1 files changed, 100 insertions, 47 deletions

diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index adb17f266b2..20c3af7692c 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -31,11 +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 __KVM_HAVE_IOAPIC
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 /*
  * --------------------------------------------------------------------
  * irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -100,11 +101,13 @@ irqfd_inject(struct work_struct *work)
 	struct kvm *kvm = irqfd->kvm;
 
 	if (!irqfd->resampler) {
-		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
-		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
+		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);
+			    irqfd->gsi, 1, false);
 }
 
 /*
@@ -116,19 +119,22 @@ 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(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
-		    resampler->notifier.gsi, 0);
+	kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+		    resampler->notifier.gsi, 0, false);
 
-	rcu_read_lock();
+	idx = srcu_read_lock(&kvm->irq_srcu);
 
 	list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
 		eventfd_signal(irqfd->resamplefd, 1);
 
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
 static void
@@ -140,13 +146,13 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd)
 	mutex_lock(&kvm->irqfds.resampler_lock);
 
 	list_del_rcu(&irqfd->resampler_link);
-	synchronize_rcu();
+	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);
+			    resampler->notifier.gsi, 0, false);
 		kfree(resampler);
 	}
 
@@ -219,16 +225,18 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
 	unsigned long flags = (unsigned long)key;
 	struct kvm_kernel_irq_routing_entry *irq;
 	struct kvm *kvm = irqfd->kvm;
+	int idx;
 
 	if (flags & POLLIN) {
-		rcu_read_lock();
-		irq = rcu_dereference(irqfd->irq_entry);
+		idx = srcu_read_lock(&kvm->irq_srcu);
+		irq = srcu_dereference(irqfd->irq_entry, &kvm->irq_srcu);
 		/* An event has been signaled, inject an interrupt */
 		if (irq)
-			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1);
+			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
+					false);
 		else
 			schedule_work(&irqfd->inject);
-		rcu_read_unlock();
+		srcu_read_unlock(&kvm->irq_srcu, idx);
 	}
 
 	if (flags & POLLHUP) {
@@ -288,7 +296,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 {
 	struct kvm_irq_routing_table *irq_rt;
 	struct _irqfd *irqfd, *tmp;
-	struct file *file = NULL;
+	struct fd f;
 	struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
 	int ret;
 	unsigned int events;
@@ -303,13 +311,13 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	INIT_WORK(&irqfd->inject, irqfd_inject);
 	INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
 
-	file = eventfd_fget(args->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;
@@ -360,7 +368,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 		}
 
 		list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
-		synchronize_rcu();
+		synchronize_srcu(&kvm->irq_srcu);
 
 		mutex_unlock(&kvm->irqfds.resampler_lock);
 	}
@@ -388,24 +396,24 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 					   lockdep_is_held(&kvm->irqfds.lock));
 	irqfd_update(kvm, irqfd, irq_rt);
 
-	events = file->f_op->poll(file, &irqfd->pt);
-
 	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);
 
-	spin_unlock_irq(&kvm->irqfds.lock);
-
 	/*
 	 * do not drop the file until the irqfd is fully initialized, otherwise
 	 * we might race against the POLLHUP
 	 */
-	fput(file);
+	fdput(f);
 
 	return 0;
 
@@ -419,9 +427,9 @@ fail:
 	if (eventfd && !IS_ERR(eventfd))
 		eventfd_ctx_put(eventfd);
 
-	if (!IS_ERR(file))
-		fput(file);
+	fdput(f);
 
+out:
 	kfree(irqfd);
 	return ret;
 }
@@ -430,7 +438,7 @@ fail:
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
-#ifdef __KVM_HAVE_IOAPIC
+#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);
@@ -439,7 +447,7 @@ kvm_eventfd_init(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
-#ifdef __KVM_HAVE_IOAPIC
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -462,7 +470,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 			 * 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_rcu done by caller
+			 * It is paired with synchronize_srcu done by caller
 			 * of that function.
 			 */
 			rcu_assign_pointer(irqfd->irq_entry, NULL);
@@ -521,7 +529,7 @@ kvm_irqfd_release(struct kvm *kvm)
 
 /*
  * Change irq_routing and irqfd.
- * Caller must invoke synchronize_rcu afterwards.
+ * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
  */
 void kvm_irq_routing_update(struct kvm *kvm,
 			    struct kvm_irq_routing_table *irq_rt)
@@ -543,7 +551,7 @@ void kvm_irq_routing_update(struct kvm *kvm,
  * 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)
@@ -552,13 +560,10 @@ 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
 
 /*
@@ -577,6 +582,7 @@ struct _ioeventfd {
 	struct eventfd_ctx  *eventfd;
 	u64                  datamatch;
 	struct kvm_io_device dev;
+	u8                   bus_idx;
 	bool                 wildcard;
 };
 
@@ -599,7 +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;
 
@@ -669,25 +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;
-	enum kvm_bus              bus_idx = 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:
@@ -705,6 +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);
@@ -717,6 +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;
 
@@ -741,12 +775,25 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	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);
 
 	mutex_unlock(&kvm->slots_lock);
 
 	return 0;
 
+register_fail:
+	kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
 unlock_fail:
 	mutex_unlock(&kvm->slots_lock);
 
@@ -760,12 +807,12 @@ fail:
 static int
 kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
-	int                       pio = args->flags & KVM_IOEVENTFD_FLAG_PIO;
-	enum kvm_bus              bus_idx = 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);
@@ -775,7 +822,8 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	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)
@@ -785,6 +833,11 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 			continue;
 
 		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;