Re: [Qemu-devel] [PATCH for-4.0 v9 13/16] qemu_thread: supplement error handling for migration

["Dr. David Alan Gilbert" <dgilbert@redhat.com>]

* Fei Li (fli@suse.com) wrote:
> Update qemu_thread_create()'s callers by
> - setting an error on qemu_thread_create() failure for callers that
>   set an error on failure;
> - reporting the error and returning failure for callers that return
>   an error code on failure;
> - reporting the error and setting some state for callers that just
>   report errors and choose not to continue on.
> 
> Cc: Markus Armbruster <armbru@redhat.com>
> Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
> Cc: Peter Xu <peterx@redhat.com>
> Signed-off-by: Fei Li <fli@suse.com>
> ---
>  migration/migration.c    | 33 ++++++++++++++++++++++-----------
>  migration/postcopy-ram.c | 16 ++++++++++++----
>  migration/ram.c          | 44 ++++++++++++++++++++++++++++++--------------
>  migration/savevm.c       | 12 ++++++++----
>  4 files changed, 72 insertions(+), 33 deletions(-)
> 
> diff --git a/migration/migration.c b/migration/migration.c
> index ea5839ff0d..9654bde101 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -447,10 +447,13 @@ static void process_incoming_migration_co(void *opaque)
>              goto fail;
>          }
>  
> -        /* TODO: let the further caller handle the error instead of abort() */
> -        qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming",
> -                           colo_process_incoming_thread, mis,
> -                           QEMU_THREAD_JOINABLE, &error_abort);
> +        if (!qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming",
> +                                colo_process_incoming_thread, mis,
> +                                QEMU_THREAD_JOINABLE, &local_err)) {
> +            error_reportf_err(local_err, "failed to create "
> +                              "colo_process_incoming_thread: ");
> +            goto fail;
> +        }
>          mis->have_colo_incoming_thread = true;
>          qemu_coroutine_yield();

OK

> @@ -2347,6 +2350,7 @@ out:
>  static int open_return_path_on_source(MigrationState *ms,
>                                        bool create_thread)
>  {
> +    Error *local_err = NULL;
>  
>      ms->rp_state.from_dst_file = qemu_file_get_return_path(ms->to_dst_file);
>      if (!ms->rp_state.from_dst_file) {
> @@ -2360,10 +2364,13 @@ static int open_return_path_on_source(MigrationState *ms,
>          return 0;
>      }
>  
> -    /* TODO: let the further caller handle the error instead of abort() here */
> -    qemu_thread_create(&ms->rp_state.rp_thread, "return path",
> -                       source_return_path_thread, ms,
> -                       QEMU_THREAD_JOINABLE, &error_abort);
> +    if (!qemu_thread_create(&ms->rp_state.rp_thread, "return path",
> +                            source_return_path_thread, ms,
> +                            QEMU_THREAD_JOINABLE, &local_err)) {
> +        error_reportf_err(local_err,
> +                          "failed to create source_return_path_thread: ");
> +        return -1;
> +     }

I think that has to close the from_dst_file and set the
from_dst_file=NULL.  That file is owned by the thread, and it's normally
the thread that cleans it up.

I think other than that missing close it's fine; and we can do that as a
fix later, so:


Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

>  
>      trace_open_return_path_on_source_continue();
>  
> @@ -3193,9 +3200,13 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
>          migrate_fd_cleanup(s);
>          return;
>      }
> -    /* TODO: let the further caller handle the error instead of abort() here */
> -    qemu_thread_create(&s->thread, "live_migration", migration_thread, s,
> -                       QEMU_THREAD_JOINABLE, &error_abort);
> +    if (!qemu_thread_create(&s->thread, "live_migration", migration_thread, s,
> +                            QEMU_THREAD_JOINABLE, &error_in)) {
> +        error_reportf_err(error_in, "failed to create migration_thread: ");
> +        migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
> +        migrate_fd_cleanup(s);
> +        return;
> +    }

OK

>      s->migration_thread_running = true;
>  }
>  
> diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
> index 221ea24919..80bfa9c4a2 100644
> --- a/migration/postcopy-ram.c
> +++ b/migration/postcopy-ram.c
> @@ -1083,6 +1083,8 @@ retry:
>  
>  int postcopy_ram_enable_notify(MigrationIncomingState *mis)
>  {
> +    Error *local_err = NULL;
> +
>      /* Open the fd for the kernel to give us userfaults */
>      mis->userfault_fd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
>      if (mis->userfault_fd == -1) {
> @@ -1109,10 +1111,16 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
>      }
>  
>      qemu_sem_init(&mis->fault_thread_sem, 0);
> -    /* TODO: let the further caller handle the error instead of abort() here */
> -    qemu_thread_create(&mis->fault_thread, "postcopy/fault",
> -                       postcopy_ram_fault_thread, mis,
> -                       QEMU_THREAD_JOINABLE, &error_abort);
> +    if (!qemu_thread_create(&mis->fault_thread, "postcopy/fault",
> +                            postcopy_ram_fault_thread, mis,
> +                            QEMU_THREAD_JOINABLE, &local_err)) {
> +        error_reportf_err(local_err,
> +                          "failed to create postcopy_ram_fault_thread: ");
> +        close(mis->userfault_event_fd);
> +        close(mis->userfault_fd);
> +        qemu_sem_destroy(&mis->fault_thread_sem);
> +        return -1;
> +    }
>      qemu_sem_wait(&mis->fault_thread_sem);
>      qemu_sem_destroy(&mis->fault_thread_sem);
>      mis->have_fault_thread = true;

