1 files changed, 382 insertions, 62 deletions

diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 554f9a6..bb5775a 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -15,34 +15,56 @@
 #include <linux/vfio.h>
 #include <linux/iommufd.h>
 
-#include "hw/vfio/vfio-common.h"
+#include "hw/vfio/vfio-device.h"
 #include "qemu/error-report.h"
 #include "trace.h"
 #include "qapi/error.h"
-#include "sysemu/iommufd.h"
+#include "system/iommufd.h"
 #include "hw/qdev-core.h"
-#include "sysemu/reset.h"
+#include "hw/vfio/vfio-cpr.h"
+#include "system/reset.h"
 #include "qemu/cutils.h"
 #include "qemu/chardev_open.h"
+#include "migration/cpr.h"
 #include "pci.h"
+#include "vfio-iommufd.h"
+#include "vfio-helpers.h"
+#include "vfio-listener.h"
 
-static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
-                            ram_addr_t size, void *vaddr, bool readonly)
+#define TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO             \
+            TYPE_HOST_IOMMU_DEVICE_IOMMUFD "-vfio"
+
+static int iommufd_cdev_map(const VFIOContainer *bcontainer, hwaddr iova,
+                            uint64_t size, void *vaddr, bool readonly,
+                            MemoryRegion *mr)
 {
-    const VFIOIOMMUFDContainer *container =
-        container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
+    const VFIOIOMMUFDContainer *container = VFIO_IOMMU_IOMMUFD(bcontainer);
 
     return iommufd_backend_map_dma(container->be,
                                    container->ioas_id,
                                    iova, size, vaddr, readonly);
 }
 
-static int iommufd_cdev_unmap(const VFIOContainerBase *bcontainer,
-                              hwaddr iova, ram_addr_t size,
-                              IOMMUTLBEntry *iotlb)
+static int iommufd_cdev_map_file(const VFIOContainer *bcontainer,
+                                 hwaddr iova, uint64_t size,
+                                 int fd, unsigned long start, bool readonly)
+{
+    const VFIOIOMMUFDContainer *container = VFIO_IOMMU_IOMMUFD(bcontainer);
+
+    return iommufd_backend_map_file_dma(container->be,
+                                        container->ioas_id,
+                                        iova, size, fd, start, readonly);
+}
+
+static int iommufd_cdev_unmap(const VFIOContainer *bcontainer,
+                              hwaddr iova, uint64_t size,
+                              IOMMUTLBEntry *iotlb, bool unmap_all)
 {
-    const VFIOIOMMUFDContainer *container =
-        container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
+    const VFIOIOMMUFDContainer *container = VFIO_IOMMU_IOMMUFD(bcontainer);
+
+    if (unmap_all) {
+        size = UINT64_MAX;
+    }
 
     /* TODO: Handle dma_unmap_bitmap with iotlb args (migration) */
     return iommufd_backend_unmap_dma(container->be,
@@ -84,6 +106,10 @@ static bool iommufd_cdev_connect_and_bind(VFIODevice *vbasedev, Error **errp)
         goto err_kvm_device_add;
     }
 
+    if (cpr_is_incoming()) {
+        goto skip_bind;
+    }
+
     /* Bind device to iommufd */
     bind.iommufd = iommufd->fd;
     if (ioctl(vbasedev->fd, VFIO_DEVICE_BIND_IOMMUFD, &bind)) {
@@ -95,6 +121,8 @@ static bool iommufd_cdev_connect_and_bind(VFIODevice *vbasedev, Error **errp)
     vbasedev->devid = bind.out_devid;
     trace_iommufd_cdev_connect_and_bind(bind.iommufd, vbasedev->name,
                                         vbasedev->fd, vbasedev->devid);
+
+skip_bind:
     return true;
 err_bind:
     iommufd_cdev_kvm_device_del(vbasedev);
@@ -110,6 +138,65 @@ static void iommufd_cdev_unbind_and_disconnect(VFIODevice *vbasedev)
     iommufd_backend_disconnect(vbasedev->iommufd);
 }
 
