Merge tag 'staging-pull-request' of https://gitlab.com/peterx/qemu into staging

Migration/Memory Pull for 10.2

- PeterX's fix on tls warning for preempt channel when migratino completes
- Arun's series to enhance error reporting for vTPM and migration framework
- PeterX's patch to cleanup multifd send TLS BYE messages
- Juraj's fix on postcopy start state transition when switchover failed
- Yanfei's fix to migrate APIC before VFIO-PCI to avoid irq fallbacks
- Dan's cleanup to simplify error reporting in qemu_fill_buffer()
- PeterM's fix on address space leak when cpu hot plug / unplug
- Steve's cpr-exec wholeset

# -----BEGIN PGP SIGNATURE-----
#
# iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCaN/uIhIccGV0ZXJ4QHJl
# ZGhhdC5jb20ACgkQO1/MzfOr1wZ+mAEA1l2RS9sZS1W3vXQMCNb+Nu8Uo2p+e5Qj
# Uu6J0WVV+XsBANtzGZk2UM/frqlABywW3/ozJ4qBvIPKo758Mr6/lqUH
# =asUv
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 03 Oct 2025 08:39:14 AM PDT
# gpg:                using EDDSA key B9184DC20CC457DACF7DD1A93B5FCCCDF3ABD706
# gpg:                issuer "peterx@redhat.com"
# gpg: Good signature from "Peter Xu <xzpeter@gmail.com>" [unknown]
# gpg:                 aka "Peter Xu <peterx@redhat.com>" [unknown]
# gpg: WARNING: The key's User ID is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: B918 4DC2 0CC4 57DA CF7D  D1A9 3B5F CCCD F3AB D706

* tag 'staging-pull-request' of https://gitlab.com/peterx/qemu: (45 commits)
  migration-test: test cpr-exec
  vfio: cpr-exec mode
  migration: cpr-exec docs
  migration: cpr-exec mode
  migration: cpr-exec save and load
  migration: cpr-exec-command parameter
  oslib: qemu_clear_cloexec
  migration: add cpr_walk_fd
  migration: multi-mode notifier
  migration: simplify error reporting after channel read
  physmem: Destroy all CPU AddressSpaces on unrealize
  memory: New AS helper to serialize destroy+free
  include/system/memory.h: Clarify address_space_destroy() behaviour
  migration: ensure APIC is loaded prior to VFIO PCI devices
  migration: Fix state transition in postcopy_start() error handling
  migration/multifd/tls: Cleanup BYE message processing on sender side
  migration: HMP: Adjust the order of output fields
  migration: Make migration_has_failed() work even for CANCELLING
  io/crypto: Move tls premature termination handling into QIO layer
  backends/tpm: Propagate vTPM error on migration failure
  ...

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

1 files changed, 81 insertions, 35 deletions

diff --git a/migration/migration.c b/migration/migration.c
index e1ac4d73c2..a63b46bbef 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -74,11 +74,7 @@
 
 #define INMIGRATE_DEFAULT_EXIT_ON_ERROR true
 
-static NotifierWithReturnList migration_state_notifiers[] = {
-    NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_NORMAL),
-    NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_CPR_REBOOT),
-    NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_CPR_TRANSFER),
-};
+static GSList *migration_state_notifiers[MIG_MODE__MAX];
 
 /* Messages sent on the return path from destination to source */
 enum mig_rp_message_type {
@@ -337,6 +333,7 @@ void migration_object_init(void)
 
     ram_mig_init();
     dirty_bitmap_mig_init();
+    cpr_exec_init();
 
     /* Initialize cpu throttle timers */
     cpu_throttle_init();
@@ -623,22 +620,22 @@ void migration_incoming_disable_colo(void)
     migration_colo_enabled = false;
 }
 
