1 files changed, 346 insertions, 62 deletions

diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 30f70fd511c..20c3af7692c 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -2,6 +2,7 @@
  * kvm eventfd support - use eventfd objects to signal various KVM events
  *
  * Copyright 2009 Novell.  All Rights Reserved.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
  *
  * Author:
  *	Gregory Haskins <ghaskins@novell.com>
@@ -30,9 +31,12 @@
 #include <linux/list.h>
 #include <linux/eventfd.h>
 #include <linux/kernel.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
 
 #include "iodev.h"
 
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 /*
  * --------------------------------------------------------------------
  * irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -41,16 +45,51 @@
  * --------------------------------------------------------------------
  */
 
+/*
+ * Resampling irqfds are a special variety of irqfds used to emulate
+ * level triggered interrupts.  The interrupt is asserted on eventfd
+ * trigger.  On acknowledgement through the irq ack notifier, the
+ * interrupt is de-asserted and userspace is notified through the
+ * resamplefd.  All resamplers on the same gsi are de-asserted
+ * together, so we don't need to track the state of each individual
+ * user.  We can also therefore share the same irq source ID.
+ */
+struct _irqfd_resampler {
+	struct kvm *kvm;
+	/*
+	 * List of resampling struct _irqfd objects sharing this gsi.
+	 * RCU list modified under kvm->irqfds.resampler_lock
+	 */
+	struct list_head list;
+	struct kvm_irq_ack_notifier notifier;
+	/*
+	 * Entry in list of kvm->irqfd.resampler_list.  Use for sharing
+	 * resamplers among irqfds on the same gsi.
+	 * Accessed and modified under kvm->irqfds.resampler_lock
+	 */
+	struct list_head link;
+};
+
 struct _irqfd {
-	struct kvm               *kvm;
-	struct eventfd_ctx       *eventfd;
-	int                       gsi;
-	struct list_head          list;
-	poll_table                pt;
-	wait_queue_head_t        *wqh;
-	wait_queue_t              wait;
-	struct work_struct        inject;
-	struct work_struct        shutdown;
+	/* Used for MSI fast-path */
+	struct kvm *kvm;
+	wait_queue_t wait;
+	/* Update side is protected by irqfds.lock */
+	struct kvm_kernel_irq_routing_entry __rcu *irq_entry;
+	/* Used for level IRQ fast-path */
+	int gsi;
+	struct work_struct inject;
+	/* The resampler used by this irqfd (resampler-only) */
+	struct _irqfd_resampler *resampler;
+	/* Eventfd notified on resample (resampler-only) */
+	struct eventfd_ctx *resamplefd;
+	/* Entry in list of irqfds for a resampler (resampler-only) */
+	struct list_head resampler_link;
+	/* Used for setup/shutdown */
+	struct eventfd_ctx *eventfd;
+	struct list_head list;
+	poll_table pt;
+	struct work_struct shutdown;
 };
 
 static struct workqueue_struct *irqfd_cleanup_wq;
@@ -61,8 +100,63 @@ irqfd_inject(struct work_struct *work)
 	struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
 	struct kvm *kvm = irqfd->kvm;
 
-	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
-	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
+	if (!irqfd->resampler) {
+		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1,
+				false);
+		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0,
+				false);
+	} else
+		kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+			    irqfd->gsi, 1, false);
+}
+
+/*
+ * Since resampler irqfds share an IRQ source ID, we de-assert once
+ * then notify all of the resampler irqfds using this GSI.  We can't
+ * do multiple de-asserts or we risk racing with incoming re-asserts.
+ */
+static void
+irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
+{
+	struct _irqfd_resampler *resampler;
+	struct kvm *kvm;
+	struct _irqfd *irqfd;
+	int idx;
+
+	resampler = container_of(kian, struct _irqfd_resampler, notifier);
+	kvm = resampler->kvm;
+
+	kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+		    resampler->notifier.gsi, 0, false);
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+
+	list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
+		eventfd_signal(irqfd->resamplefd, 1);
+
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+static void
+irqfd_resampler_shutdown(struct _irqfd *irqfd)
+{
+	struct _irqfd_resampler *resampler = irqfd->resampler;
+	struct kvm *kvm = resampler->kvm;
+
+	mutex_lock(&kvm->irqfds.resampler_lock);
+
+	list_del_rcu(&irqfd->resampler_link);
+	synchronize_srcu(&kvm->irq_srcu);
+
+	if (list_empty(&resampler->list)) {
+		list_del(&resampler->link);
+		kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier);
+		kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+			    resampler->notifier.gsi, 0, false);
+		kfree(resampler);
+	}
+
+	mutex_unlock(&kvm->irqfds.resampler_lock);
 }
 
