migration: Add MIG_CMD_SWITCHOVER_START and its load handler

This QEMU_VM_COMMAND sub-command and its switchover_start SaveVMHandler is
used to mark the switchover point in main migration stream.

It can be used to inform the destination that all pre-switchover main
migration stream data has been sent/received so it can start to process
post-switchover data that it might have received via other migration
channels like the multifd ones.

Add also the relevant MigrationState bit stream compatibility property and
its hw_compat entry.

Reviewed-by: Fabiano Rosas <farosas@suse.de>
Reviewed-by: Zhang Chen <zhangckid@gmail.com> # for the COLO part
Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Link: https://lore.kernel.org/qemu-devel/311be6da85fc7e49a7598684d80aa631778dcbce.1741124640.git.maciej.szmigiero@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

hw/core/machine.c

@@ -44,6 +44,7 @@ GlobalProperty hw_compat_9_2[] = {
     { "virtio-balloon-pci-non-transitional", "vectors", "0" },
     { "virtio-mem-pci", "vectors", "0" },
     { "migration", "multifd-clean-tls-termination", "false" },
+    { "migration", "send-switchover-start", "off"},
 };
 const size_t hw_compat_9_2_len = G_N_ELEMENTS(hw_compat_9_2);
 

include/migration/client-options.h

@@ -10,6 +10,10 @@
 #ifndef QEMU_MIGRATION_CLIENT_OPTIONS_H
 #define QEMU_MIGRATION_CLIENT_OPTIONS_H
 
+
+/* properties */
+bool migrate_send_switchover_start(void);
+
 /* capabilities */
 
 bool migrate_background_snapshot(void);

include/migration/register.h

@@ -279,6 +279,18 @@ typedef struct SaveVMHandlers {
      * otherwise
      */
     bool (*switchover_ack_needed)(void *opaque);
+
+    /**
+     * @switchover_start
+     *
+     * Notifies that the switchover has started. Called only on
+     * the destination.
+     *
+     * @opaque: data pointer passed to register_savevm_live()
+     *
+     * Returns zero to indicate success and negative for error
+     */
+    int (*switchover_start)(void *opaque);
 } SaveVMHandlers;
 
 /**

migration/colo.c

@@ -452,6 +452,9 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
         bql_unlock();
         goto out;
     }
+
+    qemu_savevm_maybe_send_switchover_start(s->to_dst_file);
+
     /* Note: device state is saved into buffer */
     ret = qemu_save_device_state(fb);
 

migration/migration-hmp-cmds.c

@@ -46,6 +46,8 @@ static void migration_global_dump(Monitor *mon)
                    ms->send_configuration ? "on" : "off");
     monitor_printf(mon, "send-section-footer: %s\n",
                    ms->send_section_footer ? "on" : "off");
+    monitor_printf(mon, "send-switchover-start: %s\n",
+                   ms->send_switchover_start ? "on" : "off");
     monitor_printf(mon, "clear-bitmap-shift: %u\n",
                    ms->clear_bitmap_shift);
 }

migration/migration.c

@@ -2891,6 +2891,8 @@ static bool migration_switchover_start(MigrationState *s, Error **errp)
 
     precopy_notify_complete();
 
+    qemu_savevm_maybe_send_switchover_start(s->to_dst_file);
+
     return true;
 }
 

migration/migration.h

@@ -400,6 +400,8 @@ struct MigrationState {
     bool send_configuration;
     /* Whether we send section footer during migration */
     bool send_section_footer;
+    /* Whether we send switchover start notification during migration */
+    bool send_switchover_start;
 
     /* Needed by postcopy-pause state */
     QemuSemaphore postcopy_pause_sem;

migration/options.c

@@ -93,6 +93,8 @@ const Property migration_properties[] = {
                      send_configuration, true),
     DEFINE_PROP_BOOL("send-section-footer", MigrationState,
                      send_section_footer, true),
+    DEFINE_PROP_BOOL("send-switchover-start", MigrationState,
+                     send_switchover_start, true),
     DEFINE_PROP_BOOL("multifd-flush-after-each-section", MigrationState,
                       multifd_flush_after_each_section, false),
     DEFINE_PROP_UINT8("x-clear-bitmap-shift", MigrationState,
@@ -209,6 +211,13 @@ bool migrate_auto_converge(void)
     return s->capabilities[MIGRATION_CAPABILITY_AUTO_CONVERGE];
 }
 
+bool migrate_send_switchover_start(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return s->send_switchover_start;
+}
+
 bool migrate_background_snapshot(void)
 {
     MigrationState *s = migrate_get_current();

migration/savevm.c

@@ -90,6 +90,7 @@ enum qemu_vm_cmd {
     MIG_CMD_ENABLE_COLO,       /* Enable COLO */
     MIG_CMD_POSTCOPY_RESUME,   /* resume postcopy on dest */
     MIG_CMD_RECV_BITMAP,       /* Request for recved bitmap on dst */
+    MIG_CMD_SWITCHOVER_START,  /* Switchover start notification */
     MIG_CMD_MAX
 };
 
