migration: Add last stage indicator to global dirty log

The global dirty log synchronization is used when KVM and dirty ring
are enabled. There is a particularity for ARM64 where the backup
bitmap is used to track dirty pages in non-running-vcpu situations.
It means the dirty ring works with the combination of ring buffer
and backup bitmap. The dirty bits in the backup bitmap needs to
collected in the last stage of live migration.

In order to identify the last stage of live migration and pass it
down, an extra parameter is added to the relevant functions and
callbacks. This last stage indicator isn't used until the dirty
ring is enabled in the subsequent patches.

No functional change intended.

Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-Id: <20230509022122.20888-2-gshan@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

accel/kvm/kvm-all.c

@@ -1563,7 +1563,7 @@ static void kvm_log_sync(MemoryListener *listener,
     kvm_slots_unlock();
 }
 
-static void kvm_log_sync_global(MemoryListener *l)
+static void kvm_log_sync_global(MemoryListener *l, bool last_stage)
 {
     KVMMemoryListener *kml = container_of(l, KVMMemoryListener, listener);
     KVMState *s = kvm_state;

include/exec/memory.h

@@ -934,8 +934,11 @@ struct MemoryListener {
      * its @log_sync must be NULL.  Vice versa.
      *
      * @listener: The #MemoryListener.
+     * @last_stage: The last stage to synchronize the log during migration.
+     * The caller should gurantee that the synchronization with true for
+     * @last_stage is triggered for once after all VCPUs have been stopped.
      */
-    void (*log_sync_global)(MemoryListener *listener);
+    void (*log_sync_global)(MemoryListener *listener, bool last_stage);
 
     /**
      * @log_clear:
@@ -2422,8 +2425,10 @@ MemoryRegionSection memory_region_find(MemoryRegion *mr,
  * memory_global_dirty_log_sync: synchronize the dirty log for all memory
  *
  * Synchronizes the dirty page log for all address spaces.
+ *
+ * @last_stage: whether this is the last stage of live migration
  */
-void memory_global_dirty_log_sync(void);
+void memory_global_dirty_log_sync(bool last_stage);
 
 /**
  * memory_global_dirty_log_sync: synchronize the dirty log for all memory

migration/dirtyrate.c

@@ -100,7 +100,7 @@ void global_dirty_log_change(unsigned int flag, bool start)
 static void global_dirty_log_sync(unsigned int flag, bool one_shot)
 {
     qemu_mutex_lock_iothread();
-    memory_global_dirty_log_sync();
+    memory_global_dirty_log_sync(false);
     if (one_shot) {
         memory_global_dirty_log_stop(flag);
     }
@@ -580,7 +580,7 @@ static void calculate_dirtyrate_dirty_bitmap(struct DirtyRateConfig config)
      * skip it unconditionally and start dirty tracking
      * from 2'round of log sync
      */
-    memory_global_dirty_log_sync();
+    memory_global_dirty_log_sync(false);
 
     /*
      * reset page protect manually and unconditionally.

migration/ram.c

@@ -1039,7 +1039,7 @@ static void migration_trigger_throttle(RAMState *rs)
     }
 }
 
-static void migration_bitmap_sync(RAMState *rs)
+static void migration_bitmap_sync(RAMState *rs, bool last_stage)
 {
     RAMBlock *block;
     int64_t end_time;
@@ -1051,7 +1051,7 @@ static void migration_bitmap_sync(RAMState *rs)
     }
 
     trace_migration_bitmap_sync_start();
-    memory_global_dirty_log_sync();
+    memory_global_dirty_log_sync(last_stage);
 
     qemu_mutex_lock(&rs->bitmap_mutex);
     WITH_RCU_READ_LOCK_GUARD() {
@@ -1086,7 +1086,7 @@ static void migration_bitmap_sync(RAMState *rs)
     }
 }
 
-static void migration_bitmap_sync_precopy(RAMState *rs)
+static void migration_bitmap_sync_precopy(RAMState *rs, bool last_stage)
 {
     Error *local_err = NULL;
 
@@ -1099,7 +1099,7 @@ static void migration_bitmap_sync_precopy(RAMState *rs)
         local_err = NULL;
     }
 
-    migration_bitmap_sync(rs);
+    migration_bitmap_sync(rs, last_stage);
 
     if (precopy_notify(PRECOPY_NOTIFY_AFTER_BITMAP_SYNC, &local_err)) {
         error_report_err(local_err);
@@ -2699,7 +2699,7 @@ void ram_postcopy_send_discard_bitmap(MigrationState *ms)
     RCU_READ_LOCK_GUARD();
 