+static bool iommufd_hwpt_dirty_tracking(VFIOIOASHwpt *hwpt)
+{
+    return hwpt && hwpt->hwpt_flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
+}
+
+static int iommufd_set_dirty_page_tracking(const VFIOContainer *bcontainer,
+                                           bool start, Error **errp)
+{
+    const VFIOIOMMUFDContainer *container = VFIO_IOMMU_IOMMUFD(bcontainer);
+    VFIOIOASHwpt *hwpt;
+
+    QLIST_FOREACH(hwpt, &container->hwpt_list, next) {
+        if (!iommufd_hwpt_dirty_tracking(hwpt)) {
+            continue;
+        }
+
+        if (!iommufd_backend_set_dirty_tracking(container->be,
+                                                hwpt->hwpt_id, start, errp)) {
+            goto err;
+        }
+    }
+
+    return 0;
+
+err:
+    QLIST_FOREACH(hwpt, &container->hwpt_list, next) {
+        if (!iommufd_hwpt_dirty_tracking(hwpt)) {
+            continue;
+        }
+        iommufd_backend_set_dirty_tracking(container->be,
+                                           hwpt->hwpt_id, !start, NULL);
+    }
+    return -EINVAL;
+}
+
+static int iommufd_query_dirty_bitmap(const VFIOContainer *bcontainer,
+                                      VFIOBitmap *vbmap, hwaddr iova,
+                                      hwaddr size, Error **errp)
+{
+    VFIOIOMMUFDContainer *container = VFIO_IOMMU_IOMMUFD(bcontainer);
+    unsigned long page_size = qemu_real_host_page_size();
+    VFIOIOASHwpt *hwpt;
+
+    QLIST_FOREACH(hwpt, &container->hwpt_list, next) {
+        if (!iommufd_hwpt_dirty_tracking(hwpt)) {
+            continue;
+        }
+
+        if (!iommufd_backend_get_dirty_bitmap(container->be, hwpt->hwpt_id,
+                                              iova, size, page_size,
+                                              (uint64_t *)vbmap->bitmap,
+                                              errp)) {
+            return -EINVAL;
+        }
+    }
+
+    return 0;
+}
+
 static int iommufd_cdev_getfd(const char *sysfs_path, Error **errp)
 {
     ERRP_GUARD();
@@ -172,7 +259,7 @@ out:
     return ret;
 }
 
-static bool iommufd_cdev_attach_ioas_hwpt(VFIODevice *vbasedev, uint32_t id,
+static int iommufd_cdev_attach_ioas_hwpt(VFIODevice *vbasedev, uint32_t id,
                                          Error **errp)
 {
     int iommufd = vbasedev->iommufd->fd;
@@ -187,12 +274,12 @@ static bool iommufd_cdev_attach_ioas_hwpt(VFIODevice *vbasedev, uint32_t id,
         error_setg_errno(errp, errno,
                          "[iommufd=%d] error attach %s (%d) to id=%d",
                          iommufd, vbasedev->name, vbasedev->fd, id);
-        return false;
+        return -errno;
     }
 
     trace_iommufd_cdev_attach_ioas_hwpt(iommufd, vbasedev->name,
                                         vbasedev->fd, id);
-    return true;
+    return 0;
 }
 
 static bool iommufd_cdev_detach_ioas_hwpt(VFIODevice *vbasedev, Error **errp)
@@ -212,11 +299,134 @@ static bool iommufd_cdev_detach_ioas_hwpt(VFIODevice *vbasedev, Error **errp)
     return true;
 }
 
