1 files changed, 482 insertions, 166 deletions

diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 76e2d85789ed..1d6dd1b545bd 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -1,25 +1,68 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
 #include <linux/irqchip/arm-gic-v3.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kstrtox.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <linux/string_choices.h>
 #include <kvm/arm_vgic.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_asm.h>
 
+#include "vgic-mmio.h"
 #include "vgic.h"
 
 static bool group0_trap;
 static bool group1_trap;
 static bool common_trap;
+static bool dir_trap;
 static bool gicv4_enable;
 
-void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
+void vgic_v3_configure_hcr(struct kvm_vcpu *vcpu,
+			   struct ap_list_summary *als)
 {
 	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	cpuif->vgic_hcr |= ICH_HCR_UIE;
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return;
+
+	cpuif->vgic_hcr = ICH_HCR_EL2_En;
+
+	if (irqs_pending_outside_lrs(als))
+		cpuif->vgic_hcr |= ICH_HCR_EL2_NPIE;
+	if (irqs_active_outside_lrs(als))
+		cpuif->vgic_hcr |= ICH_HCR_EL2_LRENPIE;
+	if (irqs_outside_lrs(als))
+		cpuif->vgic_hcr |= ICH_HCR_EL2_UIE;
+
+	if (!als->nr_sgi)
+		cpuif->vgic_hcr |= ICH_HCR_EL2_vSGIEOICount;
+
+	cpuif->vgic_hcr |= (cpuif->vgic_vmcr & ICH_VMCR_ENG0_MASK) ?
+		ICH_HCR_EL2_VGrp0DIE : ICH_HCR_EL2_VGrp0EIE;
+	cpuif->vgic_hcr |= (cpuif->vgic_vmcr & ICH_VMCR_ENG1_MASK) ?
+		ICH_HCR_EL2_VGrp1DIE : ICH_HCR_EL2_VGrp1EIE;
+
+	/*
+	 * Dealing with EOImode=1 is a massive source of headache. Not
+	 * only do we need to track that we have active interrupts
+	 * outside of the LRs and force DIR to be trapped, we also
+	 * need to deal with SPIs that can be deactivated on another
+	 * CPU.
+	 *
+	 * On systems that do not implement TDIR, force the bit in the
+	 * shadow state anyway to avoid IPI-ing on these poor sods.
+	 *
+	 * Note that we set the trap irrespective of EOIMode, as that
+	 * can change behind our back without any warning...
+	 */
+	if (!cpus_have_final_cap(ARM64_HAS_ICH_HCR_EL2_TDIR) ||
+	    irqs_active_outside_lrs(als)		     ||
+	    atomic_read(&vcpu->kvm->arch.vgic.active_spis))
+		cpuif->vgic_hcr |= ICH_HCR_EL2_TDIR;
 }
 
 static bool lr_signals_eoi_mi(u64 lr_val)
@@ -28,99 +71,238 @@ static bool lr_signals_eoi_mi(u64 lr_val)
 	       !(lr_val & ICH_LR_HW);
 }
 
