Re: [PATCH v3 2/7] migration: Move postcopy_ram_listen_thread() to postcopy-ram.c

[Peter Xu <peterx@redhat.com>]

On Thu, Oct 30, 2025 at 10:49:06PM +0100, Juraj Marcin wrote:
> From: Juraj Marcin <jmarcin@redhat.com>
> 
> This patch addresses a TODO about moving postcopy_ram_listen_thread() to
> postcopy file.
> 
> Signed-off-by: Juraj Marcin <jmarcin@redhat.com>
> ---
>  migration/postcopy-ram.c | 107 +++++++++++++++++++++++++++++++++++++++
>  migration/postcopy-ram.h |   2 +
>  migration/savevm.c       | 107 ---------------------------------------
>  3 files changed, 109 insertions(+), 107 deletions(-)
> 
> diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
> index 5471efb4f0..36d5415554 100644
> --- a/migration/postcopy-ram.c
> +++ b/migration/postcopy-ram.c
> @@ -2077,3 +2077,110 @@ bool postcopy_is_paused(MigrationStatus status)
>      return status == MIGRATION_STATUS_POSTCOPY_PAUSED ||
>          status == MIGRATION_STATUS_POSTCOPY_RECOVER_SETUP;
>  }
> +
> +/*
> + * Triggered by a postcopy_listen command; this thread takes over reading
> + * the input stream, leaving the main thread free to carry on loading the rest
> + * of the device state (from RAM).
> + * (TODO:This could do with being in a postcopy file - but there again it's
> + * just another input loop, not that postcopy specific)

I suppose touching the comment while moving (as long as explicitly
mentioned in the commit message) would be fine, when the comment is exactly
about "we should move it". :)  Not a big deal, thanks for the split.

