vfio/iommufd: Add support for iova_ranges and pgsizes

Some vIOMMU such as virtio-iommu use IOVA ranges from host side to
setup reserved ranges for passthrough device, so that guest will not
use an IOVA range beyond host support.

Use an uAPI of IOMMUFD to get IOVA ranges of host side and pass to
vIOMMU just like the legacy backend, if this fails, fallback to
64bit IOVA range.

Also use out_iova_alignment returned from uAPI as pgsizes instead of
qemu_real_host_page_size() as a fallback.

Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Eric Auger <eric.auger@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, 55 insertions, 1 deletions

diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 6d31aea..01b448e 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -261,6 +261,53 @@ static int iommufd_cdev_ram_block_discard_disable(bool state)
     return ram_block_uncoordinated_discard_disable(state);
 }
 
+static int iommufd_cdev_get_info_iova_range(VFIOIOMMUFDContainer *container,
+                                            uint32_t ioas_id, Error **errp)
+{
+    VFIOContainerBase *bcontainer = &container->bcontainer;
+    struct iommu_ioas_iova_ranges *info;
+    struct iommu_iova_range *iova_ranges;
+    int ret, sz, fd = container->be->fd;
+
+    info = g_malloc0(sizeof(*info));
+    info->size = sizeof(*info);
+    info->ioas_id = ioas_id;
+
+    ret = ioctl(fd, IOMMU_IOAS_IOVA_RANGES, info);
+    if (ret && errno != EMSGSIZE) {
+        goto error;
+    }
+
+    sz = info->num_iovas * sizeof(struct iommu_iova_range);
+    info = g_realloc(info, sizeof(*info) + sz);
+    info->allowed_iovas = (uintptr_t)(info + 1);
+
+    ret = ioctl(fd, IOMMU_IOAS_IOVA_RANGES, info);
+    if (ret) {
+        goto error;
+    }
+
+    iova_ranges = (struct iommu_iova_range *)(uintptr_t)info->allowed_iovas;
+
+    for (int i = 0; i < info->num_iovas; i++) {
+        Range *range = g_new(Range, 1);
+
+        range_set_bounds(range, iova_ranges[i].start, iova_ranges[i].last);
+        bcontainer->iova_ranges =
+            range_list_insert(bcontainer->iova_ranges, range);
+    }
+    bcontainer->pgsizes = info->out_iova_alignment;
+
+    g_free(info);
+    return 0;
+
+error:
+    ret = -errno;
+    g_free(info);
+    error_setg_errno(errp, errno, "Cannot get IOVA ranges");
+    return ret;
+}
+
 static int iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
                                AddressSpace *as, Error **errp)
 {
@@ -335,7 +382,14 @@ static int iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         goto err_discard_disable;
     }
 
-    bcontainer->pgsizes = qemu_real_host_page_size();
+    ret = iommufd_cdev_get_info_iova_range(container, ioas_id, &err);
+    if (ret) {
+        error_append_hint(&err,
+                   "Fallback to default 64bit IOVA range and 4K page size\n");
+        warn_report_err(err);
+        err = NULL;
+        bcontainer->pgsizes = qemu_real_host_page_size();
+    }
 
     bcontainer->listener = vfio_memory_listener;
     memory_listener_register(&bcontainer->listener, bcontainer->space->as);