migration: Split save_live_pending() into state_pending_*

We split the function into to:

- state_pending_estimate: We estimate the remaining state size without
  stopping the machine.

- state pending_exact: We calculate the exact amount of remaining
  state.

The only "device" that implements different functions for _estimate()
and _exact() is ram.

Signed-off-by: Juan Quintela <[email protected]>
Reviewed-by: Dr. David Alan Gilbert <[email protected]>

Author: Juan Quintela

docs/devel/migration.rst

@@ -482,15 +482,17 @@ An iterative device must provide:
   - A ``load_setup`` function that initialises the data structures on the
     destination.
 
-  - A ``save_live_pending`` function that is called repeatedly and must
-    indicate how much more data the iterative data must save.  The core
-    migration code will use this to determine when to pause the CPUs
-    and complete the migration.
-
-  - A ``save_live_iterate`` function (called after ``save_live_pending``
-    when there is significant data still to be sent).  It should send
-    a chunk of data until the point that stream bandwidth limits tell it
-    to stop.  Each call generates one section.
+  - A ``state_pending_exact`` function that indicates how much more
+    data we must save.  The core migration code will use this to
+    determine when to pause the CPUs and complete the migration.
+
+  - A ``state_pending_estimate`` function that indicates how much more
+    data we must save.  When the estimated amount is smaller than the
+    threshold, we call ``state_pending_exact``.
+
+  - A ``save_live_iterate`` function should send a chunk of data until
+    the point that stream bandwidth limits tell it to stop.  Each call
+    generates one section.
 
   - A ``save_live_complete_precopy`` function that must transmit the
     last section for the device containing any remaining data.

docs/devel/vfio-migration.rst

@@ -28,7 +28,7 @@ VFIO implements the device hooks for the iterative approach as follows:
 * A ``load_setup`` function that sets up the migration region on the
   destination and sets _RESUMING flag in the VFIO device state.
 
-* A ``save_live_pending`` function that reads pending_bytes from the vendor
+* A ``state_pending_exact`` function that reads pending_bytes from the vendor
   driver, which indicates the amount of data that the vendor driver has yet to
   save for the VFIO device.
 
@@ -114,7 +114,7 @@ Live migration save path
                     (RUNNING, _SETUP, _RUNNING|_SAVING)
                                   |
                     (RUNNING, _ACTIVE, _RUNNING|_SAVING)
-             If device is active, get pending_bytes by .save_live_pending()
+             If device is active, get pending_bytes by .state_pending_exact()
           If total pending_bytes >= threshold_size, call .save_live_iterate()
                   Data of VFIO device for pre-copy phase is copied
         Iterate till total pending bytes converge and are less than threshold

hw/s390x/s390-stattrib.c

@@ -182,10 +182,10 @@ static int cmma_save_setup(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static void cmma_save_pending(void *opaque, uint64_t max_size,
-                              uint64_t *res_precopy_only,
-                              uint64_t *res_compatible,
-                              uint64_t *res_postcopy_only)
+static void cmma_state_pending(void *opaque, uint64_t max_size,
+                               uint64_t *res_precopy_only,
+                               uint64_t *res_compatible,
+                               uint64_t *res_postcopy_only)
 {
     S390StAttribState *sas = S390_STATTRIB(opaque);
     S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
@@ -371,7 +371,8 @@ static SaveVMHandlers savevm_s390_stattrib_handlers = {
     .save_setup = cmma_save_setup,
     .save_live_iterate = cmma_save_iterate,
     .save_live_complete_precopy = cmma_save_complete,
-    .save_live_pending = cmma_save_pending,
+    .state_pending_exact = cmma_state_pending,
+    .state_pending_estimate = cmma_state_pending,
     .save_cleanup = cmma_save_cleanup,
     .load_state = cmma_load,
     .is_active = cmma_active,

hw/vfio/migration.c

@@ -456,11 +456,11 @@ static void vfio_save_cleanup(void *opaque)
     trace_vfio_save_cleanup(vbasedev->name);
 }
 
-static void vfio_save_pending(void *opaque,
-                              uint64_t threshold_size,
-                              uint64_t *res_precopy_only,
-                              uint64_t *res_compatible,
-                              uint64_t *res_postcopy_only)
+static void vfio_state_pending(void *opaque,
+                               uint64_t threshold_size,
+                               uint64_t *res_precopy_only,
+                               uint64_t *res_compatible,
+                               uint64_t *res_postcopy_only)
 {
     VFIODevice *vbasedev = opaque;
     VFIOMigration *migration = vbasedev->migration;
@@ -473,7 +473,7 @@ static void vfio_save_pending(void *opaque,
 
     *res_precopy_only += migration->pending_bytes;
 
-    trace_vfio_save_pending(vbasedev->name, *res_precopy_only,
+    trace_vfio_state_pending(vbasedev->name, *res_precopy_only,
                             *res_postcopy_only, *res_compatible);
 }
 
@@ -515,9 +515,9 @@ static int vfio_save_iterate(QEMUFile *f, void *opaque)
     }
 
     /*
-     * Reset pending_bytes as .save_live_pending is not called during savevm or
-     * snapshot case, in such case vfio_update_pending() at the start of this
-     * function updates pending_bytes.
+     * Reset pending_bytes as state_pending* are not called during
+     * savevm or snapshot case, in such case vfio_update_pending() at
+     * the start of this function updates pending_bytes.
      */
     migration->pending_bytes = 0;
     trace_vfio_save_iterate(vbasedev->name, data_size);
@@ -685,7 +685,8 @@ static int vfio_load_state(QEMUFile *f, void *opaque, int version_id)
 static SaveVMHandlers savevm_vfio_handlers = {
     .save_setup = vfio_save_setup,
     .save_cleanup = vfio_save_cleanup,
-    .save_live_pending = vfio_save_pending,
+    .state_pending_exact = vfio_state_pending,
+    .state_pending_estimate = vfio_state_pending,
     .save_live_iterate = vfio_save_iterate,
     .save_live_complete_precopy = vfio_save_complete_precopy,
     .save_state = vfio_save_state,

hw/vfio/trace-events

@@ -157,7 +157,7 @@ vfio_save_cleanup(const char *name) " (%s)"
 vfio_save_buffer(const char *name, uint64_t data_offset, uint64_t data_size, uint64_t pending) " (%s) Offset 0x%"PRIx64" size 0x%"PRIx64" pending 0x%"PRIx64
 vfio_update_pending(const char *name, uint64_t pending) " (%s) pending 0x%"PRIx64
 vfio_save_device_config_state(const char *name) " (%s)"
-vfio_save_pending(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 0x%"PRIx64
+vfio_state_pending(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 0x%"PRIx64
 vfio_save_iterate(const char *name, int data_size) " (%s) data_size %d"
 vfio_save_complete_precopy(const char *name) " (%s)"
 vfio_load_device_config_state(const char *name) " (%s)"

include/migration/register.h

@@ -46,11 +46,6 @@ typedef struct SaveVMHandlers {
 
     /* This runs outside the iothread lock!  */
     int (*save_setup)(QEMUFile *f, void *opaque);
-    void (*save_live_pending)(void *opaque,
-                              uint64_t threshold_size,
-                              uint64_t *res_precopy_only,
-                              uint64_t *res_compatible,
-                              uint64_t *res_postcopy_only);
     /* Note for save_live_pending:
      * - res_precopy_only is for data which must be migrated in precopy phase
      *     or in stopped state, in other words - before target vm start
@@ -61,8 +56,18 @@ typedef struct SaveVMHandlers {
      * Sum of res_postcopy_only, res_compatible and res_postcopy_only is the
      * whole amount of pending data.
      */
-
-
+    /* This estimates the remaining data to transfer */
+    void (*state_pending_estimate)(void *opaque,
+                                   uint64_t threshold_size,
+                                   uint64_t *res_precopy_only,
+                                   uint64_t *res_compatible,
+                                   uint64_t *res_postcopy_only);
+    /* This calculate the exact remaining data to transfer */
+    void (*state_pending_exact)(void *opaque,
+                                uint64_t threshold_size,
+                                uint64_t *res_precopy_only,
+                                uint64_t *res_compatible,
+                                uint64_t *res_postcopy_only);
     LoadStateHandler *load_state;
     int (*load_setup)(QEMUFile *f, void *opaque);
     int (*load_cleanup)(void *opaque);

migration/block-dirty-bitmap.c

@@ -762,11 +762,11 @@ static int dirty_bitmap_save_complete(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static void dirty_bitmap_save_pending(void *opaque,
-                                      uint64_t max_size,
-                                      uint64_t *res_precopy_only,
-                                      uint64_t *res_compatible,
-                                      uint64_t *res_postcopy_only)
+static void dirty_bitmap_state_pending(void *opaque,
+                                       uint64_t max_size,
+                                       uint64_t *res_precopy_only,
+                                       uint64_t *res_compatible,
+                                       uint64_t *res_postcopy_only)
 {
     DBMSaveState *s = &((DBMState *)opaque)->save;
     SaveBitmapState *dbms;
@@ -784,7 +784,7 @@ static void dirty_bitmap_save_pending(void *opaque,
 
     qemu_mutex_unlock_iothread();
 
