Merge branch 'kvm-lapic-fix-and-cleanup' into HEAD

The first half or so patches fix semi-urgent, real-world relevant APICv
and AVIC bugs.

The second half fixes a variety of AVIC and optimized APIC map bugs
where KVM doesn't play nice with various edge cases that are
architecturally legal(ish), but are unlikely to occur in most real world
scenarios

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

11 files changed, 523 insertions, 356 deletions

diff --git a/Documentation/virt/kvm/x86/errata.rst b/Documentation/virt/kvm/x86/errata.rst
index 410e0aa63493..49a05f24747b 100644
--- a/Documentation/virt/kvm/x86/errata.rst
+++ b/Documentation/virt/kvm/x86/errata.rst
@@ -37,3 +37,14 @@ Nested virtualization features
 ------------------------------
 
 TBD
+
+x2APIC
+------
+When KVM_X2APIC_API_USE_32BIT_IDS is enabled, KVM activates a hack/quirk that
+allows sending events to a single vCPU using its x2APIC ID even if the target
+vCPU has legacy xAPIC enabled, e.g. to bring up hotplugged vCPUs via INIT-SIPI
+on VMs with > 255 vCPUs.  A side effect of the quirk is that, if multiple vCPUs
+have the same physical APIC ID, KVM will deliver events targeting that APIC ID
+only to the vCPU with the lowest vCPU ID.  If KVM_X2APIC_API_USE_32BIT_IDS is
+not enabled, KVM follows x86 architecture when processing interrupts (all vCPUs
+matching the target APIC ID receive the interrupt).
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index dba2909e5ae2..8dc345cc6318 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -77,7 +77,6 @@ KVM_X86_OP(set_nmi_mask)
 KVM_X86_OP(enable_nmi_window)
 KVM_X86_OP(enable_irq_window)
 KVM_X86_OP_OPTIONAL(update_cr8_intercept)
-KVM_X86_OP(check_apicv_inhibit_reasons)
 KVM_X86_OP(refresh_apicv_exec_ctrl)
 KVM_X86_OP_OPTIONAL(hwapic_irr_update)
 KVM_X86_OP_OPTIONAL(hwapic_isr_update)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8d0a0a7c34fc..4d2bc08794e4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1022,19 +1022,30 @@ struct kvm_arch_memory_slot {
 };
 
 /*
- * We use as the mode the number of bits allocated in the LDR for the
- * logical processor ID.  It happens that these are all powers of two.
- * This makes it is very easy to detect cases where the APICs are
- * configured for multiple modes; in that case, we cannot use the map and
- * hence cannot use kvm_irq_delivery_to_apic_fast either.
+ * Track the mode of the optimized logical map, as the rules for decoding the
+ * destination vary per mode.  Enabling the optimized logical map requires all
+ * software-enabled local APIs to be in the same mode, each addressable APIC to
+ * be mapped to only one MDA, and each MDA to map to at most one APIC.
  */
-#define KVM_APIC_MODE_XAPIC_CLUSTER          4
-#define KVM_APIC_MODE_XAPIC_FLAT             8
-#define KVM_APIC_MODE_X2APIC                16
+enum kvm_apic_logical_mode {
+	/* All local APICs are software disabled. */
+	KVM_APIC_MODE_SW_DISABLED,
+	/* All software enabled local APICs in xAPIC cluster addressing mode. */
+	KVM_APIC_MODE_XAPIC_CLUSTER,
+	/* All software enabled local APICs in xAPIC flat addressing mode. */
+	KVM_APIC_MODE_XAPIC_FLAT,
+	/* All software enabled local APICs in x2APIC mode. */
+	KVM_APIC_MODE_X2APIC,
+	/*
+	 * Optimized map disabled, e.g. not all local APICs in the same logical
+	 * mode, same logical ID assigned to multiple APICs, etc.
+	 */
+	KVM_APIC_MODE_MAP_DISABLED,
+};
 
 struct kvm_apic_map {
 	struct rcu_head rcu;
-	u8 mode;
+	enum kvm_apic_logical_mode logical_mode;
 	u32 max_apic_id;
 	union {
 		struct kvm_lapic *xapic_flat_map[8];
@@ -1165,6 +1176,12 @@ enum kvm_apicv_inhibit {
 	APICV_INHIBIT_REASON_BLOCKIRQ,
 
 	/*
+	 * APICv is disabled because not all vCPUs have a 1:1 mapping between
+	 * APIC ID and vCPU, _and_ KVM is not applying its x2APIC hotplug hack.
+	 */
+	APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED,
+
+	/*
 	 * For simplicity, the APIC acceleration is inhibited
 	 * first time either APIC ID or APIC base are changed by the guest
 	 * from their reset values.
@@ -1202,6 +1219,12 @@ enum kvm_apicv_inhibit {
 	 * AVIC is disabled because SEV doesn't support it.
 	 */
 	APICV_INHIBIT_REASON_SEV,
+
+	/*
+	 * AVIC is disabled because not all vCPUs with a valid LDR have a 1:1
+	 * mapping between logical ID and vCPU.
+	 */
+	APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED,
 };
 
 struct kvm_arch {
@@ -1250,10 +1273,11 @@ struct kvm_arch {
 	struct kvm_apic_map __rcu *apic_map;
 	atomic_t apic_map_dirty;
 
-	/* Protects apic_access_memslot_enabled and apicv_inhibit_reasons */
-	struct rw_semaphore apicv_update_lock;
-
 	bool apic_access_memslot_enabled;
+	bool apic_access_memslot_inhibited;
+
+	/* Protects apicv_inhibit_reasons */
+	struct rw_semaphore apicv_update_lock;
 	unsigned long apicv_inhibit_reasons;
 
 	gpa_t wall_clock;
@@ -1602,6 +1626,8 @@ struct kvm_x86_ops {
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
 	bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason);
+	const unsigned long required_apicv_inhibits;
+	bool allow_apicv_in_x2apic_without_x2apic_virtualization;
 	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(int isr);
@@ -1976,7 +2002,7 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
 
 bool kvm_apicv_activated(struct kvm *kvm);
 bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu);
-void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
+void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
 void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 				      enum kvm_apicv_inhibit reason, bool set);
 void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index cfaf1d8c64ca..7cf4eebc9bcc 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -167,9 +167,19 @@ static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu)
 	return kvm_can_post_timer_interrupt(vcpu) && vcpu->mode == IN_GUEST_MODE;
 }
 