-int migration_incoming_enable_colo(void)
+int migration_incoming_enable_colo(Error **errp)
 {
 #ifndef CONFIG_REPLICATION
-    error_report("ENABLE_COLO command come in migration stream, but the "
-                 "replication module is not built in");
+    error_setg(errp, "ENABLE_COLO command come in migration stream, but the "
+               "replication module is not built in");
     return -ENOTSUP;
 #endif
 
     if (!migrate_colo()) {
-        error_report("ENABLE_COLO command come in migration stream, but x-colo "
-                     "capability is not set");
+        error_setg(errp, "ENABLE_COLO command come in migration stream"
+                   ", but x-colo capability is not set");
         return -EINVAL;
     }
 
     if (ram_block_discard_disable(true)) {
-        error_report("COLO: cannot disable RAM discard");
+        error_setg(errp, "COLO: cannot disable RAM discard");
         return -EBUSY;
     }
     migration_colo_enabled = true;
@@ -881,7 +878,7 @@ process_incoming_migration_co(void *opaque)
                       MIGRATION_STATUS_ACTIVE);
 
     mis->loadvm_co = qemu_coroutine_self();
-    ret = qemu_loadvm_state(mis->from_src_file);
+    ret = qemu_loadvm_state(mis->from_src_file, &local_err);
     mis->loadvm_co = NULL;
 
     trace_vmstate_downtime_checkpoint("dst-precopy-loadvm-completed");
@@ -908,7 +905,8 @@ process_incoming_migration_co(void *opaque)
     }
 
     if (ret < 0) {
-        error_setg(&local_err, "load of migration failed: %s", strerror(-ret));
+        error_prepend(&local_err, "load of migration failed: %s: ",
+                      strerror(-ret));
         goto fail;
     }
 
@@ -935,6 +933,15 @@ fail:
         }
 
         exit(EXIT_FAILURE);
+    } else {
+        /*
+         * Report the error here in case that QEMU abruptly exits
+         * when postcopy is enabled.
+         */
+        WITH_QEMU_LOCK_GUARD(&s->error_mutex) {
+            error_report_err(s->error);
+            s->error = NULL;
+        }
     }
 out:
     /* Pairs with the refcount taken in qmp_migrate_incoming() */
@@ -1665,23 +1672,51 @@ void migration_cancel(void)
     }
 }
 
+static int get_modes(MigMode mode, va_list ap);
+
+static void add_notifiers(NotifierWithReturn *notify, int modes)
+{
+    for (MigMode mode = 0; mode < MIG_MODE__MAX; mode++) {
+        if (modes & BIT(mode)) {
+            migration_state_notifiers[mode] =
+                g_slist_prepend(migration_state_notifiers[mode], notify);
+        }
+    }
+}
+
+void migration_add_notifier_modes(NotifierWithReturn *notify,
+                                  MigrationNotifyFunc func, MigMode mode, ...)
+{
+    int modes;
+    va_list ap;
+
+    va_start(ap, mode);
+    modes = get_modes(mode, ap);
+    va_end(ap);
+
+    notify->notify = (NotifierWithReturnFunc)func;
+    add_notifiers(notify, modes);
+}
+
 void migration_add_notifier_mode(NotifierWithReturn *notify,
                                  MigrationNotifyFunc func, MigMode mode)
 {
-    notify->notify = (NotifierWithReturnFunc)func;
-    notifier_with_return_list_add(&migration_state_notifiers[mode], notify);
+    migration_add_notifier_modes(notify, func, mode, -1);
 }
 
 void migration_add_notifier(NotifierWithReturn *notify,
                             MigrationNotifyFunc func)
 {
-    migration_add_notifier_mode(notify, func, MIG_MODE_NORMAL);
+    migration_add_notifier_modes(notify, func, MIG_MODE_NORMAL, -1);
 }
 
 void migration_remove_notifier(NotifierWithReturn *notify)
 {
     if (notify->notify) {
-        notifier_with_return_remove(notify);
+        for (MigMode mode = 0; mode < MIG_MODE__MAX; mode++) {
+            migration_blockers[mode] =
+                g_slist_remove(migration_state_notifiers[mode], notify);
+        }
         notify->notify = NULL;
     }
 }
@@ -1691,18 +1726,29 @@ int migration_call_notifiers(MigrationState *s, MigrationEventType type,
 {
     MigMode mode = s->parameters.mode;
     MigrationEvent e;
+    NotifierWithReturn *notifier;
+    GSList *elem, *next;
     int ret;
 
