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

Pull KVM updates from Paolo Bonzini:
 "PPC:
   - Better machine check handling for HV KVM
   - Ability to support guests with threads=2, 4 or 8 on POWER9
   - Fix for a race that could cause delayed recognition of signals
   - Fix for a bug where POWER9 guests could sleep with interrupts pending.

  ARM:
   - VCPU request overhaul
   - allow timer and PMU to have their interrupt number selected from userspace
   - workaround for Cavium erratum 30115
   - handling of memory poisonning
   - the usual crop of fixes and cleanups

  s390:
   - initial machine check forwarding
   - migration support for the CMMA page hinting information
   - cleanups and fixes

  x86:
   - nested VMX bugfixes and improvements
   - more reliable NMI window detection on AMD
   - APIC timer optimizations

  Generic:
   - VCPU request overhaul + documentation of common code patterns
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (124 commits)
  Update my email address
  kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS
  x86: kvm: mmu: use ept a/d in vmcs02 iff used in vmcs12
  kvm: x86: mmu: allow A/D bits to be disabled in an mmu
  x86: kvm: mmu: make spte mmio mask more explicit
  x86: kvm: mmu: dead code thanks to access tracking
  KVM: PPC: Book3S: Fix typo in XICS-on-XIVE state saving code
  KVM: PPC: Book3S HV: Close race with testing for signals on guest entry
  KVM: PPC: Book3S HV: Simplify dynamic micro-threading code
  KVM: x86: remove ignored type attribute
  KVM: LAPIC: Fix lapic timer injection delay
  KVM: lapic: reorganize restart_apic_timer
  KVM: lapic: reorganize start_hv_timer
  kvm: nVMX: Check memory operand to INVVPID
  KVM: s390: Inject machine check into the nested guest
  KVM: s390: Inject machine check into the guest
  tools/kvm_stat: add new interactive command 'b'
  tools/kvm_stat: add new command line switch '-i'
  tools/kvm_stat: fix error on interactive command 'g'
  KVM: SVM: suppress unnecessary NMI singlestep on GIF=0 and nested exit
  ...

15 files changed, 1297 insertions, 150 deletions

diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c
index 528af4b2d09e..79c7c357804b 100644
--- a/virt/kvm/arm/aarch32.c
+++ b/virt/kvm/arm/aarch32.c
@@ -60,7 +60,7 @@ static const unsigned short cc_map[16] = {
 /*
  * Check if a trapped instruction should have been executed or not.
  */
-bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 {
 	unsigned long cpsr;
 	u32 cpsr_cond;
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 5976609ef27c..8e89d63005c7 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -21,6 +21,7 @@
 #include <linux/kvm_host.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/uaccess.h>
 
 #include <clocksource/arm_arch_timer.h>
 #include <asm/arch_timer.h>
@@ -35,6 +36,16 @@ static struct timecounter *timecounter;
 static unsigned int host_vtimer_irq;
 static u32 host_vtimer_irq_flags;
 
+static const struct kvm_irq_level default_ptimer_irq = {
+	.irq	= 30,
+	.level	= 1,
+};
+
+static const struct kvm_irq_level default_vtimer_irq = {
+	.irq	= 27,
+	.level	= 1,
+};
+
 void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	vcpu_vtimer(vcpu)->active_cleared_last = false;
@@ -95,7 +106,7 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 	 * If the vcpu is blocked we want to wake it up so that it will see
 	 * the timer has expired when entering the guest.
 	 */
-	kvm_vcpu_kick(vcpu);
+	kvm_vcpu_wake_up(vcpu);
 }
 
 static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
@@ -215,7 +226,8 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 	if (likely(irqchip_in_kernel(vcpu->kvm))) {
 		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
 					  timer_ctx->irq.irq,
-					  timer_ctx->irq.level);
+					  timer_ctx->irq.level,
+					  timer_ctx);
 		WARN_ON(ret);
 	}
 }
@@ -445,23 +457,12 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
 	kvm_timer_update_state(vcpu);
 }
 