-    trace_dirty_bitmap_save_pending(pending, max_size);
+    trace_dirty_bitmap_state_pending(pending);
 
     *res_postcopy_only += pending;
 }
@@ -1253,7 +1253,8 @@ static SaveVMHandlers savevm_dirty_bitmap_handlers = {
     .save_live_complete_postcopy = dirty_bitmap_save_complete,
     .save_live_complete_precopy = dirty_bitmap_save_complete,
     .has_postcopy = dirty_bitmap_has_postcopy,
-    .save_live_pending = dirty_bitmap_save_pending,
+    .state_pending_exact = dirty_bitmap_state_pending,
+    .state_pending_estimate = dirty_bitmap_state_pending,
     .save_live_iterate = dirty_bitmap_save_iterate,
     .is_active_iterate = dirty_bitmap_is_active_iterate,
     .load_state = dirty_bitmap_load,

migration/block.c

@@ -863,10 +863,10 @@ static int block_save_complete(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static void block_save_pending(void *opaque, uint64_t max_size,
-                               uint64_t *res_precopy_only,
-                               uint64_t *res_compatible,
-                               uint64_t *res_postcopy_only)
+static void block_state_pending(void *opaque, uint64_t max_size,
+                                uint64_t *res_precopy_only,
+                                uint64_t *res_compatible,
+                                uint64_t *res_postcopy_only)
 {
     /* Estimate pending number of bytes to send */
     uint64_t pending;
@@ -885,7 +885,7 @@ static void block_save_pending(void *opaque, uint64_t max_size,
         pending = BLK_MIG_BLOCK_SIZE;
     }
 
-    trace_migration_block_save_pending(pending);
+    trace_migration_block_state_pending(pending);
     /* We don't do postcopy */
     *res_precopy_only += pending;
 }
@@ -1020,7 +1020,8 @@ static SaveVMHandlers savevm_block_handlers = {
     .save_setup = block_save_setup,
     .save_live_iterate = block_save_iterate,
     .save_live_complete_precopy = block_save_complete,
-    .save_live_pending = block_save_pending,
+    .state_pending_exact = block_state_pending,
+    .state_pending_estimate = block_state_pending,
     .load_state = block_load,
     .save_cleanup = block_migration_cleanup,
     .is_active = block_is_active,

migration/migration.c

@@ -3778,15 +3778,23 @@ typedef enum {
  */
 static MigIterateState migration_iteration_run(MigrationState *s)
 {
-    uint64_t pending_size, pend_pre, pend_compat, pend_post;
+    uint64_t pend_pre, pend_compat, pend_post;
     bool in_postcopy = s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE;
 
-    qemu_savevm_state_pending(s->threshold_size, &pend_pre,
-                              &pend_compat, &pend_post);
-    pending_size = pend_pre + pend_compat + pend_post;
+    qemu_savevm_state_pending_estimate(s->threshold_size, &pend_pre,
+                                       &pend_compat, &pend_post);
+    uint64_t pending_size = pend_pre + pend_compat + pend_post;
 
-    trace_migrate_pending(pending_size, s->threshold_size,
-                          pend_pre, pend_compat, pend_post);
+    trace_migrate_pending_estimate(pending_size, s->threshold_size,
+                                   pend_pre, pend_compat, pend_post);
+
+    if (pend_pre + pend_compat <= s->threshold_size) {
+        qemu_savevm_state_pending_exact(s->threshold_size, &pend_pre,
+                                        &pend_compat, &pend_post);
+        pending_size = pend_pre + pend_compat + pend_post;
+        trace_migrate_pending_exact(pending_size, s->threshold_size,
+                                    pend_pre, pend_compat, pend_post);
+    }
 
     if (pending_size && pending_size >= s->threshold_size) {
         /* Still a significant amount to transfer */

migration/ram.c

@@ -3409,19 +3409,35 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static void ram_save_pending(void *opaque, uint64_t max_size,
-                             uint64_t *res_precopy_only,
-                             uint64_t *res_compatible,
-                             uint64_t *res_postcopy_only)
+static void ram_state_pending_estimate(void *opaque, uint64_t max_size,
+                                       uint64_t *res_precopy_only,
+                                       uint64_t *res_compatible,
+                                       uint64_t *res_postcopy_only)
 {
     RAMState **temp = opaque;
     RAMState *rs = *temp;
-    uint64_t remaining_size;
 
-    remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;
+    uint64_t remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;
 
