Merge tag 'migration-20230601-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration Pull request (20230601)

Hi

In this series:
- improve background migration (fiona)
- improve vmstate failure states (vladimir)
- dropped all the RDMA cleanups

Please, apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmR5LAoACgkQ9IfvGFhy
# 1yPOuxAA5QzUfswCIWehrkY8FApDjsecPDq5R6hS1p5pDZkHTF5y6j49J93I65o2
# E4qr4l0+DJvBvnxTW29JQ1i0RPqJHnJBFC9Ib4o0NaA/7iRP1sTwYxIN4wWZz6H/
# pqG3oQC0WPPqgj9tHSgDW4TNkFjETYaezTN8nddNmyiaO9UxNuR5ZKbeYMroVlfp
# KbnAYfXV6CyXKUZFT32BYcajYBDZAqBCO6y3gEn77KPlT1/TqnucoYEVuNudq5SE
# jeCamTzoAQ6SIRFM/eY+aASxdsSryqDS/WLqBFsleXs1kkJ6mkDnNels4HqS+xs9
# p2Vhv/59ktoC57XsRgTgzEklAaSHunZivcQkc5szyGVE5TZyKtWg8WhA6rvlqbjK
# lb3kKpvtVi73+pAWU0hhKFdnCrB6ieCHI70CJ5mpiIu3MzLUyrNJOK4FoKNoJDOD
# Dp45DK+W/EMg51pXyHJZZqHM1p0GGj0fmhv5T05nJ590fIWV4iqDdHFxsMZ9vEPN
# iEvAB7/pXz+yECznDFrp2e047rshOGaKKNSW3zl3/7D32Ds2FKur76dL4BoymztW
# HHLxmRWn8HmHMoKYLoawWVmCBsDqy8BFct+rHbA6h/0nSCPYIUCmMrSYVqajUbXD
# Ulkh4KNQGoBCzp5Toa0dYEXVc891wVOw4k8PTARwf2OYskSkT88=
# =Km5X
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 01 Jun 2023 04:38:50 PM PDT
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [unknown]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* tag 'migration-20230601-pull-request' of https://gitlab.com/juan.quintela/qemu:
  migration: stop tracking ram writes when cancelling background migration
  migration: restore vmstate on migration failure
  migration: switch from .vm_was_running to .vm_old_state
  runstate: drop unused runstate_store()
  migration: never fail in global_state_store()
  runstate: add runstate_get()

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

4 files changed, 52 insertions, 56 deletions

diff --git a/migration/global_state.c b/migration/global_state.c
index a33947ca32..4e2a9d8ec0 100644
--- a/migration/global_state.c
+++ b/migration/global_state.c
@@ -29,23 +29,22 @@ typedef struct {
 
 static GlobalState global_state;
 
-int global_state_store(void)
+static void global_state_do_store(RunState state)
 {
-    if (!runstate_store((char *)global_state.runstate,
-                        sizeof(global_state.runstate))) {
-        error_report("runstate name too big: %s", global_state.runstate);
-        trace_migrate_state_too_big();
-        return -EINVAL;
-    }
-    return 0;
+    const char *state_str = RunState_str(state);
+    assert(strlen(state_str) < sizeof(global_state.runstate));
+    strpadcpy((char *)global_state.runstate, sizeof(global_state.runstate),
+              state_str, '\0');
+}
+
+void global_state_store(void)
+{
+    global_state_do_store(runstate_get());
 }
 
 void global_state_store_running(void)
 {
-    const char *state = RunState_str(RUN_STATE_RUNNING);
-    assert(strlen(state) < sizeof(global_state.runstate));
-    strpadcpy((char *)global_state.runstate, sizeof(global_state.runstate),
-              state, '\0');
+    global_state_do_store(RUN_STATE_RUNNING);
 }
 
 bool global_state_received(void)
diff --git a/migration/migration.c b/migration/migration.c
index 5de7f734b9..dc05c6f6ea 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1402,7 +1402,7 @@ void migrate_init(MigrationState *s)
 
     s->start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     s->total_time = 0;
-    s->vm_was_running = false;
+    s->vm_old_state = -1;
     s->iteration_initial_bytes = 0;
     s->threshold_size = 0;
 }
@@ -2287,28 +2287,28 @@ static void migration_completion(MigrationState *s)
         qemu_mutex_lock_iothread();
         s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
         qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
-        s->vm_was_running = runstate_is_running();
-        ret = global_state_store();
-
-        if (!ret) {
-            ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
-            trace_migration_completion_vm_stop(ret);
-            if (ret >= 0) {
-                ret = migration_maybe_pause(s, &current_active_state,
-                                            MIGRATION_STATUS_DEVICE);
-            }
-            if (ret >= 0) {
-                /*
-                 * Inactivate disks except in COLO, and track that we
-                 * have done so in order to remember to reactivate
-                 * them if migration fails or is cancelled.
-                 */
-                s->block_inactive = !migrate_colo();
-                migration_rate_set(RATE_LIMIT_DISABLED);
-                ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
-                                                         s->block_inactive);
-            }
+
+        s->vm_old_state = runstate_get();
+        global_state_store();
+
+        ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+        trace_migration_completion_vm_stop(ret);
+        if (ret >= 0) {
+            ret = migration_maybe_pause(s, &current_active_state,
+                                        MIGRATION_STATUS_DEVICE);
+        }
+        if (ret >= 0) {
+            /*
+             * Inactivate disks except in COLO, and track that we
+             * have done so in order to remember to reactivate
+             * them if migration fails or is cancelled.
+             */
+            s->block_inactive = !migrate_colo();
+            migration_rate_set(RATE_LIMIT_DISABLED);
+            ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
+                                                     s->block_inactive);
         }
+
         qemu_mutex_unlock_iothread();
 
