@@ -87,5 +87,6 @@ void vfio_user_set_handler(VFIODevice *vbasedev,
int vfio_user_validate_version(VFIODevice *vbasedev, Error **errp);
extern VFIODevIO vfio_dev_io_sock;
+extern VFIOContIO vfio_cont_io_sock;
#endif /* VFIO_USER_H */
@@ -94,6 +94,7 @@ typedef struct VFIOContainer {
uint64_t max_dirty_bitmap_size;
unsigned long pgsizes;
unsigned int dma_max_mappings;
+ VFIOProxy *proxy;
QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
QLIST_HEAD(, VFIOGroup) group_list;
@@ -278,6 +279,8 @@ VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp);
void vfio_put_group(VFIOGroup *group);
int vfio_get_device(VFIOGroup *group, const char *name,
VFIODevice *vbasedev, Error **errp);
+void vfio_connect_proxy(VFIOProxy *proxy, VFIOGroup *group, AddressSpace *as);
+void vfio_disconnect_proxy(VFIOGroup *group);
extern const MemoryRegionOps vfio_region_ops;
typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
@@ -19,6 +19,7 @@
*/
#include "qemu/osdep.h"
+#include CONFIG_DEVICES
#include <sys/ioctl.h>
#ifdef CONFIG_KVM
#include <linux/kvm.h>
@@ -2209,6 +2210,62 @@ put_space_exit:
return ret;
}
+
+#ifdef CONFIG_VFIO_USER
+
+void vfio_connect_proxy(VFIOProxy *proxy, VFIOGroup *group, AddressSpace *as)
+{
+ VFIOAddressSpace *space;
+ VFIOContainer *container;
+
+ if (QLIST_EMPTY(&vfio_group_list)) {
+ qemu_register_reset(vfio_reset_handler, NULL);
+ }
+
+ QLIST_INSERT_HEAD(&vfio_group_list, group, next);
+
+ /*
+ * try to mirror vfio_connect_container()
+ * as much as possible
+ */
+
+ space = vfio_get_address_space(as);
+
+ container = g_malloc0(sizeof(*container));
+ container->space = space;
+ container->fd = -1;
+ container->io_ops = &vfio_cont_io_sock;
+ QLIST_INIT(&container->giommu_list);
+ QLIST_INIT(&container->hostwin_list);
+ container->proxy = proxy;
+
+ /*
+ * The proxy uses a SW IOMMU in lieu of the HW one
+ * used in the ioctl() version. Use TYPE1 with the
+ * target's page size for maximum capatibility
+ */
+ container->iommu_type = VFIO_TYPE1_IOMMU;
+ vfio_host_win_add(container, 0, (hwaddr)-1, TARGET_PAGE_SIZE);
+ container->pgsizes = TARGET_PAGE_SIZE;
+
+ container->dirty_pages_supported = true;
+ container->max_dirty_bitmap_size = VFIO_USER_DEF_MAX_XFER;
+ container->dirty_pgsizes = TARGET_PAGE_SIZE;
+
+ QLIST_INIT(&container->group_list);
+ QLIST_INSERT_HEAD(&space->containers, container, next);
+
+ group->container = container;
+ QLIST_INSERT_HEAD(&container->group_list, group, container_next);
+
+ container->listener = vfio_memory_listener;
+ memory_listener_register(&container->listener, container->space->as);
+ container->initialized = true;
+}
+
+#endif /* CONFIG_VFIO_USER */
+
+
static void vfio_disconnect_container(VFIOGroup *group)
{
VFIOContainer *container = group->container;
@@ -2258,6 +2315,54 @@ static void vfio_disconnect_container(VFIOGroup *group)
}
}
+
+#ifdef CONFIG_VFIO_USER
+
+void vfio_disconnect_proxy(VFIOGroup *group)
+{
+ VFIOContainer *container = group->container;
+ VFIOAddressSpace *space = container->space;
+ VFIOGuestIOMMU *giommu, *tmp;
+ VFIOHostDMAWindow *hostwin, *next;
+
+ /*
+ * try to mirror vfio_disconnect_container()
+ * as much as possible, knowing each device
+ * is in one group and one container
+ */
+
+ QLIST_REMOVE(group, container_next);
+ group->container = NULL;
+
+ /*
+ * Explicitly release the listener first before unset container,
+ * since unset may destroy the backend container if it's the last
+ * group.
+ */
+ memory_listener_unregister(&container->listener);
+
+ QLIST_REMOVE(container, next);
+
+ QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
+ memory_region_unregister_iommu_notifier(
+ MEMORY_REGION(giommu->iommu), &giommu->n);
+ QLIST_REMOVE(giommu, giommu_next);
+ g_free(giommu);
+ }
+
+ QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next,
+ next) {
+ QLIST_REMOVE(hostwin, hostwin_next);
+ g_free(hostwin);
+ }
+
+ g_free(container);
+ vfio_put_address_space(space);
+}
+
+#endif /* CONFIG_VFIO_USER */
+
+
VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp)
{
VFIOGroup *group;
@@ -3562,6 +3562,7 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
VFIODevice *vbasedev = &vdev->vbasedev;
SocketAddress addr;
VFIOProxy *proxy;
+ VFIOGroup *group = NULL;
struct vfio_device_info info;
int ret;
Error *err = NULL;
@@ -3608,6 +3609,19 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
vbasedev->ops = &vfio_user_pci_ops;
vbasedev->io_ops = &vfio_dev_io_sock;
+ /*
+ * each device gets its own group and container
+ * make them unrelated to any host IOMMU groupings
+ */
+ group = g_malloc0(sizeof(*group));
+ group->fd = -1;
+ group->groupid = -1;
+ QLIST_INIT(&group->device_list);
+ QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
+ vbasedev->group = group;
+
+ vfio_connect_proxy(proxy, group, pci_device_iommu_address_space(pdev));
+
ret = VDEV_GET_INFO(vbasedev, &info);
if (ret) {
error_setg_errno(errp, -ret, "get info failure");
@@ -3673,6 +3687,10 @@ out_teardown:
vfio_teardown_msi(vdev);
vfio_bars_exit(vdev);
error:
+ if (group != NULL) {
+ vfio_disconnect_proxy(group);
+ g_free(group);
+ }
vfio_user_disconnect(proxy);
error_prepend(errp, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
@@ -3681,6 +3699,13 @@ static void vfio_user_instance_finalize(Object *obj)
{
VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
VFIODevice *vbasedev = &vdev->vbasedev;
+ VFIOGroup *group = vbasedev->group;
+
+ if (group != NULL) {
+ vfio_disconnect_proxy(group);
+ g_free(group);
+ vbasedev->group = NULL;
+ }
if (vdev->msix != NULL) {
vfio_user_msix_teardown(vdev);
@@ -1337,3 +1337,6 @@ VFIODevIO vfio_dev_io_sock = {
.region_write = vfio_user_io_region_write,
};
+
+VFIOContIO vfio_cont_io_sock = {
+};