/* Open vhost I/O on given TAP file descriptor and specified memory
range. The caller is responsible for passing a valid tap file
descriptor and memory structure but not for initializing the vio
struct.
Return 0 on success.
See this link for a discussion of the Linux/KVM vhost_net feature:
http://blog.vmsplice.net/2011/09/qemu-internals-vhost-architecture.html */
int vhost_open(struct vio *vio, int tapfd, struct vio_memory *memory)
{
vio->tapfd = tapfd;
if ((vio->vhostfd = open("/dev/vhost-net", O_RDWR)) < 0 ||
(ioctl(vio->vhostfd, VHOST_SET_OWNER, NULL)) < 0 ||
(ioctl(vio->vhostfd, VHOST_GET_FEATURES, &vio->features)) < 0 ||
vhost_set_memory(vio, memory) ||
setup_vring(vio, 0) < 0 ||
setup_vring(vio, 1) < 0) {
/* Error */
if (vio->vhostfd >= 0) { close(vio->vhostfd); vio->vhostfd = -1; }
return -1;
}
return 0;
}
static void vhost_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
memory_listener);
if (!vhost_section(section)) {
return;
}
++dev->n_mem_sections;
dev->mem_sections = g_renew(MemoryRegionSection, dev->mem_sections,
dev->n_mem_sections);
dev->mem_sections[dev->n_mem_sections - 1] = *section;
vhost_set_memory(listener, section, true);
}
static void vhost_region_del(MemoryListener *listener,
MemoryRegionSection *section)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
memory_listener);
int i;
if (!vhost_section(section)) {
return;
}
vhost_set_memory(listener, section, false);
for (i = 0; i < dev->n_mem_sections; ++i) {
if (dev->mem_sections[i].offset_within_address_space
== section->offset_within_address_space) {
--dev->n_mem_sections;
memmove(&dev->mem_sections[i], &dev->mem_sections[i+1],
(dev->n_mem_sections - i) * sizeof(*dev->mem_sections));
break;
}
}
}
/* Caller must have device mutex */
long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct file *eventfp, *filep = NULL;
struct eventfd_ctx *ctx = NULL;
u64 p;
long r;
int i, fd;
/* If you are not the owner, you can become one */
if (ioctl == VHOST_SET_OWNER) {
r = vhost_dev_set_owner(d);
goto done;
}
/* You must be the owner to do anything else */
r = vhost_dev_check_owner(d);
if (r)
goto done;
switch (ioctl) {
case VHOST_SET_MEM_TABLE:
r = vhost_set_memory(d, argp);
break;
case VHOST_SET_LOG_BASE:
r = copy_from_user(&p, argp, sizeof p);
if (r < 0)
break;
if ((u64)(unsigned long)p != p) {
r = -EFAULT;
break;
}
for (i = 0; i < d->nvqs; ++i) {
struct vhost_virtqueue *vq;
void __user *base = (void __user *)(unsigned long)p;
vq = d->vqs + i;
mutex_lock(&vq->mutex);
/* If ring is inactive, will check when it's enabled. */
if (vq->private_data && !vq_log_access_ok(vq, base))
r = -EFAULT;
else
vq->log_base = base;
mutex_unlock(&vq->mutex);
}
break;
case VHOST_SET_LOG_FD:
r = get_user(fd, (int __user *)argp);
if (r < 0)
break;
eventfp = fd == -1 ? NULL : eventfd_fget(fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != d->log_file) {
filep = d->log_file;
ctx = d->log_ctx;
d->log_ctx = eventfp ?
eventfd_ctx_fileget(eventfp) : NULL;
} else
filep = eventfp;
for (i = 0; i < d->nvqs; ++i) {
mutex_lock(&d->vqs[i].mutex);
d->vqs[i].log_ctx = d->log_ctx;
mutex_unlock(&d->vqs[i].mutex);
}
if (ctx)
eventfd_ctx_put(ctx);
if (filep)
fput(filep);
break;
default:
r = vhost_set_vring(d, ioctl, argp);
break;
}
done:
return r;
}
