1 files changed, 55 insertions, 50 deletions

diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 88b2fe3ddf42..375d6285475e 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * KVM coalesced MMIO
  *
@@ -8,7 +9,7 @@
  *
  */
 
-#include "iodev.h"
+#include <kvm/iodev.h>
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
@@ -39,50 +40,40 @@ static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev,
 	return 1;
 }
 
-static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev)
-{
-	struct kvm_coalesced_mmio_ring *ring;
-	unsigned avail;
-
-	/* Are we able to batch it ? */
-
-	/* last is the first free entry
-	 * check if we don't meet the first used entry
-	 * there is always one unused entry in the buffer
-	 */
-	ring = dev->kvm->coalesced_mmio_ring;
-	avail = (ring->first - ring->last - 1) % KVM_COALESCED_MMIO_MAX;
-	if (avail == 0) {
-		/* full */
-		return 0;
-	}
-
-	return 1;
-}
-
-static int coalesced_mmio_write(struct kvm_io_device *this,
-				gpa_t addr, int len, const void *val)
+static int coalesced_mmio_write(struct kvm_vcpu *vcpu,
+				struct kvm_io_device *this, gpa_t addr,
+				int len, const void *val)
 {
 	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
+	__u32 insert;
 
 	if (!coalesced_mmio_in_range(dev, addr, len))
 		return -EOPNOTSUPP;
 
 	spin_lock(&dev->kvm->ring_lock);
 
-	if (!coalesced_mmio_has_room(dev)) {
+	/*
+	 * last is the index of the entry to fill.  Verify userspace hasn't
+	 * set last to be out of range, and that there is room in the ring.
+	 * Leave one entry free in the ring so that userspace can differentiate
+	 * between an empty ring and a full ring.
+	 */
+	insert = READ_ONCE(ring->last);
+	if (insert >= KVM_COALESCED_MMIO_MAX ||
+	    (insert + 1) % KVM_COALESCED_MMIO_MAX == READ_ONCE(ring->first)) {
 		spin_unlock(&dev->kvm->ring_lock);
 		return -EOPNOTSUPP;
 	}
 
 	/* copy data in first free entry of the ring */
 
-	ring->coalesced_mmio[ring->last].phys_addr = addr;
-	ring->coalesced_mmio[ring->last].len = len;
-	memcpy(ring->coalesced_mmio[ring->last].data, val, len);
+	ring->coalesced_mmio[insert].phys_addr = addr;
+	ring->coalesced_mmio[insert].len = len;
+	memcpy(ring->coalesced_mmio[insert].data, val, len);
+	ring->coalesced_mmio[insert].pio = dev->zone.pio;
 	smp_wmb();
-	ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
+	ring->last = (insert + 1) % KVM_COALESCED_MMIO_MAX;
 	spin_unlock(&dev->kvm->ring_lock);
 	return 0;
 }
@@ -104,26 +95,22 @@ static const struct kvm_io_device_ops coalesced_mmio_ops = {
 int kvm_coalesced_mmio_init(struct kvm *kvm)
 {
 	struct page *page;
-	int ret;
 
-	ret = -ENOMEM;
-	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!page)
-		goto out_err;
+		return -ENOMEM;
 
-	ret = 0;
 	kvm->coalesced_mmio_ring = page_address(page);
 
 	/*
 	 * We're using this spinlock to sync access to the coalesced ring.
-	 * The list doesn't need it's own lock since device registration and
+	 * The list doesn't need its own lock since device registration and
 	 * unregistration should only happen when kvm->slots_lock is held.
 	 */
 	spin_lock_init(&kvm->ring_lock);
 	INIT_LIST_HEAD(&kvm->coalesced_zones);
 
-out_err:
-	return ret;
+	return 0;
 }
 
 void kvm_coalesced_mmio_free(struct kvm *kvm)
@@ -138,7 +125,11 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	int ret;
 	struct kvm_coalesced_mmio_dev *dev;
 
-	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
+	if (zone->pio != 1 && zone->pio != 0)
+		return -EINVAL;
+
+	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev),
+		      GFP_KERNEL_ACCOUNT);
 	if (!dev)
 		return -ENOMEM;
 
@@ -147,40 +138,54 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	dev->zone = *zone;
 
 	mutex_lock(&kvm->slots_lock);
-	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, zone->addr,
-				      zone->size, &dev->dev);
+	ret = kvm_io_bus_register_dev(kvm,
+				zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS,
+				zone->addr, zone->size, &dev->dev);
 	if (ret < 0)
 		goto out_free_dev;
 	list_add_tail(&dev->list, &kvm->coalesced_zones);
 	mutex_unlock(&kvm->slots_lock);
 
-	return ret;
+	return 0;
 
 out_free_dev:
 	mutex_unlock(&kvm->slots_lock);
-
 	kfree(dev);
 
-	if (dev == NULL)
-		return -ENXIO;
-
-	return 0;
+	return ret;
 }
 
 int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 					   struct kvm_coalesced_mmio_zone *zone)
 {
 	struct kvm_coalesced_mmio_dev *dev, *tmp;
+	int r;
+
+	if (zone->pio != 1 && zone->pio != 0)
+		return -EINVAL;
 
 	mutex_lock(&kvm->slots_lock);
 
-	list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list)
-		if (coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
-			kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dev->dev);
-			kvm_iodevice_destructor(&dev->dev);
+	list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) {
+		if (zone->pio == dev->zone.pio &&
+		    coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
+			r = kvm_io_bus_unregister_dev(kvm,
+				zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
+			/*
+			 * On failure, unregister destroys all devices on the
+			 * bus, including the target device. There's no need
+			 * to restart the walk as there aren't any zones left.
+			 */
+			if (r)
+				break;
 		}
+	}
 
 	mutex_unlock(&kvm->slots_lock);
 
+	/*
+	 * Ignore the result of kvm_io_bus_unregister_dev(), from userspace's
+	 * perspective, the coalesced MMIO is most definitely unregistered.
+	 */
 	return 0;
 }