+static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
+{
+	return ((id >> 4) << 16) | (1 << (id & 0xf));
+}
+
 static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 		u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) {
-	switch (map->mode) {
+	switch (map->logical_mode) {
+	case KVM_APIC_MODE_SW_DISABLED:
+		/* Arbitrarily use the flat map so that @cluster isn't NULL. */
+		*cluster = map->xapic_flat_map;
+		*mask = 0;
+		return true;
 	case KVM_APIC_MODE_X2APIC: {
 		u32 offset = (dest_id >> 16) * 16;
 		u32 max_apic_id = map->max_apic_id;
@@ -194,8 +204,10 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 		*cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf];
 		*mask = dest_id & 0xf;
 		return true;
+	case KVM_APIC_MODE_MAP_DISABLED:
+		return false;
 	default:
-		/* Not optimized. */
+		WARN_ON_ONCE(1);
 		return false;
 	}
 }
@@ -207,6 +219,134 @@ static void kvm_apic_map_free(struct rcu_head *rcu)
 	kvfree(map);
 }
 
+static int kvm_recalculate_phys_map(struct kvm_apic_map *new,
+				    struct kvm_vcpu *vcpu,
+				    bool *xapic_id_mismatch)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u32 x2apic_id = kvm_x2apic_id(apic);
+	u32 xapic_id = kvm_xapic_id(apic);
+	u32 physical_id;
+
+	/*
+	 * Deliberately truncate the vCPU ID when detecting a mismatched APIC
+	 * ID to avoid false positives if the vCPU ID, i.e. x2APIC ID, is a
+	 * 32-bit value.  Any unwanted aliasing due to truncation results will
+	 * be detected below.
+	 */
+	if (!apic_x2apic_mode(apic) && xapic_id != (u8)vcpu->vcpu_id)
+		*xapic_id_mismatch = true;
+
+	/*
+	 * Apply KVM's hotplug hack if userspace has enable 32-bit APIC IDs.
+	 * Allow sending events to vCPUs by their x2APIC ID even if the target
+	 * vCPU is in legacy xAPIC mode, and silently ignore aliased xAPIC IDs
+	 * (the x2APIC ID is truncated to 8 bits, causing IDs > 0xff to wrap
+	 * and collide).
+	 *
+	 * Honor the architectural (and KVM's non-optimized) behavior if
+	 * userspace has not enabled 32-bit x2APIC IDs.  Each APIC is supposed
+	 * to process messages independently.  If multiple vCPUs have the same
+	 * effective APIC ID, e.g. due to the x2APIC wrap or because the guest
+	 * manually modified its xAPIC IDs, events targeting that ID are
+	 * supposed to be recognized by all vCPUs with said ID.
+	 */
+	if (vcpu->kvm->arch.x2apic_format) {
+		/* See also kvm_apic_match_physical_addr(). */
+		if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) &&
+			x2apic_id <= new->max_apic_id)
+			new->phys_map[x2apic_id] = apic;
+
+		if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id])
+			new->phys_map[xapic_id] = apic;
+	} else {
+		/*
+		 * Disable the optimized map if the physical APIC ID is already
+		 * mapped, i.e. is aliased to multiple vCPUs.  The optimized
+		 * map requires a strict 1:1 mapping between IDs and vCPUs.
+		 */
+		if (apic_x2apic_mode(apic))
+			physical_id = x2apic_id;
+		else
+			physical_id = xapic_id;
+
+		if (new->phys_map[physical_id])
+			return -EINVAL;
+
+		new->phys_map[physical_id] = apic;
+	}
+
+	return 0;
+}
+
+static void kvm_recalculate_logical_map(struct kvm_apic_map *new,
+					struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	enum kvm_apic_logical_mode logical_mode;
+	struct kvm_lapic **cluster;
+	u16 mask;
+	u32 ldr;
+
+	if (new->logical_mode == KVM_APIC_MODE_MAP_DISABLED)
+		return;
+
+	if (!kvm_apic_sw_enabled(apic))
+		return;
+
+	ldr = kvm_lapic_get_reg(apic, APIC_LDR);
+	if (!ldr)
+		return;
+
+	if (apic_x2apic_mode(apic)) {
+		logical_mode = KVM_APIC_MODE_X2APIC;
+	} else {
+		ldr = GET_APIC_LOGICAL_ID(ldr);
+		if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT)
+			logical_mode = KVM_APIC_MODE_XAPIC_FLAT;
+		else
+			logical_mode = KVM_APIC_MODE_XAPIC_CLUSTER;
+	}
+
+	/*
+	 * To optimize logical mode delivery, all software-enabled APICs must
+	 * be configured for the same mode.
+	 */
+	if (new->logical_mode == KVM_APIC_MODE_SW_DISABLED) {
+		new->logical_mode = logical_mode;
+	} else if (new->logical_mode != logical_mode) {
+		new->logical_mode = KVM_APIC_MODE_MAP_DISABLED;
+		return;
+	}
+
+	/*
+	 * In x2APIC mode, the LDR is read-only and derived directly from the
+	 * x2APIC ID, thus is guaranteed to be addressable.  KVM reuses
+	 * kvm_apic_map.phys_map to optimize logical mode x2APIC interrupts by
+	 * reversing the LDR calculation to get cluster of APICs, i.e. no
+	 * additional work is required.
+	 */
+	if (apic_x2apic_mode(apic)) {
+		WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic)));
+		return;
+	}
+
+	if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr,
+							&cluster, &mask))) {
+		new->logical_mode = KVM_APIC_MODE_MAP_DISABLED;
+		return;
+	}
+
+	if (!mask)
+		return;
+
+	ldr = ffs(mask) - 1;
+	if (!is_power_of_2(mask) || cluster[ldr])
+		new->logical_mode = KVM_APIC_MODE_MAP_DISABLED;
+	else
+		cluster[ldr] = apic;
+}
+
 /*
  * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock.
  *
@@ -225,6 +365,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 	u32 max_id = 255; /* enough space for any xAPIC ID */
+	bool xapic_id_mismatch = false;
 