 /*
@@ -72,12 +166,13 @@ static void
 irqfd_shutdown(struct work_struct *work)
 {
 	struct _irqfd *irqfd = container_of(work, struct _irqfd, shutdown);
+	u64 cnt;
 
 	/*
 	 * Synchronize with the wait-queue and unhook ourselves to prevent
 	 * further events.
 	 */
-	remove_wait_queue(irqfd->wqh, &irqfd->wait);
+	eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt);
 
 	/*
 	 * We know no new events will be scheduled at this point, so block
@@ -85,6 +180,11 @@ irqfd_shutdown(struct work_struct *work)
 	 */
 	flush_work(&irqfd->inject);
 
+	if (irqfd->resampler) {
+		irqfd_resampler_shutdown(irqfd);
+		eventfd_ctx_put(irqfd->resamplefd);
+	}
+
 	/*
 	 * It is now safe to release the object's resources
 	 */
@@ -123,14 +223,24 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
 {
 	struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait);
 	unsigned long flags = (unsigned long)key;
+	struct kvm_kernel_irq_routing_entry *irq;
+	struct kvm *kvm = irqfd->kvm;
+	int idx;
 
-	if (flags & POLLIN)
+	if (flags & POLLIN) {
+		idx = srcu_read_lock(&kvm->irq_srcu);
+		irq = srcu_dereference(irqfd->irq_entry, &kvm->irq_srcu);
 		/* An event has been signaled, inject an interrupt */
-		schedule_work(&irqfd->inject);
+		if (irq)
+			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
+					false);
+		else
+			schedule_work(&irqfd->inject);
+		srcu_read_unlock(&kvm->irq_srcu, idx);
+	}
 
 	if (flags & POLLHUP) {
 		/* The eventfd is closing, detach from KVM */
-		struct kvm *kvm = irqfd->kvm;
 		unsigned long flags;
 
 		spin_lock_irqsave(&kvm->irqfds.lock, flags);
@@ -158,17 +268,36 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
 			poll_table *pt)
 {
 	struct _irqfd *irqfd = container_of(pt, struct _irqfd, pt);
-
-	irqfd->wqh = wqh;
 	add_wait_queue(wqh, &irqfd->wait);
 }
 
+/* Must be called under irqfds.lock */
+static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd,
+			 struct kvm_irq_routing_table *irq_rt)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+
+	if (irqfd->gsi >= irq_rt->nr_rt_entries) {
+		rcu_assign_pointer(irqfd->irq_entry, NULL);
+		return;
+	}
+
+	hlist_for_each_entry(e, &irq_rt->map[irqfd->gsi], link) {
+		/* Only fast-path MSI. */
+		if (e->type == KVM_IRQ_ROUTING_MSI)
+			rcu_assign_pointer(irqfd->irq_entry, e);
+		else
+			rcu_assign_pointer(irqfd->irq_entry, NULL);
+	}
+}
+
 static int
-kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
+kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 {
-	struct _irqfd *irqfd;
-	struct file *file = NULL;
-	struct eventfd_ctx *eventfd = NULL;
+	struct kvm_irq_routing_table *irq_rt;
+	struct _irqfd *irqfd, *tmp;
+	struct fd f;
+	struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
 	int ret;
 	unsigned int events;
 
@@ -177,18 +306,18 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 		return -ENOMEM;
 
 	irqfd->kvm = kvm;
-	irqfd->gsi = gsi;
+	irqfd->gsi = args->gsi;
 	INIT_LIST_HEAD(&irqfd->list);
 	INIT_WORK(&irqfd->inject, irqfd_inject);
 	INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
 
-	file = eventfd_fget(fd);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
-		goto fail;
+	f = fdget(args->fd);
+	if (!f.file) {
+		ret = -EBADF;
+		goto out;
 	}
 