     /* This should be our last sync, the src is now paused */
-    migration_bitmap_sync(rs);
+    migration_bitmap_sync(rs, false);
 
     /* Easiest way to make sure we don't resume in the middle of a host-page */
     rs->pss[RAM_CHANNEL_PRECOPY].last_sent_block = NULL;
@@ -2890,7 +2890,7 @@ static void ram_init_bitmaps(RAMState *rs)
         /* We don't use dirty log with background snapshots */
         if (!migrate_background_snapshot()) {
             memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
-            migration_bitmap_sync_precopy(rs);
+            migration_bitmap_sync_precopy(rs, false);
         }
     }
     qemu_mutex_unlock_ramlist();
@@ -3214,7 +3214,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
 
     WITH_RCU_READ_LOCK_GUARD() {
         if (!migration_in_postcopy()) {
-            migration_bitmap_sync_precopy(rs);
+            migration_bitmap_sync_precopy(rs, true);
         }
 
         ram_control_before_iterate(f, RAM_CONTROL_FINISH);
@@ -3288,7 +3288,7 @@ static void ram_state_pending_exact(void *opaque, uint64_t *must_precopy,
     if (!migration_in_postcopy() && remaining_size < s->threshold_size) {
         qemu_mutex_lock_iothread();
         WITH_RCU_READ_LOCK_GUARD() {
-            migration_bitmap_sync_precopy(rs);
+            migration_bitmap_sync_precopy(rs, false);
         }
         qemu_mutex_unlock_iothread();
         remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;
@@ -3523,7 +3523,7 @@ void colo_incoming_start_dirty_log(void)
     qemu_mutex_lock_iothread();
     qemu_mutex_lock_ramlist();
 
-    memory_global_dirty_log_sync();
+    memory_global_dirty_log_sync(false);
     WITH_RCU_READ_LOCK_GUARD() {
         RAMBLOCK_FOREACH_NOT_IGNORED(block) {
             ramblock_sync_dirty_bitmap(ram_state, block);
@@ -3813,7 +3813,7 @@ void colo_flush_ram_cache(void)
     void *src_host;
     unsigned long offset = 0;
 
-    memory_global_dirty_log_sync();
+    memory_global_dirty_log_sync(false);
     qemu_mutex_lock(&ram_state->bitmap_mutex);
     WITH_RCU_READ_LOCK_GUARD() {
         RAMBLOCK_FOREACH_NOT_IGNORED(block) {

softmmu/memory.c

@@ -2253,7 +2253,7 @@ void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr,
  * If memory region `mr' is NULL, do global sync.  Otherwise, sync
  * dirty bitmap for the specified memory region.
  */
-static void memory_region_sync_dirty_bitmap(MemoryRegion *mr)
+static void memory_region_sync_dirty_bitmap(MemoryRegion *mr, bool last_stage)
 {
     MemoryListener *listener;
     AddressSpace *as;
@@ -2283,7 +2283,7 @@ static void memory_region_sync_dirty_bitmap(MemoryRegion *mr)
              * is to do a global sync, because we are not capable to
              * sync in a finer granularity.
              */
-            listener->log_sync_global(listener);
+            listener->log_sync_global(listener, last_stage);
             trace_memory_region_sync_dirty(mr ? mr->name : "(all)", listener->name, 1);
         }
     }
@@ -2347,7 +2347,7 @@ DirtyBitmapSnapshot *memory_region_snapshot_and_clear_dirty(MemoryRegion *mr,
 {
     DirtyBitmapSnapshot *snapshot;
     assert(mr->ram_block);
-    memory_region_sync_dirty_bitmap(mr);
+    memory_region_sync_dirty_bitmap(mr, false);
     snapshot = cpu_physical_memory_snapshot_and_clear_dirty(mr, addr, size, client);
     memory_global_after_dirty_log_sync();
     return snapshot;
@@ -2873,9 +2873,9 @@ bool memory_region_present(MemoryRegion *container, hwaddr addr)
     return mr && mr != container;
 }
 
-void memory_global_dirty_log_sync(void)
+void memory_global_dirty_log_sync(bool last_stage)
 {
-    memory_region_sync_dirty_bitmap(NULL);
+    memory_region_sync_dirty_bitmap(NULL, last_stage);
 }
 
 void memory_global_after_dirty_log_sync(void)