1 files changed, 732 insertions, 209 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index cfdc6e0ef00..00691185817 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -34,6 +34,7 @@
 #include <asm/current.h>
 #include <asm/apicdef.h>
 #include <linux/atomic.h>
+#include <linux/jump_label.h>
 #include "kvm_cache_regs.h"
 #include "irq.h"
 #include "trace.h"
@@ -65,31 +66,27 @@
 #define APIC_DEST_NOSHORT		0x0
 #define APIC_DEST_MASK			0x800
 #define MAX_APIC_VECTOR			256
+#define APIC_VECTORS_PER_REG		32
 
 #define VEC_POS(v) ((v) & (32 - 1))
 #define REG_POS(v) (((v) >> 5) << 4)
 
-static unsigned int min_timer_period_us = 500;
-module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
-
-static inline u32 apic_get_reg(struct kvm_lapic *apic, int reg_off)
-{
-	return *((u32 *) (apic->regs + reg_off));
-}
-
 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_and_set_vector(int vec, void *bitmap)
+static inline int apic_test_vector(int vec, void *bitmap)
 {
-	return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
 }
 
-static inline int apic_test_and_clear_vector(int vec, void *bitmap)
+bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector)
 {
-	return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	return apic_test_vector(vector, apic->regs + APIC_ISR) ||
+		apic_test_vector(vector, apic->regs + APIC_IRR);
 }
 
 static inline void apic_set_vector(int vec, void *bitmap)
@@ -102,19 +99,33 @@ static inline void apic_clear_vector(int vec, void *bitmap)
 	clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
 }
 
-static inline int apic_hw_enabled(struct kvm_lapic *apic)
+static inline int __apic_test_and_set_vector(int vec, void *bitmap)
 {
-	return (apic)->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
+	return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
 }
 
-static inline int  apic_sw_enabled(struct kvm_lapic *apic)
+static inline int __apic_test_and_clear_vector(int vec, void *bitmap)
 {
-	return apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED;
+	return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
+struct static_key_deferred apic_hw_disabled __read_mostly;
+struct static_key_deferred apic_sw_disabled __read_mostly;
+
+static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
+{
+	if ((kvm_apic_get_reg(apic, APIC_SPIV) ^ val) & APIC_SPIV_APIC_ENABLED) {
+		if (val & APIC_SPIV_APIC_ENABLED)
+			static_key_slow_dec_deferred(&apic_sw_disabled);
+		else
+			static_key_slow_inc(&apic_sw_disabled.key);
+	}
+	apic_set_reg(apic, APIC_SPIV, val);
 }
 
 static inline int apic_enabled(struct kvm_lapic *apic)
 {
-	return apic_sw_enabled(apic) &&	apic_hw_enabled(apic);
+	return kvm_apic_sw_enabled(apic) &&	kvm_apic_hw_enabled(apic);
 }
 
 #define LVT_MASK	\
@@ -126,34 +137,116 @@ static inline int apic_enabled(struct kvm_lapic *apic)
 
 static inline int kvm_apic_id(struct kvm_lapic *apic)
 {
-	return (apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+}
+
+#define KVM_X2APIC_CID_BITS 0
+
+static void recalculate_apic_map(struct kvm *kvm)
+{
+	struct kvm_apic_map *new, *old = NULL;
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL);
+
+	mutex_lock(&kvm->arch.apic_map_lock);
+
+	if (!new)
+		goto out;
+
+	new->ldr_bits = 8;
+	/* flat mode is default */
+	new->cid_shift = 8;
+	new->cid_mask = 0;
+	new->lid_mask = 0xff;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvm_lapic *apic = vcpu->arch.apic;
+		u16 cid, lid;
+		u32 ldr;
+
+		if (!kvm_apic_present(vcpu))
+			continue;
+
+		/*
+		 * All APICs have to be configured in the same mode by an OS.
+		 * We take advatage of this while building logical id loockup
+		 * table. After reset APICs are in xapic/flat mode, so if we
+		 * find apic with different setting we assume this is the mode
+		 * OS wants all apics to be in; build lookup table accordingly.
+		 */
+		if (apic_x2apic_mode(apic)) {
+			new->ldr_bits = 32;
+			new->cid_shift = 16;
+			new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1;
+			new->lid_mask = 0xffff;
+		} else if (kvm_apic_sw_enabled(apic) &&
+				!new->cid_mask /* flat mode */ &&
+				kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
+			new->cid_shift = 4;
+			new->cid_mask = 0xf;
+			new->lid_mask = 0xf;
+		}
+
+		new->phys_map[kvm_apic_id(apic)] = apic;
+
+		ldr = kvm_apic_get_reg(apic, APIC_LDR);
+		cid = apic_cluster_id(new, ldr);
+		lid = apic_logical_id(new, ldr);
+
+		if (lid)
+			new->logical_map[cid][ffs(lid) - 1] = apic;
+	}
+out:
+	old = rcu_dereference_protected(kvm->arch.apic_map,
+			lockdep_is_held(&kvm->arch.apic_map_lock));
+	rcu_assign_pointer(kvm->arch.apic_map, new);
+	mutex_unlock(&kvm->arch.apic_map_lock);
+
+	if (old)
+		kfree_rcu(old, rcu);
+
+	kvm_vcpu_request_scan_ioapic(kvm);
+}
+
+static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
+{
+	apic_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);
+	recalculate_apic_map(apic->vcpu->kvm);
 }
 
 static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
 {
-	return !(apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
+	return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
 }
 
 static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type)
 {
-	return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
+	return kvm_apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
 }
 
 static inline int apic_lvtt_oneshot(struct kvm_lapic *apic)
 {
-	return ((apic_get_reg(apic, APIC_LVTT) &
+	return ((kvm_apic_get_reg(apic, APIC_LVTT) &
 		apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_ONESHOT);
 }
 
 static inline int apic_lvtt_period(struct kvm_lapic *apic)
 {
-	return ((apic_get_reg(apic, APIC_LVTT) &
+	return ((kvm_apic_get_reg(apic, APIC_LVTT) &
 		apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_PERIODIC);
 }
 
 static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic)
 {
-	return ((apic_get_reg(apic, APIC_LVTT) &
+	return ((kvm_apic_get_reg(apic, APIC_LVTT) &
 		apic->lapic_timer.timer_mode_mask) ==
 			APIC_LVT_TIMER_TSCDEADLINE);
 }
@@ -169,7 +262,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	struct kvm_cpuid_entry2 *feat;
 	u32 v = APIC_VERSION;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return;
 
 	feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
@@ -178,12 +271,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	apic_set_reg(apic, APIC_LVR, v);
 }
 
-static inline int apic_x2apic_mode(struct kvm_lapic *apic)
-{
-	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
-}
-
-static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
+static const unsigned int apic_lvt_mask[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 */
@@ -193,22 +281,50 @@ static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
 
 static int find_highest_vector(void *bitmap)
 {
-	u32 *word = bitmap;
-	int word_offset = MAX_APIC_VECTOR >> 5;
+	int vec;
+	u32 *reg;
 
-	while ((word_offset != 0) && (word[(--word_offset) << 2] == 0))
-		continue;
+	for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG;
+	     vec >= 0; vec -= APIC_VECTORS_PER_REG) {
+		reg = bitmap + REG_POS(vec);
+		if (*reg)
+			return fls(*reg) - 1 + vec;
+	}
 
-	if (likely(!word_offset && !word[0]))
-		return -1;
-	else
-		return fls(word[word_offset << 2]) - 1 + (word_offset << 5);
+	return -1;
+}
+
+static u8 count_vectors(void *bitmap)
+{
+	int vec;
+	u32 *reg;
+	u8 count = 0;
+
+	for (vec = 0; vec < MAX_APIC_VECTOR; vec += APIC_VECTORS_PER_REG) {
+		reg = bitmap + REG_POS(vec);
+		count += hweight32(*reg);
+	}
+
+	return count;
+}
+
+void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
+{
+	u32 i, pir_val;
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	for (i = 0; i <= 7; i++) {
+		pir_val = xchg(&pir[i], 0);
+		if (pir_val)
+			*((u32 *)(apic->regs + APIC_IRR + i * 0x10)) |= pir_val;
+	}
 }
+EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
 
-static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
+static inline void apic_set_irr(int vec, struct kvm_lapic *apic)
 {
 	apic->irr_pending = true;
-	return apic_test_and_set_vector(vec, apic->regs + APIC_IRR);
+	apic_set_vector(vec, apic->regs + APIC_IRR);
 }
 
 static inline int apic_search_irr(struct kvm_lapic *apic)
@@ -220,9 +336,14 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 {
 	int result;
 
+	/*
+	 * Note that irr_pending is just a hint. It will be always
+	 * true with virtual interrupt delivery enabled.
+	 */
 	if (!apic->irr_pending)
 		return -1;
 
+	kvm_x86_ops->sync_pir_to_irr(apic->vcpu);
 	result = apic_search_irr(apic);
 	ASSERT(result == -1 || result >= 16);
 
@@ -237,9 +358,67 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 		apic->irr_pending = true;
 }
 
+static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
+{
+	/* Note that we never get here with APIC virtualization enabled.  */
+
+	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+		++apic->isr_count;
+	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+	/*
+	 * ISR (in service register) bit is set when injecting an interrupt.
+	 * The highest vector is injected. Thus the latest bit set matches
+	 * the highest bit in ISR.
+	 */
+	apic->highest_isr_cache = vec;
+}
+
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+	int result;
+
+	/*
+	 * Note that isr_count is always 1, and highest_isr_cache
+	 * is always -1, with APIC virtualization enabled.
+	 */
+	if (!apic->isr_count)
+		return -1;
+	if (likely(apic->highest_isr_cache != -1))
+		return apic->highest_isr_cache;
+
+	result = find_highest_vector(apic->regs + APIC_ISR);
+	ASSERT(result == -1 || result >= 16);
+
+	return result;
+}
+
+static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
+{
+	struct kvm_vcpu *vcpu;
+	if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * We do get here for APIC virtualization enabled if the guest
+	 * uses the Hyper-V APIC enlightenment.  In this case we may need
+	 * to trigger a new interrupt delivery by writing the SVI field;
+	 * on the other hand isr_count and highest_isr_cache are unused
+	 * and must be left alone.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+					       apic_find_highest_isr(apic));
+	else {
+		--apic->isr_count;
+		BUG_ON(apic->isr_count < 0);
+		apic->highest_isr_cache = -1;
+	}
+}
+
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
 	int highest_irr;
 
 	/* This may race with setting of irr in __apic_accept_irq() and
@@ -247,32 +426,81 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 	 * will cause vmexit immediately and the value will be recalculated
 	 * on the next vmentry.
 	 */
-	if (!apic)
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return 0;
-	highest_irr = apic_find_highest_irr(apic);
+	highest_irr = apic_find_highest_irr(vcpu->arch.apic);
 
 	return highest_irr;
 }
 
 static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
-			     int vector, int level, int trig_mode);
+			     int vector, int level, int trig_mode,
+			     unsigned long *dest_map);
 
