1 files changed, 310 insertions, 163 deletions

diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index c0f7872a912..518d86471b7 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2006 Intel Corporation
  * Copyright (c) 2007 Keir Fraser, XenSource Inc
  * Copyright (c) 2008 Intel Corporation
+ * Copyright 2009 Red Hat, Inc. and/or its affiliates.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -29,10 +30,14 @@
  *   Based on QEMU and Xen.
  */
 
+#define pr_fmt(fmt) "pit: " fmt
+
 #include <linux/kvm_host.h>
+#include <linux/slab.h>
 
 #include "irq.h"
 #include "i8254.h"
+#include "x86.h"
 
 #ifndef CONFIG_X86_64
 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
@@ -98,6 +103,39 @@ static int pit_get_gate(struct kvm *kvm, int channel)
 	return kvm->arch.vpit->pit_state.channels[channel].gate;
 }
 
+static s64 __kpit_elapsed(struct kvm *kvm)
+{
+	s64 elapsed;
+	ktime_t remaining;
+	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
+
+	if (!ps->period)
+		return 0;
+
+	/*
+	 * The Counter does not stop when it reaches zero. In
+	 * Modes 0, 1, 4, and 5 the Counter ``wraps around'' to
+	 * the highest count, either FFFF hex for binary counting
+	 * or 9999 for BCD counting, and continues counting.
+	 * Modes 2 and 3 are periodic; the Counter reloads
+	 * itself with the initial count and continues counting
+	 * from there.
+	 */
+	remaining = hrtimer_get_remaining(&ps->timer);
+	elapsed = ps->period - ktime_to_ns(remaining);
+
+	return elapsed;
+}
+
+static s64 kpit_elapsed(struct kvm *kvm, struct kvm_kpit_channel_state *c,
+			int channel)
+{
+	if (channel == 0)
+		return __kpit_elapsed(kvm);
+
+	return ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+}
+
 static int pit_get_count(struct kvm *kvm, int channel)
 {
 	struct kvm_kpit_channel_state *c =
@@ -107,7 +145,7 @@ static int pit_get_count(struct kvm *kvm, int channel)
 
 	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
 
-	t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+	t = kpit_elapsed(kvm, c, channel);
 	d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
 
 	switch (c->mode) {
@@ -137,7 +175,7 @@ static int pit_get_out(struct kvm *kvm, int channel)
 
 	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
 
-	t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+	t = kpit_elapsed(kvm, c, channel);
 	d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
 
 	switch (c->mode) {
@@ -193,83 +231,143 @@ static void pit_latch_status(struct kvm *kvm, int channel)
 	}
 }
 
-static int __pit_timer_fn(struct kvm_kpit_state *ps)
+static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 {
-	struct kvm_vcpu *vcpu0 = ps->pit->kvm->vcpus[0];
-	struct kvm_kpit_timer *pt = &ps->pit_timer;
-
-	if (!atomic_inc_and_test(&pt->pending))
-		set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
-	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
-		vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-		wake_up_interruptible(&vcpu0->wq);
-	}
+	struct kvm_kpit_state *ps = container_of(kian, struct kvm_kpit_state,
+						 irq_ack_notifier);
+	int value;
+
+	spin_lock(&ps->inject_lock);
+	value = atomic_dec_return(&ps->pending);
+	if (value < 0)
+		/* spurious acks can be generated if, for example, the
+		 * PIC is being reset.  Handle it gracefully here
+		 */
+		atomic_inc(&ps->pending);
+	else if (value > 0)
+		/* in this case, we had multiple outstanding pit interrupts
+		 * that we needed to inject.  Reinject
+		 */
+		queue_kthread_work(&ps->pit->worker, &ps->pit->expired);
+	ps->irq_ack = 1;
+	spin_unlock(&ps->inject_lock);
+}
 
-	pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
-	pt->scheduled = ktime_to_ns(pt->timer.expires);
+void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+	struct hrtimer *timer;
+
+	if (!kvm_vcpu_is_bsp(vcpu) || !pit)
+		return;
 
-	return (pt->period == 0 ? 0 : 1);
+	timer = &pit->pit_state.timer;
+	if (hrtimer_cancel(timer))
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
-int pit_has_pending_timer(struct kvm_vcpu *vcpu)
+static void destroy_pit_timer(struct kvm_pit *pit)
 {
-	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+	hrtimer_cancel(&pit->pit_state.timer);
+	flush_kthread_work(&pit->expired);
+}
 
-	if (pit && vcpu->vcpu_id == 0 && pit->pit_state.inject_pending)
-		return atomic_read(&pit->pit_state.pit_timer.pending);
+static void pit_do_work(struct kthread_work *work)
+{
+	struct kvm_pit *pit = container_of(work, struct kvm_pit, expired);
+	struct kvm *kvm = pit->kvm;
+	struct kvm_vcpu *vcpu;
+	int i;
+	struct kvm_kpit_state *ps = &pit->pit_state;
+	int inject = 0;
 
-	return 0;
+	/* Try to inject pending interrupts when
+	 * last one has been acked.
+	 */
+	spin_lock(&ps->inject_lock);
+	if (ps->irq_ack) {
+		ps->irq_ack = 0;
+		inject = 1;
+	}
+	spin_unlock(&ps->inject_lock);
+	if (inject) {
+		kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1, false);
+		kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0, false);
+
+		/*
+		 * Provides NMI watchdog support via Virtual Wire mode.
+		 * The route is: PIT -> PIC -> LVT0 in NMI mode.
+		 *
+		 * Note: Our Virtual Wire implementation is simplified, only
+		 * propagating PIT interrupts to all VCPUs when they have set
+		 * LVT0 to NMI delivery. Other PIC interrupts are just sent to
+		 * VCPU0, and only if its LVT0 is in EXTINT mode.
+		 */
+		if (kvm->arch.vapics_in_nmi_mode > 0)
+			kvm_for_each_vcpu(i, vcpu, kvm)
+				kvm_apic_nmi_wd_deliver(vcpu);
+	}
 }
 
 static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 {
-	struct kvm_kpit_state *ps;
-	int restart_timer = 0;
-
-	ps = container_of(data, struct kvm_kpit_state, pit_timer.timer);
+	struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer);
+	struct kvm_pit *pt = ps->kvm->arch.vpit;
 
-	restart_timer = __pit_timer_fn(ps);
+	if (ps->reinject || !atomic_read(&ps->pending)) {
+		atomic_inc(&ps->pending);
+		queue_kthread_work(&pt->worker, &pt->expired);
+	}
 
-	if (restart_timer)
+	if (ps->is_periodic) {
+		hrtimer_add_expires_ns(&ps->timer, ps->period);
 		return HRTIMER_RESTART;
-	else
+	} else
 		return HRTIMER_NORESTART;
 }
 
-void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
+static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 {
-	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
-	struct hrtimer *timer;
+	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
+	s64 interval;
 
-	if (vcpu->vcpu_id != 0 || !pit)
+	if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
 		return;
 
-	timer = &pit->pit_state.pit_timer.timer;
-	if (hrtimer_cancel(timer))
-		hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
-}
+	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
 
-static void destroy_pit_timer(struct kvm_kpit_timer *pt)
-{
-	pr_debug("pit: execute del timer!\n");
-	hrtimer_cancel(&pt->timer);
-}
+	pr_debug("create pit timer, interval is %llu nsec\n", interval);
 
-static void create_pit_timer(struct kvm_kpit_timer *pt, u32 val, int is_period)
-{
-	s64 interval;
+	/* TODO The new value only affected after the retriggered */
+	hrtimer_cancel(&ps->timer);
+	flush_kthread_work(&ps->pit->expired);
+	ps->period = interval;
+	ps->is_periodic = is_period;
 
-	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
+	ps->timer.function = pit_timer_fn;
+	ps->kvm = ps->pit->kvm;
 
-	pr_debug("pit: create pit timer, interval is %llu nsec\n", interval);
+	atomic_set(&ps->pending, 0);
+	ps->irq_ack = 1;
 
-	/* TODO The new value only affected after the retriggered */
-	hrtimer_cancel(&pt->timer);
-	pt->period = (is_period == 0) ? 0 : interval;
-	pt->timer.function = pit_timer_fn;
-	atomic_set(&pt->pending, 0);
+	/*
+	 * Do not allow the guest to program periodic timers with small
+	 * interval, since the hrtimers are not throttled by the host
+	 * scheduler.
+	 */
+	if (ps->is_periodic) {
+		s64 min_period = min_timer_period_us * 1000LL;
+
+		if (ps->period < min_period) {
+			pr_info_ratelimited(
+			    "kvm: requested %lld ns "
+			    "i8254 timer period limited to %lld ns\n",
+			    ps->period, min_period);
+			ps->period = min_period;
+		}
+	}
 
-	hrtimer_start(&pt->timer, ktime_add_ns(ktime_get(), interval),
+	hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval),
 		      HRTIMER_MODE_ABS);
 }
 