OK

> diff --git a/migration/ram.c b/migration/ram.c
> index eed1daf302..1e24a78eaa 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -473,6 +473,7 @@ static void compress_threads_save_cleanup(void)
>  static int compress_threads_save_setup(void)
>  {
>      int i, thread_count;
> +    Error *local_err = NULL;
>  
>      if (!migrate_use_compression()) {
>          return 0;
> @@ -502,10 +503,12 @@ static int compress_threads_save_setup(void)
>          comp_param[i].quit = false;
>          qemu_mutex_init(&comp_param[i].mutex);
>          qemu_cond_init(&comp_param[i].cond);
> -        /* TODO: let the further caller handle the error instead of abort() */
> -        qemu_thread_create(compress_threads + i, "compress",
> -                           do_data_compress, comp_param + i,
> -                           QEMU_THREAD_JOINABLE, &error_abort);
> +        if (!qemu_thread_create(compress_threads + i, "compress",
> +                                do_data_compress, comp_param + i,
> +                                QEMU_THREAD_JOINABLE, &local_err)) {
> +            error_reportf_err(local_err, "failed to create do_data_compress: ");
> +            goto exit;
> +        }

OK

>      }
>      return 0;
>  
> @@ -1076,9 +1079,14 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque)
>          p->c = QIO_CHANNEL(sioc);
>          qio_channel_set_delay(p->c, false);
>          p->running = true;
> -        /* TODO: let the further caller handle the error instead of abort() */
> -        qemu_thread_create(&p->thread, p->name, multifd_send_thread, p,
> -                           QEMU_THREAD_JOINABLE, &error_abort);
> +        if (!qemu_thread_create(&p->thread, p->name, multifd_send_thread, p,
> +                                QEMU_THREAD_JOINABLE, &local_err)) {
> +            migrate_set_error(migrate_get_current(), local_err);
> +            error_reportf_err(local_err,
> +                              "failed to create multifd_send_thread: ");
> +            multifd_save_cleanup();
> +            return;
> +        }
>  
>          atomic_inc(&multifd_send_state->count);
>      }
> @@ -1357,9 +1365,13 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
>      p->num_packets = 1;
>  
>      p->running = true;
> -    /* TODO: let the further caller handle the error instead of abort() here */
> -    qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p,
> -                       QEMU_THREAD_JOINABLE, &error_abort);
> +    if (!qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p,
> +                            QEMU_THREAD_JOINABLE, &local_err)) {
> +        error_propagate_prepend(errp, local_err,
> +                                "failed to create multifd_recv_thread: ");
> +        multifd_recv_terminate_threads(local_err);
> +        return false;
> +    }
>      atomic_inc(&multifd_recv_state->count);
>      return atomic_read(&multifd_recv_state->count) ==
>             migrate_multifd_channels();
> @@ -3625,6 +3637,7 @@ static void compress_threads_load_cleanup(void)
>  static int compress_threads_load_setup(QEMUFile *f)
>  {
>      int i, thread_count;
> +    Error *local_err = NULL;
>  
>      if (!migrate_use_compression()) {
>          return 0;
> @@ -3646,10 +3659,13 @@ static int compress_threads_load_setup(QEMUFile *f)
>          qemu_cond_init(&decomp_param[i].cond);
>          decomp_param[i].done = true;
>          decomp_param[i].quit = false;
> -        /* TODO: let the further caller handle the error instead of abort() */
> -        qemu_thread_create(decompress_threads + i, "decompress",
> -                           do_data_decompress, decomp_param + i,
> -                           QEMU_THREAD_JOINABLE, &error_abort);
> +        if (!qemu_thread_create(decompress_threads + i, "decompress",
> +                                do_data_decompress, decomp_param + i,
> +                                QEMU_THREAD_JOINABLE, &local_err)) {
> +            error_reportf_err(local_err,
> +                              "failed to create do_data_decompress: ");
> +            goto exit;
> +        }
>      }
>      return 0;
>  exit:
> diff --git a/migration/savevm.c b/migration/savevm.c
> index 46ce7af239..b8bdcde5d8 100644
> --- a/migration/savevm.c
> +++ b/migration/savevm.c
> @@ -1747,10 +1747,14 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis)
>      mis->have_listen_thread = true;
>      /* Start up the listening thread and wait for it to signal ready */
>      qemu_sem_init(&mis->listen_thread_sem, 0);
> -    /* TODO: let the further caller handle the error instead of abort() here */
> -    qemu_thread_create(&mis->listen_thread, "postcopy/listen",
> -                       postcopy_ram_listen_thread, NULL,
> -                       QEMU_THREAD_DETACHED, &error_abort);
> +    if (!qemu_thread_create(&mis->listen_thread, "postcopy/listen",
> +                            postcopy_ram_listen_thread, NULL,
> +                            QEMU_THREAD_DETACHED, &local_err)) {
> +        error_reportf_err(local_err,
> +                          "failed to create postcopy_ram_listen_thread: ");
> +        qemu_sem_destroy(&mis->listen_thread_sem);
> +        return -1;
> +    }
>      qemu_sem_wait(&mis->listen_thread_sem);
>      qemu_sem_destroy(&mis->listen_thread_sem);
>  
> -- 
> 2.13.7
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK