vfio/pci: Make vfio cdev pre-openable by passing a file handle

This gives management tools like libvirt a chance to open the vfio
cdev with privilege and pass FD to qemu. This way qemu never needs
to have privilege to open a VFIO or iommu cdev node.

Together with the earlier support of pre-opening /dev/iommu device,
now we have full support of passing a vfio device to unprivileged
qemu by management tool. This mode is no more considered for the
legacy backend. So let's remove the "TODO" comment.

Add helper functions vfio_device_set_fd() and vfio_device_get_name()
to set fd and get device name, they will also be used by other vfio
devices.

There is no easy way to check if a device is mdev with FD passing,
so fail the x-balloon-allowed check unconditionally in this case.

There is also no easy way to get BDF as name with FD passing, so
we fake a name by VFIO_FD[fd].

Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>

1 files changed, 16 insertions, 12 deletions

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index c5984b0598..445d58c8e5 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2944,17 +2944,19 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
     VFIODevice *vbasedev = &vdev->vbasedev;
     char *tmp, *subsys;
     Error *err = NULL;
-    struct stat st;
     int i, ret;
     bool is_mdev;
     char uuid[UUID_STR_LEN];
     char *name;
 
-    if (!vbasedev->sysfsdev) {
+    if (vbasedev->fd < 0 && !vbasedev->sysfsdev) {
         if (!(~vdev->host.domain || ~vdev->host.bus ||
               ~vdev->host.slot || ~vdev->host.function)) {
             error_setg(errp, "No provided host device");
             error_append_hint(errp, "Use -device vfio-pci,host=DDDD:BB:DD.F "
+#ifdef CONFIG_IOMMUFD
+                              "or -device vfio-pci,fd=DEVICE_FD "
+#endif
                               "or -device vfio-pci,sysfsdev=PATH_TO_DEVICE\n");
             return;
         }
@@ -2964,13 +2966,9 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
                             vdev->host.slot, vdev->host.function);
     }
 
-    if (stat(vbasedev->sysfsdev, &st) < 0) {
-        error_setg_errno(errp, errno, "no such host device");
-        error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->sysfsdev);
+    if (vfio_device_get_name(vbasedev, errp) < 0) {
         return;
     }
-
-    vbasedev->name = g_path_get_basename(vbasedev->sysfsdev);
     vbasedev->ops = &vfio_pci_ops;
     vbasedev->type = VFIO_DEVICE_TYPE_PCI;
     vbasedev->dev = DEVICE(vdev);
@@ -3330,6 +3328,7 @@ static void vfio_instance_init(Object *obj)
     vdev->host.bus = ~0U;
     vdev->host.slot = ~0U;
     vdev->host.function = ~0U;
+    vdev->vbasedev.fd = -1;
 
     vdev->nv_gpudirect_clique = 0xFF;
 
@@ -3383,11 +3382,6 @@ static Property vfio_pci_dev_properties[] = {
                                    qdev_prop_nv_gpudirect_clique, uint8_t),
     DEFINE_PROP_OFF_AUTO_PCIBAR("x-msix-relocation", VFIOPCIDevice, msix_relo,
                                 OFF_AUTOPCIBAR_OFF),
-    /*
-     * TODO - support passed fds... is this necessary?
-     * DEFINE_PROP_STRING("vfiofd", VFIOPCIDevice, vfiofd_name),
-     * DEFINE_PROP_STRING("vfiogroupfd, VFIOPCIDevice, vfiogroupfd_name),
-     */
 #ifdef CONFIG_IOMMUFD
     DEFINE_PROP_LINK("iommufd", VFIOPCIDevice, vbasedev.iommufd,
                      TYPE_IOMMUFD_BACKEND, IOMMUFDBackend *),
@@ -3395,6 +3389,13 @@ static Property vfio_pci_dev_properties[] = {
     DEFINE_PROP_END_OF_LIST(),
 };
 
+#ifdef CONFIG_IOMMUFD
+static void vfio_pci_set_fd(Object *obj, const char *str, Error **errp)
+{
+    vfio_device_set_fd(&VFIO_PCI(obj)->vbasedev, str, errp);
+}
+#endif
+
 static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
@@ -3402,6 +3403,9 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
 
     dc->reset = vfio_pci_reset;
     device_class_set_props(dc, vfio_pci_dev_properties);
+#ifdef CONFIG_IOMMUFD
+    object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd);
+#endif
     dc->desc = "VFIO-based PCI device assignment";
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     pdc->realize = vfio_realize;