@@ -279,56 +377,81 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
 
 	WARN_ON(!mutex_is_locked(&ps->lock));
 
-	pr_debug("pit: load_count val is %d, channel is %d\n", val, channel);
+	pr_debug("load_count val is %d, channel is %d\n", val, channel);
 
 	/*
-	 * Though spec said the state of 8254 is undefined after power-up,
-	 * seems some tricky OS like Windows XP depends on IRQ0 interrupt
-	 * when booting up.
-	 * So here setting initialize rate for it, and not a specific number
+	 * The largest possible initial count is 0; this is equivalent
+	 * to 216 for binary counting and 104 for BCD counting.
 	 */
 	if (val == 0)
 		val = 0x10000;
 
-	ps->channels[channel].count_load_time = ktime_get();
 	ps->channels[channel].count = val;
 
-	if (channel != 0)
+	if (channel != 0) {
+		ps->channels[channel].count_load_time = ktime_get();
 		return;
+	}
 
 	/* Two types of timer
 	 * mode 1 is one shot, mode 2 is period, otherwise del timer */
 	switch (ps->channels[0].mode) {
+	case 0:
 	case 1:
         /* FIXME: enhance mode 4 precision */
 	case 4:
-		create_pit_timer(&ps->pit_timer, val, 0);
+		create_pit_timer(kvm, val, 0);
 		break;
 	case 2:
 	case 3:
-		create_pit_timer(&ps->pit_timer, val, 1);
+		create_pit_timer(kvm, val, 1);
 		break;
 	default:
-		destroy_pit_timer(&ps->pit_timer);
+		destroy_pit_timer(kvm->arch.vpit);
+	}
+}
+
+void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start)
+{
+	u8 saved_mode;
+	if (hpet_legacy_start) {
+		/* save existing mode for later reenablement */
+		saved_mode = kvm->arch.vpit->pit_state.channels[0].mode;
+		kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */
+		pit_load_count(kvm, channel, val);
+		kvm->arch.vpit->pit_state.channels[0].mode = saved_mode;
+	} else {
+		pit_load_count(kvm, channel, val);
 	}
 }
 
-void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val)
+static inline struct kvm_pit *dev_to_pit(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pit, dev);
+}
+
+static inline struct kvm_pit *speaker_to_pit(struct kvm_io_device *dev)
 {
-	mutex_lock(&kvm->arch.vpit->pit_state.lock);
-	pit_load_count(kvm, channel, val);
-	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+	return container_of(dev, struct kvm_pit, speaker_dev);
 }
 
-static void pit_ioport_write(struct kvm_io_device *this,
-			     gpa_t addr, int len, const void *data)
+static inline int pit_in_range(gpa_t addr)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
+		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
+}
+
+static int pit_ioport_write(struct kvm_io_device *this,
+			    gpa_t addr, int len, const void *data)
+{
+	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	int channel, access;
 	struct kvm_kpit_channel_state *s;
 	u32 val = *(u32 *) data;
+	if (!pit_in_range(addr))
+		return -EOPNOTSUPP;
 
 	val  &= 0xff;
 	addr &= KVM_PIT_CHANNEL_MASK;
@@ -336,8 +459,8 @@ static void pit_ioport_write(struct kvm_io_device *this,
 	mutex_lock(&pit_state->lock);
 
 	if (val != 0)
-		pr_debug("pit: write addr is 0x%x, len is %d, val is 0x%x\n",
-			  (unsigned int)addr, len, val);
+		pr_debug("write addr is 0x%x, len is %d, val is 0x%x\n",
+			 (unsigned int)addr, len, val);
 
 	if (addr == 3) {
 		channel = val >> 6;
@@ -391,18 +514,24 @@ static void pit_ioport_write(struct kvm_io_device *this,
 	}
 
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static void pit_ioport_read(struct kvm_io_device *this,
-			    gpa_t addr, int len, void *data)
+static int pit_ioport_read(struct kvm_io_device *this,
+			   gpa_t addr, int len, void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	int ret, count;
 	struct kvm_kpit_channel_state *s;
+	if (!pit_in_range(addr))
+		return -EOPNOTSUPP;
 
 	addr &= KVM_PIT_CHANNEL_MASK;
+	if (addr == 3)
+		return 0;
+
 	s = &pit_state->channels[addr];
 
 	mutex_lock(&pit_state->lock);
@@ -455,37 +584,36 @@ static void pit_ioport_read(struct kvm_io_device *this,
 	memcpy(data, (char *)&ret, len);
 
