Linux-libre 4.7.1-gnupck-4.7.1-gnu

12 files changed, 975 insertions, 226 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index bbbaa802d..7597b42a8 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -75,7 +75,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 		return 0;
 
 	/* Update OSXSAVE bit */
-	if (cpu_has_xsave && best->function == 0x1) {
+	if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1) {
 		best->ecx &= ~F(OSXSAVE);
 		if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE))
 			best->ecx |= F(OSXSAVE);
@@ -181,19 +181,22 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			     struct kvm_cpuid_entry __user *entries)
 {
 	int r, i;
-	struct kvm_cpuid_entry *cpuid_entries;
+	struct kvm_cpuid_entry *cpuid_entries = NULL;
 
 	r = -E2BIG;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
 		goto out;
 	r = -ENOMEM;
-	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
-	if (!cpuid_entries)
-		goto out;
-	r = -EFAULT;
-	if (copy_from_user(cpuid_entries, entries,
-			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
-		goto out_free;
+	if (cpuid->nent) {
+		cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) *
+					cpuid->nent);
+		if (!cpuid_entries)
+			goto out;
+		r = -EFAULT;
+		if (copy_from_user(cpuid_entries, entries,
+				   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
+			goto out;
+	}
 	for (i = 0; i < cpuid->nent; i++) {
 		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
 		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
@@ -212,9 +215,8 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 	kvm_x86_ops->cpuid_update(vcpu);
 	r = kvm_update_cpuid(vcpu);
 
-out_free:
-	vfree(cpuid_entries);
 out:
+	vfree(cpuid_entries);
 	return r;
 }
 
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 9db47090e..5f42d038f 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -443,7 +443,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 		spin_lock(&ioapic->lock);
 
 		if (trigger_mode != IOAPIC_LEVEL_TRIG ||
-		    kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
+		    kvm_lapic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
 			continue;
 
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
index a22a488b4..306928190 100644
--- a/arch/x86/kvm/iommu.c
+++ b/arch/x86/kvm/iommu.c
@@ -254,7 +254,7 @@ int kvm_iommu_map_guest(struct kvm *kvm)
 	    !iommu_capable(&pci_bus_type, IOMMU_CAP_INTR_REMAP)) {
 		printk(KERN_WARNING "%s: No interrupt remapping support,"
 		       " disallowing device assignment."
-		       " Re-enble with \"allow_unsafe_assigned_interrupts=1\""
+		       " Re-enable with \"allow_unsafe_assigned_interrupts=1\""
 		       " module option.\n", __func__);
 		iommu_domain_free(kvm->arch.iommu_domain);
 		kvm->arch.iommu_domain = NULL;
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 54ead79e4..dfb4c6476 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -382,9 +382,6 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 	u32 i, nr_ioapic_pins;
 	int idx;
 
-	/* kvm->irq_routing must be read after clearing
-	 * KVM_SCAN_IOAPIC. */
-	smp_mb();
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
 	nr_ioapic_pins = min_t(u32, table->nr_rt_entries,
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 1a2da0e5a..a39720028 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -59,9 +59,8 @@
 /* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
 #define apic_debug(fmt, arg...)
 
-#define APIC_LVT_NUM			6
 /* 14 is the version for Xeon and Pentium 8.4.8*/
-#define APIC_VERSION			(0x14UL | ((APIC_LVT_NUM - 1) << 16))
+#define APIC_VERSION			(0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16))
 #define LAPIC_MMIO_LENGTH		(1 << 12)
 /* followed define is not in apicdef.h */
 #define APIC_SHORT_MASK			0xc0000
@@ -73,14 +72,6 @@
 #define APIC_BROADCAST			0xFF
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
-#define VEC_POS(v) ((v) & (32 - 1))
-#define REG_POS(v) (((v) >> 5) << 4)
-
-static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
-{
-	*((u32 *) (apic->regs + reg_off)) = val;
-}
-
 static inline int apic_test_vector(int vec, void *bitmap)
 {
 	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -94,11 +85,6 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector)
 		apic_test_vector(vector, apic->regs + APIC_IRR);
 }
 
-static inline void apic_set_vector(int vec, void *bitmap)
-{
-	set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
 static inline void apic_clear_vector(int vec, void *bitmap)
 {
 	clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -173,7 +159,7 @@ static void recalculate_apic_map(struct kvm *kvm)
 			continue;
 
 		aid = kvm_apic_id(apic);
-		ldr = kvm_apic_get_reg(apic, APIC_LDR);
+		ldr = kvm_lapic_get_reg(apic, APIC_LDR);
 
 		if (aid < ARRAY_SIZE(new->phys_map))
 			new->phys_map[aid] = apic;
@@ -182,7 +168,7 @@ static void recalculate_apic_map(struct kvm *kvm)
 			new->mode |= KVM_APIC_MODE_X2APIC;
 		} else if (ldr) {
 			ldr = GET_APIC_LOGICAL_ID(ldr);
-			if (kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT)
+			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;
@@ -212,7 +198,7 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
 {
 	bool enabled = val & APIC_SPIV_APIC_ENABLED;
 
-	apic_set_reg(apic, APIC_SPIV, val);
+	kvm_lapic_set_reg(apic, APIC_SPIV, val);
 
 	if (enabled != apic->sw_enabled) {
 		apic->sw_enabled = enabled;
@@ -226,13 +212,13 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
 
 static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
 {
-	apic_set_reg(apic, APIC_ID, id << 24);
+	kvm_lapic_set_reg(apic, APIC_ID, id << 24);
 	recalculate_apic_map(apic->vcpu->kvm);
 }
 
 static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 {
-	apic_set_reg(apic, APIC_LDR, id);
+	kvm_lapic_set_reg(apic, APIC_LDR, id);
 	recalculate_apic_map(apic->vcpu->kvm);
 }
 
@@ -240,19 +226,19 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id)
 {
 	u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
 
-	apic_set_reg(apic, APIC_ID, id << 24);
-	apic_set_reg(apic, APIC_LDR, ldr);
+	kvm_lapic_set_reg(apic, APIC_ID, id << 24);
+	kvm_lapic_set_reg(apic, APIC_LDR, ldr);
 	recalculate_apic_map(apic->vcpu->kvm);
 }
 
 static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
 {
-	return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
+	return !(kvm_lapic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
 }
 
 static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type)
 {
-	return kvm_apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
+	return kvm_lapic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
 }
 
 static inline int apic_lvtt_oneshot(struct kvm_lapic *apic)
@@ -287,10 +273,10 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
 	if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31))))
 		v |= APIC_LVR_DIRECTED_EOI;
-	apic_set_reg(apic, APIC_LVR, v);
+	kvm_lapic_set_reg(apic, APIC_LVR, v);
 }
 
-static const unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
+static const unsigned int apic_lvt_mask[KVM_APIC_LVT_NUM] = {
 	LVT_MASK ,      /* part LVTT mask, timer mode mask added at runtime */
 	LVT_MASK | APIC_MODE_MASK,	/* LVTTHMR */
 	LVT_MASK | APIC_MODE_MASK,	/* LVTPC */
@@ -349,16 +335,6 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
 }
 EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
 
-static inline void apic_set_irr(int vec, struct kvm_lapic *apic)
-{
-	apic_set_vector(vec, apic->regs + APIC_IRR);
-	/*
-	 * irr_pending must be true if any interrupt is pending; set it after
-	 * APIC_IRR to avoid race with apic_clear_irr
-	 */
-	apic->irr_pending = true;
-}
-
 static inline int apic_search_irr(struct kvm_lapic *apic)
 {
 	return find_highest_vector(apic->regs + APIC_IRR);
@@ -416,7 +392,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 	 * just set SVI.
 	 */
 	if (unlikely(vcpu->arch.apicv_active))
-		kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
+		kvm_x86_ops->hwapic_isr_update(vcpu, vec);
 	else {
 		++apic->isr_count;
 		BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
@@ -464,7 +440,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 	 * and must be left alone.
 	 */
 	if (unlikely(vcpu->arch.apicv_active))
-		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+		kvm_x86_ops->hwapic_isr_update(vcpu,
 					       apic_find_highest_isr(apic));
 	else {
 		--apic->isr_count;
@@ -549,8 +525,8 @@ static void apic_update_ppr(struct kvm_lapic *apic)
 	u32 tpr, isrv, ppr, old_ppr;
 	int isr;
 
-	old_ppr = kvm_apic_get_reg(apic, APIC_PROCPRI);
-	tpr = kvm_apic_get_reg(apic, APIC_TASKPRI);
+	old_ppr = kvm_lapic_get_reg(apic, APIC_PROCPRI);
+	tpr = kvm_lapic_get_reg(apic, APIC_TASKPRI);
 	isr = apic_find_highest_isr(apic);
 	isrv = (isr != -1) ? isr : 0;
 
