diff options
Diffstat (limited to 'migration/migration.c')
| -rw-r--r-- | migration/migration.c | 396 |
1 files changed, 248 insertions, 148 deletions
diff --git a/migration/migration.c b/migration/migration.c index 55ec4bf..a63b46b 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 { @@ -95,6 +91,9 @@ enum mig_rp_message_type { MIG_RP_MSG_MAX }; +/* Migration channel types */ +enum { CH_MAIN, CH_MULTIFD, CH_POSTCOPY }; + /* When we add fault tolerance, we could have several migrations at once. For now we don't need to add dynamic creation of migration */ @@ -259,6 +258,24 @@ migration_channels_and_transport_compatible(MigrationAddress *addr, return true; } +static bool +migration_capabilities_and_transport_compatible(MigrationAddress *addr, + Error **errp) +{ + if (addr->transport == MIGRATION_ADDRESS_TYPE_RDMA) { + return migrate_rdma_caps_check(migrate_get_current()->capabilities, + errp); + } + + return true; +} + +static bool migration_transport_compatible(MigrationAddress *addr, Error **errp) +{ + return migration_channels_and_transport_compatible(addr, errp) && + migration_capabilities_and_transport_compatible(addr, errp); +} + static gint page_request_addr_cmp(gconstpointer ap, gconstpointer bp) { uintptr_t a = (uintptr_t) ap, b = (uintptr_t) bp; @@ -316,6 +333,7 @@ void migration_object_init(void) ram_mig_init(); dirty_bitmap_mig_init(); + cpr_exec_init(); /* Initialize cpu throttle timers */ cpu_throttle_init(); @@ -555,22 +573,27 @@ int migrate_send_rp_message_req_pages(MigrationIncomingState *mis, } int migrate_send_rp_req_pages(MigrationIncomingState *mis, - RAMBlock *rb, ram_addr_t start, uint64_t haddr) + RAMBlock *rb, ram_addr_t start, uint64_t haddr, + uint32_t tid) { void *aligned = (void *)(uintptr_t)ROUND_DOWN(haddr, qemu_ram_pagesize(rb)); bool received = false; WITH_QEMU_LOCK_GUARD(&mis->page_request_mutex) { received = ramblock_recv_bitmap_test_byte_offset(rb, start); - if (!received && !g_tree_lookup(mis->page_requested, aligned)) { - /* - * The page has not been received, and it's not yet in the page - * request list. Queue it. Set the value of element to 1, so that - * things like g_tree_lookup() will return TRUE (1) when found. - */ - g_tree_insert(mis->page_requested, aligned, (gpointer)1); - qatomic_inc(&mis->page_requested_count); - trace_postcopy_page_req_add(aligned, mis->page_requested_count); + if (!received) { + if (!g_tree_lookup(mis->page_requested, aligned)) { + /* + * The page has not been received, and it's not yet in the + * page request list. Queue it. Set the value of element + * to 1, so that things like g_tree_lookup() will return + * TRUE (1) when found. + */ + g_tree_insert(mis->page_requested, aligned, (gpointer)1); + qatomic_inc(&mis->page_requested_count); + trace_postcopy_page_req_add(aligned, mis->page_requested_count); + } + mark_postcopy_blocktime_begin(haddr, tid, rb); } } @@ -597,22 +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; @@ -750,7 +773,7 @@ static void qemu_start_incoming_migration(const char *uri, bool has_channels, } /* transport mechanism not suitable for migration? */ - if (!migration_channels_and_transport_compatible(addr, errp)) { + if (!migration_transport_compatible(addr, errp)) { return; } @@ -769,14 +792,6 @@ static void qemu_start_incoming_migration(const char *uri, bool has_channels, } #ifdef CONFIG_RDMA } else if (addr->transport == MIGRATION_ADDRESS_TYPE_RDMA) { - if (migrate_xbzrle()) { - error_setg(errp, "RDMA and XBZRLE can't be used together"); - return; - } - if (migrate_multifd()) { - error_setg(errp, "RDMA and multifd can't be used together"); - return; - } rdma_start_incoming_migration(&addr->u.rdma, errp); #endif } else if (addr->transport == MIGRATION_ADDRESS_TYPE_EXEC) { @@ -863,7 +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"); @@ -890,7 +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; } @@ -917,6 +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() */ @@ -931,10 +956,9 @@ static void migration_incoming_setup(QEMUFile *f) { MigrationIncomingState *mis = migration_incoming_get_current(); - if (!mis->from_src_file) { - mis->from_src_file = f; - } - qemu_file_set_blocking(f, false); + assert(!mis->from_src_file); + mis->from_src_file = f; + qemu_file_set_blocking(f, false, &error_abort); } void migration_incoming_process(void) @@ -954,7 +978,7 @@ static bool postcopy_try_recover(void) /* This should be set already in migration_incoming_setup() */ assert(mis->from_src_file); /* Postcopy has standalone thread to do vm load */ - qemu_file_set_blocking(mis->from_src_file, true); + qemu_file_set_blocking(mis->from_src_file, true, &error_abort); /* Re-configure the return path */ mis->to_src_file = qemu_file_get_return_path(mis->from_src_file); @@ -985,28 +1009,19 @@ void migration_fd_process_incoming(QEMUFile *f) migration_incoming_process(); } -/* - * Returns true when we want to start a new incoming migration process, - * false otherwise. - */ -static bool migration_should_start_incoming(bool main_channel) +static bool migration_has_main_and_multifd_channels(void) { - /* Multifd doesn't start unless all channels are established */ - if (migrate_multifd()) { - return migration_has_all_channels(); + MigrationIncomingState *mis = migration_incoming_get_current(); + if (!mis->from_src_file) { + /* main channel not established */ + return false; } - /* Preempt channel only starts when the main channel is created */ - if (migrate_postcopy_preempt()) { - return main_channel; + if (migrate_multifd() && !multifd_recv_all_channels_created()) { + return false; } - /* - * For all the rest types of migration, we should only reach here when - * it's the main channel that's being created, and we should always - * proceed with this channel. - */ - assert(main_channel); + /* main and all multifd channels are established */ return true; } @@ -1015,59 +1030,81 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp) MigrationIncomingState *mis = migration_incoming_get_current(); Error *local_err = NULL; QEMUFile *f; - bool default_channel = true; + uint8_t channel; uint32_t channel_magic = 0; int ret = 0; - if (migrate_multifd() && !migrate_mapped_ram() && - !migrate_postcopy_ram() && - qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) { - /* - * With multiple channels, it is possible that we receive channels - * out of order on destination side, causing incorrect mapping of - * source channels on destination side. Check channel MAGIC to - * decide type of channel. Please note this is best effort, postcopy - * preempt channel does not send any magic number so avoid it for - * postcopy live migration. Also tls live migration already does - * tls handshake while initializing main channel so with tls this - * issue is not possible. - */ - ret = migration_channel_read_peek(ioc, (void *)&channel_magic, - sizeof(channel_magic), errp); + if (!migration_has_main_and_multifd_channels()) { + if (qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) { + /* + * With multiple channels, it is possible that we receive channels + * out of order on destination side, causing incorrect mapping of + * source channels on destination side. Check channel MAGIC to + * decide type of channel. Please note this is best effort, + * postcopy preempt channel does not send any magic number so + * avoid it for postcopy live migration. Also tls live migration + * already does tls handshake while initializing main channel so + * with tls this issue is not possible. + */ + ret = migration_channel_read_peek(ioc, (void *)&channel_magic, + sizeof(channel_magic), errp); + if (ret != 0) { + return; + } - if (ret != 0) { + channel_magic = be32_to_cpu(channel_magic); + if (channel_magic == QEMU_VM_FILE_MAGIC) { + channel = CH_MAIN; + } else if (channel_magic == MULTIFD_MAGIC) { + assert(migrate_multifd()); + channel = CH_MULTIFD; + } else if (!mis->from_src_file && + mis->state == MIGRATION_STATUS_POSTCOPY_PAUSED) { + /* reconnect main channel for postcopy recovery */ + channel = CH_MAIN; + } else { + error_setg(errp, "unknown channel magic: %u", channel_magic); + return; + } + } else if (mis->from_src_file && migrate_multifd()) { + /* + * Non-peekable channels like tls/file are processed as + * multifd channels when multifd is enabled. + */ + channel = CH_MULTIFD; + } else if (!mis->from_src_file) { + channel = CH_MAIN; + } else { + error_setg(errp, "non-peekable