-int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
+		unsigned long *dest_map)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	return __apic_accept_irq(apic, irq->delivery_mode, irq->vector,
-			irq->level, irq->trig_mode);
+			irq->level, irq->trig_mode, dest_map);
 }
 
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+static int pv_eoi_put_user(struct kvm_vcpu *vcpu, u8 val)
 {
-	int result;
 
-	result = find_highest_vector(apic->regs + APIC_ISR);
-	ASSERT(result == -1 || result >= 16);
+	return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, &val,
+				      sizeof(val));
+}
 
-	return result;
+static int pv_eoi_get_user(struct kvm_vcpu *vcpu, u8 *val)
+{
+
+	return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, val,
+				      sizeof(*val));
+}
+
+static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED;
+}
+
+static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
+{
+	u8 val;
+	if (pv_eoi_get_user(vcpu, &val) < 0)
+		apic_debug("Can't read EOI MSR value: 0x%llx\n",
+			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
+	return val & 0x1;
+}
+
+static void pv_eoi_set_pending(struct kvm_vcpu *vcpu)
+{
+	if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) {
+		apic_debug("Can't set EOI MSR value: 0x%llx\n",
+			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
+		return;
+	}
+	__set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
+}
+
+static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
+{
+	if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) {
+		apic_debug("Can't clear EOI MSR value: 0x%llx\n",
+			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
+		return;
+	}
+	__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
+}
+
+void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		apic_set_reg(apic, APIC_TMR + 0x10 * i, tmr[i]);
 }
 
 static void apic_update_ppr(struct kvm_lapic *apic)
@@ -280,8 +508,8 @@ static void apic_update_ppr(struct kvm_lapic *apic)
 	u32 tpr, isrv, ppr, old_ppr;
 	int isr;
 
-	old_ppr = apic_get_reg(apic, APIC_PROCPRI);
-	tpr = apic_get_reg(apic, APIC_TASKPRI);
+	old_ppr = kvm_apic_get_reg(apic, APIC_PROCPRI);
+	tpr = kvm_apic_get_reg(apic, APIC_TASKPRI);
 	isr = apic_find_highest_isr(apic);
 	isrv = (isr != -1) ? isr : 0;
 
@@ -317,13 +545,13 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
 	u32 logical_id;
 
 	if (apic_x2apic_mode(apic)) {
-		logical_id = apic_get_reg(apic, APIC_LDR);
+		logical_id = kvm_apic_get_reg(apic, APIC_LDR);
 		return logical_id & mda;
 	}
 
-	logical_id = GET_APIC_LOGICAL_ID(apic_get_reg(apic, APIC_LDR));
+	logical_id = GET_APIC_LOGICAL_ID(kvm_apic_get_reg(apic, APIC_LDR));
 
-	switch (apic_get_reg(apic, APIC_DFR)) {
+	switch (kvm_apic_get_reg(apic, APIC_DFR)) {
 	case APIC_DFR_FLAT:
 		if (logical_id & mda)
 			result = 1;
@@ -335,7 +563,7 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
 		break;
 	default:
 		apic_debug("Bad DFR vcpu %d: %08x\n",
-			   apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR));
+			   apic->vcpu->vcpu_id, kvm_apic_get_reg(apic, APIC_DFR));
 		break;
 	}
 
@@ -380,12 +608,79 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 	return result;
 }
 
+bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map)
+{
+	struct kvm_apic_map *map;
+	unsigned long bitmap = 1;
+	struct kvm_lapic **dst;
+	int i;
+	bool ret = false;
+
+	*r = -1;
+
+	if (irq->shorthand == APIC_DEST_SELF) {
+		*r = kvm_apic_set_irq(src->vcpu, irq, dest_map);
+		return true;
+	}
+
+	if (irq->shorthand)
+		return false;
+
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
+
+	if (!map)
+		goto out;
+
+	if (irq->dest_mode == 0) { /* physical mode */
+		if (irq->delivery_mode == APIC_DM_LOWEST ||
+				irq->dest_id == 0xff)
+			goto out;
+		dst = &map->phys_map[irq->dest_id & 0xff];
+	} else {
+		u32 mda = irq->dest_id << (32 - map->ldr_bits);
+
+		dst = map->logical_map[apic_cluster_id(map, mda)];
+
+		bitmap = apic_logical_id(map, mda);
+
+		if (irq->delivery_mode == APIC_DM_LOWEST) {
+			int l = -1;
+			for_each_set_bit(i, &bitmap, 16) {
+				if (!dst[i])
+					continue;
+				if (l < 0)
+					l = i;
+				else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
+					l = i;
+			}
+
+			bitmap = (l >= 0) ? 1 << l : 0;
+		}
+	}
+
+	for_each_set_bit(i, &bitmap, 16) {
+		if (!dst[i])
+			continue;
+		if (*r < 0)
+			*r = 0;
+		*r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
+	}
+
+	ret = true;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
 /*
  * Add a pending IRQ into lapic.
  * Return 1 if successfully added and 0 if discarded.
  */
 static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
-			     int vector, int level, int trig_mode)
+			     int vector, int level, int trig_mode,
+			     unsigned long *dest_map)
 {
 	int result = 0;
 	struct kvm_vcpu *vcpu = apic->vcpu;
@@ -398,28 +693,28 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		if (unlikely(!apic_enabled(apic)))
 			break;
 
-		if (trig_mode) {
-			apic_debug("level trig mode for vector %d", vector);
-			apic_set_vector(vector, apic->regs + APIC_TMR);
-		} else
-			apic_clear_vector(vector, apic->regs + APIC_TMR);
+		result = 1;
 
-		result = !apic_test_and_set_irr(vector, apic);
-		trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
-					  trig_mode, vector, !result);
-		if (!result) {
-			if (trig_mode)
-				apic_debug("level trig mode repeatedly for "
-						"vector %d", vector);
-			break;
-		}
+		if (dest_map)
+			__set_bit(vcpu->vcpu_id, dest_map);
 
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
-		kvm_vcpu_kick(vcpu);
+		if (kvm_x86_ops->deliver_posted_interrupt)
+			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
+		else {
+			apic_set_irr(vector, apic);
+
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
+			kvm_vcpu_kick(vcpu);
+		}
+		trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
+					  trig_mode, vector, false);
 		break;
 
 	case APIC_DM_REMRD:
-		apic_debug("Ignoring delivery mode 3\n");
+		result = 1;
+		vcpu->arch.pv.pv_unhalted = 1;
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		kvm_vcpu_kick(vcpu);
 		break;
 
 	case APIC_DM_SMI:
@@ -433,9 +728,13 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		break;
 
 	case APIC_DM_INIT:
-		if (level) {
+		if (!trig_mode || level) {
 			result = 1;
-			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+			/* assumes that there are only KVM_APIC_INIT/SIPI */
+			apic->pending_events = (1UL << KVM_APIC_INIT);
+			/* make sure pending_events is visible before sending
+			 * the request */
+			smp_wmb();
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		} else {
@@ -447,13 +746,13 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	case APIC_DM_STARTUP:
 		apic_debug("SIPI to vcpu %d vector 0x%02x\n",
 			   vcpu->vcpu_id, vector);
-		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
-			result = 1;
-			vcpu->arch.sipi_vector = vector;
-			vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
-			kvm_vcpu_kick(vcpu);
-		}
+		result = 1;
+		apic->sipi_vector = vector;
+		/* make sure sipi_vector is visible for the receiver */
+		smp_wmb();
+		set_bit(KVM_APIC_SIPI, &apic->pending_events);
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		kvm_vcpu_kick(vcpu);
 		break;
 
 	case APIC_DM_EXTINT:
@@ -477,33 +776,59 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
 }
 
-static void apic_set_eoi(struct kvm_lapic *apic)
+static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
+{
+	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
+	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+		int trigger_mode;
+		if (apic_test_vector(vector, apic->regs + APIC_TMR))
+			trigger_mode = IOAPIC_LEVEL_TRIG;
+		else
+			trigger_mode = IOAPIC_EDGE_TRIG;
+		kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode);
+	}
+}
+
+static int apic_set_eoi(struct kvm_lapic *apic)
 {
 	int vector = apic_find_highest_isr(apic);
-	int trigger_mode;
+
+	trace_kvm_eoi(apic, vector);
+
 	/*
 	 * Not every write EOI will has corresponding ISR,
 	 * one example is when Kernel check timer on setup_IO_APIC
 	 */
 	if (vector == -1)
-		return;
+		return vector;
 
-	apic_clear_vector(vector, apic->regs + APIC_ISR);
+	apic_clear_isr(vector, apic);
 	apic_update_ppr(apic);
 
-	if (apic_test_and_clear_vector(vector, apic->regs + APIC_TMR))
-		trigger_mode = IOAPIC_LEVEL_TRIG;
-	else
-		trigger_mode = IOAPIC_EDGE_TRIG;
-	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI))
-		kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
+	kvm_ioapic_send_eoi(apic, vector);
 	kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
+	return vector;
 }
 
+/*
+ * this interface assumes a trap-like exit, which has already finished
+ * desired side effect including vISR and vPPR update.
+ */
+void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	trace_kvm_eoi(apic, vector);
+
+	kvm_ioapic_send_eoi(apic, vector);
+	kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated);
+
 static void apic_send_ipi(struct kvm_lapic *apic)
 {
-	u32 icr_low = apic_get_reg(apic, APIC_ICR);
-	u32 icr_high = apic_get_reg(apic, APIC_ICR2);
+	u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR);
+	u32 icr_high = kvm_apic_get_reg(apic, APIC_ICR2);
 	struct kvm_lapic_irq irq;
 
 	irq.vector = icr_low & APIC_VECTOR_MASK;
@@ -526,7 +851,7 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 		   irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
 		   irq.vector);
 
-	kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq);
+	kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL);
 }
 
 static u32 apic_get_tmcct(struct kvm_lapic *apic)
@@ -538,7 +863,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	ASSERT(apic != NULL);
 
 	/* if initial count is 0, current count should also be 0 */
-	if (apic_get_reg(apic, APIC_TMICT) == 0)
+	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 ||
+		apic->lapic_timer.period == 0)
 		return 0;
 
 	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
@@ -592,13 +918,15 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 
 		val = apic_get_tmcct(apic);
 		break;
-
+	case APIC_PROCPRI:
+		apic_update_ppr(apic);
+		val = kvm_apic_get_reg(apic, offset);
+		break;
 	case APIC_TASKPRI:
 		report_tpr_access(apic, false);
 		/* fall thru */
 	default:
-		apic_update_ppr(apic);
-		val = apic_get_reg(apic, offset);
+		val = kvm_apic_get_reg(apic, offset);
 		break;
 	}
 
@@ -615,7 +943,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 {
 	unsigned char alignment = offset & 0xf;
 	u32 result;
-	/* this bitmask has a bit cleared for each reserver register */
+	/* this bitmask has a bit cleared for each reserved register */
 	static const u64 rmask = 0x43ff01ffffffe70cULL;
 
 	if ((alignment + len) > 4) {
@@ -650,7 +978,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 
 static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
 {
-	return apic_hw_enabled(apic) &&
+	return kvm_apic_hw_enabled(apic) &&
 	    addr >= apic->base_address &&
 	    addr < apic->base_address + LAPIC_MMIO_LENGTH;
 }
@@ -673,7 +1001,7 @@ static void update_divide_count(struct kvm_lapic *apic)
 {
 	u32 tmp1, tmp2, tdcr;
 
-	tdcr = apic_get_reg(apic, APIC_TDCR);
+	tdcr = kvm_apic_get_reg(apic, APIC_TDCR);
 	tmp1 = tdcr & 0xf;
 	tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1;
 	apic->divide_count = 0x1 << (tmp2 & 0x7);
@@ -688,9 +1016,9 @@ static void start_apic_timer(struct kvm_lapic *apic)
 	atomic_set(&apic->lapic_timer.pending, 0);
 
 	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
-		/* lapic timer in oneshot or peroidic mode */
+		/* lapic timer in oneshot or periodic mode */
 		now = apic->lapic_timer.timer.base->get_time();
-		apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT)
+		apic->lapic_timer.period = (u64)kvm_apic_get_reg(apic, APIC_TMICT)
 			    * APIC_BUS_CYCLE_NS * apic->divide_count;
 
 		if (!apic->lapic_timer.period)
@@ -722,7 +1050,7 @@ 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),
-			   apic_get_reg(apic, APIC_TMICT),
+			   kvm_apic_get_reg(apic, APIC_TMICT),
 			   apic->lapic_timer.period,
 			   ktime_to_ns(ktime_add_ns(now,
 					apic->lapic_timer.period)));
@@ -731,7 +1059,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
 		u64 ns = 0;
 		struct kvm_vcpu *vcpu = apic->vcpu;
-		unsigned long this_tsc_khz = vcpu_tsc_khz(vcpu);
+		unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
 		unsigned long flags;
 
 		if (unlikely(!tscdeadline || !this_tsc_khz))
@@ -740,7 +1068,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		local_irq_save(flags);
 
 		now = apic->lapic_timer.timer.base->get_time();
-		guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu);
+		guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
 		if (likely(tscdeadline > guest_tsc)) {
 			ns = (tscdeadline - guest_tsc) * 1000000ULL;
 			do_div(ns, this_tsc_khz);
@@ -754,7 +1082,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 
 static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 {
-	int nmi_wd_enabled = apic_lvt_nmi_mode(apic_get_reg(apic, APIC_LVT0));
+	int nmi_wd_enabled = apic_lvt_nmi_mode(kvm_apic_get_reg(apic, APIC_LVT0));
 
 	if (apic_lvt_nmi_mode(lvt0_val)) {
 		if (!nmi_wd_enabled) {
@@ -775,7 +1103,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	switch (reg) {
 	case APIC_ID:		/* Local APIC ID */
 		if (!apic_x2apic_mode(apic))
-			apic_set_reg(apic, APIC_ID, val);
+			kvm_apic_set_id(apic, val >> 24);
 		else
 			ret = 1;
 		break;
@@ -791,29 +1119,30 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 	case APIC_LDR:
 		if (!apic_x2apic_mode(apic))
-			apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK);
+			kvm_apic_set_ldr(apic, val & APIC_LDR_MASK);
 		else
 			ret = 1;
 		break;
 
 	case APIC_DFR:
-		if (!apic_x2apic_mode(apic))
+		if (!apic_x2apic_mode(apic)) {
 			apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
-		else
+			recalculate_apic_map(apic->vcpu->kvm);
+		} else
 			ret = 1;
 		break;
 
 	case APIC_SPIV: {
 		u32 mask = 0x3ff;
-		if (apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
+		if (kvm_apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
 			mask |= APIC_SPIV_DIRECTED_EOI;
-		apic_set_reg(apic, APIC_SPIV, val & mask);
+		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 = apic_get_reg(apic,
+				lvt_val = kvm_apic_get_reg(apic,
 						       APIC_LVTT + 0x10 * i);
 				apic_set_reg(apic, APIC_LVTT + 0x10 * i,
 					     lvt_val | APIC_LVT_MASKED);
@@ -842,7 +1171,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_LVT1:
 	case APIC_LVTERR:
 		/* TODO: Check vector */
-		if (!apic_sw_enabled(apic))
+		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
 
 		val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
@@ -851,12 +1180,12 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 		break;
 
 	case APIC_LVTT:
-		if ((apic_get_reg(apic, APIC_LVTT) &
+		if ((kvm_apic_get_reg(apic, APIC_LVTT) &
 		    apic->lapic_timer.timer_mode_mask) !=
 		   (val & apic->lapic_timer.timer_mode_mask))
 			hrtimer_cancel(&apic->lapic_timer.timer);
 
-		if (!apic_sw_enabled(apic))
+		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);
@@ -935,24 +1264,45 @@ static int apic_mmio_write(struct kvm_io_device *this,
 
 void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
-
-	if (apic)
+	if (kvm_vcpu_has_lapic(vcpu))
 		apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
 
