1 files changed, 300 insertions, 388 deletions

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 067f8e3f5a0d..a34c5c3b164e 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -18,6 +18,7 @@
 #include <linux/hashtable.h>
 #include <linux/amd-iommu.h>
 #include <linux/kvm_host.h>
+#include <linux/kvm_irqfd.h>
 
 #include <asm/irq_remapping.h>
 #include <asm/msr.h>
@@ -29,36 +30,39 @@
 #include "svm.h"
 
 /*
- * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID,
- * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry
- * if an interrupt can't be delivered, e.g. because the vCPU isn't running.
+ * Encode the arbitrary VM ID and the vCPU's _index_ into the GATag so that
+ * KVM can retrieve the correct vCPU from a GALog entry if an interrupt can't
+ * be delivered, e.g. because the vCPU isn't running.  Use the vCPU's index
+ * instead of its ID (a.k.a. its default APIC ID), as KVM is guaranteed a fast
+ * lookup on the index, where as vCPUs whose index doesn't match their ID need
+ * to walk the entire xarray of vCPUs in the worst case scenario.
  *
- * For the vCPU ID, use however many bits are currently allowed for the max
+ * For the vCPU index, use however many bits are currently allowed for the max
  * guest physical APIC ID (limited by the size of the physical ID table), and
  * use whatever bits remain to assign arbitrary AVIC IDs to VMs.  Note, the
  * size of the GATag is defined by hardware (32 bits), but is an opaque value
  * as far as hardware is concerned.
  */
-#define AVIC_VCPU_ID_MASK		AVIC_PHYSICAL_MAX_INDEX_MASK
+#define AVIC_VCPU_IDX_MASK		AVIC_PHYSICAL_MAX_INDEX_MASK
 
 #define AVIC_VM_ID_SHIFT		HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK)
 #define AVIC_VM_ID_MASK			(GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT)
 
 #define AVIC_GATAG_TO_VMID(x)		((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK)
-#define AVIC_GATAG_TO_VCPUID(x)		(x & AVIC_VCPU_ID_MASK)
+#define AVIC_GATAG_TO_VCPUIDX(x)	(x & AVIC_VCPU_IDX_MASK)
 
-#define __AVIC_GATAG(vm_id, vcpu_id)	((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \
-					 ((vcpu_id) & AVIC_VCPU_ID_MASK))
-#define AVIC_GATAG(vm_id, vcpu_id)					\
+#define __AVIC_GATAG(vm_id, vcpu_idx)	((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \
+					 ((vcpu_idx) & AVIC_VCPU_IDX_MASK))
+#define AVIC_GATAG(vm_id, vcpu_idx)					\
 ({									\
-	u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_id);			\
+	u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_idx);			\
 									\
-	WARN_ON_ONCE(AVIC_GATAG_TO_VCPUID(ga_tag) != (vcpu_id));	\
+	WARN_ON_ONCE(AVIC_GATAG_TO_VCPUIDX(ga_tag) != (vcpu_idx));	\
 	WARN_ON_ONCE(AVIC_GATAG_TO_VMID(ga_tag) != (vm_id));		\
 	ga_tag;								\
 })
 
-static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u);
+static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_IDX_MASK) == -1u);
 
 static bool force_avic;
 module_param_unsafe(force_avic, bool, 0444);
@@ -75,14 +79,6 @@ static bool next_vm_id_wrapped = 0;
 static DEFINE_SPINLOCK(svm_vm_data_hash_lock);
 bool x2avic_enabled;
 
-/*
- * This is a wrapper of struct amd_iommu_ir_data.
- */
-struct amd_svm_iommu_ir {
-	struct list_head node;	/* Used by SVM for per-vcpu ir_list */
-	void *data;		/* Storing pointer to struct amd_ir_data */
-};
-
 static void avic_activate_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -147,16 +143,16 @@ int avic_ga_log_notifier(u32 ga_tag)
 	struct kvm_svm *kvm_svm;
 	struct kvm_vcpu *vcpu = NULL;
 	u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag);
-	u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag);
+	u32 vcpu_idx = AVIC_GATAG_TO_VCPUIDX(ga_tag);
 