 	/* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map.  */
 	if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN)
@@ -257,54 +398,41 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 		goto out;
 
 	new->max_apic_id = max_id;
+	new->logical_mode = KVM_APIC_MODE_SW_DISABLED;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct kvm_lapic *apic = vcpu->arch.apic;
-		struct kvm_lapic **cluster;
-		u16 mask;
-		u32 ldr;
-		u8 xapic_id;
-		u32 x2apic_id;
-
 		if (!kvm_apic_present(vcpu))
 			continue;
 
-		xapic_id = kvm_xapic_id(apic);
-		x2apic_id = kvm_x2apic_id(apic);
-
-		/* Hotplug hack: see kvm_apic_match_physical_addr(), ... */
-		if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) &&
-				x2apic_id <= new->max_apic_id)
-			new->phys_map[x2apic_id] = apic;
-		/*
-		 * ... xAPIC ID of VCPUs with APIC ID > 0xff will wrap-around,
-		 * prevent them from masking VCPUs with APIC ID <= 0xff.
-		 */
-		if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id])
-			new->phys_map[xapic_id] = apic;
-
-		if (!kvm_apic_sw_enabled(apic))
-			continue;
-
-		ldr = kvm_lapic_get_reg(apic, APIC_LDR);
-
-		if (apic_x2apic_mode(apic)) {
-			new->mode |= KVM_APIC_MODE_X2APIC;
-		} else if (ldr) {
-			ldr = GET_APIC_LOGICAL_ID(ldr);
-			if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT)
-				new->mode |= KVM_APIC_MODE_XAPIC_FLAT;
-			else
-				new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER;
+		if (kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch)) {
+			kvfree(new);
+			new = NULL;
+			goto out;
 		}
 
-		if (!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask))
-			continue;
-
-		if (mask)
-			cluster[ffs(mask) - 1] = apic;
+		kvm_recalculate_logical_map(new, vcpu);
 	}
 out:
+	/*
+	 * The optimized map is effectively KVM's internal version of APICv,
+	 * and all unwanted aliasing that results in disabling the optimized
+	 * map also applies to APICv.
+	 */
+	if (!new)
+		kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED);
+	else
+		kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED);
+
+	if (!new || new->logical_mode == KVM_APIC_MODE_MAP_DISABLED)
+		kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED);
+	else
+		kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED);
+
+	if (xapic_id_mismatch)
+		kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED);
+	else
+		kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED);
+
 	old = rcu_dereference_protected(kvm->arch.apic_map,
 			lockdep_is_held(&kvm->arch.apic_map_lock));
 	rcu_assign_pointer(kvm->arch.apic_map, new);
@@ -361,11 +489,6 @@ static inline void kvm_apic_set_dfr(struct kvm_lapic *apic, u32 val)
 	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
-static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
-{
-	return ((id >> 4) << 16) | (1 << (id & 0xf));
-}
-
 static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
 {
 	u32 ldr = kvm_apic_calc_x2apic_ldr(id);
@@ -951,7 +1074,7 @@ static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src,
 {
 	if (kvm->arch.x2apic_broadcast_quirk_disabled) {
 		if ((irq->dest_id == APIC_BROADCAST &&
-				map->mode != KVM_APIC_MODE_X2APIC))
+		     map->logical_mode != KVM_APIC_MODE_X2APIC))
 			return true;
 		if (irq->dest_id == X2APIC_BROADCAST)
 			return true;
@@ -2068,19 +2191,6 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 	}
 }
 
-static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic)
-{
-	struct kvm *kvm = apic->vcpu->kvm;
-
-	if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm))
-		return;
-
-	if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id)
-		return;
-
-	kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED);
-}
-
 static int get_lvt_index(u32 reg)
 {
 	if (reg == APIC_LVTCMCI)
@@ -2101,7 +2211,6 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_ID:		/* Local APIC ID */
 		if (!apic_x2apic_mode(apic)) {
 			kvm_apic_set_xapic_id(apic, val >> 24);
-			kvm_lapic_xapic_id_updated(apic);
 		} else {
 			ret = 1;
 		}
@@ -2284,23 +2393,18 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u64 val;
 
-	if (apic_x2apic_mode(apic)) {
-		if (KVM_BUG_ON(kvm_lapic_msr_read(apic, offset, &val), vcpu->kvm))
-			return;
-	} else {
-		val = kvm_lapic_get_reg(apic, offset);
-	}
-
 	/*
 	 * ICR is a single 64-bit register when x2APIC is enabled.  For legacy
 	 * xAPIC, ICR writes need to go down the common (slightly slower) path
 	 * to get the upper half from ICR2.
 	 */
 	if (apic_x2apic_mode(apic) && offset == APIC_ICR) {
+		val = kvm_lapic_get_reg64(apic, APIC_ICR);
 		kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32));
 		trace_kvm_apic_write(APIC_ICR, val);
 	} else {
 		/* TODO: optimize to just emulate side effect w/o one more write */
+		val = kvm_lapic_get_reg(apic, offset);
 		kvm_lapic_reg_write(apic, offset, (u32)val);
 	}
 }
@@ -2398,7 +2502,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id);
 
 	if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) {
-		kvm_vcpu_update_apicv(vcpu);
+		kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
 		static_call_cond(kvm_x86_set_virtual_apic_mode)(vcpu);
 	}
 
