Message ID | 20181129100340.13823-5-fli@suse.com |
---|---|
State | New |
Headers | show |
Series | fix some segmentation faults and migration issues | expand |
On 29/11/18 11:03, Fei Li wrote: > Always call migrate_set_error() to set the error state without relying > on whether multifd_save_cleanup() succeeds. As the passed &local_err > is never used in multifd_save_cleanup(), remove it. And make the > function be: void multifd_save_cleanup(void). Reading this after your patch 1/5, maybe multifd_save_cleanup() lacks error reporting on failure. So the actual prototype is correct, we just need to use **errp in that function (like reporting invalid thread instead of calling qemu_thread_join()). > > Signed-off-by: Fei Li <fli@suse.com> > Reviewed-by: Juan Quintela <quintela@redhat.com> > --- > migration/migration.c | 5 +---- > migration/ram.c | 11 ++++------- > migration/ram.h | 2 +- > 3 files changed, 6 insertions(+), 12 deletions(-) > > diff --git a/migration/migration.c b/migration/migration.c > index 72106bddf0..0537fc0c26 100644 > --- a/migration/migration.c > +++ b/migration/migration.c > @@ -1386,7 +1386,6 @@ static void migrate_fd_cleanup(void *opaque) > qemu_savevm_state_cleanup(); > > if (s->to_dst_file) { > - Error *local_err = NULL; > QEMUFile *tmp; > > trace_migrate_fd_cleanup(); > @@ -1397,9 +1396,7 @@ static void migrate_fd_cleanup(void *opaque) > } > qemu_mutex_lock_iothread(); > > - if (multifd_save_cleanup(&local_err) != 0) { > - error_report_err(local_err); > - } > + multifd_save_cleanup(); > qemu_mutex_lock(&s->qemu_file_lock); > tmp = s->to_dst_file; > s->to_dst_file = NULL; > diff --git a/migration/ram.c b/migration/ram.c > index e13b9349d0..c44cb6f56d 100644 > --- a/migration/ram.c > +++ b/migration/ram.c > @@ -917,13 +917,12 @@ static void multifd_send_terminate_threads(Error *err) > } > } > > -int multifd_save_cleanup(Error **errp) > +void multifd_save_cleanup(void) > { > int i; > - int ret = 0; > > if (!migrate_use_multifd()) { > - return 0; > + return; > } > multifd_send_terminate_threads(NULL); > for (i = 0; i < migrate_multifd_channels(); i++) { > @@ -953,7 +952,6 @@ int multifd_save_cleanup(Error **errp) > multifd_send_state->pages = NULL; > g_free(multifd_send_state); > multifd_send_state = NULL; > - return ret; > } > > static void multifd_send_sync_main(void) > @@ -1071,9 +1069,8 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque) > Error *local_err = NULL; > > if (qio_task_propagate_error(task, &local_err)) { > - if (multifd_save_cleanup(&local_err) != 0) { > - migrate_set_error(migrate_get_current(), local_err); > - } > + migrate_set_error(migrate_get_current(), local_err); > + multifd_save_cleanup(); > } else { > p->c = QIO_CHANNEL(sioc); > qio_channel_set_delay(p->c, false); > diff --git a/migration/ram.h b/migration/ram.h > index 046d3074be..936177b3e9 100644 > --- a/migration/ram.h > +++ b/migration/ram.h > @@ -43,7 +43,7 @@ uint64_t ram_bytes_remaining(void); > uint64_t ram_bytes_total(void); > > int multifd_save_setup(void); > -int multifd_save_cleanup(Error **errp); > +void multifd_save_cleanup(void); > int multifd_load_setup(void); > int multifd_load_cleanup(Error **errp); > bool multifd_recv_all_channels_created(void); >
On Thu, Nov 29, 2018 at 3:50 PM Philippe Mathieu-Daudé <philmd@redhat.com> wrote: > On 29/11/18 11:03, Fei Li wrote: > > Always call migrate_set_error() to set the error state without relying > > on whether multifd_save_cleanup() succeeds. As the passed &local_err > > is never used in multifd_save_cleanup(), remove it. And make the > > function be: void multifd_save_cleanup(void). > > Reading this after your patch 1/5, maybe multifd_save_cleanup() lacks I wanted to write "2/5: qemu_thread_join: fix segmentation fault" > error reporting on failure. So the actual prototype is correct, we just > need to use **errp in that function (like reporting invalid thread > instead of calling qemu_thread_join()). > > > > > Signed-off-by: Fei Li <fli@suse.com> > > Reviewed-by: Juan Quintela <quintela@redhat.com> > > --- > > migration/migration.c | 5 +---- > > migration/ram.c | 11 ++++------- > > migration/ram.h | 2 +- > > 3 files changed, 6 insertions(+), 12 deletions(-) > > > > diff --git a/migration/migration.c b/migration/migration.c > > index 72106bddf0..0537fc0c26 100644 > > --- a/migration/migration.c > > +++ b/migration/migration.c > > @@ -1386,7 +1386,6 @@ static void migrate_fd_cleanup(void *opaque) > > qemu_savevm_state_cleanup(); > > > > if (s->to_dst_file) { > > - Error *local_err = NULL; > > QEMUFile *tmp; > > > > trace_migrate_fd_cleanup(); > > @@ -1397,9 +1396,7 @@ static void migrate_fd_cleanup(void *opaque) > > } > > qemu_mutex_lock_iothread(); > > > > - if (multifd_save_cleanup(&local_err) != 0) { > > - error_report_err(local_err); > > - } > > + multifd_save_cleanup(); > > qemu_mutex_lock(&s->qemu_file_lock); > > tmp = s->to_dst_file; > > s->to_dst_file = NULL; > > diff --git a/migration/ram.c b/migration/ram.c > > index e13b9349d0..c44cb6f56d 100644 > > --- a/migration/ram.c > > +++ b/migration/ram.c > > @@ -917,13 +917,12 @@ static void multifd_send_terminate_threads(Error *err) > > } > > } > > > > -int multifd_save_cleanup(Error **errp) > > +void multifd_save_cleanup(void) > > { > > int i; > > - int ret = 0; > > > > if (!migrate_use_multifd()) { > > - return 0; > > + return; > > } > > multifd_send_terminate_threads(NULL); > > for (i = 0; i < migrate_multifd_channels(); i++) { > > @@ -953,7 +952,6 @@ int multifd_save_cleanup(Error **errp) > > multifd_send_state->pages = NULL; > > g_free(multifd_send_state); > > multifd_send_state = NULL; > > - return ret; > > } > > > > static void multifd_send_sync_main(void) > > @@ -1071,9 +1069,8 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque) > > Error *local_err = NULL; > > > > if (qio_task_propagate_error(task, &local_err)) { > > - if (multifd_save_cleanup(&local_err) != 0) { > > - migrate_set_error(migrate_get_current(), local_err); > > - } > > + migrate_set_error(migrate_get_current(), local_err); > > + multifd_save_cleanup(); > > } else { > > p->c = QIO_CHANNEL(sioc); > > qio_channel_set_delay(p->c, false); > > diff --git a/migration/ram.h b/migration/ram.h > > index 046d3074be..936177b3e9 100644 > > --- a/migration/ram.h > > +++ b/migration/ram.h > > @@ -43,7 +43,7 @@ uint64_t ram_bytes_remaining(void); > > uint64_t ram_bytes_total(void); > > > > int multifd_save_setup(void); > > -int multifd_save_cleanup(Error **errp); > > +void multifd_save_cleanup(void); > > int multifd_load_setup(void); > > int multifd_load_cleanup(Error **errp); > > bool multifd_recv_all_channels_created(void); > >
On 11/29/2018 10:50 PM, Philippe Mathieu-Daudé wrote: > On 29/11/18 11:03, Fei Li wrote: >> Always call migrate_set_error() to set the error state without relying >> on whether multifd_save_cleanup() succeeds. As the passed &local_err >> is never used in multifd_save_cleanup(), remove it. And make the >> function be: void multifd_save_cleanup(void). > Reading this after your patch 1/5, maybe multifd_save_cleanup() lacks > error reporting on failure. So the actual prototype is correct, we just > need to use **errp in that function (like reporting invalid thread > instead of calling qemu_thread_join()). Sorry that maybe the patch sequences causethe mis-understanding. The patch "2/5: qemu_thread_join: fix segmentation fault" is added to fix another problem when qemu_thread_create() fails. The qemu_thread_join() => pthread_join in multifd_save_cleanup() is used to terminate the already created/running thread, so I do not think it should be replaced. Besides, do we need to report the invalid thread for users? But for multifd_save_cleanup() itself, it is called when 1. fails to send one multifd channel. In this way, the error reason has been stored in MigrationState->error, but not be printed. I think we can add a `error_report_err(local_err)` in multifd_new_send_channel_async() just as follows: @@ -1070,6 +1070,7 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque) if (qio_task_propagate_error(task, &local_err)) { migrate_set_error(migrate_get_current(), local_err); + error_report_err(local_err); multifd_save_cleanup(); } else { BTW, we also need to notify the main thread that the migrate_state is failed in this case, but currently this issue is still under discussion. Please see patch 5/9 in"[PATCH RFC v7 0/9] qemu_thread_create: propagate errors to callers to check." for more details. :) 2. migrate_fd_cleanup() is called to do the cleanup (In this way, the real error reason is stored and also will be printed inside in migrate_fd_cleanup() or before migrate_fd_cleanup() is called. Thus IMO no update is needed here.) Have a nice day, thanks Fei >> Signed-off-by: Fei Li <fli@suse.com> >> Reviewed-by: Juan Quintela <quintela@redhat.com> >> --- >> migration/migration.c | 5 +---- >> migration/ram.c | 11 ++++------- >> migration/ram.h | 2 +- >> 3 files changed, 6 insertions(+), 12 deletions(-) >> >> diff --git a/migration/migration.c b/migration/migration.c >> index 72106bddf0..0537fc0c26 100644 >> --- a/migration/migration.c >> +++ b/migration/migration.c >> @@ -1386,7 +1386,6 @@ static void migrate_fd_cleanup(void *opaque) >> qemu_savevm_state_cleanup(); >> >> if (s->to_dst_file) { >> - Error *local_err = NULL; >> QEMUFile *tmp; >> >> trace_migrate_fd_cleanup(); >> @@ -1397,9 +1396,7 @@ static void migrate_fd_cleanup(void *opaque) >> } >> qemu_mutex_lock_iothread(); >> >> - if (multifd_save_cleanup(&local_err) != 0) { >> - error_report_err(local_err); >> - } >> + multifd_save_cleanup(); >> qemu_mutex_lock(&s->qemu_file_lock); >> tmp = s->to_dst_file; >> s->to_dst_file = NULL; >> diff --git a/migration/ram.c b/migration/ram.c >> index e13b9349d0..c44cb6f56d 100644 >> --- a/migration/ram.c >> +++ b/migration/ram.c >> @@ -917,13 +917,12 @@ static void multifd_send_terminate_threads(Error *err) >> } >> } >> >> -int multifd_save_cleanup(Error **errp) >> +void multifd_save_cleanup(void) >> { >> int i; >> - int ret = 0; >> >> if (!migrate_use_multifd()) { >> - return 0; >> + return; >> } >> multifd_send_terminate_threads(NULL); >> for (i = 0; i < migrate_multifd_channels(); i++) { >> @@ -953,7 +952,6 @@ int multifd_save_cleanup(Error **errp) >> multifd_send_state->pages = NULL; >> g_free(multifd_send_state); >> multifd_send_state = NULL; >> - return ret; >> } >> >> static void multifd_send_sync_main(void) >> @@ -1071,9 +1069,8 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque) >> Error *local_err = NULL; >> >> if (qio_task_propagate_error(task, &local_err)) { >> - if (multifd_save_cleanup(&local_err) != 0) { >> - migrate_set_error(migrate_get_current(), local_err); >> - } >> + migrate_set_error(migrate_get_current(), local_err); >> + multifd_save_cleanup(); >> } else { >> p->c = QIO_CHANNEL(sioc); >> qio_channel_set_delay(p->c, false); >> diff --git a/migration/ram.h b/migration/ram.h >> index 046d3074be..936177b3e9 100644 >> --- a/migration/ram.h >> +++ b/migration/ram.h >> @@ -43,7 +43,7 @@ uint64_t ram_bytes_remaining(void); >> uint64_t ram_bytes_total(void); >> >> int multifd_save_setup(void); >> -int multifd_save_cleanup(Error **errp); >> +void multifd_save_cleanup(void); >> int multifd_load_setup(void); >> int multifd_load_cleanup(Error **errp); >> bool multifd_recv_all_channels_created(void); >> >
diff --git a/migration/migration.c b/migration/migration.c index 72106bddf0..0537fc0c26 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -1386,7 +1386,6 @@ static void migrate_fd_cleanup(void *opaque) qemu_savevm_state_cleanup(); if (s->to_dst_file) { - Error *local_err = NULL; QEMUFile *tmp; trace_migrate_fd_cleanup(); @@ -1397,9 +1396,7 @@ static void migrate_fd_cleanup(void *opaque) } qemu_mutex_lock_iothread(); - if (multifd_save_cleanup(&local_err) != 0) { - error_report_err(local_err); - } + multifd_save_cleanup(); qemu_mutex_lock(&s->qemu_file_lock); tmp = s->to_dst_file; s->to_dst_file = NULL; diff --git a/migration/ram.c b/migration/ram.c index e13b9349d0..c44cb6f56d 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -917,13 +917,12 @@ static void multifd_send_terminate_threads(Error *err) } } -int multifd_save_cleanup(Error **errp) +void multifd_save_cleanup(void) { int i; - int ret = 0; if (!migrate_use_multifd()) { - return 0; + return; } multifd_send_terminate_threads(NULL); for (i = 0; i < migrate_multifd_channels(); i++) { @@ -953,7 +952,6 @@ int multifd_save_cleanup(Error **errp) multifd_send_state->pages = NULL; g_free(multifd_send_state); multifd_send_state = NULL; - return ret; } static void multifd_send_sync_main(void) @@ -1071,9 +1069,8 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque) Error *local_err = NULL; if (qio_task_propagate_error(task, &local_err)) { - if (multifd_save_cleanup(&local_err) != 0) { - migrate_set_error(migrate_get_current(), local_err); - } + migrate_set_error(migrate_get_current(), local_err); + multifd_save_cleanup(); } else { p->c = QIO_CHANNEL(sioc); qio_channel_set_delay(p->c, false); diff --git a/migration/ram.h b/migration/ram.h index 046d3074be..936177b3e9 100644 --- a/migration/ram.h +++ b/migration/ram.h @@ -43,7 +43,7 @@ uint64_t ram_bytes_remaining(void); uint64_t ram_bytes_total(void); int multifd_save_setup(void); -int multifd_save_cleanup(Error **errp); +void multifd_save_cleanup(void); int multifd_load_setup(void); int multifd_load_cleanup(Error **errp); bool multifd_recv_all_channels_created(void);