-int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
-			 const struct kvm_irq_level *virt_irq,
-			 const struct kvm_irq_level *phys_irq)
+int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
 	/*
-	 * The vcpu timer irq number cannot be determined in
-	 * kvm_timer_vcpu_init() because it is called much before
-	 * kvm_vcpu_set_target(). To handle this, we determine
-	 * vcpu timer irq number when the vcpu is reset.
-	 */
-	vtimer->irq.irq = virt_irq->irq;
-	ptimer->irq.irq = phys_irq->irq;
-
-	/*
 	 * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8
 	 * and to 0 for ARMv7.  We provide an implementation that always
 	 * resets the timer to be disabled and unmasked and is compliant with
@@ -496,6 +497,8 @@ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff)
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
 	/* Synchronize cntvoff across all vtimers of a VM. */
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
@@ -504,6 +507,9 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	INIT_WORK(&timer->expired, kvm_timer_inject_irq_work);
 	hrtimer_init(&timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	timer->timer.function = kvm_timer_expire;
+
+	vtimer->irq.irq = default_vtimer_irq.irq;
+	ptimer->irq.irq = default_ptimer_irq.irq;
 }
 
 static void kvm_timer_init_interrupt(void *info)
@@ -613,6 +619,30 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
 	kvm_vgic_unmap_phys_irq(vcpu, vtimer->irq.irq);
 }
 
+static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
+{
+	int vtimer_irq, ptimer_irq;
+	int i, ret;
+
+	vtimer_irq = vcpu_vtimer(vcpu)->irq.irq;
+	ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu));
+	if (ret)
+		return false;
+
+	ptimer_irq = vcpu_ptimer(vcpu)->irq.irq;
+	ret = kvm_vgic_set_owner(vcpu, ptimer_irq, vcpu_ptimer(vcpu));
+	if (ret)
+		return false;
+
+	kvm_for_each_vcpu(i, vcpu, vcpu->kvm) {
+		if (vcpu_vtimer(vcpu)->irq.irq != vtimer_irq ||
+		    vcpu_ptimer(vcpu)->irq.irq != ptimer_irq)
+			return false;
+	}
+
+	return true;
+}
+
 int kvm_timer_enable(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
@@ -632,6 +662,11 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (!vgic_initialized(vcpu->kvm))
 		return -ENODEV;
 
+	if (!timer_irqs_are_valid(vcpu)) {
+		kvm_debug("incorrectly configured timer irqs\n");
+		return -EINVAL;
+	}
+
 	/*
 	 * Find the physical IRQ number corresponding to the host_vtimer_irq
 	 */
@@ -681,3 +716,79 @@ void kvm_timer_init_vhe(void)
 	val |= (CNTHCTL_EL1PCTEN << cnthctl_shift);
 	write_sysreg(val, cnthctl_el2);
 }
+
+static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		vcpu_vtimer(vcpu)->irq.irq = vtimer_irq;
+		vcpu_ptimer(vcpu)->irq.irq = ptimer_irq;
+	}
+}
+
+int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	int __user *uaddr = (int __user *)(long)attr->addr;
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
+	int irq;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return -EINVAL;
+
+	if (get_user(irq, uaddr))
+		return -EFAULT;
+
+	if (!(irq_is_ppi(irq)))
+		return -EINVAL;
+
+	if (vcpu->arch.timer_cpu.enabled)
+		return -EBUSY;
+
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
+		set_timer_irqs(vcpu->kvm, irq, ptimer->irq.irq);
+		break;
+	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
+		set_timer_irqs(vcpu->kvm, vtimer->irq.irq, irq);
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	int __user *uaddr = (int __user *)(long)attr->addr;
+	struct arch_timer_context *timer;
+	int irq;
+
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
+		timer = vcpu_vtimer(vcpu);
+		break;
+	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
+		timer = vcpu_ptimer(vcpu);
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	irq = timer->irq.irq;
+	return put_user(irq, uaddr);
+}
+
+int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
+	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
+		return 0;
+	}
+
+	return -ENXIO;
+}
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 3417e184c8e1..a39a1e161e63 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -368,6 +368,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_timer_vcpu_put(vcpu);
 }
 
