VisionFive2 Linux kernel

diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 0d9438e9de2a..93bd59b46848 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -788,7 +788,7 @@ u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
 					  vcpu_ptimer(vcpu), TIMER_REG_CTL);
 	case KVM_REG_ARM_PTIMER_CNT:
 		return kvm_arm_timer_read(vcpu,
-					  vcpu_vtimer(vcpu), TIMER_REG_CNT);
+					  vcpu_ptimer(vcpu), TIMER_REG_CNT);
 	case KVM_REG_ARM_PTIMER_CVAL:
 		return kvm_arm_timer_read(vcpu,
 					  vcpu_ptimer(vcpu), TIMER_REG_CVAL);
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index bfdba1caf59d..376c6a74166d 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -625,6 +625,14 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu))
 			kvm_update_stolen_time(vcpu);
+
+		if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) {
+			/* The distributor enable bits were changed */
+			preempt_disable();
+			vgic_v4_put(vcpu, false);
+			vgic_v4_load(vcpu);
+			preempt_enable();
+		}
 	}
 }
 
@@ -742,9 +750,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		guest_enter_irqoff();
 
 		if (has_vhe()) {
-			kvm_arm_vhe_guest_enter();
 			ret = kvm_vcpu_run_vhe(vcpu);
-			kvm_arm_vhe_guest_exit();
 		} else {
 			ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu);
 		}
diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h
index 204d210d01c2..cc94ccc68821 100644
--- a/virt/kvm/arm/trace.h
+++ b/virt/kvm/arm/trace.h
@@ -4,6 +4,7 @@
 
 #include <kvm/arm_arch_timer.h>
 #include <linux/tracepoint.h>
+#include <asm/kvm_arm.h>
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c
index cc12fe9b2df3..b13a9e3f99dd 100644
--- a/virt/kvm/arm/vgic/vgic-debug.c
+++ b/virt/kvm/arm/vgic/vgic-debug.c
@@ -178,6 +178,8 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq,
 			    struct kvm_vcpu *vcpu)
 {
 	char *type;
+	bool pending;
+
 	if (irq->intid < VGIC_NR_SGIS)
 		type = "SGI";
 	else if (irq->intid < VGIC_NR_PRIVATE_IRQS)
@@ -190,6 +192,16 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq,
 	if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS)
 		print_header(s, irq, vcpu);
 
+	pending = irq->pending_latch;
+	if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+		int err;
+
+		err = irq_get_irqchip_state(irq->host_irq,
+					    IRQCHIP_STATE_PENDING,
+					    &pending);
+		WARN_ON_ONCE(err);
+	}
+
 	seq_printf(s, "       %s %4d "
 		      "    %2d "
 		      "%d%d%d%d%d%d%d "
@@ -201,7 +213,7 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq,
 		      "\n",
 			type, irq->intid,
 			(irq->target_vcpu) ? irq->target_vcpu->vcpu_id : -1,
-			irq->pending_latch,
+			pending,
 			irq->line_level,
 			irq->active,
 			irq->enabled,
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index ebc218840fc2..e72dcc454247 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -3,9 +3,11 @@
  * VGICv3 MMIO handling functions
  */
 
+#include <linux/bitfield.h>
 #include <linux/irqchip/arm-gic-v3.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <linux/interrupt.h>
 #include <kvm/iodev.h>
 #include <kvm/arm_vgic.h>
 
@@ -69,6 +71,8 @@ static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu,
 		if (vgic->enabled)
 			value |= GICD_CTLR_ENABLE_SS_G1;
 		value |= GICD_CTLR_ARE_NS | GICD_CTLR_DS;
+		if (vgic->nassgireq)
+			value |= GICD_CTLR_nASSGIreq;
 		break;
 	case GICD_TYPER:
 		value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS;
@@ -80,6 +84,10 @@ static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu,
 			value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19;
 		}
 		break;
+	case GICD_TYPER2:
+		if (kvm_vgic_global_state.has_gicv4_1)
+			value = GICD_TYPER2_nASSGIcap;
+		break;
 	case GICD_IIDR:
 		value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) |
 			(vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) |
@@ -97,17 +105,46 @@ static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu,
 				    unsigned long val)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	bool was_enabled = dist->enabled;
 
 	switch (addr & 0x0c) {
-	case GICD_CTLR:
+	case GICD_CTLR: {
+		bool was_enabled, is_hwsgi;
+
+		mutex_lock(&vcpu->kvm->lock);
+
+		was_enabled = dist->enabled;
+		is_hwsgi = dist->nassgireq;
+
 		dist->enabled = val & GICD_CTLR_ENABLE_SS_G1;
 