+static void vgic_v3_fold_lr(struct kvm_vcpu *vcpu, u64 val)
+{
+	struct vgic_irq *irq;
+	bool is_v2_sgi = false;
+	bool deactivated;
+	u32 intid;
+
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+		intid = val & ICH_LR_VIRTUAL_ID_MASK;
+	} else {
+		intid = val & GICH_LR_VIRTUALID;
+		is_v2_sgi = vgic_irq_is_sgi(intid);
+	}
+
+	irq = vgic_get_vcpu_irq(vcpu, intid);
+	if (!irq)	/* An LPI could have been unmapped. */
+		return;
+
+	scoped_guard(raw_spinlock, &irq->irq_lock) {
+		/* Always preserve the active bit for !LPIs, note deactivation */
+		if (irq->intid >= VGIC_MIN_LPI)
+			val &= ~ICH_LR_ACTIVE_BIT;
+		deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT);
+		irq->active = !!(val & ICH_LR_ACTIVE_BIT);
+
+		/* Edge is the only case where we preserve the pending bit */
+		if (irq->config == VGIC_CONFIG_EDGE &&
+		    (val & ICH_LR_PENDING_BIT))
+			irq->pending_latch = true;
+
+		/*
+		 * Clear soft pending state when level irqs have been acked.
+		 */
+		if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE))
+			irq->pending_latch = false;
+
+		if (is_v2_sgi) {
+			u8 cpuid = FIELD_GET(GICH_LR_PHYSID_CPUID, val);
+
+			if (irq->active)
+				irq->active_source = cpuid;
+
+			if (val & ICH_LR_PENDING_BIT)
+				irq->source |= BIT(cpuid);
+		}
+
+		/* Handle resampling for mapped interrupts if required */
+		vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT);
+
+		irq->on_lr = false;
+	}
+
+	/* Notify fds when the guest EOI'ed a level-triggered SPI, and drop the refcount */
+	if (deactivated && lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) {
+		kvm_notify_acked_irq(vcpu->kvm, 0,
+				     intid - VGIC_NR_PRIVATE_IRQS);
+		atomic_dec_if_positive(&vcpu->kvm->arch.vgic.active_spis);
+	}
+
+	vgic_put_irq(vcpu->kvm, irq);
+}
+
+static u64 vgic_v3_compute_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq);
+
+static void vgic_v3_deactivate_phys(u32 intid)
+{
+	if (cpus_have_final_cap(ARM64_HAS_GICV5_LEGACY))
+		gic_insn(intid | FIELD_PREP(GICV5_GIC_CDDI_TYPE_MASK, 1), CDDI);
+	else
+		gic_write_dir(intid);
+}
+
 void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3;
-	u32 model = vcpu->kvm->arch.vgic.vgic_model;
-	int lr;
+	u32 eoicount = FIELD_GET(ICH_HCR_EL2_EOIcount, cpuif->vgic_hcr);
+	struct vgic_irq *irq;
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
-	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+	for (int lr = 0; lr < cpuif->used_lrs; lr++)
+		vgic_v3_fold_lr(vcpu, cpuif->vgic_lr[lr]);
 
-	for (lr = 0; lr < cpuif->used_lrs; lr++) {
-		u64 val = cpuif->vgic_lr[lr];
-		u32 intid, cpuid;
-		struct vgic_irq *irq;
-		bool is_v2_sgi = false;
-
-		cpuid = val & GICH_LR_PHYSID_CPUID;
-		cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+	/*
+	 * EOIMode=0: use EOIcount to emulate deactivation. We are
+	 * guaranteed to deactivate in reverse order of the activation, so
+	 * just pick one active interrupt after the other in the ap_list,
+	 * and replay the deactivation as if the CPU was doing it. We also
+	 * rely on priority drop to have taken place, and the list to be
+	 * sorted by priority.
+	 */
+	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+		u64 lr;
 
-		if (model == KVM_DEV_TYPE_ARM_VGIC_V3) {
-			intid = val & ICH_LR_VIRTUAL_ID_MASK;
+		/*
+		 * I would have loved to write this using a scoped_guard(),
+		 * but using 'continue' here is a total train wreck.
+		 */
+		if (!eoicount) {
+			break;
 		} else {
-			intid = val & GICH_LR_VIRTUALID;
-			is_v2_sgi = vgic_irq_is_sgi(intid);
+			guard(raw_spinlock)(&irq->irq_lock);
+
+			if (!(likely(vgic_target_oracle(irq) == vcpu) &&
+			      irq->active))
+				continue;
+
+			lr = vgic_v3_compute_lr(vcpu, irq) & ~ICH_LR_ACTIVE_BIT;
 		}
 
-		/* Notify fds when the guest EOI'ed a level-triggered IRQ */
-		if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
-			kvm_notify_acked_irq(vcpu->kvm, 0,
-					     intid - VGIC_NR_PRIVATE_IRQS);
+		if (lr & ICH_LR_HW)
+			vgic_v3_deactivate_phys(FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
 
-		irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
-		if (!irq)	/* An LPI could have been unmapped. */
-			continue;
+		vgic_v3_fold_lr(vcpu, lr);
+		eoicount--;
+	}
 
-		raw_spin_lock(&irq->irq_lock);
+	cpuif->used_lrs = 0;
+}
 
-		/* Always preserve the active bit */
-		irq->active = !!(val & ICH_LR_ACTIVE_BIT);
+void vgic_v3_deactivate(struct kvm_vcpu *vcpu, u64 val)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3;
+	u32 model = vcpu->kvm->arch.vgic.vgic_model;
+	struct kvm_vcpu *target_vcpu = NULL;
+	bool mmio = false, is_v2_sgi;
+	struct vgic_irq *irq;
+	unsigned long flags;
+	u64 lr = 0;
+	u8 cpuid;
 