Reviewed-by: Peter Xu <peterx@redhat.com>

> + */
> +void *postcopy_ram_listen_thread(void *opaque)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
> +    QEMUFile *f = mis->from_src_file;
> +    int load_res;
> +    MigrationState *migr = migrate_get_current();
> +    Error *local_err = NULL;
> +
> +    object_ref(OBJECT(migr));
> +
> +    migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
> +                                   MIGRATION_STATUS_POSTCOPY_ACTIVE);
> +    qemu_event_set(&mis->thread_sync_event);
> +    trace_postcopy_ram_listen_thread_start();
> +
> +    rcu_register_thread();
> +    /*
> +     * Because we're a thread and not a coroutine we can't yield
> +     * in qemu_file, and thus we must be blocking now.
> +     */
> +    qemu_file_set_blocking(f, true, &error_fatal);
> +
> +    /* TODO: sanity check that only postcopiable data will be loaded here */
> +    load_res = qemu_loadvm_state_main(f, mis, &local_err);
> +
> +    /*
> +     * This is tricky, but, mis->from_src_file can change after it
> +     * returns, when postcopy recovery happened. In the future, we may
> +     * want a wrapper for the QEMUFile handle.
> +     */
> +    f = mis->from_src_file;
> +
> +    /* And non-blocking again so we don't block in any cleanup */
> +    qemu_file_set_blocking(f, false, &error_fatal);
> +
> +    trace_postcopy_ram_listen_thread_exit();
> +    if (load_res < 0) {
> +        qemu_file_set_error(f, load_res);
> +        dirty_bitmap_mig_cancel_incoming();
> +        if (postcopy_state_get() == POSTCOPY_INCOMING_RUNNING &&
> +            !migrate_postcopy_ram() && migrate_dirty_bitmaps())
> +        {
> +            error_report("%s: loadvm failed during postcopy: %d: %s. All states "
> +                         "are migrated except dirty bitmaps. Some dirty "
> +                         "bitmaps may be lost, and present migrated dirty "
> +                         "bitmaps are correctly migrated and valid.",
> +                         __func__, load_res, error_get_pretty(local_err));
> +            g_clear_pointer(&local_err, error_free);
> +            load_res = 0; /* prevent further exit() */
> +        } else {
> +            error_prepend(&local_err,
> +                          "loadvm failed during postcopy: %d: ", load_res);
> +            migrate_set_error(migr, local_err);
> +            g_clear_pointer(&local_err, error_report_err);
> +            migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
> +                                           MIGRATION_STATUS_FAILED);
> +        }
> +    }
> +    if (load_res >= 0) {
> +        /*
> +         * This looks good, but it's possible that the device loading in the
> +         * main thread hasn't finished yet, and so we might not be in 'RUN'
> +         * state yet; wait for the end of the main thread.
> +         */
> +        qemu_event_wait(&mis->main_thread_load_event);
> +    }
> +    postcopy_ram_incoming_cleanup(mis);
> +
> +    if (load_res < 0) {
> +        /*
> +         * If something went wrong then we have a bad state so exit;
> +         * depending how far we got it might be possible at this point
> +         * to leave the guest running and fire MCEs for pages that never
> +         * arrived as a desperate recovery step.
> +         */
> +        rcu_unregister_thread();
> +        exit(EXIT_FAILURE);
> +    }
> +
> +    migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
> +                                   MIGRATION_STATUS_COMPLETED);
> +    /*
> +     * If everything has worked fine, then the main thread has waited
> +     * for us to start, and we're the last use of the mis.
> +     * (If something broke then qemu will have to exit anyway since it's
> +     * got a bad migration state).
> +     */
> +    bql_lock();
> +    migration_incoming_state_destroy();
> +    bql_unlock();
> +
> +    rcu_unregister_thread();
> +    mis->have_listen_thread = false;
> +    postcopy_state_set(POSTCOPY_INCOMING_END);
> +
> +    object_unref(OBJECT(migr));
> +
> +    return NULL;
> +}
> diff --git a/migration/postcopy-ram.h b/migration/postcopy-ram.h
> index ca19433b24..3e26db3e6b 100644
> --- a/migration/postcopy-ram.h
> +++ b/migration/postcopy-ram.h
> @@ -199,4 +199,6 @@ bool postcopy_is_paused(MigrationStatus status);
>  void mark_postcopy_blocktime_begin(uintptr_t addr, uint32_t ptid,
>                                     RAMBlock *rb);
>  
> +void *postcopy_ram_listen_thread(void *opaque);
> +
>  #endif
> diff --git a/migration/savevm.c b/migration/savevm.c
> index 232cae090b..97fdd08c08 100644
> --- a/migration/savevm.c
> +++ b/migration/savevm.c
> @@ -2087,113 +2087,6 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis,
>      return 0;
>  }
>  
> -/*
> - * Triggered by a postcopy_listen command; this thread takes over reading
> - * the input stream, leaving the main thread free to carry on loading the rest
> - * of the device state (from RAM).
> - * (TODO:This could do with being in a postcopy file - but there again it's
> - * just another input loop, not that postcopy specific)
> - */
> -static void *postcopy_ram_listen_thread(void *opaque)
> -{
> -    MigrationIncomingState *mis = migration_incoming_get_current();
> -    QEMUFile *f = mis->from_src_file;
> -    int load_res;
> -    MigrationState *migr = migrate_get_current();
> -    Error *local_err = NULL;
> -
> -    object_ref(OBJECT(migr));
> -
> -    migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
> -                                   MIGRATION_STATUS_POSTCOPY_ACTIVE);
> -    qemu_event_set(&mis->thread_sync_event);
> -    trace_postcopy_ram_listen_thread_start();
> -
> -    rcu_register_thread();
> -    /*
> -     * Because we're a thread and not a coroutine we can't yield
> -     * in qemu_file, and thus we must be blocking now.
> -     */
> -    qemu_file_set_blocking(f, true, &error_fatal);
> -
> -    /* TODO: sanity check that only postcopiable data will be loaded here */
> -    load_res = qemu_loadvm_state_main(f, mis, &local_err);
> -
> -    /*
> -     * This is tricky, but, mis->from_src_file can change after it
> -     * returns, when postcopy recovery happened. In the future, we may
> -     * want a wrapper for the QEMUFile handle.
> -     */
> -    f = mis->from_src_file;
> -
> -    /* And non-blocking again so we don't block in any cleanup */
> -    qemu_file_set_blocking(f, false, &error_fatal);
> -
> -    trace_postcopy_ram_listen_thread_exit();
> -    if (load_res < 0) {
> -        qemu_file_set_error(f, load_res);
> -        dirty_bitmap_mig_cancel_incoming();
> -        if (postcopy_state_get() == POSTCOPY_INCOMING_RUNNING &&
> -            !migrate_postcopy_ram() && migrate_dirty_bitmaps())
> -        {
> -            error_report("%s: loadvm failed during postcopy: %d: %s. All states "
> -                         "are migrated except dirty bitmaps. Some dirty "
> -                         "bitmaps may be lost, and present migrated dirty "
> -                         "bitmaps are correctly migrated and valid.",
> -                         __func__, load_res, error_get_pretty(local_err));
> -            g_clear_pointer(&local_err, error_free);
> -            load_res = 0; /* prevent further exit() */
> -        } else {
> -            error_prepend(&local_err,
> -                          "loadvm failed during postcopy: %d: ", load_res);
> -            migrate_set_error(migr, local_err);
> -            g_clear_pointer(&local_err, error_report_err);
> -            migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
> -                                           MIGRATION_STATUS_FAILED);
> -        }
> -    }
> -    if (load_res >= 0) {
> -        /*
> -         * This looks good, but it's possible that the device loading in the
> -         * main thread hasn't finished yet, and so we might not be in 'RUN'
> -         * state yet; wait for the end of the main thread.
> -         */
> -        qemu_event_wait(&mis->main_thread_load_event);
> -    }
> -    postcopy_ram_incoming_cleanup(mis);
> -
> -    if (load_res < 0) {
> -        /*
> -         * If something went wrong then we have a bad state so exit;
> -         * depending how far we got it might be possible at this point
> -         * to leave the guest running and fire MCEs for pages that never
> -         * arrived as a desperate recovery step.
> -         */
> -        rcu_unregister_thread();
> -        exit(EXIT_FAILURE);
> -    }
> -
> -    migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
> -                                   MIGRATION_STATUS_COMPLETED);
> -    /*
> -     * If everything has worked fine, then the main thread has waited
> -     * for us to start, and we're the last use of the mis.
> -     * (If something broke then qemu will have to exit anyway since it's
> -     * got a bad migration state).
> -     */
> -    bql_lock();
> -    migration_incoming_state_destroy();
> -    bql_unlock();
> -
> -    rcu_unregister_thread();
> -    mis->have_listen_thread = false;
> -    postcopy_state_set(POSTCOPY_INCOMING_END);
> -
> -    object_unref(OBJECT(migr));
> -
> -    return NULL;
> -}
> -
>  /* After this message we must be able to immediately receive postcopy data */
>  static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis,
>                                           Error **errp)
> -- 
> 2.51.0
> 

-- 
Peter Xu