+static void vcpu_power_off(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.power_off = true;
+	kvm_make_request(KVM_REQ_SLEEP, vcpu);
+	kvm_vcpu_kick(vcpu);
+}
+
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
@@ -387,7 +394,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 		vcpu->arch.power_off = false;
 		break;
 	case KVM_MP_STATE_STOPPED:
-		vcpu->arch.power_off = true;
+		vcpu_power_off(vcpu);
 		break;
 	default:
 		return -EINVAL;
@@ -520,6 +527,10 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	}
 
 	ret = kvm_timer_enable(vcpu);
+	if (ret)
+		return ret;
+
+	ret = kvm_arm_pmu_v3_enable(vcpu);
 
 	return ret;
 }
@@ -536,21 +547,7 @@ void kvm_arm_halt_guest(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		vcpu->arch.pause = true;
-	kvm_make_all_cpus_request(kvm, KVM_REQ_VCPU_EXIT);
-}
-
-void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.pause = true;
-	kvm_vcpu_kick(vcpu);
-}
-
-void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu)
-{
-	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
-
-	vcpu->arch.pause = false;
-	swake_up(wq);
+	kvm_make_all_cpus_request(kvm, KVM_REQ_SLEEP);
 }
 
 void kvm_arm_resume_guest(struct kvm *kvm)
@@ -558,16 +555,23 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 	int i;
 	struct kvm_vcpu *vcpu;
 
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_arm_resume_vcpu(vcpu);
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		vcpu->arch.pause = false;
+		swake_up(kvm_arch_vcpu_wq(vcpu));
+	}
 }
 
-static void vcpu_sleep(struct kvm_vcpu *vcpu)
+static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 {
 	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
 	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
+
+	if (vcpu->arch.power_off || vcpu->arch.pause) {
+		/* Awaken to handle a signal, request we sleep again later. */
+		kvm_make_request(KVM_REQ_SLEEP, vcpu);
+	}
 }
 
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
@@ -575,6 +579,20 @@ static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
 	return vcpu->arch.target >= 0;
 }
 
+static void check_vcpu_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_request_pending(vcpu)) {
+		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
+			vcpu_req_sleep(vcpu);
+
+		/*
+		 * Clear IRQ_PENDING requests that were made to guarantee
+		 * that a VCPU sees new virtual interrupts.
+		 */
+		kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu);
+	}
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -620,8 +638,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		update_vttbr(vcpu->kvm);
 
-		if (vcpu->arch.power_off || vcpu->arch.pause)
-			vcpu_sleep(vcpu);
+		check_vcpu_requests(vcpu);
 
 		/*
 		 * Preparing the interrupts to be injected also
@@ -650,8 +667,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			run->exit_reason = KVM_EXIT_INTR;
 		}
 
+		/*
+		 * Ensure we set mode to IN_GUEST_MODE after we disable
+		 * interrupts and before the final VCPU requests check.
+		 * See the comment in kvm_vcpu_exiting_guest_mode() and
+		 * Documentation/virtual/kvm/vcpu-requests.rst
+		 */
+		smp_store_mb(vcpu->mode, IN_GUEST_MODE);
+
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
-			vcpu->arch.power_off || vcpu->arch.pause) {
+		    kvm_request_pending(vcpu)) {
+			vcpu->mode = OUTSIDE_GUEST_MODE;
 			local_irq_enable();
 			kvm_pmu_sync_hwstate(vcpu);
 			kvm_timer_sync_hwstate(vcpu);
@@ -667,7 +693,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
 		guest_enter_irqoff();
-		vcpu->mode = IN_GUEST_MODE;
 