-		if (irq->active && is_v2_sgi)
-			irq->active_source = cpuid;
+	/* Snapshot CPUID, and remove it from the INTID */
+	cpuid = FIELD_GET(GENMASK_ULL(12, 10), val);
+	val &= ~GENMASK_ULL(12, 10);
 
-		/* Edge is the only case where we preserve the pending bit */
-		if (irq->config == VGIC_CONFIG_EDGE &&
-		    (val & ICH_LR_PENDING_BIT)) {
-			irq->pending_latch = true;
+	is_v2_sgi = (model == KVM_DEV_TYPE_ARM_VGIC_V2 &&
+		     val < VGIC_NR_SGIS);
 
-			if (is_v2_sgi)
-				irq->source |= (1 << cpuid);
-		}
+	/*
+	 * We only deal with DIR when EOIMode==1, and only for SGI,
+	 * PPI or SPI.
+	 */
+	if (!(cpuif->vgic_vmcr & ICH_VMCR_EOIM_MASK) ||
+	    val >= vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)
+		return;
 
-		/*
-		 * Clear soft pending state when level irqs have been acked.
-		 */
-		if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE))
-			irq->pending_latch = false;
+	/* Make sure we're in the same context as LR handling */
+	local_irq_save(flags);
+
+	irq = vgic_get_vcpu_irq(vcpu, val);
+	if (WARN_ON_ONCE(!irq))
+		goto out;
+
+	/*
+	 * EOIMode=1: we must rely on traps to handle deactivate of
+	 * overflowing interrupts, as there is no ordering guarantee and
+	 * EOIcount isn't being incremented. Priority drop will have taken
+	 * place, as ICV_EOIxR_EL1 only affects the APRs and not the LRs.
+	 *
+	 * Three possibities:
+	 *
+	 * - The irq is not queued on any CPU, and there is nothing to
+	 *   do,
+	 *
+	 * - Or the irq is in an LR, meaning that its state is not
+	 *   directly observable. Treat it bluntly by making it as if
+	 *   this was a write to GICD_ICACTIVER, which will force an
+	 *   exit on all vcpus. If it hurts, don't do that.
+	 *
+	 * - Or the irq is active, but not in an LR, and we can
+	 *   directly deactivate it by building a pseudo-LR, fold it,
+	 *   and queue a request to prune the resulting ap_list,
+	 *
+	 * Special care must be taken to match the source CPUID when
+	 * deactivating a GICv2 SGI.
+	 */
+	scoped_guard(raw_spinlock, &irq->irq_lock) {
+		target_vcpu = irq->vcpu;
+
+		/* Not on any ap_list? */
+		if (!target_vcpu)
+			goto put;
 
 		/*
-		 * Level-triggered mapped IRQs are special because we only
-		 * observe rising edges as input to the VGIC.
-		 *
-		 * If the guest never acked the interrupt we have to sample
-		 * the physical line and set the line level, because the
-		 * device state could have changed or we simply need to
-		 * process the still pending interrupt later.
-		 *
-		 * If this causes us to lower the level, we have to also clear
-		 * the physical active state, since we will otherwise never be
-		 * told when the interrupt becomes asserted again.
+		 * Urgh. We're deactivating something that we cannot
+		 * observe yet... Big hammer time.
 		 */
-		if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) {
-			irq->line_level = vgic_get_phys_line_level(irq);
+		if (irq->on_lr) {
+			mmio = true;
+			goto put;
+		}
 
-			if (!irq->line_level)
-				vgic_irq_set_phys_active(irq, false);
+		/* GICv2 SGI: check that the cpuid matches */
+		if (is_v2_sgi && irq->active_source != cpuid) {
+			target_vcpu = NULL;
+			goto put;
 		}
 
-		raw_spin_unlock(&irq->irq_lock);
-		vgic_put_irq(vcpu->kvm, irq);
+		/* (with a Dalek voice) DEACTIVATE!!!! */
+		lr = vgic_v3_compute_lr(vcpu, irq) & ~ICH_LR_ACTIVE_BIT;
 	}
 
-	cpuif->used_lrs = 0;
+	if (lr & ICH_LR_HW)
+		vgic_v3_deactivate_phys(FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
+
+	vgic_v3_fold_lr(vcpu, lr);
+
+put:
+	vgic_put_irq(vcpu->kvm, irq);
+
+out:
+	local_irq_restore(flags);
+
+	if (mmio)
+		vgic_mmio_write_cactive(vcpu, (val / 32) * 4, 4, BIT(val % 32));
+
+	/* Force the ap_list to be pruned */
+	if (target_vcpu)
+		kvm_make_request(KVM_REQ_VGIC_PROCESS_UPDATE, target_vcpu);
 }
 
 /* Requires the irq to be locked already */
-void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
+static u64 vgic_v3_compute_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 {
 	u32 model = vcpu->kvm->arch.vgic.vgic_model;
 	u64 val = irq->intid;
 	bool allow_pending = true, is_v2_sgi;
 
+	WARN_ON(irq->on_lr);
+
 	is_v2_sgi = (vgic_irq_is_sgi(irq->intid) &&
 		     model == KVM_DEV_TYPE_ARM_VGIC_V2);
 
@@ -134,7 +316,7 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 		}
 	}
 
-	if (irq->hw) {
+	if (irq->hw && !vgic_irq_needs_resampling(irq)) {
 		val |= ICH_LR_HW;
 		val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT;
 		/*
@@ -160,6 +342,35 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 	if (allow_pending && irq_is_pending(irq)) {
 		val |= ICH_LR_PENDING_BIT;
 
+		if (is_v2_sgi) {
+			u32 src = ffs(irq->source);
+
+			if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n",
+					   irq->intid))
+				return 0;
+
+			val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
+			if (irq->source & ~BIT(src - 1))
+				val |= ICH_LR_EOI;
+		}
+	}
+
+	if (irq->group)
+		val |= ICH_LR_GROUP;
+
+	val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT;
+
+	return val;
+}
+
+void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
+{
+	u32 model = vcpu->kvm->arch.vgic.vgic_model;
+	u64 val = vgic_v3_compute_lr(vcpu, irq);
+
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val;
+
+	if (val & ICH_LR_PENDING_BIT) {
 		if (irq->config == VGIC_CONFIG_EDGE)
 			irq->pending_latch = false;
 
@@ -167,16 +378,9 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 		    model == KVM_DEV_TYPE_ARM_VGIC_V2) {
 			u32 src = ffs(irq->source);
 
-			if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n",
-					   irq->intid))
-				return;
-
-			val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
-			irq->source &= ~(1 << (src - 1));
-			if (irq->source) {
+			irq->source &= ~BIT(src - 1);
+			if (irq->source)
 				irq->pending_latch = true;
-				val |= ICH_LR_EOI;
-			}
 		}
 	}
 
@@ -189,12 +393,7 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 	if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT))
 		irq->line_level = false;
 
-	if (irq->group)
-		val |= ICH_LR_GROUP;
-
-	val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT;
-
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val;
+	irq->on_lr = true;
 }
 
 void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr)
@@ -268,7 +467,7 @@ void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 	GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, SameAsInner)	| \
 	GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable))
 
-void vgic_v3_enable(struct kvm_vcpu *vcpu)
+void vgic_v3_reset(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3;
 
@@ -294,21 +493,24 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 		vgic_v3->vgic_sre = 0;
 	}
 
-	vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 &
-					   ICH_VTR_ID_BITS_MASK) >>
-					   ICH_VTR_ID_BITS_SHIFT;
-	vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 &
-					    ICH_VTR_PRI_BITS_MASK) >>
-					    ICH_VTR_PRI_BITS_SHIFT) + 1;
+	vcpu->arch.vgic_cpu.num_id_bits = FIELD_GET(ICH_VTR_EL2_IDbits,
+						    kvm_vgic_global_state.ich_vtr_el2);
+	vcpu->arch.vgic_cpu.num_pri_bits = FIELD_GET(ICH_VTR_EL2_PRIbits,
+						     kvm_vgic_global_state.ich_vtr_el2) + 1;
+}
 