-	pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id);
-	trace_kvm_avic_ga_log(vm_id, vcpu_id);
+	pr_debug("SVM: %s: vm_id=%#x, vcpu_idx=%#x\n", __func__, vm_id, vcpu_idx);
+	trace_kvm_avic_ga_log(vm_id, vcpu_idx);
 
 	spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
 	hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) {
 		if (kvm_svm->avic_vm_id != vm_id)
 			continue;
-		vcpu = kvm_get_vcpu_by_id(&kvm_svm->kvm, vcpu_id);
+		vcpu = kvm_get_vcpu(&kvm_svm->kvm, vcpu_idx);
 		break;
 	}
 	spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
@@ -180,10 +176,8 @@ void avic_vm_destroy(struct kvm *kvm)
 	if (!enable_apicv)
 		return;
 
-	if (kvm_svm->avic_logical_id_table_page)
-		__free_page(kvm_svm->avic_logical_id_table_page);
-	if (kvm_svm->avic_physical_id_table_page)
-		__free_page(kvm_svm->avic_physical_id_table_page);
+	free_page((unsigned long)kvm_svm->avic_logical_id_table);
+	free_page((unsigned long)kvm_svm->avic_physical_id_table);
 
 	spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
 	hash_del(&kvm_svm->hnode);
@@ -196,27 +190,19 @@ int avic_vm_init(struct kvm *kvm)
 	int err = -ENOMEM;
 	struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
 	struct kvm_svm *k2;
-	struct page *p_page;
-	struct page *l_page;
 	u32 vm_id;
 
 	if (!enable_apicv)
 		return 0;
 
-	/* Allocating physical APIC ID table (4KB) */
-	p_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
-	if (!p_page)
+	kvm_svm->avic_physical_id_table = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+	if (!kvm_svm->avic_physical_id_table)
 		goto free_avic;
 
-	kvm_svm->avic_physical_id_table_page = p_page;
-
-	/* Allocating logical APIC ID table (4KB) */
-	l_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
-	if (!l_page)
+	kvm_svm->avic_logical_id_table = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+	if (!kvm_svm->avic_logical_id_table)
 		goto free_avic;
 
-	kvm_svm->avic_logical_id_table_page = l_page;
-
 	spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
  again:
 	vm_id = next_vm_id = (next_vm_id + 1) & AVIC_VM_ID_MASK;
@@ -242,17 +228,19 @@ free_avic:
 	return err;
 }
 
+static phys_addr_t avic_get_backing_page_address(struct vcpu_svm *svm)
+{
+	return __sme_set(__pa(svm->vcpu.arch.apic->regs));
+}
+
 void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
 {
 	struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm);
-	phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page));
-	phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page));
-	phys_addr_t ppa = __sme_set(page_to_phys(kvm_svm->avic_physical_id_table_page));
 
-	vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK;
-	vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK;
-	vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK;
-	vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE & VMCB_AVIC_APIC_BAR_MASK;
+	vmcb->control.avic_backing_page = avic_get_backing_page_address(svm);
+	vmcb->control.avic_logical_id = __sme_set(__pa(kvm_svm->avic_logical_id_table));
+	vmcb->control.avic_physical_id = __sme_set(__pa(kvm_svm->avic_physical_id_table));
+	vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE;
 
 	if (kvm_apicv_activated(svm->vcpu.kvm))
 		avic_activate_vmcb(svm);
@@ -260,32 +248,31 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
 		avic_deactivate_vmcb(svm);
 }
 
-static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
-				       unsigned int index)
-{
-	u64 *avic_physical_id_table;
-	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
-
-	if ((!x2avic_enabled && index > AVIC_MAX_PHYSICAL_ID) ||
-	    (index > X2AVIC_MAX_PHYSICAL_ID))
-		return NULL;
-
-	avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page);
-
-	return &avic_physical_id_table[index];
-}
-
 static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 {
-	u64 *entry, new_entry;
-	int id = vcpu->vcpu_id;
+	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
 	struct vcpu_svm *svm = to_svm(vcpu);
+	u32 id = vcpu->vcpu_id;
+	u64 new_entry;
 