-	eventfd = eventfd_ctx_fileget(file);
+	eventfd = eventfd_ctx_fileget(f.file);
 	if (IS_ERR(eventfd)) {
 		ret = PTR_ERR(eventfd);
 		goto fail;
@@ -196,6 +325,54 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 
 	irqfd->eventfd = eventfd;
 
+	if (args->flags & KVM_IRQFD_FLAG_RESAMPLE) {
+		struct _irqfd_resampler *resampler;
+
+		resamplefd = eventfd_ctx_fdget(args->resamplefd);
+		if (IS_ERR(resamplefd)) {
+			ret = PTR_ERR(resamplefd);
+			goto fail;
+		}
+
+		irqfd->resamplefd = resamplefd;
+		INIT_LIST_HEAD(&irqfd->resampler_link);
+
+		mutex_lock(&kvm->irqfds.resampler_lock);
+
+		list_for_each_entry(resampler,
+				    &kvm->irqfds.resampler_list, link) {
+			if (resampler->notifier.gsi == irqfd->gsi) {
+				irqfd->resampler = resampler;
+				break;
+			}
+		}
+
+		if (!irqfd->resampler) {
+			resampler = kzalloc(sizeof(*resampler), GFP_KERNEL);
+			if (!resampler) {
+				ret = -ENOMEM;
+				mutex_unlock(&kvm->irqfds.resampler_lock);
+				goto fail;
+			}
+
+			resampler->kvm = kvm;
+			INIT_LIST_HEAD(&resampler->list);
+			resampler->notifier.gsi = irqfd->gsi;
+			resampler->notifier.irq_acked = irqfd_resampler_ack;
+			INIT_LIST_HEAD(&resampler->link);
+
+			list_add(&resampler->link, &kvm->irqfds.resampler_list);
+			kvm_register_irq_ack_notifier(kvm,
+						      &resampler->notifier);
+			irqfd->resampler = resampler;
+		}
+
+		list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
+		synchronize_srcu(&kvm->irq_srcu);
+
+		mutex_unlock(&kvm->irqfds.resampler_lock);
+	}
+
 	/*
 	 * Install our own custom wake-up handling so we are notified via
 	 * a callback whenever someone signals the underlying eventfd
@@ -203,16 +380,32 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 	init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup);
 	init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc);
 
-	events = file->f_op->poll(file, &irqfd->pt);
-
 	spin_lock_irq(&kvm->irqfds.lock);
+
+	ret = 0;
+	list_for_each_entry(tmp, &kvm->irqfds.items, list) {
+		if (irqfd->eventfd != tmp->eventfd)
+			continue;
+		/* This fd is used for another irq already. */
+		ret = -EBUSY;
+		spin_unlock_irq(&kvm->irqfds.lock);
+		goto fail;
+	}
+
+	irq_rt = rcu_dereference_protected(kvm->irq_routing,
+					   lockdep_is_held(&kvm->irqfds.lock));
+	irqfd_update(kvm, irqfd, irq_rt);
+
 	list_add_tail(&irqfd->list, &kvm->irqfds.items);
+
 	spin_unlock_irq(&kvm->irqfds.lock);
 
 	/*
 	 * Check if there was an event already pending on the eventfd
 	 * before we registered, and trigger it as if we didn't miss it.
 	 */
+	events = f.file->f_op->poll(f.file, &irqfd->pt);
+
 	if (events & POLLIN)
 		schedule_work(&irqfd->inject);
 
@@ -220,47 +413,69 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 	 * do not drop the file until the irqfd is fully initialized, otherwise
 	 * we might race against the POLLHUP
 	 */
-	fput(file);
+	fdput(f);
 
 	return 0;
 
 fail:
+	if (irqfd->resampler)
+		irqfd_resampler_shutdown(irqfd);
+
+	if (resamplefd && !IS_ERR(resamplefd))
+		eventfd_ctx_put(resamplefd);
+
 	if (eventfd && !IS_ERR(eventfd))
 		eventfd_ctx_put(eventfd);
 
-	if (!IS_ERR(file))
-		fput(file);
+	fdput(f);
 