@@ -109,6 +110,7 @@ static struct mig_cmd_args {
     [MIG_CMD_POSTCOPY_RESUME]  = { .len =  0, .name = "POSTCOPY_RESUME" },
     [MIG_CMD_PACKAGED]         = { .len =  4, .name = "PACKAGED" },
     [MIG_CMD_RECV_BITMAP]      = { .len = -1, .name = "RECV_BITMAP" },
+    [MIG_CMD_SWITCHOVER_START] = { .len =  0, .name = "SWITCHOVER_START" },
     [MIG_CMD_MAX]              = { .len = -1, .name = "MAX" },
 };
 
@@ -1201,6 +1203,19 @@ void qemu_savevm_send_recv_bitmap(QEMUFile *f, char *block_name)
     qemu_savevm_command_send(f, MIG_CMD_RECV_BITMAP, len + 1, (uint8_t *)buf);
 }
 
+static void qemu_savevm_send_switchover_start(QEMUFile *f)
+{
+    trace_savevm_send_switchover_start();
+    qemu_savevm_command_send(f, MIG_CMD_SWITCHOVER_START, 0, NULL);
+}
+
+void qemu_savevm_maybe_send_switchover_start(QEMUFile *f)
+{
+    if (migrate_send_switchover_start()) {
+        qemu_savevm_send_switchover_start(f);
+    }
+}
+
 bool qemu_savevm_state_blocked(Error **errp)
 {
     SaveStateEntry *se;
@@ -1687,6 +1702,7 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
 
     ret = qemu_file_get_error(f);
     if (ret == 0) {
+        qemu_savevm_maybe_send_switchover_start(f);
         qemu_savevm_state_complete_precopy(f, false);
         ret = qemu_file_get_error(f);
     }
@@ -2383,6 +2399,26 @@ static int loadvm_process_enable_colo(MigrationIncomingState *mis)
     return ret;
 }
 
+static int loadvm_postcopy_handle_switchover_start(void)
+{
+    SaveStateEntry *se;
+
+    QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
+        int ret;
+
+        if (!se->ops || !se->ops->switchover_start) {
+            continue;
+        }
+
+        ret = se->ops->switchover_start(se->opaque);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
+    return 0;
+}
+
 /*
  * Process an incoming 'QEMU_VM_COMMAND'
  * 0           just a normal return
@@ -2481,6 +2517,9 @@ static int loadvm_process_command(QEMUFile *f)
 
     case MIG_CMD_ENABLE_COLO:
         return loadvm_process_enable_colo(mis);
+
+    case MIG_CMD_SWITCHOVER_START:
+        return loadvm_postcopy_handle_switchover_start();
     }
 
     return 0;

migration/savevm.h

@@ -53,6 +53,7 @@ void qemu_savevm_send_postcopy_listen(QEMUFile *f);
 void qemu_savevm_send_postcopy_run(QEMUFile *f);
 void qemu_savevm_send_postcopy_resume(QEMUFile *f);
 void qemu_savevm_send_recv_bitmap(QEMUFile *f, char *block_name);
+void qemu_savevm_maybe_send_switchover_start(QEMUFile *f);
 
 void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name,
                                            uint16_t len,

migration/trace-events

@@ -39,6 +39,7 @@ savevm_send_postcopy_run(void) ""
 savevm_send_postcopy_resume(void) ""
 savevm_send_colo_enable(void) ""
 savevm_send_recv_bitmap(char *name) "%s"
+savevm_send_switchover_start(void) ""
 savevm_state_setup(void) ""
 savevm_state_resume_prepare(void) ""
 savevm_state_header(void) ""

scripts/analyze-migration.py

@@ -620,7 +620,9 @@ class MigrationDump(object):
     QEMU_VM_SUBSECTION    = 0x05
     QEMU_VM_VMDESCRIPTION = 0x06
     QEMU_VM_CONFIGURATION = 0x07
+    QEMU_VM_COMMAND       = 0x08
     QEMU_VM_SECTION_FOOTER= 0x7e
+    QEMU_MIG_CMD_SWITCHOVER_START = 0x0b
 
     def __init__(self, filename):
         self.section_classes = {
@@ -685,6 +687,15 @@ class MigrationDump(object):
             elif section_type == self.QEMU_VM_SECTION_PART or section_type == self.QEMU_VM_SECTION_END:
                 section_id = file.read32()
                 self.sections[section_id].read()
+            elif section_type == self.QEMU_VM_COMMAND:
+                command_type = file.read16()
+                command_data_len = file.read16()
+                if command_type != self.QEMU_MIG_CMD_SWITCHOVER_START:
+                    raise Exception("Unknown QEMU_VM_COMMAND: %x" %
+                                    (command_type))
+                if command_data_len != 0:
+                    raise Exception("Invalid SWITCHOVER_START length: %x" %
+                                    (command_data_len))
             elif section_type == self.QEMU_VM_SECTION_FOOTER:
                 read_section_id = file.read32()
                 if read_section_id != section_id: