[PULL 21/27] vfio/iommufd: preserve descriptors

["Cédric Le Goater" <clg@redhat.com>]

From: Steve Sistare <steven.sistare@oracle.com>

Save the iommu and vfio device fd in CPR state when it is created.
After CPR, the fd number is found in CPR state and reused.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/qemu-devel/1751493538-202042-16-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
 backends/iommufd.c    | 35 +++++++++++++++++++++++++++++------
 hw/vfio/cpr-iommufd.c | 10 ++++++++++
 hw/vfio/device.c      |  9 +--------
 3 files changed, 40 insertions(+), 14 deletions(-)

diff --git a/backends/iommufd.c b/backends/iommufd.c
index c554ce5385dd603ba35f97167ab8031750ecdc2f..e0917923bffbb60dc5c58235880335c4d5eb7df7 100644
--- a/backends/iommufd.c
+++ b/backends/iommufd.c
@@ -16,12 +16,18 @@
 #include "qemu/module.h"
 #include "qom/object_interfaces.h"
 #include "qemu/error-report.h"
+#include "migration/cpr.h"
 #include "monitor/monitor.h"
 #include "trace.h"
 #include "hw/vfio/vfio-device.h"
 #include <sys/ioctl.h>
 #include <linux/iommufd.h>
 
+static const char *iommufd_fd_name(IOMMUFDBackend *be)
+{
+    return object_get_canonical_path_component(OBJECT(be));
+}
+
 static void iommufd_backend_init(Object *obj)
 {
     IOMMUFDBackend *be = IOMMUFD_BACKEND(obj);
@@ -64,11 +70,27 @@ static bool iommufd_backend_can_be_deleted(UserCreatable *uc)
     return !be->users;
 }
 
+static void iommufd_backend_complete(UserCreatable *uc, Error **errp)
+{
+    IOMMUFDBackend *be = IOMMUFD_BACKEND(uc);
+    const char *name = iommufd_fd_name(be);
+
+    if (!be->owned) {
+        /* fd came from the command line. Fetch updated value from cpr state. */
+        if (cpr_is_incoming()) {
+            be->fd = cpr_find_fd(name, 0);
+        } else {
+            cpr_save_fd(name, 0, be->fd);
+        }
+    }
+}
+
 static void iommufd_backend_class_init(ObjectClass *oc, const void *data)
 {
     UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
 
     ucc->can_be_deleted = iommufd_backend_can_be_deleted;
+    ucc->complete = iommufd_backend_complete;
 
     object_class_property_add_str(oc, "fd", NULL, iommufd_backend_set_fd);
 }
@@ -102,7 +124,7 @@ bool iommufd_backend_connect(IOMMUFDBackend *be, Error **errp)
     int fd;
 
     if (be->owned && !be->users) {
-        fd = qemu_open("/dev/iommu", O_RDWR, errp);
+        fd = cpr_open_fd("/dev/iommu", O_RDWR, iommufd_fd_name(be), 0, errp);
         if (fd < 0) {
             return false;
         }
@@ -127,14 +149,15 @@ void iommufd_backend_disconnect(IOMMUFDBackend *be)
         goto out;
     }
     be->users--;
-    if (!be->users && be->owned) {
-        close(be->fd);
-        be->fd = -1;
-    }
-out:
     if (!be->users) {
         vfio_iommufd_cpr_unregister_iommufd(be);
+        if (be->owned) {
+            cpr_delete_fd(iommufd_fd_name(be), 0);
+            close(be->fd);
+            be->fd = -1;
+        }
     }
+out:
     trace_iommufd_backend_disconnect(be->fd, be->users);
 }
 
diff --git a/hw/vfio/cpr-iommufd.c b/hw/vfio/cpr-iommufd.c
index 4166201e3f70441ff97aef23c3b6f8bf506c76ad..a72b68daa8e4da19b9cbf3ab50631211965cdf37 100644
--- a/hw/vfio/cpr-iommufd.c
+++ b/hw/vfio/cpr-iommufd.c
@@ -166,12 +166,18 @@ void vfio_iommufd_cpr_unregister_container(VFIOIOMMUFDContainer *container)
 void vfio_iommufd_cpr_register_device(VFIODevice *vbasedev)
 {
     if (!cpr_is_incoming()) {
+        /*
+         * Beware fd may have already been saved by vfio_device_set_fd,
+         * so call resave to avoid a duplicate entry.
+         */
+        cpr_resave_fd(vbasedev->name, 0, vbasedev->fd);
         vfio_cpr_save_device(vbasedev);
     }
 }
 
 void vfio_iommufd_cpr_unregister_device(VFIODevice *vbasedev)
 {
+    cpr_delete_fd(vbasedev->name, 0);
     vfio_cpr_delete_device(vbasedev->name);
 }
 
@@ -180,5 +186,9 @@ void vfio_cpr_load_device(VFIODevice *vbasedev)
     if (cpr_is_incoming()) {
         bool ret = vfio_cpr_find_device(vbasedev);
         g_assert(ret);
+
+        if (vbasedev->fd < 0) {
+            vbasedev->fd = cpr_find_fd(vbasedev->name, 0);
+        }
     }
 }
diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index 0ae3f3c6607d329e08fd435d2934e23affc27264..96cf21462cb10f9ebaf1bda54fed13a95b79f223 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -351,14 +351,7 @@ void vfio_device_free_name(VFIODevice *vbasedev)
 
 void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp)
 {
-    ERRP_GUARD();
-    int fd = monitor_fd_param(monitor_cur(), str, errp);
-
-    if (fd < 0) {
-        error_prepend(errp, "Could not parse remote object fd %s:", str);
-        return;
-    }
-    vbasedev->fd = fd;
+    vbasedev->fd = cpr_get_fd_param(vbasedev->dev->id, str, 0, errp);
 }
 
 static VFIODeviceIOOps vfio_device_io_ops_ioctl;
-- 
2.50.0