+	/*
+	 * Inhibit AVIC if the vCPU ID is bigger than what is supported by AVIC
+	 * hardware.  Immediately clear apicv_active, i.e. don't wait until the
+	 * KVM_REQ_APICV_UPDATE request is processed on the first KVM_RUN, as
+	 * avic_vcpu_load() expects to be called if and only if the vCPU has
+	 * fully initialized AVIC.
+	 */
 	if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) ||
-	    (id > X2AVIC_MAX_PHYSICAL_ID))
-		return -EINVAL;
+	    (id > X2AVIC_MAX_PHYSICAL_ID)) {
+		kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG);
+		vcpu->arch.apic->apicv_active = false;
+		return 0;
+	}
+
+	BUILD_BUG_ON((AVIC_MAX_PHYSICAL_ID + 1) * sizeof(new_entry) > PAGE_SIZE ||
+		     (X2AVIC_MAX_PHYSICAL_ID + 1) * sizeof(new_entry) > PAGE_SIZE);
 
-	if (!vcpu->arch.apic->regs)
+	if (WARN_ON_ONCE(!vcpu->arch.apic->regs))
 		return -EINVAL;
 
 	if (kvm_apicv_activated(vcpu->kvm)) {
@@ -302,19 +289,21 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
-	svm->avic_backing_page = virt_to_page(vcpu->arch.apic->regs);
+	/* Note, fls64() returns the bit position, +1. */
+	BUILD_BUG_ON(__PHYSICAL_MASK_SHIFT >
+		     fls64(AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK));
 
 	/* Setting AVIC backing page address in the phy APIC ID table */
-	entry = avic_get_physical_id_entry(vcpu, id);
-	if (!entry)
-		return -EINVAL;
+	new_entry = avic_get_backing_page_address(svm) |
+		    AVIC_PHYSICAL_ID_ENTRY_VALID_MASK;
+	svm->avic_physical_id_entry = new_entry;
 
-	new_entry = __sme_set((page_to_phys(svm->avic_backing_page) &
-			      AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
-			      AVIC_PHYSICAL_ID_ENTRY_VALID_MASK);
-	WRITE_ONCE(*entry, new_entry);
-
-	svm->avic_physical_id_cache = entry;
+	/*
+	 * Initialize the real table, as vCPUs must have a valid entry in order
+	 * for broadcast IPIs to function correctly (broadcast IPIs ignore
+	 * invalid entries, i.e. aren't guaranteed to generate a VM-Exit).
+	 */
+	WRITE_ONCE(kvm_svm->avic_physical_id_table[id], new_entry);
 
 	return 0;
 }
@@ -448,7 +437,7 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source
 		if (apic_x2apic_mode(source))
 			avic_logical_id_table = NULL;
 		else
-			avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page);
+			avic_logical_id_table = kvm_svm->avic_logical_id_table;
 
 		/*
 		 * AVIC is inhibited if vCPUs aren't mapped 1:1 with logical
@@ -550,7 +539,6 @@ unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu)
 static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
 {
 	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
-	u32 *logical_apic_id_table;
 	u32 cluster, index;
 
 	ldr = GET_APIC_LOGICAL_ID(ldr);
@@ -571,9 +559,7 @@ static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
 		return NULL;
 	index += (cluster << 2);
 
-	logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page);
-
-	return &logical_apic_id_table[index];
+	return &kvm_svm->avic_logical_id_table[index];
 }
 
 static void avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr)
@@ -722,6 +708,9 @@ int avic_init_vcpu(struct vcpu_svm *svm)
 	int ret;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
+	INIT_LIST_HEAD(&svm->ir_list);
+	spin_lock_init(&svm->ir_list_lock);
+
 	if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm))
 		return 0;
 
@@ -729,8 +718,6 @@ int avic_init_vcpu(struct vcpu_svm *svm)
 	if (ret)
 		return ret;
 
-	INIT_LIST_HEAD(&svm->ir_list);
-	spin_lock_init(&svm->ir_list_lock);
 	svm->dfr_reg = APIC_DFR_FLAT;
 
 	return ret;
@@ -742,316 +729,161 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 	avic_handle_ldr_update(vcpu);
 }
 
-static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
+static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd)
 {
-	int ret = 0;
+	struct kvm_vcpu *vcpu = irqfd->irq_bypass_vcpu;
 	unsigned long flags;
-	struct amd_svm_iommu_ir *ir;
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm))
-		return 0;
 