@@ -2429,6 +2533,78 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
 		 */
 		apic->isr_count = count_vectors(apic->regs + APIC_ISR);
 	}
+	apic->highest_isr_cache = -1;
+}
+
+int kvm_alloc_apic_access_page(struct kvm *kvm)
+{
+	struct page *page;
+	void __user *hva;
+	int ret = 0;
+
+	mutex_lock(&kvm->slots_lock);
+	if (kvm->arch.apic_access_memslot_enabled ||
+	    kvm->arch.apic_access_memslot_inhibited)
+		goto out;
+
+	hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+				      APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
+	if (IS_ERR(hva)) {
+		ret = PTR_ERR(hva);
+		goto out;
+	}
+
+	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	/*
+	 * Do not pin the page in memory, so that memory hot-unplug
+	 * is able to migrate it.
+	 */
+	put_page(page);
+	kvm->arch.apic_access_memslot_enabled = true;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_alloc_apic_access_page);
+
+void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	if (!kvm->arch.apic_access_memslot_enabled)
+		return;
+
+	kvm_vcpu_srcu_read_unlock(vcpu);
+
+	mutex_lock(&kvm->slots_lock);
+
+	if (kvm->arch.apic_access_memslot_enabled) {
+		__x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0);
+		/*
+		 * Clear "enabled" after the memslot is deleted so that a
+		 * different vCPU doesn't get a false negative when checking
+		 * the flag out of slots_lock.  No additional memory barrier is
+		 * needed as modifying memslots requires waiting other vCPUs to
+		 * drop SRCU (see above), and false positives are ok as the
+		 * flag is rechecked after acquiring slots_lock.
+		 */
+		kvm->arch.apic_access_memslot_enabled = false;
+
+		/*
+		 * Mark the memslot as inhibited to prevent reallocating the
+		 * memslot during vCPU creation, e.g. if a vCPU is hotplugged.
+		 */
+		kvm->arch.apic_access_memslot_inhibited = true;
+	}
+
+	mutex_unlock(&kvm->slots_lock);
+
+	kvm_vcpu_srcu_read_lock(vcpu);
 }
 
 void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -2484,7 +2660,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 		kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
 	kvm_apic_update_apicv(vcpu);
-	apic->highest_isr_cache = -1;
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
 
@@ -2756,9 +2931,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 	}
 	memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s));
 
-	if (!apic_x2apic_mode(apic))
-		kvm_lapic_xapic_id_updated(apic);
-
 	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	kvm_recalculate_apic_map(vcpu->kvm);
 	kvm_apic_set_version(vcpu);
@@ -2772,7 +2944,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 	__start_apic_timer(apic, APIC_TMCCT);
 	kvm_lapic_set_reg(apic, APIC_TMCCT, 0);
 	kvm_apic_update_apicv(vcpu);
-	apic->highest_isr_cache = -1;
 	if (apic->apicv_active) {
 		static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu);
 		static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic));
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 58c3242fcc7a..df316ede7546 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -112,6 +112,8 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
 		     struct dest_map *dest_map);
 int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type);
 void kvm_apic_update_apicv(struct kvm_vcpu *vcpu);
+int kvm_alloc_apic_access_page(struct kvm *kvm);
+void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu);
 
 bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index f52f5e0dd465..b3928150a37c 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -53,7 +53,7 @@ static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS);
 static u32 next_vm_id = 0;
 static bool next_vm_id_wrapped = 0;
 static DEFINE_SPINLOCK(svm_vm_data_hash_lock);
-enum avic_modes avic_mode;
+bool x2avic_enabled;
 
 /*
  * This is a wrapper of struct amd_iommu_ir_data.
@@ -72,20 +72,25 @@ static void avic_activate_vmcb(struct vcpu_svm *svm)
 
 	vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
 
-	/* Note:
-	 * KVM can support hybrid-AVIC mode, where KVM emulates x2APIC
-	 * MSR accesses, while interrupt injection to a running vCPU
-	 * can be achieved using AVIC doorbell. The AVIC hardware still
-	 * accelerate MMIO accesses, but this does not cause any harm
-	 * as the guest is not supposed to access xAPIC mmio when uses x2APIC.
+	/*
+	 * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR
+	 * accesses, while interrupt injection to a running vCPU can be
+	 * achieved using AVIC doorbell.  KVM disables the APIC access page
+	 * (deletes the memslot) if any vCPU has x2APIC enabled, thus enabling
+	 * AVIC in hybrid mode activates only the doorbell mechanism.
 	 */
-	if (apic_x2apic_mode(svm->vcpu.arch.apic) &&
-	    avic_mode == AVIC_MODE_X2) {
+	if (x2avic_enabled && apic_x2apic_mode(svm->vcpu.arch.apic)) {
 		vmcb->control.int_ctl |= X2APIC_MODE_MASK;
 		vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID;
 		/* Disabling MSR intercept for x2APIC registers */
 		svm_set_x2apic_msr_interception(svm, false);
 	} else {
+		/*
+		 * Flush the TLB, the guest may have inserted a non-APIC
+		 * mapping into the TLB while AVIC was disabled.
+		 */
+		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, &svm->vcpu);
+
 		/* For xAVIC and hybrid-xAVIC modes */
 		vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID;
 		/* Enabling MSR intercept for x2APIC registers */
@@ -241,8 +246,8 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
 	u64 *avic_physical_id_table;
 	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
 
-	if ((avic_mode == AVIC_MODE_X1 && index > AVIC_MAX_PHYSICAL_ID) ||
-	    (avic_mode == AVIC_MODE_X2 && index > X2AVIC_MAX_PHYSICAL_ID))
+	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);
@@ -250,47 +255,14 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
 	return &avic_physical_id_table[index];
 }
 
-/*
- * Note:
- * AVIC hardware walks the nested page table to check permissions,
- * but does not use the SPA address specified in the leaf page
- * table entry since it uses  address in the AVIC_BACKING_PAGE pointer
- * field of the VMCB. Therefore, we set up the
- * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here.
- */
-static int avic_alloc_access_page(struct kvm *kvm)
-{
-	void __user *ret;
-	int r = 0;
-
-	mutex_lock(&kvm->slots_lock);
-
-	if (kvm->arch.apic_access_memslot_enabled)
-		goto out;
-
-	ret = __x86_set_memory_region(kvm,
-				      APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
-				      APIC_DEFAULT_PHYS_BASE,
-				      PAGE_SIZE);
-	if (IS_ERR(ret)) {
-		r = PTR_ERR(ret);
-		goto out;
-	}
-
-	kvm->arch.apic_access_memslot_enabled = true;
-out:
-	mutex_unlock(&kvm->slots_lock);
-	return r;
-}
-
 static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 {
 	u64 *entry, new_entry;
 	int id = vcpu->vcpu_id;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if ((avic_mode == AVIC_MODE_X1 && id > AVIC_MAX_PHYSICAL_ID) ||
-	    (avic_mode == AVIC_MODE_X2 && id > X2AVIC_MAX_PHYSICAL_ID))
+	if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) ||
+	    (id > X2AVIC_MAX_PHYSICAL_ID))
 		return -EINVAL;
 
 	if (!vcpu->arch.apic->regs)
@@ -299,7 +271,13 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 	if (kvm_apicv_activated(vcpu->kvm)) {
 		int ret;
 
