[RFC V1 08/12] vfio/iommufd: register container for cpr

[Steve Sistare <steven.sistare@oracle.com>]

Register a vfio iommufd container for CPR.  Add a blocker if the kernel does
not support IOMMU_IOAS_CHANGE_PROCESS.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
---
 backends/iommufd.c            |  8 ++++++
 hw/vfio/cpr-iommufd.c         | 60 +++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/iommufd.c             |  2 ++
 hw/vfio/meson.build           |  1 +
 include/hw/vfio/vfio-common.h |  3 +++
 include/sysemu/iommufd.h      |  1 +
 6 files changed, 75 insertions(+)
 create mode 100644 hw/vfio/cpr-iommufd.c

diff --git a/backends/iommufd.c b/backends/iommufd.c
index 4bdbad2..243178e 100644
--- a/backends/iommufd.c
+++ b/backends/iommufd.c
@@ -73,6 +73,14 @@ static void iommufd_backend_class_init(ObjectClass *oc, void *data)
     object_class_property_add_str(oc, "fd", NULL, iommufd_backend_set_fd);
 }
 
+bool iommufd_change_process_capable(IOMMUFDBackend *be)
+{
+    struct iommu_ioas_change_process args = {.n_umap = -1};
+
+    ioctl(be->fd, IOMMU_IOAS_CHANGE_PROCESS, &args);
+    return (errno != ENOTTY);
+}
+
 bool iommufd_backend_connect(IOMMUFDBackend *be, const char *name, Error **errp)
 {
     int fd;
diff --git a/hw/vfio/cpr-iommufd.c b/hw/vfio/cpr-iommufd.c
new file mode 100644
index 0000000..f2e34f4
--- /dev/null
+++ b/hw/vfio/cpr-iommufd.c
@@ -0,0 +1,60 @@
+/*
+ * Copyright (c) 2021-2024 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "hw/vfio/vfio-common.h"
+#include "migration/blocker.h"
+#include "migration/cpr.h"
+#include "migration/migration.h"
+#include "migration/vmstate.h"
+#include "sysemu/iommufd.h"
+
+#define IOMMUFD_CONTAINER(base) \
+    container_of(base, VFIOIOMMUFDContainer, bcontainer)
+
+static bool vfio_can_cpr_exec(VFIOIOMMUFDContainer *container, Error **errp)
+{
+    if (!iommufd_change_process_capable(container->be)) {
+        error_setg(errp,
+                   "VFIO container does not support IOMMU_IOAS_CHANGE_PROCESS");
+        return false;
+    }
+    return true;
+}
+
+static const VMStateDescription vfio_container_vmstate = {
+    .name = "vfio-iommufd-container",
+    .version_id = 0,
+    .minimum_version_id = 0,
+    .needed = cpr_needed_for_reuse,
+    .fields = (VMStateField[]) {
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+bool vfio_iommufd_cpr_register_container(VFIOContainerBase *bcontainer,
+                                         Error **errp)
+{
+    VFIOIOMMUFDContainer *container = IOMMUFD_CONTAINER(bcontainer);
+
+    if (!vfio_can_cpr_exec(container, &bcontainer->cpr_blocker)) {
+        return migrate_add_blocker_modes(&bcontainer->cpr_blocker, errp,
+                                        MIG_MODE_CPR_EXEC, -1) == 0;
+    }
+
+    vmstate_register(NULL, -1, &vfio_container_vmstate, container);
+
+    return true;
+}
+
+void vfio_iommufd_cpr_unregister_container(VFIOContainerBase *bcontainer)
+{
+    VFIOIOMMUFDContainer *container = IOMMUFD_CONTAINER(bcontainer);
+
+    vmstate_unregister(NULL, &vfio_container_vmstate, container);
+}
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 6d77daa..585bf09 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -632,6 +632,8 @@ static void vfio_iommu_iommufd_class_init(ObjectClass *klass, void *data)
     vioc->attach_device = iommufd_cdev_attach;
     vioc->detach_device = iommufd_cdev_detach;
     vioc->pci_hot_reset = iommufd_cdev_pci_hot_reset;
+    vioc->cpr_register = vfio_iommufd_cpr_register_container;
+    vioc->cpr_unregister = vfio_iommufd_cpr_unregister_container;
 };
 
 static bool hiod_iommufd_vfio_realize(HostIOMMUDevice *hiod, void *opaque,
diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build
index 5487815..998adb5 100644
--- a/hw/vfio/meson.build
+++ b/hw/vfio/meson.build
@@ -13,6 +13,7 @@ vfio_ss.add(when: 'CONFIG_IOMMUFD', if_true: files(
 vfio_ss.add(when: 'CONFIG_VFIO_PCI', if_true: files(
   'cpr.c',
   'cpr-legacy.c',
+  'cpr-iommufd.c',
   'display.c',
   'pci-quirks.c',
   'pci.c',
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index ec5b7168..8aa02d4 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -247,6 +247,9 @@ bool vfio_legacy_cpr_register_container(VFIOContainerBase *bcontainer,
 void vfio_legacy_cpr_unregister_container(VFIOContainerBase *bcontainer);
 bool iommufd_cdev_get_info_iova_range(VFIOIOMMUFDContainer *container,
                                       uint32_t ioas_id, Error **errp);
+bool vfio_iommufd_cpr_register_container(VFIOContainerBase *bcontainer,
+                                         Error **errp);
+void vfio_iommufd_cpr_unregister_container(VFIOContainerBase *bcontainer);
 
 extern const MemoryRegionOps vfio_region_ops;
 typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
diff --git a/include/sysemu/iommufd.h b/include/sysemu/iommufd.h
index 6955ebd..f80b968 100644
--- a/include/sysemu/iommufd.h
+++ b/include/sysemu/iommufd.h
@@ -52,6 +52,7 @@ int iommufd_backend_unmap_dma(IOMMUFDBackend *be, uint32_t ioas_id,
 bool iommufd_backend_get_device_info(IOMMUFDBackend *be, uint32_t devid,
                                      uint32_t *type, void *data, uint32_t len,
                                      Error **errp);
+bool iommufd_change_process_capable(IOMMUFDBackend *be);
 
 #define TYPE_HOST_IOMMU_DEVICE_IOMMUFD TYPE_HOST_IOMMU_DEVICE "-iommufd"
 #endif
-- 
1.8.3.1