@@ -563,7 +539,7 @@ static void apic_update_ppr(struct kvm_lapic *apic)
 		   apic, ppr, isr, isrv);
 
 	if (old_ppr != ppr) {
-		apic_set_reg(apic, APIC_PROCPRI, ppr);
+		kvm_lapic_set_reg(apic, APIC_PROCPRI, ppr);
 		if (ppr < old_ppr)
 			kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
 	}
@@ -571,7 +547,7 @@ static void apic_update_ppr(struct kvm_lapic *apic)
 
 static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr)
 {
-	apic_set_reg(apic, APIC_TASKPRI, tpr);
+	kvm_lapic_set_reg(apic, APIC_TASKPRI, tpr);
 	apic_update_ppr(apic);
 }
 
@@ -601,7 +577,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
 	if (kvm_apic_broadcast(apic, mda))
 		return true;
 
-	logical_id = kvm_apic_get_reg(apic, APIC_LDR);
+	logical_id = kvm_lapic_get_reg(apic, APIC_LDR);
 
 	if (apic_x2apic_mode(apic))
 		return ((logical_id >> 16) == (mda >> 16))
@@ -610,7 +586,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
 	logical_id = GET_APIC_LOGICAL_ID(logical_id);
 	mda = GET_APIC_DEST_FIELD(mda);
 
-	switch (kvm_apic_get_reg(apic, APIC_DFR)) {
+	switch (kvm_lapic_get_reg(apic, APIC_DFR)) {
 	case APIC_DFR_FLAT:
 		return (logical_id & mda) != 0;
 	case APIC_DFR_CLUSTER:
@@ -618,7 +594,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
 		       && (logical_id & mda & 0xf) != 0;
 	default:
 		apic_debug("Bad DFR vcpu %d: %08x\n",
-			   apic->vcpu->vcpu_id, kvm_apic_get_reg(apic, APIC_DFR));
+			   apic->vcpu->vcpu_id, kvm_lapic_get_reg(apic, APIC_DFR));
 		return false;
 	}
 }
@@ -668,6 +644,7 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 		return false;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_apic_match_dest);
 
 int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
 		       const unsigned long *bitmap, u32 bitmap_size)
@@ -921,7 +898,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 
 		if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) {
 			if (trig_mode)
-				apic_set_vector(vector, apic->regs + APIC_TMR);
+				kvm_lapic_set_vector(vector, apic->regs + APIC_TMR);
 			else
 				apic_clear_vector(vector, apic->regs + APIC_TMR);
 		}
@@ -929,7 +906,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		if (vcpu->arch.apicv_active)
 			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
 		else {
-			apic_set_irr(vector, apic);
+			kvm_lapic_set_irr(vector, apic);
 
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
@@ -1073,8 +1050,8 @@ EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated);
 
 static void apic_send_ipi(struct kvm_lapic *apic)
 {
-	u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR);
-	u32 icr_high = kvm_apic_get_reg(apic, APIC_ICR2);
+	u32 icr_low = kvm_lapic_get_reg(apic, APIC_ICR);
+	u32 icr_high = kvm_lapic_get_reg(apic, APIC_ICR2);
 	struct kvm_lapic_irq irq;
 
 	irq.vector = icr_low & APIC_VECTOR_MASK;
@@ -1111,7 +1088,7 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	ASSERT(apic != NULL);
 
 	/* if initial count is 0, current count should also be 0 */
-	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 ||
+	if (kvm_lapic_get_reg(apic, APIC_TMICT) == 0 ||
 		apic->lapic_timer.period == 0)
 		return 0;
 
@@ -1168,13 +1145,13 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 		break;
 	case APIC_PROCPRI:
 		apic_update_ppr(apic);
-		val = kvm_apic_get_reg(apic, offset);
+		val = kvm_lapic_get_reg(apic, offset);
 		break;
 	case APIC_TASKPRI:
 		report_tpr_access(apic, false);
 		/* fall thru */
 	default:
-		val = kvm_apic_get_reg(apic, offset);
+		val = kvm_lapic_get_reg(apic, offset);
 		break;
 	}
 
@@ -1186,7 +1163,7 @@ static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev)
 	return container_of(dev, struct kvm_lapic, dev);
 }
 
-static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
+int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 		void *data)
 {
 	unsigned char alignment = offset & 0xf;
@@ -1223,6 +1200,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvm_lapic_reg_read);
 
 static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
 {
@@ -1240,7 +1218,7 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!apic_mmio_in_range(apic, address))
 		return -EOPNOTSUPP;
 
-	apic_reg_read(apic, offset, len, data);
+	kvm_lapic_reg_read(apic, offset, len, data);
 
 	return 0;
 }
@@ -1249,7 +1227,7 @@ static void update_divide_count(struct kvm_lapic *apic)
 {
 	u32 tmp1, tmp2, tdcr;
 
-	tdcr = kvm_apic_get_reg(apic, APIC_TDCR);
+	tdcr = kvm_lapic_get_reg(apic, APIC_TDCR);
 	tmp1 = tdcr & 0xf;
 	tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1;
 	apic->divide_count = 0x1 << (tmp2 & 0x7);
@@ -1260,7 +1238,7 @@ static void update_divide_count(struct kvm_lapic *apic)
 
 static void apic_update_lvtt(struct kvm_lapic *apic)
 {
-	u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) &
+	u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) &
 			apic->lapic_timer.timer_mode_mask;
 
 	if (apic->lapic_timer.timer_mode != timer_mode) {
@@ -1296,7 +1274,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	u32 reg = kvm_apic_get_reg(apic, APIC_LVTT);
+	u32 reg = kvm_lapic_get_reg(apic, APIC_LVTT);
 
 	if (kvm_apic_hw_enabled(apic)) {
 		int vec = reg & APIC_VECTOR_MASK;
@@ -1332,7 +1310,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 
 	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
 	if (guest_tsc < tsc_deadline)
-		__delay(tsc_deadline - guest_tsc);
+		__delay(min(tsc_deadline - guest_tsc,
+			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
 }
 
 static void start_apic_timer(struct kvm_lapic *apic)
@@ -1344,7 +1323,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
 		/* lapic timer in oneshot or periodic mode */
 		now = apic->lapic_timer.timer.base->get_time();
-		apic->lapic_timer.period = (u64)kvm_apic_get_reg(apic, APIC_TMICT)
+		apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT)
 			    * APIC_BUS_CYCLE_NS * apic->divide_count;
 
 		if (!apic->lapic_timer.period)
@@ -1376,7 +1355,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 			   "timer initial count 0x%x, period %lldns, "
 			   "expire @ 0x%016" PRIx64 ".\n", __func__,
 			   APIC_BUS_CYCLE_NS, ktime_to_ns(now),
-			   kvm_apic_get_reg(apic, APIC_TMICT),
+			   kvm_lapic_get_reg(apic, APIC_TMICT),
 			   apic->lapic_timer.period,
 			   ktime_to_ns(ktime_add_ns(now,
 					apic->lapic_timer.period)));
@@ -1425,7 +1404,7 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 	}
 }
 
-static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
+int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 {
 	int ret = 0;
 
@@ -1457,7 +1436,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 	case APIC_DFR:
 		if (!apic_x2apic_mode(apic)) {
-			apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
+			kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
 			recalculate_apic_map(apic->vcpu->kvm);
 		} else
 			ret = 1;
@@ -1465,17 +1444,17 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 	case APIC_SPIV: {
 		u32 mask = 0x3ff;
-		if (kvm_apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
+		if (kvm_lapic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
 			mask |= APIC_SPIV_DIRECTED_EOI;
 		apic_set_spiv(apic, val & mask);
 		if (!(val & APIC_SPIV_APIC_ENABLED)) {
 			int i;
 			u32 lvt_val;
 
-			for (i = 0; i < APIC_LVT_NUM; i++) {
-				lvt_val = kvm_apic_get_reg(apic,
+			for (i = 0; i < KVM_APIC_LVT_NUM; i++) {
+				lvt_val = kvm_lapic_get_reg(apic,
 						       APIC_LVTT + 0x10 * i);
-				apic_set_reg(apic, APIC_LVTT + 0x10 * i,
+				kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i,
 					     lvt_val | APIC_LVT_MASKED);
 			}
 			apic_update_lvtt(apic);
@@ -1486,14 +1465,14 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	}
 	case APIC_ICR:
 		/* No delay here, so we always clear the pending bit */
-		apic_set_reg(apic, APIC_ICR, val & ~(1 << 12));
+		kvm_lapic_set_reg(apic, APIC_ICR, val & ~(1 << 12));
 		apic_send_ipi(apic);
 		break;
 
 	case APIC_ICR2:
 		if (!apic_x2apic_mode(apic))
 			val &= 0xff000000;
-		apic_set_reg(apic, APIC_ICR2, val);
+		kvm_lapic_set_reg(apic, APIC_ICR2, val);
 		break;
 
 	case APIC_LVT0:
@@ -1507,7 +1486,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 			val |= APIC_LVT_MASKED;
 
 		val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
-		apic_set_reg(apic, reg, val);
+		kvm_lapic_set_reg(apic, reg, val);
 
 		break;
 
@@ -1515,7 +1494,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
 		val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
-		apic_set_reg(apic, APIC_LVTT, val);
+		kvm_lapic_set_reg(apic, APIC_LVTT, val);
 		apic_update_lvtt(apic);
 		break;
 
@@ -1524,14 +1503,14 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 			break;
 
 		hrtimer_cancel(&apic->lapic_timer.timer);
-		apic_set_reg(apic, APIC_TMICT, val);
+		kvm_lapic_set_reg(apic, APIC_TMICT, val);
 		start_apic_timer(apic);
 		break;
 
 	case APIC_TDCR:
 		if (val & 4)
 			apic_debug("KVM_WRITE:TDCR %x\n", val);
-		apic_set_reg(apic, APIC_TDCR, val);
+		kvm_lapic_set_reg(apic, APIC_TDCR, val);
 		update_divide_count(apic);
 		break;
 
@@ -1544,7 +1523,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 	case APIC_SELF_IPI:
 		if (apic_x2apic_mode(apic)) {
-			apic_reg_write(apic, APIC_ICR, 0x40000 | (val & 0xff));
+			kvm_lapic_reg_write(apic, APIC_ICR, 0x40000 | (val & 0xff));
 		} else
 			ret = 1;
 		break;
@@ -1556,6 +1535,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 		apic_debug("Local APIC Write to read-only register %x\n", reg);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(kvm_lapic_reg_write);
 
 static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 			    gpa_t address, int len, const void *data)
@@ -1585,14 +1565,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 		apic_debug("%s: offset 0x%x with length 0x%x, and value is "
 			   "0x%x\n", __func__, offset, len, val);
 
-	apic_reg_write(apic, offset & 0xff0, val);
+	kvm_lapic_reg_write(apic, offset & 0xff0, val);
 
 	return 0;
 }
 
 void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
 {
-	apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
+	kvm_lapic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
 
@@ -1604,10 +1584,10 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
 	/* hw has done the conditional check and inst decode */
 	offset &= 0xff0;
 
-	apic_reg_read(vcpu->arch.apic, offset, 4, &val);
+	kvm_lapic_reg_read(vcpu->arch.apic, offset, 4, &val);
 
 	/* TODO: optimize to just emulate side effect w/o one more write */
-	apic_reg_write(vcpu->arch.apic, offset, val);
+	kvm_lapic_reg_write(vcpu->arch.apic, offset, val);
 }
 EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode);
 
@@ -1667,14 +1647,14 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
-		     | (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4));
+		     | (kvm_lapic_get_reg(apic, APIC_TASKPRI) & 4));
 }
 
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 {
 	u64 tpr;
 
-	tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI);
+	tpr = (u64) kvm_lapic_get_reg(vcpu->arch.apic, APIC_TASKPRI);
 
 	return (tpr & 0xf0) >> 4;
 }
@@ -1740,28 +1720,28 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 		kvm_apic_set_id(apic, vcpu->vcpu_id);
 	kvm_apic_set_version(apic->vcpu);
 
-	for (i = 0; i < APIC_LVT_NUM; i++)
-		apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
+	for (i = 0; i < KVM_APIC_LVT_NUM; i++)
+		kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
 	apic_update_lvtt(apic);
 	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
-		apic_set_reg(apic, APIC_LVT0,
+		kvm_lapic_set_reg(apic, APIC_LVT0,
 			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
-	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
+	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
 
-	apic_set_reg(apic, APIC_DFR, 0xffffffffU);
+	kvm_lapic_set_reg(apic, APIC_DFR, 0xffffffffU);
 	apic_set_spiv(apic, 0xff);
-	apic_set_reg(apic, APIC_TASKPRI, 0);
+	kvm_lapic_set_reg(apic, APIC_TASKPRI, 0);
 	if (!apic_x2apic_mode(apic))
 		kvm_apic_set_ldr(apic, 0);
-	apic_set_reg(apic, APIC_ESR, 0);
-	apic_set_reg(apic, APIC_ICR, 0);
-	apic_set_reg(apic, APIC_ICR2, 0);
-	apic_set_reg(apic, APIC_TDCR, 0);
-	apic_set_reg(apic, APIC_TMICT, 0);
+	kvm_lapic_set_reg(apic, APIC_ESR, 0);
+	kvm_lapic_set_reg(apic, APIC_ICR, 0);
+	kvm_lapic_set_reg(apic, APIC_ICR2, 0);
+	kvm_lapic_set_reg(apic, APIC_TDCR, 0);
+	kvm_lapic_set_reg(apic, APIC_TMICT, 0);
 	for (i = 0; i < 8; i++) {
-		apic_set_reg(apic, APIC_IRR + 0x10 * i, 0);
-		apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
-		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
+		kvm_lapic_set_reg(apic, APIC_IRR + 0x10 * i, 0);
+		kvm_lapic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
+		kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
 	apic->irr_pending = vcpu->arch.apicv_active;
 	apic->isr_count = vcpu->arch.apicv_active ? 1 : 0;
@@ -1806,7 +1786,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu)
 
 int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
 {
-	u32 reg = kvm_apic_get_reg(apic, lvt_type);
+	u32 reg = kvm_lapic_get_reg(apic, lvt_type);
 	int vector, mode, trig_mode;
 
 	if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
@@ -1901,14 +1881,14 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	apic_update_ppr(apic);
 	highest_irr = apic_find_highest_irr(apic);
 	if ((highest_irr == -1) ||
-	    ((highest_irr & 0xF0) <= kvm_apic_get_reg(apic, APIC_PROCPRI)))
+	    ((highest_irr & 0xF0) <= kvm_lapic_get_reg(apic, APIC_PROCPRI)))
 		return -1;
 	return highest_irr;
 }
 
 int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu)
 {
-	u32 lvt0 = kvm_apic_get_reg(vcpu->arch.apic, APIC_LVT0);
+	u32 lvt0 = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVT0);
 	int r = 0;
 
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
@@ -1974,7 +1954,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
 	apic_update_lvtt(apic);
-	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
+	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
@@ -1982,9 +1962,11 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 				1 : count_vectors(apic->regs + APIC_ISR);
 	apic->highest_isr_cache = -1;
 	if (vcpu->arch.apicv_active) {
+		if (kvm_x86_ops->apicv_post_state_restore)
+			kvm_x86_ops->apicv_post_state_restore(vcpu);
 		kvm_x86_ops->hwapic_irr_update(vcpu,
 				apic_find_highest_irr(apic));
-		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+		kvm_x86_ops->hwapic_isr_update(vcpu,
 				apic_find_highest_isr(apic));
 	}
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -2097,7 +2079,7 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	tpr = kvm_apic_get_reg(apic, APIC_TASKPRI) & 0xff;
+	tpr = kvm_lapic_get_reg(apic, APIC_TASKPRI) & 0xff;
 	max_irr = apic_find_highest_irr(apic);
 	if (max_irr < 0)
 		max_irr = 0;
@@ -2139,8 +2121,8 @@ int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 
 	/* if this is ICR write vector before command */
 	if (reg == APIC_ICR)
-		apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
-	return apic_reg_write(apic, reg, (u32)data);
+		kvm_lapic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
+	return kvm_lapic_reg_write(apic, reg, (u32)data);
 }
 
 int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
@@ -2157,10 +2139,10 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 		return 1;
 	}
 
-	if (apic_reg_read(apic, reg, 4, &low))
+	if (kvm_lapic_reg_read(apic, reg, 4, &low))
 		return 1;
 	if (reg == APIC_ICR)
-		apic_reg_read(apic, APIC_ICR2, 4, &high);
+		kvm_lapic_reg_read(apic, APIC_ICR2, 4, &high);
 
 	*data = (((u64)high) << 32) | low;
 
@@ -2176,8 +2158,8 @@ int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data)
 
 	/* if this is ICR write vector before command */
 	if (reg == APIC_ICR)
-		apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
-	return apic_reg_write(apic, reg, (u32)data);
+		kvm_lapic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
+	return kvm_lapic_reg_write(apic, reg, (u32)data);
 }
 
 int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
@@ -2188,10 +2170,10 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
 	if (!lapic_in_kernel(vcpu))
 		return 1;
 
-	if (apic_reg_read(apic, reg, 4, &low))
+	if (kvm_lapic_reg_read(apic, reg, 4, &low))
 		return 1;
 	if (reg == APIC_ICR)
-		apic_reg_read(apic, APIC_ICR2, 4, &high);
+		kvm_lapic_reg_read(apic, APIC_ICR2, 4, &high);
 
 	*data = (((u64)high) << 32) | low;
 
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index f71183e50..891c6da7d 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -7,6 +7,10 @@
 
 #define KVM_APIC_INIT		0
 #define KVM_APIC_SIPI		1
+#define KVM_APIC_LVT_NUM	6
+
+#define KVM_APIC_SHORT_MASK	0xc0000
+#define KVM_APIC_DEST_MASK	0x800
 
 struct kvm_timer {
 	struct hrtimer timer;
@@ -59,6 +63,11 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu);
 void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
 u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
 void kvm_apic_set_version(struct kvm_vcpu *vcpu);
+int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val);
+int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
+		       void *data);
+bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+			   int short_hand, unsigned int dest, int dest_mode);
 
 void __kvm_apic_update_irr(u32 *pir, void *regs);
 void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir);
@@ -99,9 +108,32 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
 void kvm_lapic_init(void);
 
-static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off)
+#define VEC_POS(v) ((v) & (32 - 1))
+#define REG_POS(v) (((v) >> 5) << 4)
+
+static inline void kvm_lapic_set_vector(int vec, void *bitmap)
+{
+	set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
+static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic)
+{
+	kvm_lapic_set_vector(vec, apic->regs + APIC_IRR);
+	/*
+	 * irr_pending must be true if any interrupt is pending; set it after
+	 * APIC_IRR to avoid race with apic_clear_irr
+	 */
+	apic->irr_pending = true;
+}
+
+static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off)
+{
+	return *((u32 *) (apic->regs + reg_off));
+}
+
+static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
 {
-	        return *((u32 *) (apic->regs + reg_off));
+	*((u32 *) (apic->regs + reg_off)) = val;
 }
 
 extern struct static_key kvm_no_apic_vcpu;
@@ -169,7 +201,7 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
 
 static inline int kvm_apic_id(struct kvm_lapic *apic)
 {
-	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+	return (kvm_lapic_get_reg(apic, APIC_ID) >> 24) & 0xff;
 }
 
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b6f50e8b0..def97b3a3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -336,12 +336,12 @@ static gfn_t pse36_gfn_delta(u32 gpte)
 #ifdef CONFIG_X86_64
 static void __set_spte(u64 *sptep, u64 spte)
 {
-	*sptep = spte;
+	WRITE_ONCE(*sptep, spte);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 {
-	*sptep = spte;
+	WRITE_ONCE(*sptep, spte);
 }
 
 static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
@@ -390,7 +390,7 @@ static void __set_spte(u64 *sptep, u64 spte)
 	 */
 	smp_wmb();
 
-	ssptep->spte_low = sspte.spte_low;
+	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
@@ -400,7 +400,7 @@ static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 	ssptep = (union split_spte *)sptep;
 	sspte = (union split_spte)spte;
 
-	ssptep->spte_low = sspte.spte_low;
+	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
 
 	/*
 	 * If we map the spte from present to nonpresent, we should clear
@@ -1909,18 +1909,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
  * since it has been deleted from active_mmu_pages but still can be found
  * at hast list.
  *
- * for_each_gfn_indirect_valid_sp has skipped that kind of page and
- * kvm_mmu_get_page(), the only user of for_each_gfn_sp(), has skipped
- * all the obsolete pages.
+ * for_each_gfn_valid_sp() has skipped that kind of pages.
  */
-#define for_each_gfn_sp(_kvm, _sp, _gfn)				\
+#define for_each_gfn_valid_sp(_kvm, _sp, _gfn)				\
 	hlist_for_each_entry(_sp,					\
 	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
-		if ((_sp)->gfn != (_gfn)) {} else
+		if ((_sp)->gfn != (_gfn) || is_obsolete_sp((_kvm), (_sp)) \
+			|| (_sp)->role.invalid) {} else
 
 #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn)			\
-	for_each_gfn_sp(_kvm, _sp, _gfn)				\
-		if ((_sp)->role.direct || (_sp)->role.invalid) {} else
+	for_each_gfn_valid_sp(_kvm, _sp, _gfn)				\
+		if ((_sp)->role.direct) {} else
 
 /* @sp->gfn should be write-protected at the call site */
 static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
@@ -1961,6 +1960,11 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { }
 static void mmu_audit_disable(void) { }
 #endif
 
+static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
+}
+
 static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			 struct list_head *invalid_list)
 {
@@ -2105,11 +2109,6 @@ static void clear_sp_write_flooding_count(u64 *spte)
 	__clear_sp_write_flooding_count(sp);
 }
 
-static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
-{
-	return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
-}
-
 static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 					     gfn_t gfn,
 					     gva_t gaddr,
@@ -2136,10 +2135,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
 		role.quadrant = quadrant;
 	}
-	for_each_gfn_sp(vcpu->kvm, sp, gfn) {
-		if (is_obsolete_sp(vcpu->kvm, sp))
-			continue;
-
+	for_each_gfn_valid_sp(vcpu->kvm, sp, gfn) {
 		if (!need_sync && sp->unsync)
 			need_sync = true;
 
@@ -3844,7 +3840,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 					boot_cpu_data.x86_phys_bits,
 					context->shadow_root_level, false,
-					cpu_has_gbpages, true, true);
+					boot_cpu_has(X86_FEATURE_GBPAGES),
+					true, true);
 	else
 		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
 					    boot_cpu_data.x86_phys_bits,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 31346a3f2..16ef31b87 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -14,6 +14,9 @@
  * the COPYING file in the top-level directory.
  *
  */
+
+#define pr_fmt(fmt) "SVM: " fmt
+
 #include <linux/kvm_host.h>
 
 #include "irq.h"
@@ -32,6 +35,7 @@
 #include <linux/trace_events.h>
 #include <linux/slab.h>
 
+#include <asm/apic.h>
 #include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
@@ -68,6 +72,8 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
 #define SVM_FEATURE_DECODE_ASSIST  (1 <<  7)
 #define SVM_FEATURE_PAUSE_FILTER   (1 << 10)
 
+#define SVM_AVIC_DOORBELL	0xc001011b
+
 #define NESTED_EXIT_HOST	0	/* Exit handled on host level */
 #define NESTED_EXIT_DONE	1	/* Exit caused nested vmexit  */
 #define NESTED_EXIT_CONTINUE	2	/* Further checks needed      */
@@ -78,6 +84,18 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
 #define TSC_RATIO_MIN		0x0000000000000001ULL
 #define TSC_RATIO_MAX		0x000000ffffffffffULL
 
+#define AVIC_HPA_MASK	~((0xFFFULL << 52) | 0xFFF)
+
+/*
+ * 0xff is broadcast, so the max index allowed for physical APIC ID
+ * table is 0xfe.  APIC IDs above 0xff are reserved.
+ */
+#define AVIC_MAX_PHYSICAL_ID_COUNT	255
+
+#define AVIC_UNACCEL_ACCESS_WRITE_MASK		1
+#define AVIC_UNACCEL_ACCESS_OFFSET_MASK		0xFF0
+#define AVIC_UNACCEL_ACCESS_VECTOR_MASK		0xFFFFFFFF
+
 static bool erratum_383_found __read_mostly;
 
 static const u32 host_save_user_msrs[] = {
@@ -162,8 +180,21 @@ struct vcpu_svm {
 
 	/* cached guest cpuid flags for faster access */
 	bool nrips_enabled	: 1;
+
+	u32 ldr_reg;
+	struct page *avic_backing_page;
+	u64 *avic_physical_id_cache;
+	bool avic_is_running;
 };
 
+#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK	(0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK		(1 << 31)
+
+#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK	(0xFFULL)
+#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK	(0xFFFFFFFFFFULL << 12)
+#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK		(1ULL << 62)
+#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK		(1ULL << 63)
+
 static DEFINE_PER_CPU(u64, current_tsc_ratio);
 #define TSC_RATIO_DEFAULT	0x0100000000ULL
 
@@ -205,6 +236,12 @@ module_param(npt, int, S_IRUGO);
 static int nested = true;
 module_param(nested, int, S_IRUGO);
 
+/* enable / disable AVIC */
+static int avic;
+#ifdef CONFIG_X86_LOCAL_APIC
+module_param(avic, int, S_IRUGO);
+#endif
+
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
@@ -228,12 +265,18 @@ enum {
 	VMCB_SEG,        /* CS, DS, SS, ES, CPL */
 	VMCB_CR2,        /* CR2 only */
 	VMCB_LBR,        /* DBGCTL, BR_FROM, BR_TO, LAST_EX_FROM, LAST_EX_TO */
+	VMCB_AVIC,       /* AVIC APIC_BAR, AVIC APIC_BACKING_PAGE,
+			  * AVIC PHYSICAL_TABLE pointer,
+			  * AVIC LOGICAL_TABLE pointer
+			  */
 	VMCB_DIRTY_MAX,
 };
 
 /* TPR and CR2 are always written before VMRUN */
 #define VMCB_ALWAYS_DIRTY_MASK	((1U << VMCB_INTR) | (1U << VMCB_CR2))
 
+#define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
+
 static inline void mark_all_dirty(struct vmcb *vmcb)
 {
 	vmcb->control.clean = 0;
@@ -255,6 +298,23 @@ static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct vcpu_svm, vcpu);
 }
 
+static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data)
+{
+	svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK;
+	mark_dirty(svm->vmcb, VMCB_AVIC);
+}
+
+static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u64 *entry = svm->avic_physical_id_cache;
+
+	if (!entry)
+		return false;
+
+	return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
+}
+
 static void recalc_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *c, *h;
@@ -923,6 +983,15 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
+	if (avic) {
+		if (!npt_enabled ||
+		    !boot_cpu_has(X86_FEATURE_AVIC) ||
+		    !IS_ENABLED(CONFIG_X86_LOCAL_APIC))
+			avic = false;
+		else
+			pr_info("AVIC enabled\n");
+	}
+
 	return 0;
 
 err:
@@ -1000,6 +1069,22 @@ static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment)
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
+static void avic_init_vmcb(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = svm->vmcb;
+	struct kvm_arch *vm_data = &svm->vcpu.kvm->arch;
+	phys_addr_t bpa = page_to_phys(svm->avic_backing_page);
+	phys_addr_t lpa = page_to_phys(vm_data->avic_logical_id_table_page);
+	phys_addr_t ppa = page_to_phys(vm_data->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_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT;
+	vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
+	svm->vcpu.arch.apicv_active = true;
+}
+
 static void init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1014,7 +1099,8 @@ static void init_vmcb(struct vcpu_svm *svm)
 	set_cr_intercept(svm, INTERCEPT_CR0_WRITE);
 	set_cr_intercept(svm, INTERCEPT_CR3_WRITE);
 	set_cr_intercept(svm, INTERCEPT_CR4_WRITE);
-	set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+	if (!kvm_vcpu_apicv_active(&svm->vcpu))
+		set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
 
 	set_dr_intercepts(svm);
 
@@ -1110,9 +1196,197 @@ static void init_vmcb(struct vcpu_svm *svm)
 		set_intercept(svm, INTERCEPT_PAUSE);
 	}
 
+	if (avic)
+		avic_init_vmcb(svm);
+
 	mark_all_dirty(svm->vmcb);
 
 	enable_gif(svm);
+
+}
+
+static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, int index)
+{
+	u64 *avic_physical_id_table;
+	struct kvm_arch *vm_data = &vcpu->kvm->arch;
+
+	if (index >= AVIC_MAX_PHYSICAL_ID_COUNT)
+		return NULL;
+
+	avic_physical_id_table = page_address(vm_data->avic_physical_id_table_page);
+
+	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_init_access_page(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int ret;
+
+	if (kvm->arch.apic_access_page_done)
+		return 0;
+
+	ret = x86_set_memory_region(kvm,
+				    APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+				    APIC_DEFAULT_PHYS_BASE,
+				    PAGE_SIZE);
+	if (ret)
+		return ret;
+
+	kvm->arch.apic_access_page_done = true;
+	return 0;
+}
+
+static int avic_init_backing_page(struct kvm_vcpu *vcpu)
+{
+	int ret;
+	u64 *entry, new_entry;
+	int id = vcpu->vcpu_id;
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	ret = avic_init_access_page(vcpu);
+	if (ret)
+		return ret;
+
+	if (id >= AVIC_MAX_PHYSICAL_ID_COUNT)
+		return -EINVAL;
+
+	if (!svm->vcpu.arch.apic->regs)
+		return -EINVAL;
+
+	svm->avic_backing_page = virt_to_page(svm->vcpu.arch.apic->regs);
+
+	/* 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 = READ_ONCE(*entry);
+	new_entry = (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;
+
+	return 0;
+}
+
+static void avic_vm_destroy(struct kvm *kvm)
+{
+	struct kvm_arch *vm_data = &kvm->arch;
+
+	if (vm_data->avic_logical_id_table_page)
+		__free_page(vm_data->avic_logical_id_table_page);
+	if (vm_data->avic_physical_id_table_page)
+		__free_page(vm_data->avic_physical_id_table_page);
+}
+
+static int avic_vm_init(struct kvm *kvm)
+{
+	int err = -ENOMEM;
+	struct kvm_arch *vm_data = &kvm->arch;
+	struct page *p_page;
+	struct page *l_page;
+
+	if (!avic)
+		return 0;
+
+	/* Allocating physical APIC ID table (4KB) */
+	p_page = alloc_page(GFP_KERNEL);
+	if (!p_page)
+		goto free_avic;
+
+	vm_data->avic_physical_id_table_page = p_page;
+	clear_page(page_address(p_page));
+
+	/* Allocating logical APIC ID table (4KB) */
+	l_page = alloc_page(GFP_KERNEL);
+	if (!l_page)
+		goto free_avic;
+
+	vm_data->avic_logical_id_table_page = l_page;
+	clear_page(page_address(l_page));
+
+	return 0;
+
+free_avic:
+	avic_vm_destroy(kvm);
+	return err;
+}
+
+/**
+ * This function is called during VCPU halt/unhalt.
+ */
+static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+{
+	u64 entry;
+	int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	svm->avic_is_running = is_run;
+
+	/* ID = 0xff (broadcast), ID > 0xff (reserved) */
+	if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
+		return;
+
+	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	WARN_ON(is_run == !!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK));
+
+	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+	if (is_run)
+		entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+}
+
+static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	u64 entry;
+	/* ID = 0xff (broadcast), ID > 0xff (reserved) */
+	int h_physical_id = kvm_cpu_get_apicid(cpu);
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
+		return;
+
+	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	WARN_ON(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);
+
+	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+	if (svm->avic_is_running)
+		entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+
+	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+}
+
+static void avic_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	u64 entry;
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 }
 
 static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -1131,6 +1405,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy);
 	kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
+
+	if (kvm_vcpu_apicv_active(vcpu) && !init_event)
+		avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE);
 }
 
 static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
@@ -1169,6 +1446,17 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!hsave_page)
 		goto free_page3;
 
+	if (avic) {
+		err = avic_init_backing_page(&svm->vcpu);
+		if (err)
+			goto free_page4;
+	}
+
+	/* We initialize this flag to true to make sure that the is_running
+	 * bit would be set the first time the vcpu is loaded.
+	 */
+	svm->avic_is_running = true;
+
 	svm->nested.hsave = page_address(hsave_page);
 
 	svm->msrpm = page_address(msrpm_pages);
@@ -1187,6 +1475,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	return &svm->vcpu;
 
+free_page4:
+	__free_page(hsave_page);
 free_page3:
 	__free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
 free_page2:
@@ -1243,6 +1533,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	/* This assumes that the kernel never uses MSR_TSC_AUX */
 	if (static_cpu_has(X86_FEATURE_RDTSCP))
 		wrmsrl(MSR_TSC_AUX, svm->tsc_aux);
+
+	avic_vcpu_load(vcpu, cpu);
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
@@ -1250,11 +1542,13 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	int i;
 
+	avic_vcpu_put(vcpu);
+
 	++vcpu->stat.host_state_reload;
 	kvm_load_ldt(svm->host.ldt);
 #ifdef CONFIG_X86_64
 	loadsegment(fs, svm->host.fs);
-	wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
+	wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase);
 	load_gs_index(svm->host.gs);
 #else
 #ifdef CONFIG_X86_32_LAZY_GS
@@ -1265,6 +1559,16 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 }
 
+static void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
+{
+	avic_set_running(vcpu, false);
+}
+
+static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+	avic_set_running(vcpu, true);
+}
+
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 {
 	return to_svm(vcpu)->vmcb->save.rflags;
@@ -2673,10 +2977,11 @@ static int clgi_interception(struct vcpu_svm *svm)
 	disable_gif(svm);
 
 	/* After a CLGI no interrupts should come */
-	svm_clear_vintr(svm);
-	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
-
-	mark_dirty(svm->vmcb, VMCB_INTR);
+	if (!kvm_vcpu_apicv_active(&svm->vcpu)) {
+		svm_clear_vintr(svm);
+		svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
+		mark_dirty(svm->vmcb, VMCB_INTR);
+	}
 
 	return 1;
 }
@@ -3212,6 +3517,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
+	case MSR_IA32_APICBASE:
+		if (kvm_vcpu_apicv_active(vcpu))
+			avic_update_vapic_bar(to_svm(vcpu), data);
+		/* Follow through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -3281,6 +3590,278 @@ static int mwait_interception(struct vcpu_svm *svm)
 	return nop_interception(svm);
 }
 
+enum avic_ipi_failure_cause {
+	AVIC_IPI_FAILURE_INVALID_INT_TYPE,
+	AVIC_IPI_FAILURE_TARGET_NOT_RUNNING,
+	AVIC_IPI_FAILURE_INVALID_TARGET,
+	AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
+};
+
+static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
+{
+	u32 icrh = svm->vmcb->control.exit_info_1 >> 32;
+	u32 icrl = svm->vmcb->control.exit_info_1;
+	u32 id = svm->vmcb->control.exit_info_2 >> 32;
+	u32 index = svm->vmcb->control.exit_info_2 & 0xFF;
+	struct kvm_lapic *apic = svm->vcpu.arch.apic;
+
+	trace_kvm_avic_incomplete_ipi(svm->vcpu.vcpu_id, icrh, icrl, id, index);
+
+	switch (id) {
+	case AVIC_IPI_FAILURE_INVALID_INT_TYPE:
+		/*
+		 * AVIC hardware handles the generation of
+		 * IPIs when the specified Message Type is Fixed
+		 * (also known as fixed delivery mode) and
+		 * the Trigger Mode is edge-triggered. The hardware
+		 * also supports self and broadcast delivery modes
+		 * specified via the Destination Shorthand(DSH)
+		 * field of the ICRL. Logical and physical APIC ID
+		 * formats are supported. All other IPI types cause
+		 * a #VMEXIT, which needs to emulated.
+		 */
+		kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
+		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+		break;
+	case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
+		int i;
+		struct kvm_vcpu *vcpu;
+		struct kvm *kvm = svm->vcpu.kvm;
+		struct kvm_lapic *apic = svm->vcpu.arch.apic;
+
+		/*
+		 * At this point, we expect that the AVIC HW has already
+		 * set the appropriate IRR bits on the valid target
+		 * vcpus. So, we just need to kick the appropriate vcpu.
+		 */
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			bool m = kvm_apic_match_dest(vcpu, apic,
+						     icrl & KVM_APIC_SHORT_MASK,
+						     GET_APIC_DEST_FIELD(icrh),
+						     icrl & KVM_APIC_DEST_MASK);
+
+			if (m && !avic_vcpu_is_running(vcpu))
+				kvm_vcpu_wake_up(vcpu);
+		}
+		break;
+	}
+	case AVIC_IPI_FAILURE_INVALID_TARGET:
+		break;
+	case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
+		WARN_ONCE(1, "Invalid backing page\n");
+		break;
+	default:
+		pr_err("Unknown IPI interception\n");
+	}
+
+	return 1;
+}
+
+static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
+{
+	struct kvm_arch *vm_data = &vcpu->kvm->arch;
+	int index;
+	u32 *logical_apic_id_table;
+	int dlid = GET_APIC_LOGICAL_ID(ldr);
+
+	if (!dlid)
+		return NULL;
+
+	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;
+
+		if ((apic < 0) || (apic > 7) ||
+		    (cluster >= 0xf))
+			return NULL;
+		index = (cluster << 2) + apic;
+	}
+
+	logical_apic_id_table = (u32 *) page_address(vm_data->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,
+			  bool valid)
+{
+	bool flat;
+	u32 *entry, new_entry;
+
+	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;
+
+	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);
+	if (valid)
+		new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK;
+	else
+		new_entry &= ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK;
+	WRITE_ONCE(*entry, new_entry);
+
+	return 0;
+}
+
+static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
+{
+	int ret;
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR);
+
+	if (!ldr)
+		return 1;
+
+	ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr, true);
+	if (ret && svm->ldr_reg) {
+		avic_ldr_write(vcpu, 0, svm->ldr_reg, false);
+		svm->ldr_reg = 0;
+	} else {
+		svm->ldr_reg = ldr;
+	}
+	return ret;
+}
+
+static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
+{
+	u64 *old, *new;
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID);
+	u32 id = (apic_id_reg >> 24) & 0xff;
+
+	if (vcpu->vcpu_id == id)
+		return 0;
+
+	old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id);
+	new = avic_get_physical_id_entry(vcpu, id);
+	if (!new || !old)
+		return 1;
+
+	/* We need to move physical_id_entry to new offset */
+	*new = *old;
+	*old = 0ULL;
+	to_svm(vcpu)->avic_physical_id_cache = new;
+
+	/*
+	 * Also update the guest physical APIC ID in the logical
+	 * APIC ID table entry if already setup the LDR.
+	 */
+	if (svm->ldr_reg)
+		avic_handle_ldr_update(vcpu);
+
+	return 0;
+}
+
+static int avic_handle_dfr_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_arch *vm_data = &vcpu->kvm->arch;
+	u32 dfr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR);
+	u32 mod = (dfr >> 28) & 0xf;
+
+	/*
+	 * We assume that all local APICs are using the same type.
+	 * If this changes, we need to flush the AVIC logical
+	 * APID id table.
+	 */
+	if (vm_data->ldr_mode == mod)
+		return 0;
+
+	clear_page(page_address(vm_data->avic_logical_id_table_page));
+	vm_data->ldr_mode = mod;
+
+	if (svm->ldr_reg)
+		avic_handle_ldr_update(vcpu);
+	return 0;
+}
+
+static int avic_unaccel_trap_write(struct vcpu_svm *svm)
+{
+	struct kvm_lapic *apic = svm->vcpu.arch.apic;
+	u32 offset = svm->vmcb->control.exit_info_1 &
+				AVIC_UNACCEL_ACCESS_OFFSET_MASK;
+
+	switch (offset) {
+	case APIC_ID:
+		if (avic_handle_apic_id_update(&svm->vcpu))
+			return 0;
+		break;
+	case APIC_LDR:
+		if (avic_handle_ldr_update(&svm->vcpu))
+			return 0;
+		break;
+	case APIC_DFR:
+		avic_handle_dfr_update(&svm->vcpu);
+		break;
+	default:
+		break;
+	}
+
+	kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset));
+
+	return 1;
+}
+
+static bool is_avic_unaccelerated_access_trap(u32 offset)
+{
+	bool ret = false;
+
+	switch (offset) {
+	case APIC_ID:
+	case APIC_EOI:
+	case APIC_RRR:
+	case APIC_LDR:
+	case APIC_DFR:
+	case APIC_SPIV:
+	case APIC_ESR:
+	case APIC_ICR:
+	case APIC_LVTT:
+	case APIC_LVTTHMR:
+	case APIC_LVTPC:
+	case APIC_LVT0:
+	case APIC_LVT1:
+	case APIC_LVTERR:
+	case APIC_TMICT:
+	case APIC_TDCR:
+		ret = true;
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
+static int avic_unaccelerated_access_interception(struct vcpu_svm *svm)
+{
+	int ret = 0;
+	u32 offset = svm->vmcb->control.exit_info_1 &
+		     AVIC_UNACCEL_ACCESS_OFFSET_MASK;
+	u32 vector = svm->vmcb->control.exit_info_2 &
+		     AVIC_UNACCEL_ACCESS_VECTOR_MASK;
+	bool write = (svm->vmcb->control.exit_info_1 >> 32) &
+		     AVIC_UNACCEL_ACCESS_WRITE_MASK;
+	bool trap = is_avic_unaccelerated_access_trap(offset);
+
+	trace_kvm_avic_unaccelerated_access(svm->vcpu.vcpu_id, offset,
+					    trap, write, vector);
+	if (trap) {
+		/* Handling Trap */
+		WARN_ONCE(!write, "svm: Handling trap read.\n");
+		ret = avic_unaccel_trap_write(svm);
+	} else {
+		/* Handling Fault */
+		ret = (emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE);
+	}
+
+	return ret;
+}
+
 static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR0]			= cr_interception,
 	[SVM_EXIT_READ_CR3]			= cr_interception,
@@ -3344,6 +3925,8 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_NPF]				= pf_interception,
 	[SVM_EXIT_RSM]                          = emulate_on_interception,
+	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
+	[SVM_EXIT_AVIC_UNACCELERATED_ACCESS]	= avic_unaccelerated_access_interception,
 };
 
 static void dump_vmcb(struct kvm_vcpu *vcpu)
@@ -3375,10 +3958,14 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	pr_err("%-20s%08x\n", "exit_int_info_err:", control->exit_int_info_err);
 	pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl);
 	pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3);
+	pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar);
 	pr_err("%-20s%08x\n", "event_inj:", control->event_inj);
 	pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err);
 	pr_err("%-20s%lld\n", "lbr_ctl:", control->lbr_ctl);
 	pr_err("%-20s%016llx\n", "next_rip:", control->next_rip);
+	pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page);
+	pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id);
+	pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id);
 	pr_err("VMCB State Save Area:\n");
 	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
 	       "es:",
@@ -3562,6 +4149,7 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq)
 {
 	struct vmcb_control_area *control;
 
+	/* The following fields are ignored when AVIC is enabled */
 	control = &svm->vmcb->control;
 	control->int_vector = irq;
 	control->int_ctl &= ~V_INTR_PRIO_MASK;
@@ -3583,11 +4171,17 @@ static void svm_set_irq(struct kvm_vcpu *vcpu)
 		SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
 }
 
+static inline bool svm_nested_virtualize_tpr(struct kvm_vcpu *vcpu)
+{
+	return is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK);
+}
+
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
+	if (svm_nested_virtualize_tpr(vcpu) ||
+	    kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
@@ -3606,11 +4200,28 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 
 static bool svm_get_enable_apicv(void)
 {
-	return false;
+	return avic;
+}
+
+static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
+{
 }
 
+static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
+{
+}
+
+/* Note: Currently only used by Hyper-V. */
 static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb *vmcb = svm->vmcb;
+
+	if (!avic)
+		return;
+
+	vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
+	mark_dirty(vmcb, VMCB_INTR);
 }
 
 static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
@@ -3623,6 +4234,18 @@ static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 	return;
 }
 
+static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
+{
+	kvm_lapic_set_irr(vec, vcpu->arch.apic);
+	smp_mb__after_atomic();
+
+	if (avic_vcpu_is_running(vcpu))
+		wrmsrl(SVM_AVIC_DOORBELL,
+		       kvm_cpu_get_apicid(vcpu->cpu));
+	else
+		kvm_vcpu_wake_up(vcpu);
+}
+
 static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3677,6 +4300,9 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (kvm_vcpu_apicv_active(vcpu))
+		return;
+
 	/*
 	 * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
 	 * 1, because that's a separate STGI/VMRUN intercept.  The next time we
@@ -3728,7 +4354,7 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
+	if (svm_nested_virtualize_tpr(vcpu))
 		return;
 
 	if (!is_cr_intercept(svm, INTERCEPT_CR8_WRITE)) {
@@ -3742,7 +4368,8 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 cr8;
 
-	if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
+	if (svm_nested_virtualize_tpr(vcpu) ||
+	    kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	cr8 = kvm_get_cr8(vcpu);
@@ -4045,14 +4672,26 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_cpuid_entry2 *entry;
 
 	/* Update nrips enabled cache */
 	svm->nrips_enabled = !!guest_cpuid_has_nrips(&svm->vcpu);
+
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	entry = kvm_find_cpuid_entry(vcpu, 1, 0);
+	if (entry)
+		entry->ecx &= ~bit(X86_FEATURE_X2APIC);
 }
 
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	switch (func) {
+	case 0x1:
+		if (avic)
+			entry->ecx &= ~bit(X86_FEATURE_X2APIC);
+		break;
 	case 0x80000001:
 		if (nested)
 			entry->ecx |= (1 << 2); /* Set SVM bit */
@@ -4307,6 +4946,15 @@ static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
 }
 
+static inline void avic_post_state_restore(struct kvm_vcpu *vcpu)
+{
+	if (avic_handle_apic_id_update(vcpu) != 0)
+		return;
+	if (avic_handle_dfr_update(vcpu) != 0)
+		return;
+	avic_handle_ldr_update(vcpu);
+}
+
 static struct kvm_x86_ops svm_x86_ops = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -4322,9 +4970,14 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.vcpu_free = svm_free_vcpu,
 	.vcpu_reset = svm_vcpu_reset,
 
+	.vm_init = avic_vm_init,
+	.vm_destroy = avic_vm_destroy,
+
 	.prepare_guest_switch = svm_prepare_guest_switch,
 	.vcpu_load = svm_vcpu_load,
 	.vcpu_put = svm_vcpu_put,
+	.vcpu_blocking = svm_vcpu_blocking,
+	.vcpu_unblocking = svm_vcpu_unblocking,
 
 	.update_bp_intercept = update_bp_intercept,
 	.get_msr = svm_get_msr,
@@ -4382,6 +5035,9 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.sync_pir_to_irr = svm_sync_pir_to_irr,
+	.hwapic_irr_update = svm_hwapic_irr_update,
+	.hwapic_isr_update = svm_hwapic_isr_update,
+	.apicv_post_state_restore = avic_post_state_restore,
 
 	.set_tss_addr = svm_set_tss_addr,
 	.get_tdp_level = get_npt_level,
@@ -4415,6 +5071,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.sched_in = svm_sched_in,
 
 	.pmu_ops = &amd_pmu_ops,
+	.deliver_posted_interrupt = svm_deliver_avic_intr,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 2f1ea2f61..8de925031 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -809,8 +809,7 @@ TRACE_EVENT(kvm_write_tsc_offset,
 
 #define host_clocks					\
 	{VCLOCK_NONE, "none"},				\
-	{VCLOCK_TSC,  "tsc"},				\
-	{VCLOCK_HPET, "hpet"}				\
+	{VCLOCK_TSC,  "tsc"}				\
 
 TRACE_EVENT(kvm_update_master_clock,
 	TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched),
@@ -1292,6 +1291,63 @@ TRACE_EVENT(kvm_hv_stimer_cleanup,
 		  __entry->vcpu_id, __entry->timer_index)
 );
 
+/*
+ * Tracepoint for AMD AVIC
+ */
+TRACE_EVENT(kvm_avic_incomplete_ipi,
+	    TP_PROTO(u32 vcpu, u32 icrh, u32 icrl, u32 id, u32 index),
+	    TP_ARGS(vcpu, icrh, icrl, id, index),
+
+	TP_STRUCT__entry(
+		__field(u32, vcpu)
+		__field(u32, icrh)
+		__field(u32, icrl)
+		__field(u32, id)
+		__field(u32, index)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu = vcpu;
+		__entry->icrh = icrh;
+		__entry->icrl = icrl;
+		__entry->id = id;
+		__entry->index = index;
+	),
+
+	TP_printk("vcpu=%u, icrh:icrl=%#010x:%08x, id=%u, index=%u\n",
+		  __entry->vcpu, __entry->icrh, __entry->icrl,
+		  __entry->id, __entry->index)
+);
+
+TRACE_EVENT(kvm_avic_unaccelerated_access,
+	    TP_PROTO(u32 vcpu, u32 offset, bool ft, bool rw, u32 vec),
+	    TP_ARGS(vcpu, offset, ft, rw, vec),
+
+	TP_STRUCT__entry(
+		__field(u32, vcpu)
+		__field(u32, offset)
+		__field(bool, ft)
+		__field(bool, rw)
+		__field(u32, vec)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu = vcpu;
+		__entry->offset = offset;
+		__entry->ft = ft;
+		__entry->rw = rw;
+		__entry->vec = vec;
+	),
+
+	TP_printk("vcpu=%u, offset=%#x(%s), %s, %s, vec=%#x\n",
+		  __entry->vcpu,
+		  __entry->offset,
+		  __print_symbolic(__entry->offset, kvm_trace_symbol_apic),
+		  __entry->ft ? "trap" : "fault",
+		  __entry->rw ? "write" : "read",
+		  __entry->vec)
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c4217a23a..64a79f271 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2420,7 +2420,9 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 
 	if (is_guest_mode(vcpu))
 		msr_bitmap = vmx_msr_bitmap_nested;
-	else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
+	else if (cpu_has_secondary_exec_ctrls() &&
+		 (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
+		  SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
 		if (is_long_mode(vcpu))
 			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
 		else
@@ -3392,7 +3394,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 		}
 	}
 
-	if (cpu_has_xsaves)
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		rdmsrl(MSR_IA32_XSS, host_xss);
 
 	return 0;
@@ -4789,6 +4791,19 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
+	if (cpu_has_secondary_exec_ctrls()) {
+		if (kvm_vcpu_apicv_active(vcpu))
+			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
+				      SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				      SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+		else
+			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+					SECONDARY_EXEC_APIC_REGISTER_VIRT |
+					SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+	}
+
+	if (cpu_has_vmx_msr_bitmap())
+		vmx_set_msr_bitmap(vcpu);
 }
 
 static u32 vmx_exec_control(struct vcpu_vmx *vmx)
@@ -6335,23 +6350,20 @@ static __init int hardware_setup(void)
 
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
-	if (enable_apicv) {
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			vmx_disable_intercept_msr_read_x2apic(msr);
-
-		/* According SDM, in x2apic mode, the whole id reg is used.
-		 * But in KVM, it only use the highest eight bits. Need to
-		 * intercept it */
-		vmx_enable_intercept_msr_read_x2apic(0x802);
-		/* TMCCT */
-		vmx_enable_intercept_msr_read_x2apic(0x839);
-		/* TPR */
-		vmx_disable_intercept_msr_write_x2apic(0x808);
-		/* EOI */
-		vmx_disable_intercept_msr_write_x2apic(0x80b);
-		/* SELF-IPI */
-		vmx_disable_intercept_msr_write_x2apic(0x83f);
-	}
+	for (msr = 0x800; msr <= 0x8ff; msr++)
+		vmx_disable_intercept_msr_read_x2apic(msr);
+
+	/* According SDM, in x2apic mode, the whole id reg is used.  But in
+	 * KVM, it only use the highest eight bits. Need to intercept it */
+	vmx_enable_intercept_msr_read_x2apic(0x802);
+	/* TMCCT */
+	vmx_enable_intercept_msr_read_x2apic(0x839);
+	/* TPR */
+	vmx_disable_intercept_msr_write_x2apic(0x808);
+	/* EOI */
+	vmx_disable_intercept_msr_write_x2apic(0x80b);
+	/* SELF-IPI */
+	vmx_disable_intercept_msr_write_x2apic(0x83f);
 
 	if (enable_ept) {
 		kvm_mmu_set_mask_ptes(0ull,
@@ -8319,19 +8331,19 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
 }
 
-static void vmx_hwapic_isr_update(struct kvm *kvm, int isr)
+static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
 {
 	u16 status;
 	u8 old;
 
-	if (isr == -1)
-		isr = 0;
+	if (max_isr == -1)
+		max_isr = 0;
 
 	status = vmcs_read16(GUEST_INTR_STATUS);
 	old = status >> 8;
-	if (isr != old) {
+	if (max_isr != old) {
 		status &= 0xff;
-		status |= isr << 8;
+		status |= max_isr << 8;
 		vmcs_write16(GUEST_INTR_STATUS, status);
 	}
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6b9701bab..7da5dd205 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -161,6 +161,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "halt_exits", VCPU_STAT(halt_exits) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
 	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
+	{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "hypercalls", VCPU_STAT(hypercalls) },
 	{ "request_irq", VCPU_STAT(request_irq_exits) },
@@ -1243,12 +1244,6 @@ static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
 static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
 static unsigned long max_tsc_khz;
 
-static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
-{
-	return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
-				   vcpu->arch.virtual_tsc_shift);
-}
-
 static u32 adjust_tsc_khz(u32 khz, s32 ppm)
 {
 	u64 v = (u64)khz * (1000000 + ppm);
@@ -2002,22 +1997,8 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.pv_time_enabled = false;
 }
 
-static void accumulate_steal_time(struct kvm_vcpu *vcpu)
-{
-	u64 delta;
-
-	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
-		return;
-
-	delta = current->sched_info.run_delay - vcpu->arch.st.last_steal;
-	vcpu->arch.st.last_steal = current->sched_info.run_delay;
-	vcpu->arch.st.accum_steal = delta;
-}
-
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
-	accumulate_steal_time(vcpu);
-
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
@@ -2025,9 +2006,26 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
 		return;
 
-	vcpu->arch.st.steal.steal += vcpu->arch.st.accum_steal;
-	vcpu->arch.st.steal.version += 2;
-	vcpu->arch.st.accum_steal = 0;
+	if (vcpu->arch.st.steal.version & 1)
+		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
+
+	vcpu->arch.st.steal.version += 1;
+
+	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+
+	smp_wmb();
+
+	vcpu->arch.st.steal.steal += current->sched_info.run_delay -
+		vcpu->arch.st.last_steal;
+	vcpu->arch.st.last_steal = current->sched_info.run_delay;
+
+	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+
+	smp_wmb();
+
+	vcpu->arch.st.steal.version += 1;
 
 	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
@@ -2310,6 +2308,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_AMD64_NB_CFG:
 	case MSR_FAM10H_MMIO_CONF_BASE:
 	case MSR_AMD64_BU_CFG2:
+	case MSR_IA32_PERF_CTL:
 		msr_info->data = 0;
 		break;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
@@ -2611,7 +2610,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_MAX_MCE_BANKS;
 		break;
 	case KVM_CAP_XCRS:
-		r = cpu_has_xsave;
+		r = boot_cpu_has(X86_FEATURE_XSAVE);
 		break;
 	case KVM_CAP_TSC_CONTROL:
 		r = kvm_has_tsc_control;
@@ -2968,6 +2967,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 			      | KVM_VCPUEVENT_VALID_SMM))
 		return -EINVAL;
 
+	if (events->exception.injected &&
+	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+		return -EINVAL;
+
 	process_nmi(vcpu);
 	vcpu->arch.exception.pending = events->exception.injected;
 	vcpu->arch.exception.nr = events->exception.nr;
@@ -3099,7 +3102,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 
 	/* Set XSTATE_BV and possibly XCOMP_BV.  */
 	xsave->header.xfeatures = xstate_bv;
-	if (cpu_has_xsaves)
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
@@ -3126,7 +3129,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
-	if (cpu_has_xsave) {
+	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		memset(guest_xsave, 0, sizeof(struct kvm_xsave));
 		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
@@ -3144,7 +3147,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
 
-	if (cpu_has_xsave) {
+	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		/*
 		 * Here we allow setting states that are not present in
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
@@ -3165,7 +3168,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
 					struct kvm_xcrs *guest_xcrs)
 {
-	if (!cpu_has_xsave) {
+	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
 		guest_xcrs->nr_xcrs = 0;
 		return;
 	}
@@ -3181,7 +3184,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
 {
 	int i, r = 0;
 
-	if (!cpu_has_xsave)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -EINVAL;
 
 	if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags)
@@ -5870,7 +5873,7 @@ int kvm_arch_init(void *opaque)
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);
 
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 
 	kvm_lapic_init();
@@ -7298,7 +7301,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 static void fx_init(struct kvm_vcpu *vcpu)
 {
 	fpstate_init(&vcpu->arch.guest_fpu.state);
-	if (cpu_has_xsaves)
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
 			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
@@ -7757,6 +7760,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm_page_track_init(kvm);
 	kvm_mmu_init_vm(kvm);
 
+	if (kvm_x86_ops->vm_init)
+		return kvm_x86_ops->vm_init(kvm);
+
 	return 0;
 }
 
@@ -7813,7 +7819,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 
 	slot = id_to_memslot(slots, id);
 	if (size) {
-		if (WARN_ON(slot->npages))
+		if (slot->npages)
 			return -EEXIST;
 
 		/*
@@ -7878,6 +7884,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0);
 		x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
 	}
+	if (kvm_x86_ops->vm_destroy)
+		kvm_x86_ops->vm_destroy(kvm);
 	kvm_iommu_unmap_guest(kvm);
 	kfree(kvm->arch.vpic);
 	kfree(kvm->arch.vioapic);
@@ -8360,19 +8368,21 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
 
+bool kvm_arch_has_irq_bypass(void)
+{
+	return kvm_x86_ops->update_pi_irte != NULL;
+}
+
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
 
-	if (kvm_x86_ops->update_pi_irte) {
-		irqfd->producer = prod;
-		return kvm_x86_ops->update_pi_irte(irqfd->kvm,
-				prod->irq, irqfd->gsi, 1);
-	}
+	irqfd->producer = prod;
 
-	return -EINVAL;
+	return kvm_x86_ops->update_pi_irte(irqfd->kvm,
+					   prod->irq, irqfd->gsi, 1);
 }
 
 void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
@@ -8382,11 +8392,6 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
 
-	if (!kvm_x86_ops->update_pi_irte) {
-		WARN_ON(irqfd->producer != NULL);
-		return;
-	}
-
 	WARN_ON(irqfd->producer != prod);
 	irqfd->producer = NULL;
 
@@ -8434,3 +8439,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 7ce3634ab..a82ca466b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -2,6 +2,7 @@
 #define ARCH_X86_KVM_X86_H
 
 #include <linux/kvm_host.h>
+#include <asm/pvclock.h>
 #include "kvm_cache_regs.h"
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
@@ -195,6 +196,12 @@ extern unsigned int lapic_timer_advance_ns;
 
 extern struct static_key kvm_no_apic_vcpu;
 
+static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
+{
+	return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
+				   vcpu->arch.virtual_tsc_shift);
+}
+
 /* Same "calling convention" as do_div:
  * - divide (n << 32) by base
  * - put result in n