channel used without multifd"); return; } - - default_channel = (channel_magic == cpu_to_be32(QEMU_VM_FILE_MAGIC)); } else { - default_channel = !mis->from_src_file; + assert(migrate_postcopy_preempt()); + channel = CH_POSTCOPY; } if (multifd_recv_setup(errp) != 0) { return; } - if (default_channel) { + if (channel == CH_MAIN) { f = qemu_file_new_input(ioc); migration_incoming_setup(f); - } else { + } else if (channel == CH_MULTIFD) { /* Multiple connections */ - assert(migration_needs_multiple_sockets()); - if (migrate_multifd()) { - multifd_recv_new_channel(ioc, &local_err); - } else { - assert(migrate_postcopy_preempt()); - f = qemu_file_new_input(ioc); - postcopy_preempt_new_channel(mis, f); - } + multifd_recv_new_channel(ioc, &local_err); if (local_err) { error_propagate(errp, local_err); return; } + } else if (channel == CH_POSTCOPY) { + assert(!mis->postcopy_qemufile_dst); + f = qemu_file_new_input(ioc); + postcopy_preempt_new_channel(mis, f); + return; } - if (migration_should_start_incoming(default_channel)) { + if (migration_has_main_and_multifd_channels()) { /* If it's a recovery, we're done */ if (postcopy_try_recover()) { return; @@ -1084,18 +1121,13 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp) */ bool migration_has_all_channels(void) { - MigrationIncomingState *mis = migration_incoming_get_current(); - - if (!mis->from_src_file) { + if (!migration_has_main_and_multifd_channels()) { return false; } - if (migrate_multifd()) { - return multifd_recv_all_channels_created(); - } - - if (migrate_postcopy_preempt()) { - return mis->postcopy_qemufile_dst != NULL; + MigrationIncomingState *mis = migration_incoming_get_current(); + if (migrate_postcopy_preempt() && !mis->postcopy_qemufile_dst) { + return false; } return true; @@ -1610,7 +1642,7 @@ void migration_cancel(void) } /* If the migration is paused, kick it out of the pause */ if (old_state == MIGRATION_STATUS_PRE_SWITCHOVER) { - qemu_sem_post(&s->pause_sem); + qemu_event_set(&s->pause_event); } migrate_set_state(&s->state, old_state, MIGRATION_STATUS_CANCELLING); } while (s->state != MIGRATION_STATUS_CANCELLING); @@ -1640,23 +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; } } @@ -1666,18 +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); } @@ -1737,7 +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) @@ -2086,6 +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; } @@ -2208,7 +2286,7 @@ void qmp_migrate(const char *uri, bool has_channels, } /* transport mechanism not suitable for migration? */ - if (!migration_channels_and_transport_compatible(addr, errp)) { + if (!migration_transport_compatible(addr, errp)) { return; } @@ -2322,7 +2400,7 @@ void qmp_migrate_continue(MigrationStatus state, Error **errp) MigrationStatus_str(s->state)); return; } - qemu_sem_post(&s->pause_sem); + qemu_event_set(&s->pause_event); } int migration_rp_wait(MigrationState *s) @@ -2621,12 +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(); @@ -2635,8 +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 */ @@ -2707,6 +2780,10 @@ static int postcopy_start(MigrationState *ms, Error **errp) } } + if (!qemu_savevm_state_postcopy_prepare(ms->to_dst_file, errp)) { + return -1; + } + trace_postcopy_start(); bql_lock(); trace_postcopy_start_set_run(); @@ -2843,8 +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(); @@ -2887,21 +2965,18 @@ static bool migration_switchover_prepare(MigrationState *s) return true; } - /* Since leaving this state is not atomic with posting the semaphore + /* + * Since leaving this state is not atomic with setting the event * it's possible that someone could have issued multiple migrate_continue - * and the semaphore is incorrectly positive at this point; - * the docs say it's undefined to reinit a semaphore that's already - * init'd, so use timedwait to eat up any existing posts. + * and the event is incorrectly set at this point so reset it. */ - while (qemu_sem_timedwait(&s->pause_sem, 1) == 0) { - /* This block intentionally left blank */ - } + qemu_event_reset(&s->pause_event); /* Update [POSTCOPY_]ACTIVE to PRE_SWITCHOVER */ migrate_set_state(&s->state, s->state, MIGRATION_STATUS_PRE_SWITCHOVER); bql_unlock(); - qemu_sem_wait(&s->pause_sem); + qemu_event_wait(&s->pause_event); bql_lock(); /* @@ -3415,33 +3490,60 @@ static MigIterateState migration_iteration_run(MigrationState *s) Error *local_err = NULL; bool in_postcopy = s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE; bool can_switchover = migration_can_switchover(s); + bool complete_ready; + /* Fast path - get the estimated amount of pending data */ qemu_savevm_state_pending_estimate(&must_precopy, &can_postcopy); pending_size = must_precopy + can_postcopy; trace_migrate_pending_estimate(pending_size, must_precopy, can_postcopy); - if (pending_size < s->threshold_size) { - qemu_savevm_state_pending_exact(&must_precopy, &can_postcopy); - pending_size = must_precopy + can_postcopy; - trace_migrate_pending_exact(pending_size, must_precopy, can_postcopy); + if (in_postcopy) { + /* + * Iterate in postcopy until all pending data flushed. Note that + * postcopy completion doesn't rely on can_switchover, because when + * POSTCOPY_ACTIVE it means switchover already happened. + */ + complete_ready = !pending_size; + } else { + /* + * Exact pending reporting is only needed for precopy. Taking RAM + * as example, there'll be no extra dirty information after + * postcopy started, so ESTIMATE should always match with EXACT + * during postcopy phase. + */ + if (pending_size < s->threshold_size) { + qemu_savevm_state_pending_exact(&must_precopy, &can_postcopy); + pending_size = must_precopy + can_postcopy; + trace_migrate_pending_exact(pending_size, must_precopy, + can_postcopy); + } + + /* Should we switch to postcopy now? */ + if (must_precopy <= s->threshold_size && + can_switchover && qatomic_read(&s->start_postcopy)) { + if (postcopy_start(s, &local_err)) { + migrate_set_error(s, local_err); + error_report_err(local_err); + } + return MIG_ITERATE_SKIP; + } + + /* + * For precopy, migration can complete only if: + * + * (1) Switchover is acknowledged by destination + * (2) Pending size is no more than the threshold specified + * (which was calculated from expected downtime) + */ + complete_ready = can_switchover && (pending_size <= s->threshold_size); } - if ((!pending_size || pending_size < s->threshold_size) && can_switchover) { + if (complete_ready) { trace_migration_thread_low_pending(pending_size); migration_completion(s); return MIG_ITERATE_BREAK; } - /* Still a significant amount to transfer */ - if (!in_postcopy && must_precopy <= s->threshold_size && can_switchover && - qatomic_read(&s->start_postcopy)) { - if (postcopy_start(s, &local_err)) { - migrate_set_error(s, local_err); - error_report_err(local_err); - } - return MIG_ITERATE_SKIP; - } - /* Just another iteration step */ qemu_savevm_state_iterate(s->to_dst_file, in_postcopy); return MIG_ITERATE_RESUME; @@ -3866,9 +3968,8 @@ static void *bg_migration_thread(void *opaque) while (migration_is_active()) { MigIterateState iter_state = bg_migration_iteration_run(s); - if (iter_state == MIG_ITERATE_SKIP) { - continue; - } else if (iter_state == MIG_ITERATE_BREAK) { + + if (iter_state == MIG_ITERATE_BREAK) { break; } @@ -3950,7 +4051,9 @@ void migration_connect(MigrationState *s, Error *error_in) } migration_rate_set(rate_limit); - qemu_file_set_blocking(s->to_dst_file, true); + if (!qemu_file_set_blocking(s->to_dst_file, true, &local_err)) { + goto fail; + } /* * Open the return path. For postcopy, it is used exclusively. For @@ -3958,10 +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); } /* @@ -4033,7 +4133,7 @@ static void migration_instance_finalize(Object *obj) qemu_mutex_destroy(&ms->qemu_file_lock); qemu_sem_destroy(&ms->wait_unplug_sem); qemu_sem_destroy(&ms->rate_limit_sem); - qemu_sem_destroy(&ms->pause_sem); + qemu_event_destroy(&ms->pause_event); qemu_sem_destroy(&ms->postcopy_pause_sem); qemu_sem_destroy(&ms->rp_state.rp_sem); qemu_sem_destroy(&ms->rp_state.rp_pong_acks); @@ -4048,7 +4148,7 @@ static void migration_instance_init(Object *obj) ms->state = MIGRATION_STATUS_NONE; ms->mbps = -1; ms->pages_per_second = -1; - qemu_sem_init(&ms->pause_sem, 0); + qemu_event_init(&ms->pause_event, false); qemu_mutex_init(&ms->error_mutex); migrate_params_init(&ms->parameters); |