migration: allow to prioritize save state entries

During migration, save state entries are saved/loaded without a specific
order - we just traverse the savevm_state.handlers list and do it one by
one. This might not be enough.

There are requirements that we need to load specific device's vmstate
first before others. For example, VT-d IOMMU contains DMA address
remapping information, which is required by all the PCI devices to do
address translations. We need to make sure IOMMU's device state is
loaded before the rest of the PCI devices, so that DMA address
translation can work properly.

This patch provide a VMStateDescription.priority value to allow specify
the priority of the saved states. The loadvm operation will be done with
those devices with higher vmsd priority.

Before this patch, we are possibly achieving the ordering requirement by
an assumption that the ordering will be the same with the ordering that
objects are created. A better way is to mark it out explicitly in the
VMStateDescription table, like what this patch does.

Current ordering logic is still naive and slow, but after all that's not
a critical path so IMO it's a workable solution for now.

Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h
index 1638ee57f7d8837a6bffd22a783b55c74d090f15..1a228872fa0f3fb07809495f03ba869473996cd6 100644 (file)
--- a/include/migration/vmstate.h
+++ b/include/migration/vmstate.h
@@ -186,6 +186,11 @@ enum VMStateFlags {
     VMS_MULTIPLY_ELEMENTS = 0x4000,
 };
 
+typedef enum {
+    MIG_PRI_DEFAULT = 0,
+    MIG_PRI_MAX,
+} MigrationPriority;
+
 typedef struct {
     const char *name;
     size_t offset;
@@ -207,6 +212,7 @@ struct VMStateDescription {
     int version_id;
     int minimum_version_id;
     int minimum_version_id_old;
+    MigrationPriority priority;
     LoadStateHandler *load_state_old;
     int (*pre_load)(void *opaque);
     int (*post_load)(void *opaque, int version_id);

diff --git a/migration/savevm.c b/migration/savevm.c
index 0363372acc22693f3427ed4d83d560134bb36b23..f9c06e9f96ef661e1437058858894904a6fc560a 100644 (file)
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -532,6 +532,34 @@ static int calculate_compat_instance_id(const char *idstr)
     return instance_id;
 }
 
+static inline MigrationPriority save_state_priority(SaveStateEntry *se)
+{
+    if (se->vmsd) {
+        return se->vmsd->priority;
+    }
+    return MIG_PRI_DEFAULT;
+}
+
+static void savevm_state_handler_insert(SaveStateEntry *nse)
+{
+    MigrationPriority priority = save_state_priority(nse);
+    SaveStateEntry *se;
+
+    assert(priority <= MIG_PRI_MAX);
+
+    QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
+        if (save_state_priority(se) < priority) {
+            break;
+        }
+    }
+
+    if (se) {
+        QTAILQ_INSERT_BEFORE(se, nse, entry);
+    } else {
+        QTAILQ_INSERT_TAIL(&savevm_state.handlers, nse, entry);
+    }
+}
+
 /* TODO: Individual devices generally have very little idea about the rest
    of the system, so instance_id should be removed/replaced.
    Meanwhile pass -1 as instance_id if you do not already have a clearly
@@ -578,8 +606,7 @@ int register_savevm_live(DeviceState *dev,
         se->instance_id = instance_id;
     }
     assert(!se->compat || se->instance_id == 0);
-    /* add at the end of list */
-    QTAILQ_INSERT_TAIL(&savevm_state.handlers, se, entry);
+    savevm_state_handler_insert(se);
     return 0;
 }
 
@@ -662,8 +689,7 @@ int vmstate_register_with_alias_id(DeviceState *dev, int instance_id,
         se->instance_id = instance_id;
     }
     assert(!se->compat || se->instance_id == 0);
-    /* add at the end of list */
-    QTAILQ_INSERT_TAIL(&savevm_state.handlers, se, entry);
+    savevm_state_handler_insert(se);
     return 0;
 }