From: Zhenzhong Duan <zhenzhong.duan@intel.com>

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 it if there is a need to migrate such
large VM.

Suggested-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/qemu-devel/20251218062643.624796-9-zhenzhong.duan@intel.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
 hw/vfio/migration.c | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 58a4940b00eb0a070a5a48dc773fe56c42f377cd..e1c25ba90703e9574fdd69275ae2705684396697 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/core/boards.h"
 #include "hw/vfio/vfio-device.h"
 #include "hw/vfio/vfio-migration.h"
 #include "migration/misc.h"
@@ -1152,6 +1153,32 @@ 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 false;
+    }
+
+    /*
+     * 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
@@ -1193,6 +1220,13 @@ 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 "
+                       "backend", vbasedev->name);
+            goto add_blocker;
+        }
+
         warn_report("%s: VFIO device doesn't support device and "
                     "IOMMU dirty tracking", vbasedev->name);
     }
-- 
2.52.0