bpr0;
		else
			fn = __vgic_v3_write_bpr0;
		break;
	case SYS_ICC_DIR_EL1:
		if (unlikely(is_read))
			return 0;
		/*
		 * Full exit if required to handle overflow deactivation,
		 * unless we can emulate it in the LRs (likely the majority
		 * of the cases).
		 */
		if (vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr & ICH_HCR_EL2_TDIR) {
			int ret;

			ret = ___vgic_v3_write_dir(vcpu, __vgic_v3_read_vmcr(),
						   kvm_vcpu_sys_get_rt(vcpu));
			if (ret)
				__kvm_skip_instr(vcpu);

			return ret;
		}
		fn = __vgic_v3_write_dir;
		break;
	case SYS_ICC_RPR_EL1:
		if (unlikely(!is_read))
			return 0;
		fn = __vgic_v3_read_rpr;
		break;
	case SYS_ICC_CTLR_EL1:
		if (is_read)
			fn = __vgic_v3_read_ctlr;
		else
			fn = __vgic_v3_write_ctlr;
		break;
	case SYS_ICC_PMR_EL1:
		if (is_read)
			fn = __vgic_v3_read_pmr;
		else
			fn = __vgic_v3_write_pmr;
		break;
	default:
		return 0;
	}

	vmcr = __vgic_v3_read_vmcr();
	rt = kvm_vcpu_sys_get_rt(vcpu);
	fn(vcpu, vmcr, rt);

	__kvm_skip_instr(vcpu);

	return 1;
}