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
 
@@ -756,6 +781,7 @@ static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level)
 	 * trigger a world-switch round on the running physical CPU to set the
 	 * virtual IRQ/FIQ fields in the HCR appropriately.
 	 */
+	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
 
 	return 0;
@@ -806,7 +832,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
-		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level);
+		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level, NULL);
 	case KVM_ARM_IRQ_TYPE_SPI:
 		if (!irqchip_in_kernel(kvm))
 			return -ENXIO;
@@ -814,7 +840,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (irq_num < VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
-		return kvm_vgic_inject_irq(kvm, 0, irq_num, level);
+		return kvm_vgic_inject_irq(kvm, 0, irq_num, level, NULL);
 	}
 
 	return -EINVAL;
@@ -884,7 +910,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	 * Handle the "start in power-off" case.
 	 */
 	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
-		vcpu->arch.power_off = true;
+		vcpu_power_off(vcpu);
 	else
 		vcpu->arch.power_off = false;
 
@@ -1115,9 +1141,6 @@ static void cpu_init_hyp_mode(void *dummy)
 	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 	__cpu_init_stage2();
 
-	if (is_kernel_in_hyp_mode())
-		kvm_timer_init_vhe();
-
 	kvm_arm_init_debug();
 }
 
@@ -1137,6 +1160,7 @@ static void cpu_hyp_reinit(void)
 		 * event was cancelled before the CPU was reset.
 		 */
 		__cpu_init_stage2();
+		kvm_timer_init_vhe();
 	} else {
 		cpu_init_hyp_mode(NULL);
 	}
diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c
index 87940364570b..91728faa13fd 100644
--- a/virt/kvm/arm/hyp/vgic-v3-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v3-sr.c
@@ -19,10 +19,12 @@
 #include <linux/irqchip/arm-gic-v3.h>
 #include <linux/kvm_host.h>
 
+#include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.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))
 
 static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
 {
@@ -118,6 +120,90 @@ static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
 	}
 }
 
+static void __hyp_text __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 __hyp_text __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 __hyp_text __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 __hyp_text __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;
+}
+
 void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
@@ -154,24 +240,27 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 
 		switch (nr_pre_bits) {
 		case 7:
-			cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
-			cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
+			cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3);
+			cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2);
 		case 6:
-			cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2);
+			cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1);
 		default:
-			cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
+			cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0);
 		}
 
 		switch (nr_pre_bits) {
 		case 7:
-			cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
-			cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
+			cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3);
+			cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2);
 		case 6:
-			cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2);
+			cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1);
 		default:
-			cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
+			cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0);
 		}
 	} else {
+		if (static_branch_unlikely(&vgic_v3_cpuif_trap))
+			write_gicreg(0, ICH_HCR_EL2);
+
 		cpu_if->vgic_elrsr = 0xffff;
 		cpu_if->vgic_ap0r[0] = 0;
 		cpu_if->vgic_ap0r[1] = 0;
@@ -224,26 +313,34 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 
 		switch (nr_pre_bits) {
 		case 7:
-			write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
-			write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
+			__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3);
+			__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2);
 		case 6:
-			write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2);
+			__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1);
 		default:
-			write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
+			__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0);
 		}
 
 		switch (nr_pre_bits) {
 		case 7:
-			write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
-			write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
+			__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3);
+			__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2);
 		case 6:
-			write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2);
+			__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1);
 		default:
-			write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
+			__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0);
 		}
 
 		for (i = 0; i < used_lrs; i++)
 			__gic_v3_set_lr(cpu_if->vgic_lr[i], i);
+	} else {
+		/*
+		 * If we need to trap system registers, we must write
+		 * ICH_HCR_EL2 anyway, even if no interrupts are being
+		 * injected,
+		 */
+		if (static_branch_unlikely(&vgic_v3_cpuif_trap))
+			write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 	}
 
