[RFC v9 12/29] vfio: Force nested if iommu requires it

[Eric Auger <eric.auger@redhat.com>]

In case we detect the address space is translated by
a virtual IOMMU which requires HW nested paging to
integrate with VFIO, let's set up the container with
the VFIO_TYPE1_NESTING_IOMMU iommu_type.

Signed-off-by: Eric Auger <eric.auger@redhat.com>

---

v7 -> v8
- remove as != &address_space_memory as
  memory_region_is_iommu(as->root) is sufficient [Kunkun]

v4 -> v5:
- fail immediatly if nested is wanted but not supported

v2 -> v3:
- add "nested only is selected if requested by @force_nested"
  comment in this patch
---
 hw/vfio/common.c | 36 ++++++++++++++++++++++++++++--------
 1 file changed, 28 insertions(+), 8 deletions(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index a456455517..30dc45df90 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1579,27 +1579,38 @@ static void vfio_put_address_space(VFIOAddressSpace *space)
  * vfio_get_iommu_type - selects the richest iommu_type (v2 first)
  */
 static int vfio_get_iommu_type(VFIOContainer *container,
+                               bool want_nested,
                                Error **errp)
 {
-    int iommu_types[] = { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU,
+    int iommu_types[] = { VFIO_TYPE1_NESTING_IOMMU,
+                          VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU,
                           VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU };
-    int i;
+    int i, ret = -EINVAL;
 
     for (i = 0; i < ARRAY_SIZE(iommu_types); i++) {
         if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) {
-            return iommu_types[i];
+            if (iommu_types[i] == VFIO_TYPE1_NESTING_IOMMU && !want_nested) {
+                continue;
+            }
+            ret = iommu_types[i];
+            break;
         }
     }
-    error_setg(errp, "No available IOMMU models");
-    return -EINVAL;
+    if (ret < 0) {
+        error_setg(errp, "No available IOMMU models");
+    } else if (want_nested && ret != VFIO_TYPE1_NESTING_IOMMU) {
+        error_setg(errp, "Nested mode requested but not supported");
+        ret = -EINVAL;
+    }
+    return ret;
 }
 
 static int vfio_init_container(VFIOContainer *container, int group_fd,
-                               Error **errp)
+                               bool want_nested, Error **errp)
 {
     int iommu_type, ret;
 
-    iommu_type = vfio_get_iommu_type(container, errp);
+    iommu_type = vfio_get_iommu_type(container, want_nested, errp);
     if (iommu_type < 0) {
         return iommu_type;
     }
@@ -1704,6 +1715,14 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
     VFIOContainer *container;
     int ret, fd;
     VFIOAddressSpace *space;
+    IOMMUMemoryRegion *iommu_mr;
+    bool nested = false;
+
+    if (memory_region_is_iommu(as->root)) {
+        iommu_mr = IOMMU_MEMORY_REGION(as->root);
+        memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_VFIO_NESTED,
+                                     (void *)&nested);
+    }
 
     space = vfio_get_address_space(as);
 
@@ -1773,13 +1792,14 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
     QLIST_INIT(&container->giommu_list);
     QLIST_INIT(&container->hostwin_list);
 
-    ret = vfio_init_container(container, group->fd, errp);
+    ret = vfio_init_container(container, group->fd, nested, errp);
     if (ret) {
         goto free_container_exit;
     }
     trace_vfio_connect_new_container(group->groupid, container->fd);
 
     switch (container->iommu_type) {
+    case VFIO_TYPE1_NESTING_IOMMU:
     case VFIO_TYPE1v2_IOMMU:
     case VFIO_TYPE1_IOMMU:
     {
-- 
2.26.3