-	/*
-	 * Here, we go through the per-vcpu ir_list to update all existing
-	 * interrupt remapping table entry targeting this vcpu.
-	 */
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
-
-	if (list_empty(&svm->ir_list))
-		goto out;
+	if (!vcpu)
+		return;
 
-	list_for_each_entry(ir, &svm->ir_list, node) {
-		if (activate)
-			ret = amd_iommu_activate_guest_mode(ir->data);
-		else
-			ret = amd_iommu_deactivate_guest_mode(ir->data);
-		if (ret)
-			break;
-	}
-out:
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-	return ret;
+	spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags);
+	list_del(&irqfd->vcpu_list);
+	spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags);
 }
 
-static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+			unsigned int host_irq, uint32_t guest_irq,
+			struct kvm_vcpu *vcpu, u32 vector)
 {
-	unsigned long flags;
-	struct amd_svm_iommu_ir *cur;
-
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
-	list_for_each_entry(cur, &svm->ir_list, node) {
-		if (cur->data != pi->ir_data)
-			continue;
-		list_del(&cur->node);
-		kfree(cur);
-		break;
-	}
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-}
-
-static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
-{
-	int ret = 0;
-	unsigned long flags;
-	struct amd_svm_iommu_ir *ir;
-	u64 entry;
-
-	if (WARN_ON_ONCE(!pi->ir_data))
-		return -EINVAL;
-
-	/**
-	 * In some cases, the existing irte is updated and re-set,
-	 * so we need to check here if it's already been * added
-	 * to the ir_list.
-	 */
-	if (pi->prev_ga_tag) {
-		struct kvm *kvm = svm->vcpu.kvm;
-		u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
-		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
-		struct vcpu_svm *prev_svm;
-
-		if (!prev_vcpu) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		prev_svm = to_svm(prev_vcpu);
-		svm_ir_list_del(prev_svm, pi);
-	}
-
-	/**
-	 * Allocating new amd_iommu_pi_data, which will get
-	 * add to the per-vcpu ir_list.
-	 */
-	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
-	if (!ir) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	ir->data = pi->ir_data;
-
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
-
 	/*
-	 * Update the target pCPU for IOMMU doorbells if the vCPU is running.
-	 * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM
-	 * will update the pCPU info when the vCPU awkened and/or scheduled in.
-	 * See also avic_vcpu_load().
+	 * If the IRQ was affined to a different vCPU, remove the IRTE metadata
+	 * from the *previous* vCPU's list.
 	 */
-	entry = READ_ONCE(*(svm->avic_physical_id_cache));
-	if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
-		amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
-				    true, pi->ir_data);
-
-	list_add(&ir->node, &svm->ir_list);
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-out:
-	return ret;
-}
+	svm_ir_list_del(irqfd);
 
-/*
- * Note:
- * The HW cannot support posting multicast/broadcast
- * interrupts to a vCPU. So, we still use legacy interrupt
- * remapping for these kind of interrupts.
- *
- * For lowest-priority interrupts, we only support
- * those with single CPU as the destination, e.g. user
- * configures the interrupts via /proc/irq or uses
- * irqbalance to make the interrupts single-CPU.
- */
-static int
-get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
-		 struct vcpu_data *vcpu_info, struct vcpu_svm **svm)
-{
-	struct kvm_lapic_irq irq;
-	struct kvm_vcpu *vcpu = NULL;
-
-	kvm_set_msi_irq(kvm, e, &irq);
-
-	if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
-	    !kvm_irq_is_postable(&irq)) {
-		pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n",
-			 __func__, irq.vector);
-		return -1;
-	}
-
-	pr_debug("SVM: %s: use GA mode for irq %u\n", __func__,
-		 irq.vector);
-	*svm = to_svm(vcpu);
-	vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page));
-	vcpu_info->vector = irq.vector;
-
-	return 0;
-}
-
-/*
- * avic_pi_update_irte - set IRTE for Posted-Interrupts
- *
- * @kvm: kvm
- * @host_irq: host irq of the interrupt
- * @guest_irq: gsi of the interrupt
- * @set: set or unset PI
- * returns 0 on success, < 0 on failure
- */
-int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
-			uint32_t guest_irq, bool set)
-{
-	struct kvm_kernel_irq_routing_entry *e;
-	struct kvm_irq_routing_table *irq_rt;
-	bool enable_remapped_mode = true;
-	int idx, ret = 0;
-
-	if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
-		return 0;
-
-	pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
-		 __func__, host_irq, guest_irq, set);
-
-	idx = srcu_read_lock(&kvm->irq_srcu);
-	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-
-	if (guest_irq >= irq_rt->nr_rt_entries ||
-		hlist_empty(&irq_rt->map[guest_irq])) {
-		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
-			     guest_irq, irq_rt->nr_rt_entries);
-		goto out;
-	}
-
-	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
-		struct vcpu_data vcpu_info;
-		struct vcpu_svm *svm = NULL;
+	if (vcpu) {
+		/*
+		 * Try to enable guest_mode in IRTE, unless AVIC is inhibited,
+		 * in which case configure the IRTE for legacy mode, but track
+		 * the IRTE metadata so that it can be converted to guest mode
+		 * if AVIC is enabled/uninhibited in the future.
+		 */
+		struct amd_iommu_pi_data pi_data = {
+			.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
+					     vcpu->vcpu_idx),
+			.is_guest_mode = kvm_vcpu_apicv_active(vcpu),
+			.vapic_addr = avic_get_backing_page_address(to_svm(vcpu)),
+			.vector = vector,
+		};
+		struct vcpu_svm *svm = to_svm(vcpu);
+		u64 entry;
+		int ret;
 