+static bool iommufd_cdev_autodomains_get(VFIODevice *vbasedev,
+                                         VFIOIOMMUFDContainer *container,
+                                         Error **errp)
+{
+    ERRP_GUARD();
+    IOMMUFDBackend *iommufd = vbasedev->iommufd;
+    VFIOContainer *bcontainer = VFIO_IOMMU(container);
+    uint32_t type, flags = 0;
+    uint64_t hw_caps;
+    VFIOIOASHwpt *hwpt;
+    uint32_t hwpt_id;
+    int ret;
+
+    /* Try to find a domain */
+    QLIST_FOREACH(hwpt, &container->hwpt_list, next) {
+        if (!cpr_is_incoming()) {
+            ret = iommufd_cdev_attach_ioas_hwpt(vbasedev, hwpt->hwpt_id, errp);
+        } else if (vbasedev->cpr.hwpt_id == hwpt->hwpt_id) {
+            ret = 0;
+        } else {
+            continue;
+        }
+
+        if (ret) {
+            /* -EINVAL means the domain is incompatible with the device. */
+            if (ret == -EINVAL) {
+                /*
+                 * It is an expected failure and it just means we will try
+                 * another domain, or create one if no existing compatible
+                 * domain is found. Hence why the error is discarded below.
+                 */
+                error_free(*errp);
+                *errp = NULL;
+                continue;
+            }
+
+            return false;
+        } else {
+            vbasedev->hwpt = hwpt;
+            vbasedev->cpr.hwpt_id = hwpt->hwpt_id;
+            QLIST_INSERT_HEAD(&hwpt->device_list, vbasedev, hwpt_next);
+            vbasedev->iommu_dirty_tracking = iommufd_hwpt_dirty_tracking(hwpt);
+            return true;
+        }
+    }
+
+    /*
+     * This is quite early and VFIO Migration state isn't yet fully
+     * initialized, thus rely only on IOMMU hardware capabilities as to
+     * whether IOMMU dirty tracking is going to be requested. Later
+     * vfio_migration_realize() may decide to use VF dirty tracking
+     * instead.
+     */
+    if (!iommufd_backend_get_device_info(vbasedev->iommufd, vbasedev->devid,
+                                         &type, NULL, 0, &hw_caps, errp)) {
+        return false;
+    }
+
+    if (hw_caps & IOMMU_HW_CAP_DIRTY_TRACKING) {
+        flags = IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
+    }
+
+    if (cpr_is_incoming()) {
+        hwpt_id = vbasedev->cpr.hwpt_id;
+        goto skip_alloc;
+    }
+
+    if (!iommufd_backend_alloc_hwpt(iommufd, vbasedev->devid,
+                                    container->ioas_id, flags,
+                                    IOMMU_HWPT_DATA_NONE, 0, NULL,
+                                    &hwpt_id, errp)) {
+        return false;
+    }
+
+    ret = iommufd_cdev_attach_ioas_hwpt(vbasedev, hwpt_id, errp);
+    if (ret) {
+        iommufd_backend_free_id(container->be, hwpt_id);
+        return false;
+    }
+
+skip_alloc:
+    hwpt = g_malloc0(sizeof(*hwpt));
+    hwpt->hwpt_id = hwpt_id;
+    hwpt->hwpt_flags = flags;
+    QLIST_INIT(&hwpt->device_list);
+
+    vbasedev->hwpt = hwpt;
+    vbasedev->cpr.hwpt_id = hwpt->hwpt_id;
+    vbasedev->iommu_dirty_tracking = iommufd_hwpt_dirty_tracking(hwpt);
+    QLIST_INSERT_HEAD(&hwpt->device_list, vbasedev, hwpt_next);
+    QLIST_INSERT_HEAD(&container->hwpt_list, hwpt, next);
+    bcontainer->dirty_pages_supported |=
+                                vbasedev->iommu_dirty_tracking;
+    if (bcontainer->dirty_pages_supported &&
+        !vbasedev->iommu_dirty_tracking) {
+        warn_report("IOMMU instance for device %s doesn't support dirty tracking",
+                    vbasedev->name);
+    }
+    return true;
+}
+
+static void iommufd_cdev_autodomains_put(VFIODevice *vbasedev,
+                                         VFIOIOMMUFDContainer *container)
+{
+    VFIOIOASHwpt *hwpt = vbasedev->hwpt;
+
+    QLIST_REMOVE(vbasedev, hwpt_next);
+    vbasedev->hwpt = NULL;
+
+    if (QLIST_EMPTY(&hwpt->device_list)) {
+        QLIST_REMOVE(hwpt, next);
+        iommufd_backend_free_id(container->be, hwpt->hwpt_id);
+        g_free(hwpt);
+    }
+}
+
 static bool iommufd_cdev_attach_container(VFIODevice *vbasedev,
                                           VFIOIOMMUFDContainer *container,
                                           Error **errp)
 {
-    return iommufd_cdev_attach_ioas_hwpt(vbasedev, container->ioas_id, errp);
+    /* mdevs aren't physical devices and will fail with auto domains */
+    if (!vbasedev->mdev) {
+        return iommufd_cdev_autodomains_get(vbasedev, container, errp);
+    }
+
+    /* If CPR, we are already attached to ioas_id. */
+    return cpr_is_incoming() ||
+           !iommufd_cdev_attach_ioas_hwpt(vbasedev, container->ioas_id, errp);
 }
 