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static int pit_in_range(struct kvm_io_device *this, gpa_t addr,
-			int len, int is_write)
-{
-	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
-		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
-}
-
-static void speaker_ioport_write(struct kvm_io_device *this,
-				 gpa_t addr, int len, const void *data)
+static int speaker_ioport_write(struct kvm_io_device *this,
+				gpa_t addr, int len, const void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	u32 val = *(u32 *) data;
+	if (addr != KVM_SPEAKER_BASE_ADDRESS)
+		return -EOPNOTSUPP;
 
 	mutex_lock(&pit_state->lock);
 	pit_state->speaker_data_on = (val >> 1) & 1;
 	pit_set_gate(kvm, 2, val & 1);
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static void speaker_ioport_read(struct kvm_io_device *this,
-				gpa_t addr, int len, void *data)
+static int speaker_ioport_read(struct kvm_io_device *this,
+			       gpa_t addr, int len, void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	unsigned int refresh_clock;
 	int ret;
+	if (addr != KVM_SPEAKER_BASE_ADDRESS)
+		return -EOPNOTSUPP;
 
 	/* Refresh clock toggles at about 15us. We approximate as 2^14ns. */
 	refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1;
@@ -497,12 +625,7 @@ static void speaker_ioport_read(struct kvm_io_device *this,
 		len = sizeof(ret);
 	memcpy(data, (char *)&ret, len);
 	mutex_unlock(&pit_state->lock);
-}
-
-static int speaker_in_range(struct kvm_io_device *this, gpa_t addr,
-			    int len, int is_write)
-{
-	return (addr == KVM_SPEAKER_BASE_ADDRESS);
+	return 0;
 }
 
 void kvm_pit_reset(struct kvm_pit *pit)
@@ -511,6 +634,7 @@ void kvm_pit_reset(struct kvm_pit *pit)
 	struct kvm_kpit_channel_state *c;
 
 	mutex_lock(&pit->pit_state.lock);
+	pit->pit_state.flags = 0;
 	for (i = 0; i < 3; i++) {
 		c = &pit->pit_state.channels[i];
 		c->mode = 0xff;
@@ -519,47 +643,112 @@ void kvm_pit_reset(struct kvm_pit *pit)
 	}
 	mutex_unlock(&pit->pit_state.lock);
 
-	atomic_set(&pit->pit_state.pit_timer.pending, 0);
-	pit->pit_state.inject_pending = 1;
+	atomic_set(&pit->pit_state.pending, 0);
+	pit->pit_state.irq_ack = 1;
 }
 
-struct kvm_pit *kvm_create_pit(struct kvm *kvm)
+static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
+{
+	struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
+
+	if (!mask) {
+		atomic_set(&pit->pit_state.pending, 0);
+		pit->pit_state.irq_ack = 1;
+	}
+}
+
+static const struct kvm_io_device_ops pit_dev_ops = {
+	.read     = pit_ioport_read,
+	.write    = pit_ioport_write,
+};
+
+static const struct kvm_io_device_ops speaker_dev_ops = {
+	.read     = speaker_ioport_read,
+	.write    = speaker_ioport_write,
+};
+
+/* Caller must hold slots_lock */
+struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;
 	struct kvm_kpit_state *pit_state;
+	struct pid *pid;
+	pid_t pid_nr;
+	int ret;
 
 	pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL);
 	if (!pit)
 		return NULL;
 
+	pit->irq_source_id = kvm_request_irq_source_id(kvm);
+	if (pit->irq_source_id < 0) {
+		kfree(pit);
+		return NULL;
+	}
+
 	mutex_init(&pit->pit_state.lock);
 	mutex_lock(&pit->pit_state.lock);
-
-	/* Initialize PIO device */
-	pit->dev.read = pit_ioport_read;
-	pit->dev.write = pit_ioport_write;
-	pit->dev.in_range = pit_in_range;
-	pit->dev.private = pit;
-	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
-
-	pit->speaker_dev.read = speaker_ioport_read;
-	pit->speaker_dev.write = speaker_ioport_write;
-	pit->speaker_dev.in_range = speaker_in_range;
-	pit->speaker_dev.private = pit;
-	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
+	spin_lock_init(&pit->pit_state.inject_lock);
+
+	pid = get_pid(task_tgid(current));
+	pid_nr = pid_vnr(pid);
+	put_pid(pid);
+
+	init_kthread_worker(&pit->worker);
+	pit->worker_task = kthread_run(kthread_worker_fn, &pit->worker,
+				       "kvm-pit/%d", pid_nr);
+	if (IS_ERR(pit->worker_task)) {
+		mutex_unlock(&pit->pit_state.lock);
+		kvm_free_irq_source_id(kvm, pit->irq_source_id);
+		kfree(pit);
+		return NULL;
+	}
+	init_kthread_work(&pit->expired, pit_do_work);
 