-    if (!migration_in_postcopy() &&
-        remaining_size < max_size) {
+    if (migrate_postcopy_ram()) {
+        /* We can do postcopy, and all the data is postcopiable */
+        *res_postcopy_only += remaining_size;
+    } else {
+        *res_precopy_only += remaining_size;
+    }
+}
+
+static void ram_state_pending_exact(void *opaque, uint64_t max_size,
+                                    uint64_t *res_precopy_only,
+                                    uint64_t *res_compatible,
+                                    uint64_t *res_postcopy_only)
+{
+    RAMState **temp = opaque;
+    RAMState *rs = *temp;
+
+    uint64_t remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;
+
+    if (!migration_in_postcopy()) {
         qemu_mutex_lock_iothread();
         WITH_RCU_READ_LOCK_GUARD() {
             migration_bitmap_sync_precopy(rs);
@@ -4577,7 +4593,8 @@ static SaveVMHandlers savevm_ram_handlers = {
     .save_live_complete_postcopy = ram_save_complete,
     .save_live_complete_precopy = ram_save_complete,
     .has_postcopy = ram_has_postcopy,
-    .save_live_pending = ram_save_pending,
+    .state_pending_exact = ram_state_pending_exact,
+    .state_pending_estimate = ram_state_pending_estimate,
     .load_state = ram_load,
     .save_cleanup = ram_save_cleanup,
     .load_setup = ram_load_setup,

migration/savevm.c

@@ -1472,10 +1472,10 @@ int qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only,
  * the result is split into the amount for units that can and
  * for units that can't do postcopy.
  */
-void qemu_savevm_state_pending(uint64_t threshold_size,
-                               uint64_t *res_precopy_only,
-                               uint64_t *res_compatible,
-                               uint64_t *res_postcopy_only)
+void qemu_savevm_state_pending_estimate(uint64_t threshold_size,
+                                        uint64_t *res_precopy_only,
+                                        uint64_t *res_compatible,
+                                        uint64_t *res_postcopy_only)
 {
     SaveStateEntry *se;
 
@@ -1485,17 +1485,43 @@ void qemu_savevm_state_pending(uint64_t threshold_size,
 
 
     QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
-        if (!se->ops || !se->ops->save_live_pending) {
+        if (!se->ops || !se->ops->state_pending_exact) {
             continue;
         }
         if (se->ops->is_active) {
             if (!se->ops->is_active(se->opaque)) {
                 continue;
             }
         }
-        se->ops->save_live_pending(se->opaque, threshold_size,
-                                   res_precopy_only, res_compatible,
-                                   res_postcopy_only);
+        se->ops->state_pending_exact(se->opaque, threshold_size,
+                                     res_precopy_only, res_compatible,
+                                     res_postcopy_only);
+    }
+}
+
+void qemu_savevm_state_pending_exact(uint64_t threshold_size,
+                                     uint64_t *res_precopy_only,
+                                     uint64_t *res_compatible,
+                                     uint64_t *res_postcopy_only)
+{
+    SaveStateEntry *se;
+
+    *res_precopy_only = 0;
+    *res_compatible = 0;
+    *res_postcopy_only = 0;
+
+    QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
+        if (!se->ops || !se->ops->state_pending_estimate) {
+            continue;
+        }
+        if (se->ops->is_active) {
+            if (!se->ops->is_active(se->opaque)) {
+                continue;
+            }
+        }
+        se->ops->state_pending_estimate(se->opaque, threshold_size,
+                                        res_precopy_only, res_compatible,
+                                        res_postcopy_only);
     }
 }
 

migration/savevm.h

@@ -40,10 +40,14 @@ void qemu_savevm_state_cleanup(void);
 void qemu_savevm_state_complete_postcopy(QEMUFile *f);
 int qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only,
                                        bool inactivate_disks);
-void qemu_savevm_state_pending(uint64_t max_size,
-                               uint64_t *res_precopy_only,
-                               uint64_t *res_compatible,
-                               uint64_t *res_postcopy_only);
+void qemu_savevm_state_pending_exact(uint64_t threshold_size,
+                                     uint64_t *res_precopy_only,
+                                     uint64_t *res_compatible,
+                                     uint64_t *res_postcopy_only);
+void qemu_savevm_state_pending_estimate(uint64_t thershold_size,
+                                        uint64_t *res_precopy_only,
+                                        uint64_t *res_compatible,
+                                        uint64_t *res_postcopy_only);
 void qemu_savevm_send_ping(QEMUFile *f, uint32_t value);
 void qemu_savevm_send_open_return_path(QEMUFile *f);
 int qemu_savevm_send_packaged(QEMUFile *f, const uint8_t *buf, size_t len);