-		if (e->type != KVM_IRQ_ROUTING_MSI)
-			continue;
+		/*
+		 * Prevent the vCPU from being scheduled out or migrated until
+		 * the IRTE is updated and its metadata has been added to the
+		 * list of IRQs being posted to the vCPU, to ensure the IRTE
+		 * isn't programmed with stale pCPU/IsRunning information.
+		 */
+		guard(spinlock_irqsave)(&svm->ir_list_lock);
 
-		/**
-		 * Here, we setup with legacy mode in the following cases:
-		 * 1. When cannot target interrupt to a specific vcpu.
-		 * 2. Unsetting posted interrupt.
-		 * 3. APIC virtualization is disabled for the vcpu.
-		 * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
+		/*
+		 * Update the target pCPU for IOMMU doorbells if the vCPU is
+		 * running.  If the vCPU is NOT running, i.e. is blocking or
+		 * scheduled out, KVM will update the pCPU info when the vCPU
+		 * is awakened and/or scheduled in.  See also avic_vcpu_load().
 		 */
-		if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
-		    kvm_vcpu_apicv_active(&svm->vcpu)) {
-			struct amd_iommu_pi_data pi;
-
-			enable_remapped_mode = false;
-
-			/* Try to enable guest_mode in IRTE */
-			pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
-					    AVIC_HPA_MASK);
-			pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
-						     svm->vcpu.vcpu_id);
-			pi.is_guest_mode = true;
-			pi.vcpu_data = &vcpu_info;
-			ret = irq_set_vcpu_affinity(host_irq, &pi);
-
-			/**
-			 * Here, we successfully setting up vcpu affinity in
-			 * IOMMU guest mode. Now, we need to store the posted
-			 * interrupt information in a per-vcpu ir_list so that
-			 * we can reference to them directly when we update vcpu
-			 * scheduling information in IOMMU irte.
-			 */
-			if (!ret && pi.is_guest_mode)
-				svm_ir_list_add(svm, &pi);
+		entry = svm->avic_physical_id_entry;
+		if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) {
+			pi_data.cpu = entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
+		} else {
+			pi_data.cpu = -1;
+			pi_data.ga_log_intr = entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR;
 		}
 
-		if (!ret && svm) {
-			trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
-						 e->gsi, vcpu_info.vector,
-						 vcpu_info.pi_desc_addr, set);
-		}
+		ret = irq_set_vcpu_affinity(host_irq, &pi_data);
+		if (ret)
+			return ret;
 
-		if (ret < 0) {
-			pr_err("%s: failed to update PI IRTE\n", __func__);
-			goto out;
+		/*
+		 * Revert to legacy mode if the IOMMU didn't provide metadata
+		 * for the IRTE, which KVM needs to keep the IRTE up-to-date,
+		 * e.g. if the vCPU is migrated or AVIC is disabled.
+		 */
+		if (WARN_ON_ONCE(!pi_data.ir_data)) {
+			irq_set_vcpu_affinity(host_irq, NULL);
+			return -EIO;
 		}
-	}
 
-	ret = 0;
-	if (enable_remapped_mode) {
-		/* Use legacy mode in IRTE */
-		struct amd_iommu_pi_data pi;
+		irqfd->irq_bypass_data = pi_data.ir_data;
+		list_add(&irqfd->vcpu_list, &svm->ir_list);
+		return 0;
+	}
+	return irq_set_vcpu_affinity(host_irq, NULL);
+}
 
-		/**
-		 * Here, pi is used to:
-		 * - Tell IOMMU to use legacy mode for this interrupt.
-		 * - Retrieve ga_tag of prior interrupt remapping data.
-		 */
-		pi.prev_ga_tag = 0;
-		pi.is_guest_mode = false;
-		ret = irq_set_vcpu_affinity(host_irq, &pi);
+enum avic_vcpu_action {
+	/*
+	 * There is no need to differentiate between activate and deactivate,
+	 * as KVM only refreshes AVIC state when the vCPU is scheduled in and
+	 * isn't blocking, i.e. the pCPU must always be (in)valid when AVIC is
+	 * being (de)activated.
+	 */
+	AVIC_TOGGLE_ON_OFF	= BIT(0),
+	AVIC_ACTIVATE		= AVIC_TOGGLE_ON_OFF,
+	AVIC_DEACTIVATE		= AVIC_TOGGLE_ON_OFF,
 
-		/**
-		 * Check if the posted interrupt was previously
-		 * setup with the guest_mode by checking if the ga_tag
-		 * was cached. If so, we need to clean up the per-vcpu
-		 * ir_list.
-		 */
-		if (!ret && pi.prev_ga_tag) {
-			int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
-			struct kvm_vcpu *vcpu;
+	/*
+	 * No unique action is required to deal with a vCPU that stops/starts
+	 * running.  A vCPU that starts running by definition stops blocking as
+	 * well, and a vCPU that stops running can't have been blocking, i.e.
+	 * doesn't need to toggle GALogIntr.
+	 */
+	AVIC_START_RUNNING	= 0,
+	AVIC_STOP_RUNNING	= 0,
 
-			vcpu = kvm_get_vcpu_by_id(kvm, id);
-			if (vcpu)
-				svm_ir_list_del(to_svm(vcpu), &pi);
-		}
-	}
-out:
-	srcu_read_unlock(&kvm->irq_srcu, idx);
-	return ret;
-}
+	/*
+	 * When a vCPU starts blocking, KVM needs to set the GALogIntr flag
+	 * int all associated IRTEs so that KVM can wake the vCPU if an IRQ is
+	 * sent to the vCPU.
+	 */
+	AVIC_START_BLOCKING	= BIT(1),
+};
 
-static inline int
-avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
+static void avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu,
+					    enum avic_vcpu_action action)
 {
-	int ret = 0;
-	struct amd_svm_iommu_ir *ir;
+	bool ga_log_intr = (action & AVIC_START_BLOCKING);
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_kernel_irqfd *irqfd;
 
 	lockdep_assert_held(&svm->ir_list_lock);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm))
-		return 0;
-
 	/*
 	 * Here, we go through the per-vcpu ir_list to update all existing
 	 * interrupt remapping table entry targeting this vcpu.
 	 */
 	if (list_empty(&svm->ir_list))
-		return 0;
+		return;
 
-	list_for_each_entry(ir, &svm->ir_list, node) {
-		ret = amd_iommu_update_ga(cpu, r, ir->data);
-		if (ret)
-			return ret;
+	list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
+		void *data = irqfd->irq_bypass_data;
+
+		if (!(action & AVIC_TOGGLE_ON_OFF))
+			WARN_ON_ONCE(amd_iommu_update_ga(data, cpu, ga_log_intr));
+		else if (cpu >= 0)
+			WARN_ON_ONCE(amd_iommu_activate_guest_mode(data, cpu, ga_log_intr));
+		else
+			WARN_ON_ONCE(amd_iommu_deactivate_guest_mode(data));
 	}
-	return 0;
 }
 