+out:
 	kfree(irqfd);
 	return ret;
 }
+#endif
 
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
+	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
+	mutex_init(&kvm->irqfds.resampler_lock);
+#endif
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 /*
  * shutdown any irqfd's that match fd+gsi
  */
 static int
-kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi)
+kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 {
 	struct _irqfd *irqfd, *tmp;
 	struct eventfd_ctx *eventfd;
 
-	eventfd = eventfd_ctx_fdget(fd);
+	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
 
 	spin_lock_irq(&kvm->irqfds.lock);
 
 	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
-		if (irqfd->eventfd == eventfd && irqfd->gsi == gsi)
+		if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) {
+			/*
+			 * This rcu_assign_pointer is needed for when
+			 * another thread calls kvm_irq_routing_update before
+			 * we flush workqueue below (we synchronize with
+			 * kvm_irq_routing_update using irqfds.lock).
+			 * It is paired with synchronize_srcu done by caller
+			 * of that function.
+			 */
+			rcu_assign_pointer(irqfd->irq_entry, NULL);
 			irqfd_deactivate(irqfd);
+		}
 	}
 
 	spin_unlock_irq(&kvm->irqfds.lock);
@@ -277,12 +492,15 @@ kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi)
 }
 
 int
-kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
+kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 {
-	if (flags & KVM_IRQFD_FLAG_DEASSIGN)
-		return kvm_irqfd_deassign(kvm, fd, gsi);
+	if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_RESAMPLE))
+		return -EINVAL;
+
+	if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)
+		return kvm_irqfd_deassign(kvm, args);
 
-	return kvm_irqfd_assign(kvm, fd, gsi);
+	return kvm_irqfd_assign(kvm, args);
 }
 
 /*
@@ -310,11 +528,30 @@ kvm_irqfd_release(struct kvm *kvm)
 }
 
 /*
+ * Change irq_routing and irqfd.
+ * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
+ */
+void kvm_irq_routing_update(struct kvm *kvm,
+			    struct kvm_irq_routing_table *irq_rt)
+{
+	struct _irqfd *irqfd;
+
+	spin_lock_irq(&kvm->irqfds.lock);
+
+	rcu_assign_pointer(kvm->irq_routing, irq_rt);
+
+	list_for_each_entry(irqfd, &kvm->irqfds.items, list)
+		irqfd_update(kvm, irqfd, irq_rt);
+
+	spin_unlock_irq(&kvm->irqfds.lock);
+}
+
+/*
  * create a host-wide workqueue for issuing deferred shutdown requests
  * aggregated from all vm* instances. We need our own isolated single-thread
  * queue to prevent deadlock against flushing the normal work-queue.
  */
-static int __init irqfd_module_init(void)
+int kvm_irqfd_init(void)
 {
 	irqfd_cleanup_wq = create_singlethread_workqueue("kvm-irqfd-cleanup");
 	if (!irqfd_cleanup_wq)
@@ -323,13 +560,11 @@ static int __init irqfd_module_init(void)
 	return 0;
 }
 
-static void __exit irqfd_module_exit(void)
+void kvm_irqfd_exit(void)
 {
 	destroy_workqueue(irqfd_cleanup_wq);
 }
-
-module_init(irqfd_module_init);
-module_exit(irqfd_module_exit);
+#endif
 
 /*
  * --------------------------------------------------------------------
@@ -347,6 +582,7 @@ struct _ioeventfd {
 	struct eventfd_ctx  *eventfd;
 	u64                  datamatch;
 	struct kvm_io_device dev;
+	u8                   bus_idx;
 	bool                 wildcard;
 };
 
@@ -369,7 +605,15 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
 {
 	u64 _val;
 
-	if (!(addr == p->addr && len == p->length))
+	if (addr != p->addr)
+		/* address must be precise for a hit */
+		return false;
+
+	if (!p->length)
+		/* length = 0 means only look at the address, so always a hit */
+		return true;
+
+	if (len != p->length)
 		/* address-range must be precise for a hit */
 		return false;
 
