vfio/migration: Allow migration without VFIO IOMMU dirty tracking support

Currently, if IOMMU of a VFIO container doesn't support dirty page
tracking, migration is blocked. This is because a DMA-able VFIO device
can dirty RAM pages without updating QEMU about it, thus breaking the
migration.

However, this doesn't mean that migration can't be done at all.
In such case, allow migration and let QEMU VFIO code mark all pages
dirty.

This guarantees that all pages that might have gotten dirty are reported
back, and thus guarantees a valid migration even without VFIO IOMMU
dirty tracking support.

The motivation for this patch is the introduction of iommufd [1].
iommufd can directly implement the /dev/vfio/vfio container IOCTLs by
mapping them into its internal ops, allowing the usage of these IOCTLs
over iommufd. However, VFIO IOMMU dirty tracking is not supported by
this VFIO compatibility API.

This patch will allow migration by hosts that use the VFIO compatibility
API and prevent migration regressions caused by the lack of VFIO IOMMU
dirty tracking support.

[1]
https://lore.kernel.org/kvm/0-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com/

Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Link: https://lore.kernel.org/r/20230216143630.25610-4-avihaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 130e5d1dc7029a9fde176203c4d9e7af7801547f..f6dd5715492e7c5fac55b5503ba857d8f7b31b48 100644 (file)
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -488,6 +488,12 @@ static int vfio_dma_unmap(VFIOContainer *container,
         return -errno;
     }
 
+    if (iotlb && vfio_devices_all_running_and_saving(container)) {
+        cpu_physical_memory_set_dirty_range(iotlb->translated_addr, size,
+                                            tcg_enabled() ? DIRTY_CLIENTS_ALL :
+                                            DIRTY_CLIENTS_NOCODE);
+    }
+
     return 0;
 }
 
@@ -1201,6 +1207,10 @@ static void vfio_set_dirty_page_tracking(VFIOContainer *container, bool start)
         .argsz = sizeof(dirty),
     };
 
+    if (!container->dirty_pages_supported) {
+        return;
+    }
+
     if (start) {
         dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_START;
     } else {
@@ -1236,6 +1246,13 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
     uint64_t pages;
     int ret;
 
+    if (!container->dirty_pages_supported) {
+        cpu_physical_memory_set_dirty_range(ram_addr, size,
+                                            tcg_enabled() ? DIRTY_CLIENTS_ALL :
+                                            DIRTY_CLIENTS_NOCODE);
+        return 0;
+    }
+
     dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range));
 
     dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range);
@@ -1409,8 +1426,7 @@ static void vfio_listener_log_sync(MemoryListener *listener,
 {
     VFIOContainer *container = container_of(listener, VFIOContainer, listener);
 
-    if (vfio_listener_skipped_section(section) ||
-        !container->dirty_pages_supported) {
+    if (vfio_listener_skipped_section(section)) {
         return;
     }
 

diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 65f3f3bef795c1c2004a14bb6e1840b5268c6187..e56eef1ee83c89c7bba1b0c2c3953b2b98d9133a 100644 (file)
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -858,11 +858,10 @@ int64_t vfio_mig_bytes_transferred(void)
 
 int vfio_migration_probe(VFIODevice *vbasedev, Error **errp)
 {
-    VFIOContainer *container = vbasedev->group->container;
     struct vfio_region_info *info = NULL;
     int ret = -ENOTSUP;
 
-    if (!vbasedev->enable_migration || !container->dirty_pages_supported) {
+    if (!vbasedev->enable_migration) {
         goto add_blocker;
     }