1 files changed, 53 insertions, 27 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 2098dc689088..3c83951c619e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -382,7 +382,7 @@ enum {
 	DIRTY
 };
 
-void kvm_recalculate_apic_map(struct kvm *kvm)
+static void kvm_recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
 	struct kvm_vcpu *vcpu;
@@ -2577,7 +2577,7 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 	return (tpr & 0xf0) >> 4;
 }
 
-void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
+static void __kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value)
 {
 	u64 old_value = vcpu->arch.apic_base;
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -2625,29 +2625,60 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	}
 }
 
+int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated)
+{
+	enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
+	enum lapic_mode new_mode = kvm_apic_mode(value);
+
+	if (vcpu->arch.apic_base == value)
+		return 0;
+
+	u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff |
+		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
+
+	if ((value & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
+		return 1;
+	if (!host_initiated) {
+		if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC)
+			return 1;
+		if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC)
+			return 1;
+	}
+
+	__kvm_apic_set_base(vcpu, value);
+	kvm_recalculate_apic_map(vcpu->kvm);
+	return 0;
+}
+
 void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic->apicv_active) {
-		/* irr_pending is always true when apicv is activated. */
-		apic->irr_pending = true;
+	/*
+	 * When APICv is enabled, KVM must always search the IRR for a pending
+	 * IRQ, as other vCPUs and devices can set IRR bits even if the vCPU
+	 * isn't running.  If APICv is disabled, KVM _should_ search the IRR
+	 * for a pending IRQ.  But KVM currently doesn't ensure *all* hardware,
+	 * e.g. CPUs and IOMMUs, has seen the change in state, i.e. searching
+	 * the IRR at this time could race with IRQ delivery from hardware that
+	 * still sees APICv as being enabled.
+	 *
+	 * FIXME: Ensure other vCPUs and devices observe the change in APICv
+	 *        state prior to updating KVM's metadata caches, so that KVM
+	 *        can safely search the IRR and set irr_pending accordingly.
+	 */
+	apic->irr_pending = true;
+
+	if (apic->apicv_active)
 		apic->isr_count = 1;
-	} else {
-		/*
-		 * Don't clear irr_pending, searching the IRR can race with
-		 * updates from the CPU as APICv is still active from hardware's
-		 * perspective.  The flag will be cleared as appropriate when
-		 * KVM injects the interrupt.
-		 */
+	else
 		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;
 
@@ -2663,17 +2694,6 @@ int kvm_alloc_apic_access_page(struct kvm *kvm)
 		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);
@@ -2728,7 +2748,14 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 		msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
 		if (kvm_vcpu_is_reset_bsp(vcpu))
 			msr_val |= MSR_IA32_APICBASE_BSP;
-		kvm_lapic_set_base(vcpu, msr_val);
+
+		/*
+		 * Use the inner helper to avoid an extra recalcuation of the
+		 * optimized APIC map if some other task has dirtied the map.
+		 * The recalculation needed for this vCPU will be done after
+		 * all APIC state has been initialized (see below).
+		 */
+		__kvm_apic_set_base(vcpu, msr_val);
 	}
 
 	if (!apic)
@@ -3069,7 +3096,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 
 	kvm_x86_call(apicv_pre_state_restore)(vcpu);
 
-	kvm_lapic_set_base(vcpu, vcpu->arch.apic_base);
 	/* set SPIV separately to get count of SW disabled APICs right */
 	apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV)));