         if (ret < 0) {
@@ -2400,13 +2400,6 @@ static void bg_migration_completion(MigrationState *s)
 {
     int current_active_state = s->state;
 
-    /*
-     * Stop tracking RAM writes - un-protect memory, un-register UFFD
-     * memory ranges, flush kernel wait queues and wake up threads
-     * waiting for write fault to be resolved.
-     */
-    ram_write_tracking_stop();
-
     if (s->state == MIGRATION_STATUS_ACTIVE) {
         /*
          * By this moment we have RAM content saved into the migration stream.
@@ -2761,18 +2754,18 @@ static void migration_iteration_finish(MigrationState *s)
     case MIGRATION_STATUS_COLO:
         assert(migrate_colo());
         migrate_start_colo_process(s);
-        s->vm_was_running = true;
+        s->vm_old_state = RUN_STATE_RUNNING;
         /* Fallthrough */
     case MIGRATION_STATUS_FAILED:
     case MIGRATION_STATUS_CANCELLED:
     case MIGRATION_STATUS_CANCELLING:
-        if (s->vm_was_running) {
+        if (s->vm_old_state == RUN_STATE_RUNNING) {
             if (!runstate_check(RUN_STATE_SHUTDOWN)) {
                 vm_start();
             }
         } else {
             if (runstate_check(RUN_STATE_FINISH_MIGRATE)) {
-                runstate_set(RUN_STATE_POSTMIGRATE);
+                runstate_set(s->vm_old_state);
             }
         }
         break;
@@ -2788,6 +2781,13 @@ static void migration_iteration_finish(MigrationState *s)
 
 static void bg_migration_iteration_finish(MigrationState *s)
 {
+    /*
+     * Stop tracking RAM writes - un-protect memory, un-register UFFD
+     * memory ranges, flush kernel wait queues and wake up threads
+     * waiting for write fault to be resolved.
+     */
+    ram_write_tracking_stop();
+
     qemu_mutex_lock_iothread();
     switch (s->state) {
     case MIGRATION_STATUS_COMPLETED:
@@ -3086,11 +3086,9 @@ static void *bg_migration_thread(void *opaque)
      * transition in vm_stop_force_state() we need to wakeup it up.
      */
     qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
-    s->vm_was_running = runstate_is_running();
+    s->vm_old_state = runstate_get();
 
-    if (global_state_store()) {
-        goto fail;
-    }
+    global_state_store();
     /* Forcibly stop VM before saving state of vCPUs and devices */
     if (vm_stop_force_state(RUN_STATE_PAUSED)) {
         goto fail;
diff --git a/migration/migration.h b/migration/migration.h
index 48a46123a0..30c3e97635 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -25,6 +25,7 @@
 #include "net/announce.h"
 #include "qom/object.h"
 #include "postcopy-ram.h"
+#include "sysemu/runstate.h"
 
 struct PostcopyBlocktimeContext;
 
@@ -317,12 +318,14 @@ struct MigrationState {
     int64_t expected_downtime;
     bool capabilities[MIGRATION_CAPABILITY__MAX];
     int64_t setup_time;
+
     /*
-     * Whether guest was running when we enter the completion stage.
+     * State before stopping the vm by vm_stop_force_state().
      * If migration is interrupted by any reason, we need to continue
-     * running the guest on source.
+     * running the guest on source if it was running or restore its stopped
+     * state.
      */
-    bool vm_was_running;
+    RunState vm_old_state;
 
     /* Flag set once the migration has been asked to enter postcopy */
     bool start_postcopy;
diff --git a/migration/savevm.c b/migration/savevm.c
index 03795ce8dc..bc284087f9 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2919,11 +2919,7 @@ bool save_snapshot(const char *name, bool overwrite, const char *vmstate,
 
     saved_vm_running = runstate_is_running();
 
-    ret = global_state_store();
-    if (ret) {
-        error_setg(errp, "Error saving global state");
-        return false;
-    }
+    global_state_store();
     vm_stop(RUN_STATE_SAVE_VM);
 
     bdrv_drain_all_begin();