-		ret = avic_alloc_access_page(vcpu->kvm);
+		/*
+		 * Note, AVIC hardware walks the nested page table to check
+		 * permissions, but does not use the SPA address specified in
+		 * the leaf SPTE since it uses address in the AVIC_BACKING_PAGE
+		 * pointer field of the VMCB.
+		 */
+		ret = kvm_alloc_apic_access_page(vcpu->kvm);
 		if (ret)
 			return ret;
 	}
@@ -339,6 +317,60 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+
+static void avic_kick_vcpu(struct kvm_vcpu *vcpu, u32 icrl)
+{
+	vcpu->arch.apic->irr_pending = true;
+	svm_complete_interrupt_delivery(vcpu,
+					icrl & APIC_MODE_MASK,
+					icrl & APIC_INT_LEVELTRIG,
+					icrl & APIC_VECTOR_MASK);
+}
+
+static void avic_kick_vcpu_by_physical_id(struct kvm *kvm, u32 physical_id,
+					  u32 icrl)
+{
+	/*
+	 * KVM inhibits AVIC if any vCPU ID diverges from the vCPUs APIC ID,
+	 * i.e. APIC ID == vCPU ID.
+	 */
+	struct kvm_vcpu *target_vcpu = kvm_get_vcpu_by_id(kvm, physical_id);
+
+	/* Once again, nothing to do if the target vCPU doesn't exist. */
+	if (unlikely(!target_vcpu))
+		return;
+
+	avic_kick_vcpu(target_vcpu, icrl);
+}
+
+static void avic_kick_vcpu_by_logical_id(struct kvm *kvm, u32 *avic_logical_id_table,
+					 u32 logid_index, u32 icrl)
+{
+	u32 physical_id;
+
+	if (avic_logical_id_table) {
+		u32 logid_entry = avic_logical_id_table[logid_index];
+
+		/* Nothing to do if the logical destination is invalid. */
+		if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK)))
+			return;
+
+		physical_id = logid_entry &
+			      AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
+	} else {
+		/*
+		 * For x2APIC, the logical APIC ID is a read-only value that is
+		 * derived from the x2APIC ID, thus the x2APIC ID can be found
+		 * by reversing the calculation (stored in logid_index).  Note,
+		 * bits 31:20 of the x2APIC ID aren't propagated to the logical
+		 * ID, but KVM limits the x2APIC ID limited to KVM_MAX_VCPU_IDS.
+		 */
+		physical_id = logid_index;
+	}
+
+	avic_kick_vcpu_by_physical_id(kvm, physical_id, icrl);
+}
+
 /*
  * A fast-path version of avic_kick_target_vcpus(), which attempts to match
  * destination APIC ID to vCPU without looping through all vCPUs.
@@ -346,11 +378,10 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu)
 static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source,
 				       u32 icrl, u32 icrh, u32 index)
 {
-	u32 l1_physical_id, dest;
-	struct kvm_vcpu *target_vcpu;
 	int dest_mode = icrl & APIC_DEST_MASK;
 	int shorthand = icrl & APIC_SHORT_MASK;
 	struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
+	u32 dest;
 
 	if (shorthand != APIC_DEST_NOSHORT)
 		return -EINVAL;
@@ -367,18 +398,18 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source
 		if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST)
 			return -EINVAL;
 
-		l1_physical_id = dest;
-
-		if (WARN_ON_ONCE(l1_physical_id != index))
+		if (WARN_ON_ONCE(dest != index))
 			return -EINVAL;
 
+		avic_kick_vcpu_by_physical_id(kvm, dest, icrl);
 	} else {
-		u32 bitmap, cluster;
-		int logid_index;
+		u32 *avic_logical_id_table;
+		unsigned long bitmap, i;
+		u32 cluster;
 
 		if (apic_x2apic_mode(source)) {
 			/* 16 bit dest mask, 16 bit cluster id */
-			bitmap = dest & 0xFFFF0000;
+			bitmap = dest & 0xFFFF;
 			cluster = (dest >> 16) << 4;
 		} else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) {
 			/* 8 bit dest mask*/
@@ -390,67 +421,32 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source
 			cluster = (dest >> 4) << 2;
 		}
 
+		/* Nothing to do if there are no destinations in the cluster. */
 		if (unlikely(!bitmap))
-			/* guest bug: nobody to send the logical interrupt to */
 			return 0;
 
-		if (!is_power_of_2(bitmap))
-			/* multiple logical destinations, use slow path */
-			return -EINVAL;
-
-		logid_index = cluster + __ffs(bitmap);
-
-		if (!apic_x2apic_mode(source)) {
-			u32 *avic_logical_id_table =
-				page_address(kvm_svm->avic_logical_id_table_page);
-
-			u32 logid_entry = avic_logical_id_table[logid_index];
-
-			if (WARN_ON_ONCE(index != logid_index))
-				return -EINVAL;
-
-			/* guest bug: non existing/reserved logical destination */
-			if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK)))
-				return 0;
-
-			l1_physical_id = logid_entry &
-					 AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
-		} else {
-			/*
-			 * For x2APIC logical mode, cannot leverage the index.
-			 * Instead, calculate physical ID from logical ID in ICRH.
-			 */
-			int cluster = (icrh & 0xffff0000) >> 16;
-			int apic = ffs(icrh & 0xffff) - 1;
-
-			/*
-			 * If the x2APIC logical ID sub-field (i.e. icrh[15:0])
-			 * contains anything but a single bit, we cannot use the
-			 * fast path, because it is limited to a single vCPU.
-			 */
-			if (apic < 0 || icrh != (1 << apic))
-				return -EINVAL;
+		if (apic_x2apic_mode(source))
+			avic_logical_id_table = NULL;
+		else
+			avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page);
 
-			l1_physical_id = (cluster << 4) + apic;
-		}
+		/*
+		 * AVIC is inhibited if vCPUs aren't mapped 1:1 with logical
+		 * IDs, thus each bit in the destination is guaranteed to map
+		 * to at most one vCPU.
+		 */
+		for_each_set_bit(i, &bitmap, 16)
+			avic_kick_vcpu_by_logical_id(kvm, avic_logical_id_table,
+						     cluster + i, icrl);
 	}
 
-	target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id);
-	if (unlikely(!target_vcpu))
-		/* guest bug: non existing vCPU is a target of this IPI*/
-		return 0;
-
-	target_vcpu->arch.apic->irr_pending = true;
-	svm_complete_interrupt_delivery(target_vcpu,
-					icrl & APIC_MODE_MASK,
-					icrl & APIC_INT_LEVELTRIG,
-					icrl & APIC_VECTOR_MASK);
 	return 0;
 }
 
 static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source,
 				   u32 icrl, u32 icrh, u32 index)
 {
+	u32 dest = apic_x2apic_mode(source) ? icrh : GET_XAPIC_DEST_FIELD(icrh);
 	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
@@ -466,21 +462,9 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source,
 	 * since entered the guest will have processed pending IRQs at VMRUN.
 	 */
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		u32 dest;
-
-		if (apic_x2apic_mode(vcpu->arch.apic))
-			dest = icrh;
-		else
-			dest = GET_XAPIC_DEST_FIELD(icrh);
-
 		if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK,
-					dest, icrl & APIC_DEST_MASK)) {
-			vcpu->arch.apic->irr_pending = true;
-			svm_complete_interrupt_delivery(vcpu,
-							icrl & APIC_MODE_MASK,
-							icrl & APIC_INT_LEVELTRIG,
-							icrl & APIC_VECTOR_MASK);
-		}
+					dest, icrl & APIC_DEST_MASK))
+			avic_kick_vcpu(vcpu, icrl);
 	}
 }
 
@@ -496,14 +480,18 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
 	trace_kvm_avic_incomplete_ipi(vcpu->vcpu_id, icrh, icrl, id, index);
 
 	switch (id) {
+	case AVIC_IPI_FAILURE_INVALID_TARGET:
 	case AVIC_IPI_FAILURE_INVALID_INT_TYPE:
 		/*
 		 * Emulate IPIs that are not handled by AVIC hardware, which
-		 * only virtualizes Fixed, Edge-Triggered INTRs.  The exit is
-		 * a trap, e.g. ICR holds the correct value and RIP has been
-		 * advanced, KVM is responsible only for emulating the IPI.
-		 * Sadly, hardware may sometimes leave the BUSY flag set, in
-		 * which case KVM needs to emulate the ICR write as well in
+		 * only virtualizes Fixed, Edge-Triggered INTRs, and falls over
+		 * if _any_ targets are invalid, e.g. if the logical mode mask
+		 * is a superset of running vCPUs.
+		 *
+		 * The exit is a trap, e.g. ICR holds the correct value and RIP
+		 * has been advanced, KVM is responsible only for emulating the
+		 * IPI.  Sadly, hardware may sometimes leave the BUSY flag set,
+		 * in which case KVM needs to emulate the ICR write as well in
 		 * order to clear the BUSY flag.
 		 */
 		if (icrl & APIC_ICR_BUSY)
@@ -519,8 +507,6 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
 		 */
 		avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh, index);
 		break;
-	case AVIC_IPI_FAILURE_INVALID_TARGET:
-		break;
 	case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
 		WARN_ONCE(1, "Invalid backing page\n");
 		break;
@@ -541,33 +527,33 @@ 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);
-	int index;
 	u32 *logical_apic_id_table;
-	int dlid = GET_APIC_LOGICAL_ID(ldr);
-
-	if (!dlid)
-		return NULL;
+	u32 cluster, index;
 
-	if (flat) { /* flat */
-		index = ffs(dlid) - 1;
-		if (index > 7)
-			return NULL;
-	} else { /* cluster */
-		int cluster = (dlid & 0xf0) >> 4;
-		int apic = ffs(dlid & 0x0f) - 1;
+	ldr = GET_APIC_LOGICAL_ID(ldr);
 
-		if ((apic < 0) || (apic > 7) ||
-		    (cluster >= 0xf))
+	if (flat) {
+		cluster = 0;
+	} else {
+		cluster = (ldr >> 4);
+		if (cluster >= 0xf)
 			return NULL;
-		index = (cluster << 2) + apic;
+		ldr &= 0xf;
 	}
+	if (!ldr || !is_power_of_2(ldr))
+		return NULL;
+
+	index = __ffs(ldr);
+	if (WARN_ON_ONCE(index > 7))
+		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];
 }
 
-static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr)
+static void avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr)
 {
 	bool flat;
 	u32 *entry, new_entry;
@@ -575,15 +561,13 @@ static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr)
 	flat = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR) == APIC_DFR_FLAT;
 	entry = avic_get_logical_id_entry(vcpu, ldr, flat);
 	if (!entry)
-		return -EINVAL;
+		return;
 
 	new_entry = READ_ONCE(*entry);
 	new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
 	new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK);
 	new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK;
 	WRITE_ONCE(*entry, new_entry);
-
-	return 0;
 }
 
 static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
@@ -601,29 +585,23 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
 		clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
 }
 
-static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
+static void avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 {
-	int ret = 0;
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR);
 	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
 	/* AVIC does not support LDR update for x2APIC */
 	if (apic_x2apic_mode(vcpu->arch.apic))
-		return 0;
+		return;
 
 	if (ldr == svm->ldr_reg)
-		return 0;
+		return;
 
 	avic_invalidate_logical_id_entry(vcpu);
 
-	if (ldr)
-		ret = avic_ldr_write(vcpu, id, ldr);
-
-	if (!ret)
-		svm->ldr_reg = ldr;
-
-	return ret;
+	svm->ldr_reg = ldr;
+	avic_ldr_write(vcpu, id, ldr);
 }
 
 static void avic_handle_dfr_update(struct kvm_vcpu *vcpu)
@@ -645,12 +623,14 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu)
 
 	switch (offset) {
 	case APIC_LDR:
-		if (avic_handle_ldr_update(vcpu))
-			return 0;
+		avic_handle_ldr_update(vcpu);
 		break;
 	case APIC_DFR:
 		avic_handle_dfr_update(vcpu);
 		break;
+	case APIC_RRR:
+		/* Ignore writes to Read Remote Data, it's read-only. */
+		return 1;
 	default:
 		break;
 	}
@@ -739,18 +719,6 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 	avic_handle_ldr_update(vcpu);
 }
 