-void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu,
+			     enum avic_vcpu_action action)
 {
-	u64 entry;
+	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 	unsigned long flags;
+	u64 entry;
 
 	lockdep_assert_preemption_disabled();
 
 	if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
 		return;
 
-	/*
-	 * No need to update anything if the vCPU is blocking, i.e. if the vCPU
-	 * is being scheduled in after being preempted.  The CPU entries in the
-	 * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'.
-	 * If the vCPU was migrated, its new CPU value will be stuffed when the
-	 * vCPU unblocks.
-	 */
-	if (kvm_vcpu_is_blocking(vcpu))
+	if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= PAGE_SIZE))
 		return;
 
 	/*
@@ -1063,38 +895,57 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	 */
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
-	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	entry = svm->avic_physical_id_entry;
 	WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
 
-	entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
+	entry &= ~(AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK |
+		   AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR);
 	entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK);
 	entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 
-	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
-	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
+	svm->avic_physical_id_entry = entry;
+
+	/*
+	 * If IPI virtualization is disabled, clear IsRunning when updating the
+	 * actual Physical ID table, so that the CPU never sees IsRunning=1.
+	 * Keep the APIC ID up-to-date in the entry to minimize the chances of
+	 * things going sideways if hardware peeks at the ID.
+	 */
+	if (!enable_ipiv)
+		entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+
+	WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry);
+
+	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, action);
 
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
 
-void avic_vcpu_put(struct kvm_vcpu *vcpu)
+void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	u64 entry;
+	/*
+	 * No need to update anything if the vCPU is blocking, i.e. if the vCPU
+	 * is being scheduled in after being preempted.  The CPU entries in the
+	 * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'.
+	 * If the vCPU was migrated, its new CPU value will be stuffed when the
+	 * vCPU unblocks.
+	 */
+	if (kvm_vcpu_is_blocking(vcpu))
+		return;
+
+	__avic_vcpu_load(vcpu, cpu, AVIC_START_RUNNING);
+}
+
+static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action)
+{
+	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
 	struct vcpu_svm *svm = to_svm(vcpu);
 	unsigned long flags;
+	u64 entry = svm->avic_physical_id_entry;
 
 	lockdep_assert_preemption_disabled();
 
-	/*
-	 * Note, reading the Physical ID entry outside of ir_list_lock is safe
-	 * as only the pCPU that has loaded (or is loading) the vCPU is allowed
-	 * to modify the entry, and preemption is disabled.  I.e. the vCPU
-	 * can't be scheduled out and thus avic_vcpu_{put,load}() can't run
-	 * recursively.
-	 */
-	entry = READ_ONCE(*(svm->avic_physical_id_cache));
-
-	/* Nothing to do if IsRunning == '0' due to vCPU blocking. */
-	if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
+	if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= PAGE_SIZE))
 		return;
 
 	/*
@@ -1107,13 +958,62 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	 */
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
-	avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+	avic_update_iommu_vcpu_affinity(vcpu, -1, action);
+
+	WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR);
 
+	/*
+	 * Keep the previous APIC ID in the entry so that a rogue doorbell from
+	 * hardware is at least restricted to a CPU associated with the vCPU.
+	 */
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
-	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+
+	if (enable_ipiv)
+		WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry);
+
+	/*
+	 * Note!  Don't set AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR in the table as
+	 * it's a synthetic flag that usurps an unused should-be-zero bit.
+	 */
+	if (action & AVIC_START_BLOCKING)
+		entry |= AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR;
+
+	svm->avic_physical_id_entry = entry;
 
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+}
+
+void avic_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Note, reading the Physical ID entry outside of ir_list_lock is safe
+	 * as only the pCPU that has loaded (or is loading) the vCPU is allowed
+	 * to modify the entry, and preemption is disabled.  I.e. the vCPU
+	 * can't be scheduled out and thus avic_vcpu_{put,load}() can't run
+	 * recursively.
+	 */
+	u64 entry = to_svm(vcpu)->avic_physical_id_entry;
+
+	/*
+	 * Nothing to do if IsRunning == '0' due to vCPU blocking, i.e. if the
+	 * vCPU is preempted while its in the process of blocking.  WARN if the
+	 * vCPU wasn't running and isn't blocking, KVM shouldn't attempt to put
+	 * the AVIC if it wasn't previously loaded.
+	 */
+	if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) {
+		if (WARN_ON_ONCE(!kvm_vcpu_is_blocking(vcpu)))
+			return;
 