+/* emulate APIC access in a trap manner */
+void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
+{
+	u32 val = 0;
+
+	/* hw has done the conditional check and inst decode */
+	offset &= 0xff0;
+
+	apic_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);
+}
+EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode);
+
 void kvm_free_lapic(struct kvm_vcpu *vcpu)
 {
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
 	if (!vcpu->arch.apic)
 		return;
 
-	hrtimer_cancel(&vcpu->arch.apic->lapic_timer.timer);
+	hrtimer_cancel(&apic->lapic_timer.timer);
+
+	if (!(vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE))
+		static_key_slow_dec_deferred(&apic_hw_disabled);
 
-	if (vcpu->arch.apic->regs)
-		free_page((unsigned long)vcpu->arch.apic->regs);
+	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED))
+		static_key_slow_dec_deferred(&apic_sw_disabled);
 
-	kfree(vcpu->arch.apic);
+	if (apic->regs)
+		free_page((unsigned long)apic->regs);
+
+	kfree(apic);
 }
 
 /*
@@ -964,10 +1314,9 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu)
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	if (!apic)
-		return 0;
 
-	if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic))
+	if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+			apic_lvtt_period(apic))
 		return 0;
 
 	return apic->lapic_timer.tscdeadline;
@@ -976,10 +1325,9 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	if (!apic)
-		return;
 
-	if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic))
+	if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+			apic_lvtt_period(apic))
 		return;
 
 	hrtimer_cancel(&apic->lapic_timer.timer);
@@ -991,26 +1339,28 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!apic)
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return;
+
 	apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
-		     | (apic_get_reg(apic, APIC_TASKPRI) & 4));
+		     | (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4));
 }
 
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
 	u64 tpr;
 
-	if (!apic)
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return 0;
-	tpr = (u64) apic_get_reg(apic, APIC_TASKPRI);
+
+	tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI);
 
 	return (tpr & 0xf0) >> 4;
 }
 
 void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 {
+	u64 old_value = vcpu->arch.apic_base;
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	if (!apic) {
@@ -1021,13 +1371,27 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 
 	if (!kvm_vcpu_is_bsp(apic->vcpu))
 		value &= ~MSR_IA32_APICBASE_BSP;
-
 	vcpu->arch.apic_base = value;
-	if (apic_x2apic_mode(apic)) {
-		u32 id = kvm_apic_id(apic);
-		u32 ldr = ((id & ~0xf) << 16) | (1 << (id & 0xf));
-		apic_set_reg(apic, APIC_LDR, ldr);
+
+	/* update jump label if enable bit changes */
+	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
+		if (value & MSR_IA32_APICBASE_ENABLE)
+			static_key_slow_dec_deferred(&apic_hw_disabled);
+		else
+			static_key_slow_inc(&apic_hw_disabled.key);
+		recalculate_apic_map(vcpu->kvm);
 	}
+
+	if ((old_value ^ value) & X2APIC_ENABLE) {
+		if (value & X2APIC_ENABLE) {
+			u32 id = kvm_apic_id(apic);
+			u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+			kvm_apic_set_ldr(apic, ldr);
+			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true);
+		} else
+			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false);
+	}
+
 	apic->base_address = apic->vcpu->arch.apic_base &
 			     MSR_IA32_APICBASE_BASE;
 
@@ -1051,7 +1415,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
-	apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24);
+	kvm_apic_set_id(apic, vcpu->vcpu_id);
 	kvm_apic_set_version(apic->vcpu);
 
 	for (i = 0; i < APIC_LVT_NUM; i++)
@@ -1060,9 +1424,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 
 	apic_set_reg(apic, APIC_DFR, 0xffffffffU);
-	apic_set_reg(apic, APIC_SPIV, 0xff);
+	apic_set_spiv(apic, 0xff);
 	apic_set_reg(apic, APIC_TASKPRI, 0);
-	apic_set_reg(apic, APIC_LDR, 0);
+	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);
@@ -1073,14 +1437,19 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
-	apic->irr_pending = false;
+	apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm);
+	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm);
+	apic->highest_isr_cache = -1;
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
 	if (kvm_vcpu_is_bsp(vcpu))
-		vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
+		kvm_lapic_set_base(vcpu,
+				vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP);
+	vcpu->arch.pv_eoi.msr_val = 0;
 	apic_update_ppr(apic);
 
 	vcpu->arch.apic_arb_prio = 0;
+	vcpu->arch.apic_attention = 0;
 
 	apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
 		   "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
@@ -1088,49 +1457,39 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		   vcpu->arch.apic_base, apic->base_address);
 }
 
-bool kvm_apic_present(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.apic && apic_hw_enabled(vcpu->arch.apic);
-}
-
-int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
-{
-	return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic);
-}
-
 /*
  *----------------------------------------------------------------------
  * timer interface
  *----------------------------------------------------------------------
  */
 
-static bool lapic_is_periodic(struct kvm_timer *ktimer)
+static bool lapic_is_periodic(struct kvm_lapic *apic)
 {
-	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic,
-					      lapic_timer);
 	return apic_lvtt_period(apic);
 }
 
 int apic_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *lapic = vcpu->arch.apic;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT))
-		return atomic_read(&lapic->lapic_timer.pending);
+	if (kvm_vcpu_has_lapic(vcpu) && apic_enabled(apic) &&
+			apic_lvt_enabled(apic, APIC_LVTT))
+		return atomic_read(&apic->lapic_timer.pending);
 
 	return 0;
 }
 
 int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
 {
-	u32 reg = apic_get_reg(apic, lvt_type);
+	u32 reg = kvm_apic_get_reg(apic, lvt_type);
 	int vector, mode, trig_mode;
 
-	if (apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
+	if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
 		vector = reg & APIC_VECTOR_MASK;
 		mode = reg & APIC_MODE_MASK;
 		trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
-		return __apic_accept_irq(apic, mode, vector, 1, trig_mode);
+		return __apic_accept_irq(apic, mode, vector, 1, trig_mode,
+					NULL);
 	}
 	return 0;
 }
@@ -1143,15 +1502,40 @@ void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
 		kvm_apic_local_deliver(apic, APIC_LVT0);
 }
 
-static struct kvm_timer_ops lapic_timer_ops = {
-	.is_periodic = lapic_is_periodic,
-};
-
 static const struct kvm_io_device_ops apic_mmio_ops = {
 	.read     = apic_mmio_read,
 	.write    = apic_mmio_write,
 };
 
+static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
+{
+	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
+	struct kvm_vcpu *vcpu = apic->vcpu;
+	wait_queue_head_t *q = &vcpu->wq;
+
+	/*
+	 * There is a race window between reading and incrementing, but we do
+	 * not care about potentially losing timer events in the !reinject
+	 * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
+	 * in vcpu_enter_guest.
+	 */
+	if (!atomic_read(&ktimer->pending)) {
+		atomic_inc(&ktimer->pending);
+		/* FIXME: this code should not know anything about vcpus */
+		kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	}
+
+	if (waitqueue_active(q))
+		wake_up_interruptible(q);
+
+	if (lapic_is_periodic(apic)) {
+		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+		return HRTIMER_RESTART;
+	} else
+		return HRTIMER_NORESTART;
+}
+
 int kvm_create_lapic(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic;
@@ -1175,14 +1559,17 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS);
-	apic->lapic_timer.timer.function = kvm_timer_fn;
-	apic->lapic_timer.t_ops = &lapic_timer_ops;
-	apic->lapic_timer.kvm = vcpu->kvm;
-	apic->lapic_timer.vcpu = vcpu;
+	apic->lapic_timer.timer.function = apic_timer_fn;
 
-	apic->base_address = APIC_DEFAULT_PHYS_BASE;
-	vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE;
+	/*
+	 * APIC is created enabled. This will prevent kvm_lapic_set_base from
+	 * thinking that APIC satet has changed.
+	 */
+	vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
+	kvm_lapic_set_base(vcpu,
+			APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE);
 
+	static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
 	kvm_lapic_reset(vcpu);
 	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
 
@@ -1198,23 +1585,23 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	int highest_irr;
 
-	if (!apic || !apic_enabled(apic))
+	if (!kvm_vcpu_has_lapic(vcpu) || !apic_enabled(apic))
 		return -1;
 
 	apic_update_ppr(apic);
 	highest_irr = apic_find_highest_irr(apic);
 	if ((highest_irr == -1) ||
-	    ((highest_irr & 0xF0) <= apic_get_reg(apic, APIC_PROCPRI)))
+	    ((highest_irr & 0xF0) <= kvm_apic_get_reg(apic, APIC_PROCPRI)))
 		return -1;
 	return highest_irr;
 }
 
 int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu)
 {
-	u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0);
+	u32 lvt0 = kvm_apic_get_reg(vcpu->arch.apic, APIC_LVT0);
 	int r = 0;
 
-	if (!apic_hw_enabled(vcpu->arch.apic))
+	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		r = 1;
 	if ((lvt0 & APIC_LVT_MASKED) == 0 &&
 	    GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT)
@@ -1226,9 +1613,12 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic && atomic_read(&apic->lapic_timer.pending) > 0) {
-		if (kvm_apic_local_deliver(apic, APIC_LVTT))
-			atomic_dec(&apic->lapic_timer.pending);
+	if (!kvm_vcpu_has_lapic(vcpu))
+		return;
+
+	if (atomic_read(&apic->lapic_timer.pending) > 0) {
+		kvm_apic_local_deliver(apic, APIC_LVTT);
+		atomic_set(&apic->lapic_timer.pending, 0);
 	}
 }
 
@@ -1237,21 +1627,28 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	int vector = kvm_apic_has_interrupt(vcpu);
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	/* Note that we never get here with APIC virtualization enabled.  */
+
 	if (vector == -1)
 		return -1;
 
-	apic_set_vector(vector, apic->regs + APIC_ISR);
+	apic_set_isr(vector, apic);
 	apic_update_ppr(apic);
 	apic_clear_irr(vector, apic);
 	return vector;
 }
 
-void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
+void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
+		struct kvm_lapic_state *s)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	apic->base_address = vcpu->arch.apic_base &
-			     MSR_IA32_APICBASE_BASE;
+	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)));
+	memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
+	/* call kvm_apic_set_id() to put apic into apic_map */
+	kvm_apic_set_id(apic, kvm_apic_id(apic));
 	kvm_apic_set_version(vcpu);
 
 	apic_update_ppr(apic);
@@ -1259,49 +1656,117 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
+	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ?
+				1 : count_vectors(apic->regs + APIC_ISR);
+	apic->highest_isr_cache = -1;
+	kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic));
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
+	kvm_rtc_eoi_tracking_restore_one(vcpu);
 }
 
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct hrtimer *timer;
 
-	if (!apic)
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return;
 
