With default config, kernel VFIO IOMMU type1 driver limits dirty bitmap to
256MB for unmap_bitmap ioctl so the maximum guest memory region is no more
than 8TB size for the ioctl to succeed.

Be conservative here to limit total guest memory to max value supported
by unmap_bitmap ioctl or else add a migration blocker. IOMMUFD backend
doesn't have such limit, one can use IOMMUFD backed device if there is a
need to migration such large VM.

Suggested-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
---
 hw/vfio/iommufd.c   |  5 +++++
 hw/vfio/migration.c | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index ba5c6b6586..8de765c769 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -633,6 +633,11 @@ skip_ioas_alloc:
     QLIST_INIT(&container->hwpt_list);
 
     bcontainer = VFIO_IOMMU(container);
+
+    /* There is no limitation on dirty bitmap size in IOMMUFD */
+    bcontainer->max_dirty_bitmap_size = UINT64_MAX;
+    bcontainer->dirty_pgsizes = qemu_real_host_page_size();
+
     vfio_address_space_insert(space, bcontainer);
 
     if (!iommufd_cdev_attach_container(vbasedev, container, errp)) {
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 4c06e3db93..44bab024b7 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -16,6 +16,7 @@
 #include <sys/ioctl.h>
 
 #include "system/runstate.h"
+#include "hw/boards.h"
 #include "hw/vfio/vfio-device.h"
 #include "hw/vfio/vfio-migration.h"
 #include "migration/misc.h"
@@ -1152,6 +1153,31 @@ static bool vfio_viommu_preset(VFIODevice *vbasedev)
     return vbasedev->bcontainer->space->as != &address_space_memory;
 }
 
+static bool vfio_dirty_tracking_exceed_limit(VFIODevice *vbasedev)
+{
+    VFIOContainer *bcontainer = vbasedev->bcontainer;
+    uint64_t max_size, page_size;
+
+    if (!bcontainer->dirty_pages_supported) {
+        return true;
+    }
+    /*
+     * VFIO IOMMU type1 driver has limitation of bitmap size on unmap_bitmap
+     * ioctl(), calculate the limit and compare with guest memory size to
+     * catch dirty tracking failure early.
+     *
+     * This limit is 8TB with default kernel and QEMU config, we are a bit
+     * conservative here as VM memory layout may be nonconsecutive or VM
+     * can run with vIOMMU enabled so the limitation could be relaxed. One
+     * can also switch to use IOMMUFD backend if there is a need to migrate
+     * large VM.
+     */
+    page_size = 1 << ctz64(bcontainer->dirty_pgsizes);
+    max_size = bcontainer->max_dirty_bitmap_size * BITS_PER_BYTE * page_size;
+
+    return current_machine->ram_size > max_size;
+}
+
 /*
  * Return true when either migration initialized or blocker registered.
  * Currently only return false when adding blocker fails which will
@@ -1208,6 +1234,13 @@ bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp)
         goto add_blocker;
     }
 
+    if (vfio_dirty_tracking_exceed_limit(vbasedev)) {
+        error_setg(&err, "%s: Migration is currently not supported with "
+                   "large memory VM due to dirty tracking limitation in "
+                   "VFIO type1 driver", vbasedev->name);
+        goto add_blocker;
+    }
+
     trace_vfio_migration_realize(vbasedev->name);
     return true;
 
-- 
2.47.1