 static void iommufd_cdev_detach_container(VFIODevice *vbasedev,
@@ -227,19 +437,24 @@ static void iommufd_cdev_detach_container(VFIODevice *vbasedev,
     if (!iommufd_cdev_detach_ioas_hwpt(vbasedev, &err)) {
         error_report_err(err);
     }
+
+    if (vbasedev->hwpt) {
+        iommufd_cdev_autodomains_put(vbasedev, container);
+    }
+
 }
 
 static void iommufd_cdev_container_destroy(VFIOIOMMUFDContainer *container)
 {
-    VFIOContainerBase *bcontainer = &container->bcontainer;
+    VFIOContainer *bcontainer = VFIO_IOMMU(container);
 
     if (!QLIST_EMPTY(&bcontainer->device_list)) {
         return;
     }
-    memory_listener_unregister(&bcontainer->listener);
-    vfio_container_destroy(bcontainer);
+    vfio_iommufd_cpr_unregister_container(container);
+    vfio_listener_unregister(bcontainer);
     iommufd_backend_free_id(container->be, container->ioas_id);
-    g_free(container);
+    object_unref(container);
 }
 
 static int iommufd_cdev_ram_block_discard_disable(bool state)
@@ -253,7 +468,7 @@ static int iommufd_cdev_ram_block_discard_disable(bool state)
 static bool iommufd_cdev_get_info_iova_range(VFIOIOMMUFDContainer *container,
                                              uint32_t ioas_id, Error **errp)
 {
-    VFIOContainerBase *bcontainer = &container->bcontainer;
+    VFIOContainer *bcontainer = VFIO_IOMMU(container);
     g_autofree struct iommu_ioas_iova_ranges *info = NULL;
     struct iommu_iova_range *iova_ranges;
     int sz, fd = container->be->fd;
@@ -295,16 +510,19 @@ error:
 static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
                                 AddressSpace *as, Error **errp)
 {
-    VFIOContainerBase *bcontainer;
+    VFIOContainer *bcontainer;
     VFIOIOMMUFDContainer *container;
     VFIOAddressSpace *space;
     struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) };
     int ret, devfd;
+    bool res;
     uint32_t ioas_id;
     Error *err = NULL;
     const VFIOIOMMUClass *iommufd_vioc =
         VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_IOMMUFD));
 
+    vfio_cpr_load_device(vbasedev);
+
     if (vbasedev->fd < 0) {
         devfd = iommufd_cdev_getfd(vbasedev->sysfsdev, errp);
         if (devfd < 0) {
@@ -319,16 +537,24 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         goto err_connect_bind;
     }
 
-    space = vfio_get_address_space(as);
+    space = vfio_address_space_get(as);
 
     /* try to attach to an existing container in this space */
     QLIST_FOREACH(bcontainer, &space->containers, next) {
-        container = container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
-        if (bcontainer->ops != iommufd_vioc ||
+        container = VFIO_IOMMU_IOMMUFD(bcontainer);
+        if (VFIO_IOMMU_GET_CLASS(bcontainer) != iommufd_vioc ||
             vbasedev->iommufd != container->be) {
             continue;
         }
-        if (!iommufd_cdev_attach_container(vbasedev, container, &err)) {
+
+        if (!cpr_is_incoming() ||
+            (vbasedev->cpr.ioas_id == container->ioas_id)) {
+            res = iommufd_cdev_attach_container(vbasedev, container, &err);
+        } else {
+            continue;
+        }
+
+        if (!res) {
             const char *msg = error_get_pretty(err);
 