 	/*
@@ -287,3 +384,697 @@ void __hyp_text __vgic_v3_write_vmcr(u32 vmcr)
 {
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
+
+#ifdef CONFIG_ARM64
+
+static int __hyp_text __vgic_v3_bpr_min(void)
+{
+	/* See Pseudocode for VPriorityGroup */
+	return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2));
+}
+
+static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
+{
+	u32 esr = kvm_vcpu_get_hsr(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 __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
+						    u32 vmcr,
+						    u64 *lr_val)
+{
+	unsigned int used_lrs = vcpu->arch.vgic_cpu.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_ENG0_MASK))
+			continue;
+
+		/* Group-1 interrupt, but Group-1 disabled? */
+		if ((val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_ENG1_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 __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu,
+					       int intid, u64 *lr_val)
+{
+	unsigned int used_lrs = vcpu->arch.vgic_cpu.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 __hyp_text __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 __hyp_text __vgic_v3_get_bpr0(u32 vmcr)
+{
+	return (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
+}
+
+static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr)
+{
+	unsigned int bpr;
+
+	if (vmcr & ICH_VMCR_CBPR_MASK) {
+		bpr = __vgic_v3_get_bpr0(vmcr);
+		if (bpr < 7)
+			bpr++;
+	} else {
+		bpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
+	}
+
+	return bpr;
+}
+
+/*
+ * Convert a priority to a preemption level, taking the relevant BPR
+ * into account by zeroing the sub-priority bits.
+ */
+static u8 __hyp_text __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 minumal 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 __hyp_text __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 __hyp_text __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 __hyp_text __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 = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
+	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;
+	/* No active state for LPIs */
+	if ((lr_val & ICH_LR_VIRTUAL_ID_MASK) <= VGIC_MAX_SPI)
+		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 __hyp_text __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 __hyp_text __vgic_v3_bump_eoicount(void)
+{
+	u32 hcr;
+
+	hcr = read_gicreg(ICH_HCR_EL2);
+	hcr += 1 << ICH_HCR_EOIcount_SHIFT;
+	write_gicreg(hcr, ICH_HCR_EL2);
+}
+
+static void __hyp_text __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_EOIM_MASK))
+		return;
+
+	/* No deactivate to be performed on an LPI */
+	if (vid >= VGIC_MIN_LPI)
+		return;
+
+	lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val);
+	if (lr == -1) {
+		__vgic_v3_bump_eoicount();
+		return;
+	}
+
+	__vgic_v3_clear_active_lr(lr, lr_val);
+}
+
+static void __hyp_text __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();
+
+	/* If EOIing an LPI, no deactivate to be performed */
+	if (vid >= VGIC_MIN_LPI)
+		return;
+
+	/* EOImode == 1, nothing to be done here */
+	if (vmcr & ICH_VMCR_EOIM_MASK)
+		return;
+
+	lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val);
+	if (lr == -1) {
+		__vgic_v3_bump_eoicount();
+		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 __hyp_text __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+{
+	vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG0_MASK));
+}
+
+static void __hyp_text __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+{
+	vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG1_MASK));
+}
+
+static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+{
+	u64 val = vcpu_get_reg(vcpu, rt);
+
+	if (val & 1)
+		vmcr |= ICH_VMCR_ENG0_MASK;
+	else
+		vmcr &= ~ICH_VMCR_ENG0_MASK;
+
+	__vgic_v3_write_vmcr(vmcr);
+}
+
+static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+{
+	u64 val = vcpu_get_reg(vcpu, rt);
+
+	if (val & 1)
+		vmcr |= ICH_VMCR_ENG1_MASK;
+	else
+		vmcr &= ~ICH_VMCR_ENG1_MASK;
+
+	__vgic_v3_write_vmcr(vmcr);
+}
+
+static void __hyp_text __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+{
+	vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr));
+}
+
+static void __hyp_text __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+{
+	vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr));
+}
+
+static void __hyp_text __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;
+
+	val <<= ICH_VMCR_BPR0_SHIFT;
+	val &= ICH_VMCR_BPR0_MASK;
+	vmcr &= ~ICH_VMCR_BPR0_MASK;
+	vmcr |= val;
+
+	__vgic_v3_write_vmcr(vmcr);
+}
+
+static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+{
+	u64 val = vcpu_get_reg(vcpu, rt);
+	u8 bpr_min = __vgic_v3_bp