-void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
-{
-	if (!lapic_in_kernel(vcpu) || avic_mode == AVIC_MODE_NONE)
-		return;
-
-	if (kvm_get_apic_mode(vcpu) == LAPIC_MODE_INVALID) {
-		WARN_ONCE(true, "Invalid local APIC state (vcpu_id=%d)", vcpu->vcpu_id);
-		return;
-	}
-	avic_refresh_apicv_exec_ctrl(vcpu);
-}
-
 static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 {
 	int ret = 0;
@@ -995,23 +963,6 @@ out:
 	return ret;
 }
 
-bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
-{
-	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
-			  BIT(APICV_INHIBIT_REASON_ABSENT) |
-			  BIT(APICV_INHIBIT_REASON_HYPERV) |
-			  BIT(APICV_INHIBIT_REASON_NESTED) |
-			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
-			  BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
-			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
-			  BIT(APICV_INHIBIT_REASON_SEV)      |
-			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
-			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
-
-	return supported & BIT(reason);
-}
-
-
 static inline int
 avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 {
@@ -1064,6 +1015,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		return;
 
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
 	entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK);
@@ -1092,17 +1044,15 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 }
 
-
-void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
+void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb01.ptr;
-	bool activated = kvm_vcpu_apicv_active(vcpu);
 
-	if (!enable_apicv)
+	if (!lapic_in_kernel(vcpu) || !enable_apicv)
 		return;
 
-	if (activated) {
+	if (kvm_vcpu_apicv_active(vcpu)) {
 		/**
 		 * During AVIC temporary deactivation, guest could update
 		 * APIC ID, DFR and LDR registers, which would not be trapped
@@ -1116,6 +1066,16 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 		avic_deactivate_vmcb(svm);
 	}
 	vmcb_mark_dirty(vmcb, VMCB_AVIC);
+}
+
+void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
+{
+	bool activated = kvm_vcpu_apicv_active(vcpu);
+
+	if (!enable_apicv)
+		return;
+
+	avic_refresh_virtual_apic_mode(vcpu);
 
 	if (activated)
 		avic_vcpu_load(vcpu, vcpu->cpu);
@@ -1165,32 +1125,32 @@ bool avic_hardware_setup(struct kvm_x86_ops *x86_ops)
 	if (!npt_enabled)
 		return false;
 
+	/* AVIC is a prerequisite for x2AVIC. */
+	if (!boot_cpu_has(X86_FEATURE_AVIC) && !force_avic) {
+		if (boot_cpu_has(X86_FEATURE_X2AVIC)) {
+			pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled");
+			pr_warn(FW_BUG "Try enable AVIC using force_avic option");
+		}
+		return false;
+	}
+
 	if (boot_cpu_has(X86_FEATURE_AVIC)) {
-		avic_mode = AVIC_MODE_X1;
 		pr_info("AVIC enabled\n");
 	} else if (force_avic) {
 		/*
 		 * Some older systems does not advertise AVIC support.
 		 * See Revision Guide for specific AMD processor for more detail.
 		 */
-		avic_mode = AVIC_MODE_X1;
 		pr_warn("AVIC is not supported in CPUID but force enabled");
 		pr_warn("Your system might crash and burn");
 	}
 
 	/* AVIC is a prerequisite for x2AVIC. */
-	if (boot_cpu_has(X86_FEATURE_X2AVIC)) {
-		if (avic_mode == AVIC_MODE_X1) {
-			avic_mode = AVIC_MODE_X2;
-			pr_info("x2AVIC enabled\n");
-		} else {
-			pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled");
-			pr_warn(FW_BUG "Try enable AVIC using force_avic option");
-		}
-	}
+	x2avic_enabled = boot_cpu_has(X86_FEATURE_X2AVIC);
+	if (x2avic_enabled)
+		pr_info("x2AVIC enabled\n");
 
-	if (avic_mode != AVIC_MODE_NONE)
-		amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
+	amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
 
-	return !!avic_mode;
+	return true;
 }
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 500da957e590..700df66d23c7 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1104,7 +1104,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	 * to benefit from it right away.
 	 */
 	if (kvm_apicv_activated(vcpu->kvm))
-		kvm_vcpu_update_apicv(vcpu);
+		__kvm_vcpu_update_apicv(vcpu);
 
 	return 0;
 }
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 799b24801d31..d13cf53e7390 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -825,7 +825,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
 	if (intercept == svm->x2avic_msrs_intercepted)
 		return;
 
-	if (avic_mode != AVIC_MODE_X2 ||
+	if (!x2avic_enabled ||
 	    !apic_x2apic_mode(svm->vcpu.arch.apic))
 		return;
 
@@ -4769,10 +4769,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.enable_nmi_window = svm_enable_nmi_window,
 	.enable_irq_window = svm_enable_irq_window,
 	.update_cr8_intercept = svm_update_cr8_intercept,
-	.set_virtual_apic_mode = avic_set_virtual_apic_mode,
+	.set_virtual_apic_mode = avic_refresh_virtual_apic_mode,
 	.refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl,
-	.check_apicv_inhibit_reasons = avic_check_apicv_inhibit_reasons,
 	.apicv_post_state_restore = avic_apicv_post_state_restore,
+	.required_apicv_inhibits = AVIC_REQUIRED_APICV_INHIBITS,
 
 	.get_exit_info = svm_get_exit_info,
 
@@ -5026,6 +5026,8 @@ static __init int svm_hardware_setup(void)
 		svm_x86_ops.vcpu_blocking = NULL;
 		svm_x86_ops.vcpu_unblocking = NULL;
 		svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL;
+	} else if (!x2avic_enabled) {
+		svm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization = true;
 	}
 
 	if (vls) {
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 4826e6cc611b..41eabb098b13 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -35,14 +35,7 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
 extern int vgif;
 extern bool intercept_smi;
-
-enum avic_modes {
-	AVIC_MODE_NONE = 0,
-	AVIC_MODE_X1,
-	AVIC_MODE_X2,
-};
-
-extern enum avic_modes avic_mode;
+extern bool x2avic_enabled;
 