             trace_iommufd_cdev_fail_attach_existing_container(msg);
@@ -337,14 +563,19 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         } else {
             ret = iommufd_cdev_ram_block_discard_disable(true);
             if (ret) {
-                error_setg(errp,
-                              "Cannot set discarding of RAM broken (%d)", ret);
+                error_setg_errno(errp, -ret,
+                                 "Cannot set discarding of RAM broken");
                 goto err_discard_disable;
             }
             goto found_container;
         }
     }
 
+    if (cpr_is_incoming()) {
+        ioas_id = vbasedev->cpr.ioas_id;
+        goto skip_ioas_alloc;
+    }
+
     /* Need to allocate a new dedicated container */
     if (!iommufd_backend_alloc_ioas(vbasedev->iommufd, &ioas_id, errp)) {
         goto err_alloc_ioas;
@@ -352,13 +583,14 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
 
     trace_iommufd_cdev_alloc_ioas(vbasedev->iommufd->fd, ioas_id);
 
-    container = g_malloc0(sizeof(*container));
+skip_ioas_alloc:
+    container = VFIO_IOMMU_IOMMUFD(object_new(TYPE_VFIO_IOMMU_IOMMUFD));
     container->be = vbasedev->iommufd;
     container->ioas_id = ioas_id;
+    QLIST_INIT(&container->hwpt_list);
 
-    bcontainer = &container->bcontainer;
-    vfio_container_init(bcontainer, space, iommufd_vioc);
-    QLIST_INSERT_HEAD(&space->containers, bcontainer, next);
+    bcontainer = VFIO_IOMMU(container);
+    vfio_address_space_insert(space, bcontainer);
 
     if (!iommufd_cdev_attach_container(vbasedev, container, errp)) {
         goto err_attach_container;
@@ -366,6 +598,7 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
 
     ret = iommufd_cdev_ram_block_discard_disable(true);
     if (ret) {
+        error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken");
         goto err_discard_disable;
     }
 
@@ -377,25 +610,31 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         bcontainer->pgsizes = qemu_real_host_page_size();
     }
 
-    bcontainer->listener = vfio_memory_listener;
-    memory_listener_register(&bcontainer->listener, bcontainer->space->as);
+    if (!vfio_listener_register(bcontainer, errp)) {
+        goto err_listener_register;
+    }
 
-    if (bcontainer->error) {
-        error_propagate_prepend(errp, bcontainer->error,
-                                "memory listener initialization failed: ");
+    if (!vfio_iommufd_cpr_register_container(container, errp)) {
         goto err_listener_register;
     }
 
     bcontainer->initialized = true;
 
 found_container:
+    vbasedev->cpr.ioas_id = container->ioas_id;
+
     ret = ioctl(devfd, VFIO_DEVICE_GET_INFO, &dev_info);
     if (ret) {
         error_setg_errno(errp, errno, "error getting device info");
         goto err_listener_register;
     }
 
-    if (!vfio_cpr_register_container(bcontainer, errp)) {
+    /*
+     * Do not move this code before attachment! The nested IOMMU support
+     * needs device and hwpt id which are generated only after attachment.
+     */
+    if (!vfio_device_hiod_create_and_realize(vbasedev,
+                     TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO, errp)) {
         goto err_listener_register;
     }
 
@@ -407,17 +646,12 @@ found_container:
         iommufd_cdev_ram_block_discard_disable(false);
     }
 
-    vbasedev->group = 0;
-    vbasedev->num_irqs = dev_info.num_irqs;
-    vbasedev->num_regions = dev_info.num_regions;
-    vbasedev->flags = dev_info.flags;
-    vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);
-    vbasedev->bcontainer = bcontainer;
-    QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
-    QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+    vfio_device_prepare(vbasedev, bcontainer, &dev_info);
+    vfio_iommufd_cpr_register_device(vbasedev);
 
     trace_iommufd_cdev_device_info(vbasedev->name, devfd, vbasedev->num_irqs,
-                                   vbasedev->num_regions, vbasedev->flags);
+                                   vbasedev->num_initial_regions,
+                                   vbasedev->flags);
     return true;
 
 err_listener_register:
@@ -427,7 +661,7 @@ err_discard_disable:
 err_attach_container:
     iommufd_cdev_container_destroy(container);
 err_alloc_ioas:
-    vfio_put_address_space(space);
+    vfio_address_space_put(space);
     iommufd_cdev_unbind_and_disconnect(vbasedev);
 err_connect_bind:
     close(vbasedev->fd);
@@ -436,24 +670,22 @@ err_connect_bind:
 
 static void iommufd_cdev_detach(VFIODevice *vbasedev)
 {
-    VFIOContainerBase *bcontainer = vbasedev->bcontainer;
+    VFIOContainer *bcontainer = vbasedev->bcontainer;
     VFIOAddressSpace *space = bcontainer->space;
-    VFIOIOMMUFDContainer *container = container_of(bcontainer,
-                                                   VFIOIOMMUFDContainer,
-                                                   bcontainer);
-    QLIST_REMOVE(vbasedev, global_next);
-    QLIST_REMOVE(vbasedev, container_next);
-    vbasedev->bcontainer = NULL;
+    VFIOIOMMUFDContainer *container = VFIO_IOMMU_IOMMUFD(bcontainer);
+
+    vfio_device_unprepare(vbasedev);
 
     if (!vbasedev->ram_block_discard_allowed) {
         iommufd_cdev_ram_block_discard_disable(false);
     }
 
-    vfio_cpr_unregister_container(bcontainer);
+    object_unref(vbasedev->hiod);
     iommufd_cdev_detach_container(vbasedev, container);
     iommufd_cdev_container_destroy(container);
-    vfio_put_address_space(space);
+    vfio_address_space_put(space);
 
+    vfio_iommufd_cpr_unregister_device(vbasedev);
     iommufd_cdev_unbind_and_disconnect(vbasedev);
     close(vbasedev->fd);
 }
@@ -465,7 +697,7 @@ static VFIODevice *iommufd_cdev_pci_find_by_devid(__u32 devid)
         VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_IOMMUFD));
 
     QLIST_FOREACH(vbasedev_iter, &vfio_device_list, global_next) {
-        if (vbasedev_iter->bcontainer->ops != iommufd_vioc) {
+        if (VFIO_IOMMU_GET_CLASS(vbasedev_iter->bcontainer) != iommufd_vioc) {
             continue;
         }
         if (devid == vbasedev_iter->devid) {
@@ -487,8 +719,8 @@ iommufd_cdev_dep_get_realized_vpdev(struct vfio_pci_dependent_device *dep_dev,
     }
 
     vbasedev_tmp = iommufd_cdev_pci_find_by_devid(dep_dev->devid);
-    if (!vbasedev_tmp || !vbasedev_tmp->dev->realized ||
-        vbasedev_tmp->type != VFIO_DEVICE_TYPE_PCI) {
+    if (!vfio_pci_from_vfio_device(vbasedev_tmp) ||
+        !vbasedev_tmp->dev->realized) {
         return NULL;
     }
 
@@ -608,23 +840,111 @@ out_single:
     return ret;
 }
 
-static void vfio_iommu_iommufd_class_init(ObjectClass *klass, void *data)
+static void vfio_iommu_iommufd_class_init(ObjectClass *klass, const void *data)
 {
     VFIOIOMMUClass *vioc = VFIO_IOMMU_CLASS(klass);
 
