[V2,40/45] vfio/iommufd: reconstruct device

Commit Message

Steven Sistare Feb. 14, 2025, 2:14 p.m. UTC

Reconstruct userland device state after CPR.  During vfio_realize, skip
all ioctls that configure the device, as it was already configured in old
QEMU.

Save the ioas_id in vmstate, and skip its allocation in vfio_realize.
Because we skip ioctl's, it is not needed at realize time.  However, we do
need the range info, so defer the call to iommufd_cdev_get_info_iova_range
to a post_load handler, at which time the ioas_id is known.

This reconstruction is not complete.  hwpt_id and devid need special
treatment, handled in subsequent patches.

Signed-off-by: Steve Sistare <[e-mail]>
---
 hw/vfio/cpr-iommufd.c |  8 ++++++++
 hw/vfio/iommufd.c     | 23 +++++++++++++++++++++--
 2 files changed, 29 insertions(+), 2 deletions(-)

Patch

diff --git a/hw/vfio/cpr-iommufd.c b/hw/vfio/cpr-iommufd.c
index 8c2fa3a..8453d76 100644
--- a/hw/vfio/cpr-iommufd.c
+++ b/hw/vfio/cpr-iommufd.c
@@ -30,6 +30,13 @@  static int vfio_container_post_load(void *opaque, int version_id)
     VFIOIOMMUFDContainer *container = opaque;
     VFIOContainerBase *bcontainer = &container->bcontainer;
     VFIODevice *vbasedev;
+    Error *err = NULL;
+    uint32_t ioas_id = container->ioas_id;
+
+    if (!iommufd_cdev_get_info_iova_range(container, ioas_id, &err)) {
+        error_report_err(err);
+        return -1;
+    }
 
     QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
         vbasedev->cpr.reused = false;
@@ -46,6 +53,7 @@  static const VMStateDescription vfio_container_vmstate = {
     .post_load = vfio_container_post_load,
     .needed = cpr_needed_for_reuse,
     .fields = (VMStateField[]) {
+        VMSTATE_UINT32(ioas_id, VFIOIOMMUFDContainer),
         VMSTATE_END_OF_LIST()
     }
 };
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 6c44303..3fc530d 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -99,6 +99,10 @@  static bool iommufd_cdev_connect_and_bind(VFIODevice *vbasedev, Error **errp)
         goto err_kvm_device_add;
     }
 
+    if (vbasedev->cpr.reused) {
+        goto skip_bind;
+    }
+
     /* Bind device to iommufd */
     bind.iommufd = iommufd->fd;
     if (ioctl(vbasedev->fd, VFIO_DEVICE_BIND_IOMMUFD, &bind)) {
@@ -110,6 +114,8 @@  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);
@@ -541,7 +547,8 @@  static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
             vbasedev->iommufd != container->be) {
             continue;
         }
-        if (!iommufd_cdev_attach_container(vbasedev, container, &err)) {
+        if (!vbasedev->cpr.reused &&
+            !iommufd_cdev_attach_container(vbasedev, container, &err)) {
             const char *msg = error_get_pretty(err);
 
             trace_iommufd_cdev_fail_attach_existing_container(msg);
@@ -558,6 +565,11 @@  static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         }
     }
 
+    if (vbasedev->cpr.reused) {
+        ioas_id = -1;           /* ioas_id will be received from vmstate */
+        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;
@@ -565,6 +577,7 @@  static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
 
     trace_iommufd_cdev_alloc_ioas(vbasedev->iommufd->fd, ioas_id);
 
+skip_ioas_alloc:
     container = VFIO_IOMMU_IOMMUFD(object_new(TYPE_VFIO_IOMMU_IOMMUFD));
     container->be = vbasedev->iommufd;
     container->ioas_id = ioas_id;
@@ -573,7 +586,8 @@  static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
     bcontainer = &container->bcontainer;
     vfio_address_space_insert(space, bcontainer);
 
-    if (!iommufd_cdev_attach_container(vbasedev, container, errp)) {
+    if (!vbasedev->cpr.reused &&
+        !iommufd_cdev_attach_container(vbasedev, container, errp)) {
         goto err_attach_container;
     }
 
@@ -583,6 +597,10 @@  static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         goto err_discard_disable;
     }
 
+    if (vbasedev->cpr.reused) {
+        goto skip_info;
+    }
+
     if (!iommufd_cdev_get_info_iova_range(container, ioas_id, &err)) {
         error_append_hint(&err,
                    "Fallback to default 64bit IOVA range and 4K page size\n");
@@ -591,6 +609,7 @@  static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         bcontainer->pgsizes = qemu_real_host_page_size();
     }
 
+skip_info:
     bcontainer->listener = vfio_memory_listener;
     memory_listener_register(&bcontainer->listener, bcontainer->space->as);