linux/virt/kvm/coalesced_mmio.c

/*
 * KVM coalesced MMIO
 *
 * Copyright (c) 2008 Bull S.A.S.
 *
 *  Author: Laurent Vivier <Laurent.Vivier@bull.net>
 *
 */

#include "iodev.h"

#include <linux/kvm_host.h>
#include <linux/kvm.h>

#include "coalesced_mmio.h"

static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev)
{
	return container_of(dev, struct kvm_coalesced_mmio_dev, dev);
}

static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev,
				   gpa_t addr, int len)
{
	struct kvm_coalesced_mmio_zone *zone;
	struct kvm_coalesced_mmio_ring *ring;
	unsigned avail;
	int i;

	/* 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 < KVM_MAX_VCPUS) {
		/* full */
		return 0;
	}

	/* is it in a batchable area ? */

	for (i = 0; i < dev->nb_zones; i++) {
		zone = &dev->zone[i];

		/* (addr,len) is fully included in
		 * (zone->addr, zone->size)
		 */

		if (zone->addr <= addr &&
		    addr + len <= zone->addr + zone->size)
			return 1;
	}
	return 0;
}

static int coalesced_mmio_write(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;
	if (!coalesced_mmio_in_range(dev, addr, len))
		return -EOPNOTSUPP;

	spin_lock(&dev->lock);

	/* 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);
	smp_wmb();
	ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
	spin_unlock(&dev->lock);
	return 0;
}

static void coalesced_mmio_destructor(struct kvm_io_device *this)
{
	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);

	kfree(dev);
}

static const struct kvm_io_device_ops coalesced_mmio_ops = {
	.write      = coalesced_mmio_write,
	.destructor = coalesced_mmio_destructor,
};

int kvm_coalesced_mmio_init(struct kvm *kvm)
{
	struct kvm_coalesced_mmio_dev *dev;
	struct page *page;
	int ret;

	ret = -ENOMEM;
	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
	if (!page)
		goto out_err;
	kvm->coalesced_mmio_ring = page_address(page);

	ret = -ENOMEM;
	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
	if (!dev)
		goto out_free_page;
	spin_lock_init(&dev->lock);
	kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops);
	dev->kvm = kvm;
	kvm->coalesced_mmio_dev = dev;

	ret = kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &dev->dev);
	if (ret < 0)
		goto out_free_dev;

	return ret;

out_free_dev:
	kfree(dev);
out_free_page:
	__free_page(page);
out_err:
	return ret;
}

void kvm_coalesced_mmio_free(struct kvm *kvm)
{
	if (kvm->coalesced_mmio_ring)
		free_page((unsigned long)kvm->coalesced_mmio_ring);
}

int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
				         struct kvm_coalesced_mmio_zone *zone)
{
	struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev;

	if (dev == NULL)
		return -EINVAL;

	down_write(&kvm->slots_lock);
	if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) {
		up_write(&kvm->slots_lock);
		return -ENOBUFS;
	}

	dev->zone[dev->nb_zones] = *zone;
	dev->nb_zones++;

	up_write(&kvm->slots_lock);
	return 0;
}

int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
					   struct kvm_coalesced_mmio_zone *zone)
{
	int i;
	struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev;
	struct kvm_coalesced_mmio_zone *z;

	if (dev == NULL)
		return -EINVAL;

	down_write(&kvm->slots_lock);

	i = dev->nb_zones;
	while(i) {
		z = &dev->zone[i - 1];

		/* unregister all zones
		 * included in (zone->addr, zone->size)
		 */

		if (zone->addr <= z->addr &&
		    z->addr + z->size <= zone->addr + zone->size) {
			dev->nb_zones--;
			*z = dev->zone[dev->nb_zones];
		}
		i--;
	}

	up_write(&kvm->slots_lock);

	return 0;
}