 	kvm->arch.vpit = pit;
 	pit->kvm = kvm;
 
 	pit_state = &pit->pit_state;
 	pit_state->pit = pit;
-	hrtimer_init(&pit_state->pit_timer.timer,
-		     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	pit_state->irq_ack_notifier.gsi = 0;
+	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
+	kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
+	pit_state->reinject = true;
 	mutex_unlock(&pit->pit_state.lock);
 
 	kvm_pit_reset(pit);
 
+	pit->mask_notifier.func = pit_mask_notifer;
+	kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+
+	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
+	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, KVM_PIT_BASE_ADDRESS,
+				      KVM_PIT_MEM_LENGTH, &pit->dev);
+	if (ret < 0)
+		goto fail;
+
+	if (flags & KVM_PIT_SPEAKER_DUMMY) {
+		kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
+		ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS,
+					      KVM_SPEAKER_BASE_ADDRESS, 4,
+					      &pit->speaker_dev);
+		if (ret < 0)
+			goto fail_unregister;
+	}
+
 	return pit;
+
+fail_unregister:
+	kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
+
+fail:
+	kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+	kvm_unregister_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
+	kvm_free_irq_source_id(kvm, pit->irq_source_id);
+	kthread_stop(pit->worker_task);
+	kfree(pit);
+	return NULL;
 }
 
 void kvm_free_pit(struct kvm *kvm)
@@ -567,62 +756,20 @@ void kvm_free_pit(struct kvm *kvm)
 	struct hrtimer *timer;
 
 	if (kvm->arch.vpit) {
+		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &kvm->arch.vpit->dev);
+		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
+					      &kvm->arch.vpit->speaker_dev);
+		kvm_unregister_irq_mask_notifier(kvm, 0,
+					       &kvm->arch.vpit->mask_notifier);
+		kvm_unregister_irq_ack_notifier(kvm,
+				&kvm->arch.vpit->pit_state.irq_ack_notifier);
 		mutex_lock(&kvm->arch.vpit->pit_state.lock);
-		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
+		timer = &kvm->arch.vpit->pit_state.timer;
 		hrtimer_cancel(timer);
+		flush_kthread_work(&kvm->arch.vpit->expired);
+		kthread_stop(kvm->arch.vpit->worker_task);
+		kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id);
 		mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 		kfree(kvm->arch.vpit);
 	}
 }
-
-static void __inject_pit_timer_intr(struct kvm *kvm)
-{
-	mutex_lock(&kvm->lock);
-	kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 1);
-	kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 0);
-	kvm_pic_set_irq(pic_irqchip(kvm), 0, 1);
-	kvm_pic_set_irq(pic_irqchip(kvm), 0, 0);
-	mutex_unlock(&kvm->lock);
-}
-
-void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
-	struct kvm *kvm = vcpu->kvm;
-	struct kvm_kpit_state *ps;
-
-	if (vcpu && pit) {
-		ps = &pit->pit_state;
-
-		/* Try to inject pending interrupts when:
-		 * 1. Pending exists
-		 * 2. Last interrupt was accepted or waited for too long time*/
-		if (atomic_read(&ps->pit_timer.pending) &&
-		    (ps->inject_pending ||
-		    (jiffies - ps->last_injected_time
-				>= KVM_MAX_PIT_INTR_INTERVAL))) {
-			ps->inject_pending = 0;
-			__inject_pit_timer_intr(kvm);
-			ps->last_injected_time = jiffies;
-		}
-	}
-}
-
-void kvm_pit_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
-{
-	struct kvm_arch *arch = &vcpu->kvm->arch;
-	struct kvm_kpit_state *ps;
-
-	if (vcpu && arch->vpit) {
-		ps = &arch->vpit->pit_state;
-		if (atomic_read(&ps->pit_timer.pending) &&
-		(((arch->vpic->pics[0].imr & 1) == 0 &&
-		  arch->vpic->pics[0].irq_base == vec) ||
-		  (arch->vioapic->redirtbl[0].fields.vector == vec &&
-		  arch->vioapic->redirtbl[0].fields.mask != 1))) {
-			ps->inject_pending = 1;
-			atomic_dec(&ps->pit_timer.pending);
-			ps->channels[0].count_load_time = ktime_get();
-		}
-	}
-}