     vioc->dma_map = iommufd_cdev_map;
+    vioc->dma_map_file = iommufd_cdev_map_file;
     vioc->dma_unmap = iommufd_cdev_unmap;
     vioc->attach_device = iommufd_cdev_attach;
     vioc->detach_device = iommufd_cdev_detach;
     vioc->pci_hot_reset = iommufd_cdev_pci_hot_reset;
+    vioc->set_dirty_page_tracking = iommufd_set_dirty_page_tracking;
+    vioc->query_dirty_bitmap = iommufd_query_dirty_bitmap;
+};
+
+static bool
+host_iommu_device_iommufd_vfio_attach_hwpt(HostIOMMUDeviceIOMMUFD *idev,
+                                           uint32_t hwpt_id, Error **errp)
+{
+    VFIODevice *vbasedev = HOST_IOMMU_DEVICE(idev)->agent;
+
+    return !iommufd_cdev_attach_ioas_hwpt(vbasedev, hwpt_id, errp);
+}
+
+static bool
+host_iommu_device_iommufd_vfio_detach_hwpt(HostIOMMUDeviceIOMMUFD *idev,
+                                           Error **errp)
+{
+    VFIODevice *vbasedev = HOST_IOMMU_DEVICE(idev)->agent;
+
+    return iommufd_cdev_detach_ioas_hwpt(vbasedev, errp);
+}
+
+static bool hiod_iommufd_vfio_realize(HostIOMMUDevice *hiod, void *opaque,
+                                      Error **errp)
+{
+    VFIODevice *vdev = opaque;
+    HostIOMMUDeviceIOMMUFD *idev;
+    HostIOMMUDeviceCaps *caps = &hiod->caps;
+    VendorCaps *vendor_caps = &caps->vendor_caps;
+    enum iommu_hw_info_type type;
+    uint64_t hw_caps;
+
+    hiod->agent = opaque;
+
+    if (!iommufd_backend_get_device_info(vdev->iommufd, vdev->devid, &type,
+                                         vendor_caps, sizeof(*vendor_caps),
+                                         &hw_caps, errp)) {
+        return false;
+    }
+
+    hiod->name = g_strdup(vdev->name);
+    caps->type = type;
+    caps->hw_caps = hw_caps;
+
+    idev = HOST_IOMMU_DEVICE_IOMMUFD(hiod);
+    idev->iommufd = vdev->iommufd;
+    idev->devid = vdev->devid;
+    idev->hwpt_id = vdev->hwpt->hwpt_id;
+
+    return true;
+}
+
+static GList *
+hiod_iommufd_vfio_get_iova_ranges(HostIOMMUDevice *hiod)
+{
+    VFIODevice *vdev = hiod->agent;
+
+    g_assert(vdev);
+    return vfio_container_get_iova_ranges(vdev->bcontainer);
+}
+
+static uint64_t
+hiod_iommufd_vfio_get_page_size_mask(HostIOMMUDevice *hiod)
+{
+    VFIODevice *vdev = hiod->agent;
+
+    g_assert(vdev);
+    return vfio_container_get_page_size_mask(vdev->bcontainer);
+}
+
+
+static void hiod_iommufd_vfio_class_init(ObjectClass *oc, const void *data)
+{
+    HostIOMMUDeviceClass *hiodc = HOST_IOMMU_DEVICE_CLASS(oc);
+    HostIOMMUDeviceIOMMUFDClass *idevc = HOST_IOMMU_DEVICE_IOMMUFD_CLASS(oc);
+
+    hiodc->realize = hiod_iommufd_vfio_realize;
+    hiodc->get_iova_ranges = hiod_iommufd_vfio_get_iova_ranges;
+    hiodc->get_page_size_mask = hiod_iommufd_vfio_get_page_size_mask;
+
+    idevc->attach_hwpt = host_iommu_device_iommufd_vfio_attach_hwpt;
+    idevc->detach_hwpt = host_iommu_device_iommufd_vfio_detach_hwpt;
 };
 
 static const TypeInfo types[] = {
     {
         .name = TYPE_VFIO_IOMMU_IOMMUFD,
         .parent = TYPE_VFIO_IOMMU,
+        .instance_size = sizeof(VFIOIOMMUFDContainer),
         .class_init = vfio_iommu_iommufd_class_init,
-    },
+    }, {
+        .name = TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO,
+        .parent = TYPE_HOST_IOMMU_DEVICE_IOMMUFD,
+        .class_init = hiod_iommufd_vfio_class_init,
+    }
 };
 
 DEFINE_TYPES(types)