@@ -439,25 +683,38 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
 	struct _ioeventfd *_p;
 
 	list_for_each_entry(_p, &kvm->ioeventfds, list)
-		if (_p->addr == p->addr && _p->length == p->length &&
-		    (_p->wildcard || p->wildcard ||
-		     _p->datamatch == p->datamatch))
+		if (_p->bus_idx == p->bus_idx &&
+		    _p->addr == p->addr &&
+		    (!_p->length || !p->length ||
+		     (_p->length == p->length &&
+		      (_p->wildcard || p->wildcard ||
+		       _p->datamatch == p->datamatch))))
 			return true;
 
 	return false;
 }
 
+static enum kvm_bus ioeventfd_bus_from_flags(__u32 flags)
+{
+	if (flags & KVM_IOEVENTFD_FLAG_PIO)
+		return KVM_PIO_BUS;
+	if (flags & KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY)
+		return KVM_VIRTIO_CCW_NOTIFY_BUS;
+	return KVM_MMIO_BUS;
+}
+
 static int
 kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
-	int                       pio = args->flags & KVM_IOEVENTFD_FLAG_PIO;
-	struct kvm_io_bus        *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus;
+	enum kvm_bus              bus_idx;
 	struct _ioeventfd        *p;
 	struct eventfd_ctx       *eventfd;
 	int                       ret;
 
-	/* must be natural-word sized */
+	bus_idx = ioeventfd_bus_from_flags(args->flags);
+	/* must be natural-word sized, or 0 to ignore length */
 	switch (args->len) {
+	case 0:
 	case 1:
 	case 2:
 	case 4:
@@ -475,6 +732,12 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
 		return -EINVAL;
 
+	/* ioeventfd with no length can't be combined with DATAMATCH */
+	if (!args->len &&
+	    args->flags & (KVM_IOEVENTFD_FLAG_PIO |
+			   KVM_IOEVENTFD_FLAG_DATAMATCH))
+		return -EINVAL;
+
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
@@ -487,6 +750,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	INIT_LIST_HEAD(&p->list);
 	p->addr    = args->addr;
+	p->bus_idx = bus_idx;
 	p->length  = args->len;
 	p->eventfd = eventfd;
 
@@ -496,9 +760,9 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	else
 		p->wildcard = true;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
-	/* Verify that there isnt a match already */
+	/* Verify that there isn't a match already */
 	if (ioeventfd_check_collision(kvm, p)) {
 		ret = -EEXIST;
 		goto unlock_fail;
@@ -506,18 +770,32 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	kvm_iodevice_init(&p->dev, &ioeventfd_ops);
 
-	ret = __kvm_io_bus_register_dev(bus, &p->dev);
+	ret = kvm_io_bus_register_dev(kvm, bus_idx, p->addr, p->length,
+				      &p->dev);
 	if (ret < 0)
 		goto unlock_fail;
 
+	/* When length is ignored, MMIO is also put on a separate bus, for
+	 * faster lookups.
+	 */
+	if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) {
+		ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS,
+					      p->addr, 0, &p->dev);
+		if (ret < 0)
+			goto register_fail;
+	}
+
+	kvm->buses[bus_idx]->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 
 	return 0;
 
+register_fail:
+	kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
 unlock_fail:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 
 fail:
 	kfree(p);
@@ -529,22 +807,23 @@ fail:
 static int
 kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
-	int                       pio = args->flags & KVM_IOEVENTFD_FLAG_PIO;
-	struct kvm_io_bus        *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus;
+	enum kvm_bus              bus_idx;
 	struct _ioeventfd        *p, *tmp;
 	struct eventfd_ctx       *eventfd;
 	int                       ret = -ENOENT;
 
+	bus_idx = ioeventfd_bus_from_flags(args->flags);
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) {
 		bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH);
 
-		if (p->eventfd != eventfd  ||
+		if (p->bus_idx != bus_idx ||
+		    p->eventfd != eventfd  ||
 		    p->addr != args->addr  ||
 		    p->length != args->len ||
 		    p->wildcard != wildcard)
@@ -553,13 +832,18 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 		if (!p->wildcard && p->datamatch != args->datamatch)
 			continue;
 
-		__kvm_io_bus_unregister_dev(bus, &p->dev);
+		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
+		if (!p->length) {
+			kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS,
+						  &p->dev);
+		}
+		kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
 		break;
 	}
 
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 
 	eventfd_ctx_put(eventfd);