+		/*
+		 * The vCPU was preempted while blocking, ensure its IRTEs are
+		 * configured to generate GA Log Interrupts.
+		 */
+		if (!(WARN_ON_ONCE(!(entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR))))
+			return;
+	}
+
+	__avic_vcpu_put(vcpu, kvm_vcpu_is_blocking(vcpu) ? AVIC_START_BLOCKING :
+							   AVIC_STOP_RUNNING);
 }
 
 void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu)
@@ -1142,19 +1042,18 @@ void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu)
 
 void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
-	bool activated = kvm_vcpu_apicv_active(vcpu);
-
 	if (!enable_apicv)
 		return;
 
+	/* APICv should only be toggled on/off while the vCPU is running. */
+	WARN_ON_ONCE(kvm_vcpu_is_blocking(vcpu));
+
 	avic_refresh_virtual_apic_mode(vcpu);
 
-	if (activated)
-		avic_vcpu_load(vcpu, vcpu->cpu);
+	if (kvm_vcpu_apicv_active(vcpu))
+		__avic_vcpu_load(vcpu, vcpu->cpu, AVIC_ACTIVATE);
 	else
-		avic_vcpu_put(vcpu);
-
-	avic_set_pi_irte_mode(vcpu, activated);
+		__avic_vcpu_put(vcpu, AVIC_DEACTIVATE);
 }
 
 void avic_vcpu_blocking(struct kvm_vcpu *vcpu)
@@ -1162,20 +1061,25 @@ void avic_vcpu_blocking(struct kvm_vcpu *vcpu)
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
-       /*
-        * Unload the AVIC when the vCPU is about to block, _before_
-        * the vCPU actually blocks.
-        *
-        * Any IRQs that arrive before IsRunning=0 will not cause an
-        * incomplete IPI vmexit on the source, therefore vIRR will also
-        * be checked by kvm_vcpu_check_block() before blocking.  The
-        * memory barrier implicit in set_current_state orders writing
-        * IsRunning=0 before reading the vIRR.  The processor needs a
-        * matching memory barrier on interrupt delivery between writing
-        * IRR and reading IsRunning; the lack of this barrier might be
-        * the cause of errata #1235).
-        */
-	avic_vcpu_put(vcpu);
+	/*
+	 * Unload the AVIC when the vCPU is about to block, _before_ the vCPU
+	 * actually blocks.
+	 *
+	 * Note, any IRQs that arrive before IsRunning=0 will not cause an
+	 * incomplete IPI vmexit on the source; kvm_vcpu_check_block() handles
+	 * this by checking vIRR one last time before blocking.  The memory
+	 * barrier implicit in set_current_state orders writing IsRunning=0
+	 * before reading the vIRR.  The processor needs a matching memory
+	 * barrier on interrupt delivery between writing IRR and reading
+	 * IsRunning; the lack of this barrier might be the cause of errata #1235).
+	 *
+	 * Clear IsRunning=0 even if guest IRQs are disabled, i.e. even if KVM
+	 * doesn't need to detect events for scheduling purposes.  The doorbell
+	 * used to signal running vCPUs cannot be blocked, i.e. will perturb the
+	 * CPU and cause noisy neighbor problems if the VM is sending interrupts
+	 * to the vCPU while it's scheduled out.
+	 */
+	__avic_vcpu_put(vcpu, AVIC_START_BLOCKING);
 }
 
 void avic_vcpu_unblocking(struct kvm_vcpu *vcpu)
@@ -1228,6 +1132,14 @@ bool avic_hardware_setup(void)
 	if (x2avic_enabled)
 		pr_info("x2AVIC enabled\n");
 
+	/*
+	 * Disable IPI virtualization for AMD Family 17h CPUs (Zen1 and Zen2)
+	 * due to erratum 1235, which results in missed VM-Exits on the sender
+	 * and thus missed wake events for blocking vCPUs due to the CPU
+	 * failing to see a software update to clear IsRunning.
+	 */
+	enable_ipiv = enable_ipiv && boot_cpu_data.x86 != 0x17;
+
 	amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
 
 	return true;