     e.type = type;
-    ret = notifier_with_return_list_notify(&migration_state_notifiers[mode],
-                                           &e, errp);
-    assert(!ret || type == MIG_EVENT_PRECOPY_SETUP);
-    return ret;
+
+    for (elem = migration_state_notifiers[mode]; elem; elem = next) {
+        next = elem->next;
+        notifier = (NotifierWithReturn *)elem->data;
+        ret = notifier->notify(notifier, &e, errp);
+        if (ret) {
+            assert(type == MIG_EVENT_PRECOPY_SETUP);
+            return ret;
+        }
+    }
+
+    return 0;
 }
 
 bool migration_has_failed(MigrationState *s)
 {
-    return (s->state == MIGRATION_STATUS_CANCELLED ||
+    return (s->state == MIGRATION_STATUS_CANCELLING ||
+            s->state == MIGRATION_STATUS_CANCELLED ||
             s->state == MIGRATION_STATUS_FAILED);
 }
 
@@ -1762,7 +1808,8 @@ bool migrate_mode_is_cpr(MigrationState *s)
 {
     MigMode mode = s->parameters.mode;
     return mode == MIG_MODE_CPR_REBOOT ||
-           mode == MIG_MODE_CPR_TRANSFER;
+           mode == MIG_MODE_CPR_TRANSFER ||
+           mode == MIG_MODE_CPR_EXEC;
 }
 
 int migrate_init(MigrationState *s, Error **errp)
@@ -2111,6 +2158,12 @@ static bool migrate_prepare(MigrationState *s, bool resume, Error **errp)
         return false;
     }
 
+    if (migrate_mode() == MIG_MODE_CPR_EXEC &&
+        !s->parameters.has_cpr_exec_command) {
+        error_setg(errp, "cpr-exec mode requires setting cpr-exec-command");
+        return false;
+    }
+
     if (migration_is_blocked(errp)) {
         return false;
     }
@@ -2646,12 +2699,9 @@ out:
     return NULL;
 }
 
-static int open_return_path_on_source(MigrationState *ms)
+static void open_return_path_on_source(MigrationState *ms)
 {
     ms->rp_state.from_dst_file = qemu_file_get_return_path(ms->to_dst_file);
-    if (!ms->rp_state.from_dst_file) {
-        return -1;
-    }
 
     trace_open_return_path_on_source();
 
@@ -2660,8 +2710,6 @@ static int open_return_path_on_source(MigrationState *ms)
     ms->rp_state.rp_thread_created = true;
 
     trace_open_return_path_on_source_continue();
-
-    return 0;
 }
 
 /* Return true if error detected, or false otherwise */
@@ -2872,8 +2920,9 @@ static int postcopy_start(MigrationState *ms, Error **errp)
 fail_closefb:
     qemu_fclose(fb);
 fail:
-    migrate_set_state(&ms->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
-                          MIGRATION_STATUS_FAILED);
+    if (ms->state != MIGRATION_STATUS_CANCELLING) {
+        migrate_set_state(&ms->state, ms->state, MIGRATION_STATUS_FAILED);
+    }
     migration_block_activate(NULL);
     migration_call_notifiers(ms, MIG_EVENT_PRECOPY_FAILED, NULL);
     bql_unlock();
@@ -4012,10 +4061,7 @@ void migration_connect(MigrationState *s, Error *error_in)
      * QEMU uses the return path.
      */
     if (migrate_postcopy_ram() || migrate_return_path()) {
-        if (open_return_path_on_source(s)) {
-            error_setg(&local_err, "Unable to open return-path for postcopy");
-            goto fail;
-        }
+        open_return_path_on_source(s);
     }
 
     /*