From a1f2a51d1a789c46e806adb332236ca16d538bf9 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Tue, 2 May 2023 15:52:12 -0500 Subject: [PATCH 3/5] migration: Attempt disk reactivation in more failure scenarios RH-Author: Eric Blake RH-MergeRequest: 273: migration: prevent source core dump if NFS dies mid-migration RH-Bugzilla: 2177957 RH-Acked-by: Miroslav Rezanina RH-Acked-by: quintela1 RH-Acked-by: Kevin Wolf RH-Commit: [3/3] e84bf1e7233c0273ca3136ecaa6b2cfc9c0efacb (ebblake/qemu-kvm) Commit fe904ea824 added a fail_inactivate label, which tries to reactivate disks on the source after a failure while s->state == MIGRATION_STATUS_ACTIVE, but didn't actually use the label if qemu_savevm_state_complete_precopy() failed. This failure to reactivate is also present in commit 6039dd5b1c (also covering the new s->state == MIGRATION_STATUS_DEVICE state) and 403d18ae (ensuring s->block_inactive is set more reliably). Consolidate the two labels back into one - no matter HOW migration is failed, if there is any chance we can reach vm_start() after having attempted inactivation, it is essential that we have tried to restart disks before then. This also makes the cleanup more like migrate_fd_cancel(). Suggested-by: Kevin Wolf Signed-off-by: Eric Blake Message-Id: <20230502205212.134680-1-eblake@redhat.com> Acked-by: Peter Xu Reviewed-by: Juan Quintela Reviewed-by: Kevin Wolf Signed-off-by: Kevin Wolf (cherry picked from commit 6dab4c93ecfae48e2e67b984d1032c1e988d3005) [eblake: downstream migrate_colo() => migrate_colo_enabled()] Signed-off-by: Eric Blake --- migration/migration.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/migration/migration.c b/migration/migration.c index 6ba8eb0fdf..817170d52d 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -3255,6 +3255,11 @@ static void migration_completion(MigrationState *s) 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_enabled(); qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX); ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false, @@ -3290,13 +3295,13 @@ static void migration_completion(MigrationState *s) rp_error = await_return_path_close_on_source(s); trace_migration_return_path_end_after(rp_error); if (rp_error) { - goto fail_invalidate; + goto fail; } } if (qemu_file_get_error(s->to_dst_file)) { trace_migration_completion_file_err(); - goto fail_invalidate; + goto fail; } if (!migrate_colo_enabled()) { @@ -3306,26 +3311,25 @@ static void migration_completion(MigrationState *s) return; -fail_invalidate: - /* If not doing postcopy, vm_start() will be called: let's regain - * control on images. - */ - if (s->state == MIGRATION_STATUS_ACTIVE || - s->state == MIGRATION_STATUS_DEVICE) { +fail: + if (s->block_inactive && (s->state == MIGRATION_STATUS_ACTIVE || + s->state == MIGRATION_STATUS_DEVICE)) { + /* + * If not doing postcopy, vm_start() will be called: let's + * regain control on images. + */ Error *local_err = NULL; qemu_mutex_lock_iothread(); bdrv_invalidate_cache_all(&local_err); if (local_err) { error_report_err(local_err); - s->block_inactive = true; } else { s->block_inactive = false; } qemu_mutex_unlock_iothread(); } -fail: migrate_set_state(&s->state, current_active_state, MIGRATION_STATUS_FAILED); } -- 2.39.1