-	/* Get the show on the road... */
-	vgic_v3->vgic_hcr = ICH_HCR_EN;
-	if (group0_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TALL0;
-	if (group1_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TALL1;
-	if (common_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TC;
+void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3;
+
+	if (!vgic_is_v3(vcpu->kvm))
+		return;
+
+	/* Hide GICv3 sysreg if necessary */
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2 ||
+	    !irqchip_in_kernel(vcpu->kvm))
+		vgic_v3->vgic_hcr |= (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 |
+				      ICH_HCR_EL2_TC);
 }
 
 int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
@@ -349,14 +551,37 @@ retry:
 	if (status) {
 		/* clear consumed data */
 		val &= ~(1 << bit_nr);
-		ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
+		ret = vgic_write_guest_lock(kvm, ptr, &val, 1);
 		if (ret)
 			return ret;
 	}
 	return 0;
 }
 
-/**
+/*
+ * The deactivation of the doorbell interrupt will trigger the
+ * unmapping of the associated vPE.
+ */
+static void unmap_all_vpes(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	int i;
+
+	for (i = 0; i < dist->its_vm.nr_vpes; i++)
+		free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i));
+}
+
+static void map_all_vpes(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	int i;
+
+	for (i = 0; i < dist->its_vm.nr_vpes; i++)
+		WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i),
+						dist->its_vm.vpes[i]->irq));
+}
+
+/*
  * vgic_v3_save_pending_tables - Save the pending tables into guest RAM
  * kvm lock and all vcpu lock must be held
  */
@@ -365,13 +590,29 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct vgic_irq *irq;
 	gpa_t last_ptr = ~(gpa_t)0;
-	int ret;
+	bool vlpi_avail = false;
+	unsigned long index;
+	int ret = 0;
 	u8 val;
 
-	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+	if (unlikely(!vgic_initialized(kvm)))
+		return -ENXIO;
+
+	/*
+	 * A preparation for getting any VLPI states.
+	 * The above vgic initialized check also ensures that the allocation
+	 * and enabling of the doorbells have already been done.
+	 */
+	if (kvm_vgic_global_state.has_gicv4_1) {
+		unmap_all_vpes(kvm);
+		vlpi_avail = true;
+	}
+
+	xa_for_each(&dist->lpi_xa, index, irq) {
 		int byte_offset, bit_nr;
 		struct kvm_vcpu *vcpu;
 		gpa_t pendbase, ptr;
+		bool is_pending;
 		bool stored;
 
 		vcpu = irq->target_vcpu;
@@ -387,24 +628,35 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		if (ptr != last_ptr) {
 			ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 			if (ret)
-				return ret;
+				goto out;
 			last_ptr = ptr;
 		}
 
 		stored = val & (1U << bit_nr);
-		if (stored == irq->pending_latch)
+
+		is_pending = irq->pending_latch;
+
+		if (irq->hw && vlpi_avail)
+			vgic_v4_get_vlpi_state(irq, &is_pending);
+
+		if (stored == is_pending)
 			continue;
 
-		if (irq->pending_latch)
+		if (is_pending)
 			val |= 1 << bit_nr;
 		else
 			val &= ~(1 << bit_nr);
 
-		ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
+		ret = vgic_write_guest_lock(kvm, ptr, &val, 1);
 		if (ret)
-			return ret;
+			goto out;
 	}
-	return 0;
+
+out:
+	if (vlpi_avail)
+		map_all_vpes(kvm);
+
+	return ret;
 }
 
 /**
@@ -444,8 +696,10 @@ bool vgic_v3_check_base(struct kvm *kvm)
 		return false;
 
 	list_for_each_entry(rdreg, &d->rd_regions, list) {
-		if (rdreg->base + vgic_v3_rd_region_size(kvm, rdreg) <
-			rdreg->base)
+		size_t sz = vgic_v3_rd_region_size(kvm, rdreg);
+
+		if (vgic_check_iorange(kvm, VGIC_ADDR_UNDEF,
+				       rdreg->base, SZ_64K, sz))
 			return false;
 	}
 
@@ -497,32 +751,25 @@ int vgic_v3_map_resources(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;
-	int ret = 0;
-	int c;
-
-	if (vgic_ready(kvm))
-		goto out;
+	unsigned long c;
 
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
 		if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) {
-			kvm_debug("vcpu %d redistributor base not set\n", c);
-			ret = -ENXIO;
-			goto out;
+			kvm_debug("vcpu %ld redistributor base not set\n", c);
+			return -ENXIO;
 		}
 	}
 
 	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) {
-		kvm_err("Need to set vgic distributor addresses first\n");
-		ret = -ENXIO;
-		goto out;
+		kvm_debug("Need to set vgic distributor addresses first\n");
+		return -ENXIO;
 	}
 
 	if (!vgic_v3_check_base(kvm)) {
-		kvm_err("VGIC redist and dist frames overlap\n");
-		ret = -EINVAL;
-		goto out;
+		kvm_debug("VGIC redist and dist frames overlap\n");
+		return -EINVAL;
 	}
 
 	/*
@@ -530,50 +777,109 @@ int vgic_v3_map_resources(struct kvm *kvm)
 	 * the VGIC before we need to use it.
 	 */
 	if (!vgic_initialized(kvm)) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3);
-	if (ret) {
-		kvm_err("Unable to register VGICv3 dist MMIO regions\n");
-		goto out;
+		return -EBUSY;
 	}
 
 	if (kvm_vgic_global_state.has_gicv4_1)
 		vgic_v4_configure_vsgis(kvm);
-	dist->ready = true;
 
-out:
-	return ret;
+	return 0;
 }
 
 DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap);
+DEFINE_STATIC_KEY_FALSE(vgic_v3_has_v2_compat);
 
 static int __init early_group0_trap_cfg(char *buf)
 {
-	return strtobool(buf, &group0_trap);
+	return kstrtobool(buf, &group0_trap);
 }
 early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg);
 
 static int __init early_group1_trap_cfg(char *buf)
 {
-	return strtobool(buf, &group1_trap);
+	return kstrtobool(buf, &group1_trap);
 }
 early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg);
 
 static int __init early_common_trap_cfg(char *buf)
 {
-	return strtobool(buf, &common_trap);
+	return kstrtobool(buf, &common_trap);
 }
 early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg);
 
 static int __init early_gicv4_enable(char *buf)
 {
-	return strtobool(buf, &gicv4_enable);
+	return kstrtobool(buf, &gicv4_enable);
 }
 early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable);
 
+static const struct midr_range broken_seis[] = {
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX),
+	{},
+};
+
+static bool vgic_v3_broken_seis(void)
+{
+	return (is_kernel_in_hyp_mode() &&
+		is_midr_in_range_list(broken_seis) &&
+		(read_sysreg_s(SYS_ICH_VTR_EL2) & ICH_VTR_EL2_SEIS));
+}
+
+void noinstr kvm_compute_ich_hcr_trap_bits(struct alt_instr *alt,
+					   __le32 *origptr, __le32 *updptr,
+					   int nr_inst)
+{
+	u32 insn, oinsn, rd;
+	u64 hcr = 0;
+
+	if (cpus_have_cap(ARM64_WORKAROUND_CAVIUM_30115)) {
+		group0_trap = true;
+		group1_trap = true;
+	}
+
+	if (vgic_v3_broken_seis()) {
+		/* We know that these machines have ICH_HCR_EL2.TDIR */
+		group0_trap = true;
+		group1_trap = true;
+		dir_trap = true;
+	}
+
+	if (!cpus_have_cap(ARM64_HAS_ICH_HCR_EL2_TDIR))
+		common_trap = true;
+
+	if (group0_trap)
+		hcr |= ICH_HCR_EL2_TALL0;
+	if (group1_trap)
+		hcr |= ICH_HCR_EL2_TALL1;
+	if (common_trap)
+		hcr |= ICH_HCR_EL2_TC;
+	if (dir_trap)
+		hcr |= ICH_HCR_EL2_TDIR;
+
+	/* Compute target register */
+	oinsn = le32_to_cpu(*origptr);
+	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, oinsn);
+
+	/* movz rd, #(val & 0xffff) */
+	insn = aarch64_insn_gen_movewide(rd,
+					 (u16)hcr,
+					 0,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_ZERO);
+	*updptr = cpu_to_le32(insn);
+}
+
 /**
  * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller
  * @info:	pointer to the GIC description
@@ -583,9 +889,14 @@ early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable);
  */
 int vgic_v3_probe(const struct gic_kvm_info *info)
 {
-	u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2);
+	u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
+	bool has_v2;
+	u64 traps;
 	int ret;
 
+	has_v2 = ich_vtr_el2 >> 63;
+	ich_vtr_el2 = (u32)ich_vtr_el2;
+
 	/*
 	 * The ListRegs field is 5 bits, but there is an architectural
 	 * maximum of 16 list registers. Just ignore bit 4...
@@ -598,19 +909,21 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	if (info->has_v4) {
 		kvm_vgic_global_state.has_gicv4 = gicv4_enable;
 		kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable;
-		kvm_info("GICv4%s support %sabled\n",
+		kvm_info("GICv4%s support %s\n",
 			 kvm_vgic_global_state.has_gicv4_1 ? ".1" : "",
-			 gicv4_enable ? "en" : "dis");
+			 str_enabled_disabled(gicv4_enable));
 	}
 
+	kvm_vgic_global_state.vcpu_base = 0;
+
 	if (!info->vcpu.start) {
 		kvm_info("GICv3: no GICV resource entry\n");
-		kvm_vgic_global_state.vcpu_base = 0;
+	} else if (!has_v2) {
+		pr_warn(FW_BUG "CPU interface incapable of MMIO access\n");
 	} else if (!PAGE_ALIGNED(info->vcpu.start)) {
 		pr_warn("GICV physical address 0x%llx not page aligned\n",
 			(unsigned long long)info->vcpu.start);
-		kvm_vgic_global_state.vcpu_base = 0;
-	} else {
+	} else if (kvm_get_mode() != KVM_MODE_PROTECTED) {
 		kvm_vgic_global_state.vcpu_base = info->vcpu.start;
 		kvm_vgic_global_state.can_emulate_gicv2 = true;
 		ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2);
@@ -630,16 +943,25 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	if (kvm_vgic_global_state.vcpu_base == 0)
 		kvm_info("disabling GICv2 emulation\n");
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_30115)) {
-		group0_trap = true;
-		group1_trap = true;
+	/*
+	 * Flip the static branch if the HW supports v2, even if we're
+	 * not using it (such as in protected mode).
+	 */
+	if (has_v2)
+		static_branch_enable(&vgic_v3_has_v2_compat);
+
+	if (vgic_v3_broken_seis()) {
+		kvm_info("GICv3 with broken locally generated SEI\n");
+		kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_EL2_SEIS;
 	}
 
-	if (group0_trap || group1_trap || common_trap) {
-		kvm_info("GICv3 sysreg trapping enabled ([%s%s%s], reduced performance)\n",
-			 group0_trap ? "G0" : "",
-			 group1_trap ? "G1" : "",
-			 common_trap ? "C"  : "");
+	traps = vgic_ich_hcr_trap_bits();
+	if (traps) {
+		kvm_info("GICv3 sysreg trapping enabled ([%s%s%s%s], reduced performance)\n",
+			 (traps & ICH_HCR_EL2_TALL0) ? "G0" : "",
+			 (traps & ICH_HCR_EL2_TALL1) ? "G1" : "",
+			 (traps & ICH_HCR_EL2_TC)    ? "C"  : "",
+			 (traps & ICH_HCR_EL2_TDIR)  ? "D"  : "");
 		static_branch_enable(&vgic_v3_cpuif_trap);
 	}
 
@@ -654,15 +976,14 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	/*
-	 * 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 (likely(cpu_if->vgic_sre))
-		kvm_call_hyp(__vgic_v3_write_vmcr, cpu_if->vgic_vmcr);
+	/* If the vgic is nested, perform the full state loading */
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_load_nested(vcpu);
+		return;
+	}
 
-	kvm_call_hyp(__vgic_v3_restore_aprs, kern_hyp_va(cpu_if));
+	if (likely(!is_protected_kvm_enabled()))
+		kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
 
 	if (has_vhe())
 		__vgic_v3_activate_traps(cpu_if);
@@ -670,23 +991,18 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 	WARN_ON(vgic_v4_load(vcpu));
 }
 
-void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
-{
-	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
-
-	if (likely(cpu_if->vgic_sre))
-		cpu_if->vgic_vmcr = kvm_call_hyp_ret(__vgic_v3_read_vmcr);
-}
-
 void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	WARN_ON(vgic_v4_put(vcpu, false));
-
-	vgic_v3_vmcr_sync(vcpu);
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_put_nested(vcpu);
+		return;
+	}
 
-	kvm_call_hyp(__vgic_v3_save_aprs, kern_hyp_va(cpu_if));
+	if (likely(!is_protected_kvm_enabled()))
+		kvm_call_hyp(__vgic_v3_save_aprs, cpu_if);
+	WARN_ON(vgic_v4_put(vcpu));
 
 	if (has_vhe())
 		__vgic_v3_deactivate_traps(cpu_if);