-		if (!was_enabled && dist->enabled)
+		/* Not a GICv4.1? No HW SGIs */
+		if (!kvm_vgic_global_state.has_gicv4_1)
+			val &= ~GICD_CTLR_nASSGIreq;
+
+		/* Dist stays enabled? nASSGIreq is RO */
+		if (was_enabled && dist->enabled) {
+			val &= ~GICD_CTLR_nASSGIreq;
+			val |= FIELD_PREP(GICD_CTLR_nASSGIreq, is_hwsgi);
+		}
+
+		/* Switching HW SGIs? */
+		dist->nassgireq = val & GICD_CTLR_nASSGIreq;
+		if (is_hwsgi != dist->nassgireq)
+			vgic_v4_configure_vsgis(vcpu->kvm);
+
+		if (kvm_vgic_global_state.has_gicv4_1 &&
+		    was_enabled != dist->enabled)
+			kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_RELOAD_GICv4);
+		else if (!was_enabled && dist->enabled)
 			vgic_kick_vcpus(vcpu->kvm);
+
+		mutex_unlock(&vcpu->kvm->lock);
 		break;
+	}
 	case GICD_TYPER:
+	case GICD_TYPER2:
 	case GICD_IIDR:
+		/* This is at best for documentation purposes... */
 		return;
 	}
 }
@@ -116,10 +153,22 @@ static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu,
 					   gpa_t addr, unsigned int len,
 					   unsigned long val)
 {
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
 	switch (addr & 0x0c) {
+	case GICD_TYPER2:
 	case GICD_IIDR:
 		if (val != vgic_mmio_read_v3_misc(vcpu, addr, len))
 			return -EINVAL;
+		return 0;
+	case GICD_CTLR:
+		/* Not a GICv4.1? No HW SGIs */
+		if (!kvm_vgic_global_state.has_gicv4_1)
+			val &= ~GICD_CTLR_nASSGIreq;
+
+		dist->enabled = val & GICD_CTLR_ENABLE_SS_G1;
+		dist->nassgireq = val & GICD_CTLR_nASSGIreq;
+		return 0;
 	}
 
 	vgic_mmio_write_v3_misc(vcpu, addr, len, val);
@@ -257,8 +306,18 @@ static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu,
 	 */
 	for (i = 0; i < len * 8; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+		bool state = irq->pending_latch;
 
-		if (irq->pending_latch)
+		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+			int err;
+
+			err = irq_get_irqchip_state(irq->host_irq,
+						    IRQCHIP_STATE_PENDING,
+						    &state);
+			WARN_ON(err);
+		}
+
+		if (state)
 			value |= (1U << i);
 
 		vgic_put_irq(vcpu->kvm, irq);
@@ -942,8 +1001,18 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1)
 		 * generate interrupts of either group.
 		 */
 		if (!irq->group || allow_group1) {
-			irq->pending_latch = true;
-			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
+			if (!irq->hw) {
+				irq->pending_latch = true;
+				vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
+			} else {
+				/* HW SGI? Ask the GIC to inject it */
+				int err;
+				err = irq_set_irqchip_state(irq->host_irq,
+							    IRQCHIP_STATE_PENDING,
+							    true);
+				WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
+				raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+			}
 		} else {
 			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		}
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 97fb2a40e6ba..2199302597fa 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -5,6 +5,8 @@
 
 #include <linux/bitops.h>
 #include <linux/bsearch.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <kvm/iodev.h>
@@ -59,6 +61,11 @@ unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu,
 	return value;
 }
 
+static void vgic_update_vsgi(struct vgic_irq *irq)
+{
+	WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group));
+}
+
 void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr,
 			   unsigned int len, unsigned long val)
 {
@@ -71,7 +78,12 @@ void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr,
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->group = !!(val & BIT(i));
-		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
+		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+			vgic_update_vsgi(irq);
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+		} else {
+			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
+		}
 
 		vgic_put_irq(vcpu->kvm, irq);
 	}
@@ -113,7 +125,21 @@ void vgic_mmio_write_senable(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		if (vgic_irq_is_mapped_level(irq)) {
+		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+			if (!irq->enabled) {
+				struct irq_data *data;
+
+				irq->enabled = true;
+				data = &irq_to_desc(irq->host_irq)->irq_data;
+				while (irqd_irq_disabled(data))
+					enable_irq(irq->host_irq);
+			}
+
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+			vgic_put_irq(vcpu->kvm, irq);
+
+			continue;
+		} else if (vgic_irq_is_mapped_level(irq)) {
 			bool was_high = irq->line_level;
 
 			/*
@@ -148,6 +174,8 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+		if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled)
+			disable_irq_nosync(irq->host_irq);
 
 		irq->enabled = false;
 