-	timer = &apic->lapic_timer.timer;
+	timer = &vcpu->arch.apic->lapic_timer.timer;
 	if (hrtimer_cancel(timer))
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
+/*
+ * apic_sync_pv_eoi_from_guest - called on vmexit or cancel interrupt
+ *
+ * Detect whether guest triggered PV EOI since the
+ * last entry. If yes, set EOI on guests's behalf.
+ * Clear PV EOI in guest memory in any case.
+ */
+static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu,
+					struct kvm_lapic *apic)
+{
+	bool pending;
+	int vector;
+	/*
+	 * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host
+	 * and KVM_PV_EOI_ENABLED in guest memory as follows:
+	 *
+	 * KVM_APIC_PV_EOI_PENDING is unset:
+	 * 	-> host disabled PV EOI.
+	 * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is set:
+	 * 	-> host enabled PV EOI, guest did not execute EOI yet.
+	 * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is unset:
+	 * 	-> host enabled PV EOI, guest executed EOI.
+	 */
+	BUG_ON(!pv_eoi_enabled(vcpu));
+	pending = pv_eoi_get_pending(vcpu);
+	/*
+	 * Clear pending bit in any case: it will be set again on vmentry.
+	 * While this might not be ideal from performance point of view,
+	 * this makes sure pv eoi is only enabled when we know it's safe.
+	 */
+	pv_eoi_clr_pending(vcpu);
+	if (pending)
+		return;
+	vector = apic_set_eoi(apic);
+	trace_kvm_pv_eoi(apic, vector);
+}
+
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 {
 	u32 data;
-	void *vapic;
 
-	if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
+	if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention))
+		apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic);
+
+	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page, KM_USER0);
-	data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr));
-	kunmap_atomic(vapic, KM_USER0);
+	kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				sizeof(u32));
 
 	apic_set_tpr(vcpu->arch.apic, data & 0xff);
 }
 
+/*
+ * apic_sync_pv_eoi_to_guest - called before vmentry
+ *
+ * Detect whether it's safe to enable PV EOI and
+ * if yes do so.
+ */
+static void apic_sync_pv_eoi_to_guest(struct kvm_vcpu *vcpu,
+					struct kvm_lapic *apic)
+{
+	if (!pv_eoi_enabled(vcpu) ||
+	    /* IRR set or many bits in ISR: could be nested. */
+	    apic->irr_pending ||
+	    /* Cache not set: could be safe but we don't bother. */
+	    apic->highest_isr_cache == -1 ||
+	    /* Need EOI to update ioapic. */
+	    kvm_ioapic_handles_vector(vcpu->kvm, apic->highest_isr_cache)) {
+		/*
+		 * PV EOI was disabled by apic_sync_pv_eoi_from_guest
+		 * so we need not do anything here.
+		 */
+		return;
+	}
+
+	pv_eoi_set_pending(apic->vcpu);
+}
+
 void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 {
 	u32 data, tpr;
 	int max_irr, max_isr;
-	struct kvm_lapic *apic;
-	void *vapic;
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	apic_sync_pv_eoi_to_guest(vcpu, apic);
 
-	if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
+	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	apic = vcpu->arch.apic;
-	tpr = apic_get_reg(apic, APIC_TASKPRI) & 0xff;
+	tpr = kvm_apic_get_reg(apic, APIC_TASKPRI) & 0xff;
 	max_irr = apic_find_highest_irr(apic);
 	if (max_irr < 0)
 		max_irr = 0;
@@ -1310,17 +1775,24 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 		max_isr = 0;
 	data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24);
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page, KM_USER0);
-	*(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data;
-	kunmap_atomic(vapic, KM_USER0);
+	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				sizeof(u32));
 }
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
 {
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return;
+	if (vapic_addr) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+					&vcpu->arch.apic->vapic_cache,
+					vapic_addr, sizeof(u32)))
+			return -EINVAL;
+		__set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+	} else {
+		__clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+	}
 
 	vcpu->arch.apic->vapic_addr = vapic_addr;
+	return 0;
 }
 
 int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
@@ -1359,7 +1831,7 @@ int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return 1;
 
 	/* if this is ICR write vector before command */
@@ -1373,7 +1845,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 low, high = 0;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return 1;
 
 	if (apic_reg_read(apic, reg, 4, &low))
@@ -1385,3 +1857,54 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
 
 	return 0;
 }
+
+int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
+{
+	u64 addr = data & ~KVM_MSR_ENABLED;
+	if (!IS_ALIGNED(addr, 4))
+		return 1;
+
+	vcpu->arch.pv_eoi.msr_val = data;
+	if (!pv_eoi_enabled(vcpu))
+		return 0;
+	return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
+					 addr, sizeof(u8));
+}
+
+void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	unsigned int sipi_vector;
+	unsigned long pe;
+
+	if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
+		return;
+
+	pe = xchg(&apic->pending_events, 0);
+
+	if (test_bit(KVM_APIC_INIT, &pe)) {
+		kvm_lapic_reset(vcpu);
+		kvm_vcpu_reset(vcpu);
+		if (kvm_vcpu_is_bsp(apic->vcpu))
+			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		else
+			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+	}
+	if (test_bit(KVM_APIC_SIPI, &pe) &&
+	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
+		/* evaluate pending_events before reading the vector */
+		smp_rmb();
+		sipi_vector = apic->sipi_vector;
+		pr_debug("vcpu %d received sipi with vector # %x\n",
+			 vcpu->vcpu_id, sipi_vector);
+		kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector);
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	}
+}
+
+void kvm_lapic_init(void)
+{
+	/* do not patch jump label more than once per second */
+	jump_label_rate_limit(&apic_hw_disabled, HZ);
+	jump_label_rate_limit(&apic_sw_disabled, HZ);
+}