 /*
  * Clean bits in VMCB.
@@ -628,6 +621,21 @@ void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb);
 extern struct kvm_x86_nested_ops svm_nested_ops;
 
 /* avic.c */
+#define AVIC_REQUIRED_APICV_INHIBITS			\
+(							\
+	BIT(APICV_INHIBIT_REASON_DISABLE) |		\
+	BIT(APICV_INHIBIT_REASON_ABSENT) |		\
+	BIT(APICV_INHIBIT_REASON_HYPERV) |		\
+	BIT(APICV_INHIBIT_REASON_NESTED) |		\
+	BIT(APICV_INHIBIT_REASON_IRQWIN) |		\
+	BIT(APICV_INHIBIT_REASON_PIT_REINJ) |		\
+	BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |		\
+	BIT(APICV_INHIBIT_REASON_SEV)      |		\
+	BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) |	\
+	BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |	\
+	BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) |	\
+	BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED)	\
+)
 
 bool avic_hardware_setup(struct kvm_x86_ops *ops);
 int avic_ga_log_notifier(u32 ga_tag);
@@ -641,14 +649,13 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void avic_vcpu_put(struct kvm_vcpu *vcpu);
 void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu);
 void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu);
-bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason);
 int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 			uint32_t guest_irq, bool set);
 void avic_vcpu_blocking(struct kvm_vcpu *vcpu);
 void avic_vcpu_unblocking(struct kvm_vcpu *vcpu);
 void avic_ring_doorbell(struct kvm_vcpu *vcpu);
 unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu);
-void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
+void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu);
 
 
 /* sev.c */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 73005d7e4e43..c788aa382611 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3904,39 +3904,6 @@ static void seg_setup(int seg)
 	vmcs_write32(sf->ar_bytes, ar);
 }
 
-static int alloc_apic_access_page(struct kvm *kvm)
-{
-	struct page *page;
-	void __user *hva;
-	int ret = 0;
-
-	mutex_lock(&kvm->slots_lock);
-	if (kvm->arch.apic_access_memslot_enabled)
-		goto out;
-	hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
-				      APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
-	if (IS_ERR(hva)) {
-		ret = PTR_ERR(hva);
-		goto out;
-	}
-
-	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
-	if (is_error_page(page)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	/*
-	 * Do not pin the page in memory, so that memory hot-unplug
-	 * is able to migrate it.
-	 */
-	put_page(page);
-	kvm->arch.apic_access_memslot_enabled = true;
-out:
-	mutex_unlock(&kvm->slots_lock);
-	return ret;
-}
-
 int allocate_vpid(void)
 {
 	int vpid;
@@ -7490,7 +7457,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu)
 	vmx->loaded_vmcs = &vmx->vmcs01;
 
 	if (cpu_need_virtualize_apic_accesses(vcpu)) {
-		err = alloc_apic_access_page(vcpu->kvm);
+		err = kvm_alloc_apic_access_page(vcpu->kvm);
 		if (err)
 			goto free_vmcs;
 	}
@@ -8129,17 +8096,16 @@ static void vmx_hardware_unsetup(void)
 	free_kvm_area();
 }
 
-static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
-{
-	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
-			  BIT(APICV_INHIBIT_REASON_ABSENT) |
-			  BIT(APICV_INHIBIT_REASON_HYPERV) |
-			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
-			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
-			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
-
-	return supported & BIT(reason);
-}
+#define VMX_REQUIRED_APICV_INHIBITS			\
+(							\
+	BIT(APICV_INHIBIT_REASON_DISABLE)|		\
+	BIT(APICV_INHIBIT_REASON_ABSENT) |		\
+	BIT(APICV_INHIBIT_REASON_HYPERV) |		\
+	BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |		\
+	BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) |	\
+	BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |	\
+	BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED)	\
+)
 
 static void vmx_vm_destroy(struct kvm *kvm)
 {
@@ -8225,7 +8191,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
 	.load_eoi_exitmap = vmx_load_eoi_exitmap,
 	.apicv_post_state_restore = vmx_apicv_post_state_restore,
-	.check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons,
+	.required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
 	.hwapic_irr_update = vmx_hwapic_irr_update,
 	.hwapic_isr_update = vmx_hwapic_isr_update,
 	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c3ac88036b52..508074e47bc0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10148,7 +10148,7 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm)
 	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
 }
 
-void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
+void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	bool activate;
@@ -10183,7 +10183,30 @@ out:
 	preempt_enable();
 	up_read(&vcpu->kvm->arch.apicv_update_lock);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv);
+EXPORT_SYMBOL_GPL(__kvm_vcpu_update_apicv);
+
+static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
+{
+	if (!lapic_in_kernel(vcpu))
+		return;
+
+	/*
+	 * Due to sharing page tables across vCPUs, the xAPIC memslot must be
+	 * deleted if any vCPU has xAPIC virtualization and x2APIC enabled, but
+	 * and hardware doesn't support x2APIC virtualization.  E.g. some AMD
+	 * CPUs support AVIC but not x2APIC.  KVM still allows enabling AVIC in
+	 * this case so that KVM can the AVIC doorbell to inject interrupts to
+	 * running vCPUs, but KVM must not create SPTEs for the APIC base as
+	 * the vCPU would incorrectly be able to access the vAPIC page via MMIO
+	 * despite being in x2APIC mode.  For simplicity, inhibiting the APIC
+	 * access page is sticky.
+	 */
+	if (apic_x2apic_mode(vcpu->arch.apic) &&
+	    kvm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization)
+		kvm_inhibit_apic_access_page(vcpu);
+
+	__kvm_vcpu_update_apicv(vcpu);
+}
 
 void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 				      enum kvm_apicv_inhibit reason, bool set)
@@ -10192,7 +10215,7 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 
 	lockdep_assert_held_write(&kvm->arch.apicv_update_lock);
 
-	if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(reason))
+	if (!(kvm_x86_ops.required_apicv_inhibits & BIT(reason)))
 		return;
 
 	old = new = kvm->arch.apicv_inhibit_reasons;