@@ -167,10 +195,22 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 	for (i = 0; i < len * 8; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 		unsigned long flags;
+		bool val;
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		if (irq_is_pending(irq))
-			value |= (1U << i);
+		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+			int err;
+
+			val = false;
+			err = irq_get_irqchip_state(irq->host_irq,
+						    IRQCHIP_STATE_PENDING,
+						    &val);
+			WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
+		} else {
+			val = irq_is_pending(irq);
+		}
+
+		value |= ((u32)val << i);
 		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 		vgic_put_irq(vcpu->kvm, irq);
@@ -215,6 +255,21 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 		}
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+
+		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+			/* HW SGI? Ask the GIC to inject it */
+			int err;
+			err = irq_set_irqchip_state(irq->host_irq,
+						    IRQCHIP_STATE_PENDING,
+						    true);
+			WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
+
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+			vgic_put_irq(vcpu->kvm, irq);
+
+			continue;
+		}
+
 		if (irq->hw)
 			vgic_hw_irq_spending(vcpu, irq, is_uaccess);
 		else
@@ -269,6 +324,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
+		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+			/* HW SGI? Ask the GIC to clear its pending bit */
+			int err;
+			err = irq_set_irqchip_state(irq->host_irq,
+						    IRQCHIP_STATE_PENDING,
+						    false);
+			WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
+
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+			vgic_put_irq(vcpu->kvm, irq);
+
+			continue;
+		}
+
 		if (irq->hw)
 			vgic_hw_irq_cpending(vcpu, irq, is_uaccess);
 		else
@@ -318,8 +387,15 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
-	if (irq->hw) {
+	if (irq->hw && !vgic_irq_is_sgi(irq->intid)) {
 		vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
+	} else if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+		/*
+		 * GICv4.1 VSGI feature doesn't track an active state,
+		 * so let's not kid ourselves, there is nothing we can
+		 * do here.
+		 */
+		irq->active = false;
 	} else {
 		u32 model = vcpu->kvm->arch.vgic.vgic_model;
 		u8 active_source;
@@ -493,6 +569,8 @@ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu,
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		/* Narrow the priority range to what we actually support */
 		irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS);
+		if (irq->hw && vgic_irq_is_sgi(irq->intid))
+			vgic_update_vsgi(irq);
 		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 		vgic_put_irq(vcpu->kvm, irq);
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index f45635a6f0ec..2c9fc13e2c59 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -540,6 +540,8 @@ int vgic_v3_map_resources(struct kvm *kvm)
 		goto out;
 	}
 
+	if (kvm_vgic_global_state.has_gicv4_1)
+		vgic_v4_configure_vsgis(kvm);
 	dist->ready = true;
 
 out:
@@ -595,7 +597,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	/* GICv4 support? */
 	if (info->has_v4) {
 		kvm_vgic_global_state.has_gicv4 = gicv4_enable;
-		kvm_info("GICv4 support %sabled\n",
+		kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable;
+		kvm_info("GICv4%s support %sabled\n",
+			 kvm_vgic_global_state.has_gicv4_1 ? ".1" : "",
 			 gicv4_enable ? "en" : "dis");
 	}
 
diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c
index 46f875589c47..27ac833e5ec7 100644
--- a/virt/kvm/arm/vgic/vgic-v4.c
+++ b/virt/kvm/arm/vgic/vgic-v4.c
@@ -67,10 +67,10 @@
  * it. And if we've migrated our vcpu from one CPU to another, we must
  * tell the ITS (so that the messages reach the right redistributor).
  * This is done in two steps: first issue a irq_set_affinity() on the
- * irq corresponding to the vcpu, then call its_schedule_vpe(). You
- * must be in a non-preemptible context. On exit, another call to
- * its_schedule_vpe() tells the redistributor that we're done with the
- * vcpu.
+ * irq corresponding to the vcpu, then call its_make_vpe_resident().
+ * You must be in a non-preemptible context. On exit, a call to
+ * its_make_vpe_non_resident() tells the redistributor that we're done
+ * with the vcpu.
  *
  * Finally, the doorbell handling: Each vcpu is allocated an interrupt
  * which will fire each time a VLPI is made pending whilst the vcpu is
@@ -86,7 +86,8 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 	struct kvm_vcpu *vcpu = info;
 
 	/* We got the message, no need to fire again */
-	if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
+	if (!kvm_vgic_global_state.has_gicv4_1 &&
+	    !irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
 		disable_irq_nosync(irq);
 
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
@@ -96,6 +97,104 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 	return IRQ_HANDLED;
 }
 
+static void vgic_v4_sync_sgi_config(struct its_vpe *vpe, struct vgic_irq *irq)
+{
+	vpe->sgi_config[irq->intid].enabled	= irq->enabled;
+	vpe->sgi_config[irq->intid].group 	= irq->group;
+	vpe->sgi_config[irq->intid].priority	= irq->priority;
+}
+
+static void vgic_v4_enable_vsgis(struct kvm_vcpu *vcpu)
+{
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+	int i;
+
+	/*
+	 * With GICv4.1, every virtual SGI can be directly injected. So
+	 * let's pretend that they are HW interrupts, tied to a host
+	 * IRQ. The SGI code will do its magic.
+	 */
+	for (i = 0; i < VGIC_NR_SGIS; i++) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i);
+		struct irq_desc *desc;
+		unsigned long flags;
+		int ret;
+
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+
+		if (irq->hw)
+			goto unlock;
+
+		irq->hw = true;
+		irq->host_irq = irq_find_mapping(vpe->sgi_domain, i);
+
+		/* Transfer the full irq state to the vPE */
+		vgic_v4_sync_sgi_config(vpe, irq);
+		desc = irq_to_desc(irq->host_irq);
+		ret = irq_domain_activate_irq(irq_desc_get_irq_data(desc),
+					      false);
+		if (!WARN_ON(ret)) {
+			/* Transfer pending state */
+			ret = irq_set_irqchip_state(irq->host_irq,
+						    IRQCHIP_STATE_PENDING,
+						    irq->pending_latch);
+			WARN_ON(ret);
+			irq->pending_latch = false;
+		}
+	unlock:
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+}
+
+static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu)
+{
+	int i;
+
+	for (i = 0; i < VGIC_NR_SGIS; i++) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i);
+		struct irq_desc *desc;
+		unsigned long flags;
+		int ret;
+
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+
+		if (!irq->hw)
+			goto unlock;
+
+		irq->hw = false;
+		ret = irq_get_irqchip_state(irq->host_irq,
+					    IRQCHIP_STATE_PENDING,
+					    &irq->pending_latch);
+		WARN_ON(ret);
+
+		desc = irq_to_desc(irq->host_irq);
+		irq_domain_deactivate_irq(irq_desc_get_irq_data(desc));
+	unlock:
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+}
+
+/* Must be called with the kvm lock held */
+void vgic_v4_configure_vsgis(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_arm_halt_guest(kvm);
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (dist->nassgireq)
+			vgic_v4_enable_vsgis(vcpu);
+		else
+			vgic_v4_disable_vsgis(vcpu);
+	}
+
+	kvm_arm_resume_guest(kvm);
+}
+
 /**
  * vgic_v4_init - Initialize the GICv4 data structures
  * @kvm:	Pointer to the VM being initialized
@@ -140,6 +239,7 @@ int vgic_v4_init(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		int irq = dist->its_vm.vpes[i]->irq;
+		unsigned long irq_flags = DB_IRQ_FLAGS;
 
 		/*
 		 * Don't automatically enable the doorbell, as we're
@@ -147,8 +247,14 @@ int vgic_v4_init(struct kvm *kvm)
 		 * blocked. Also disable the lazy disabling, as the
 		 * doorbell could kick us out of the guest too
 		 * early...
+		 *
+		 * On GICv4.1, the doorbell is managed in HW and must
+		 * be left enabled.
 		 */
-		irq_set_status_flags(irq, DB_IRQ_FLAGS);
+		if (kvm_vgic_global_state.has_gicv4_1)
+			irq_flags &= ~IRQ_NOAUTOEN;
+		irq_set_status_flags(irq, irq_flags);
+
 		ret = request_irq(irq, vgic_v4_doorbell_handler,
 				  0, "vcpu", vcpu);
 		if (ret) {
@@ -199,19 +305,11 @@ void vgic_v4_teardown(struct kvm *kvm)
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
 {
 	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
-	struct irq_desc *desc = irq_to_desc(vpe->irq);
 
 	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	/*
-	 * If blocking, a doorbell is required. Undo the nested
-	 * disable_irq() calls...
-	 */
-	while (need_db && irqd_irq_disabled(&desc->irq_data))
-		enable_irq(vpe->irq);
-
-	return its_schedule_vpe(vpe, false);
+	return its_make_vpe_non_resident(vpe, need_db);
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)
@@ -232,18 +330,19 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	/* Disabled the doorbell, as we're about to enter the guest */
-	disable_irq_nosync(vpe->irq);
-
-	err = its_schedule_vpe(vpe, true);
+	err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled);
 	if (err)
 		return err;
 
 	/*
 	 * Now that the VPE is resident, let's get rid of a potential
-	 * doorbell interrupt that would still be pending.
+	 * doorbell interrupt that would still be pending. This is a
+	 * GICv4.0 only "feature"...
 	 */
-	return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
+	if (!kvm_vgic_global_state.has_gicv4_1)
+		err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
+
+	return err;
 }
 
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index c7fefd6b1c80..769e4802645e 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -316,5 +316,6 @@ void vgic_its_invalidate_cache(struct kvm *kvm);
 bool vgic_supports_direct_msis(struct kvm *kvm);
 int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);
+void vgic_v4_configure_vsgis(struct kvm *kvm);
 
 #endif