diff options
Diffstat (limited to 'migration')
| -rw-r--r-- | migration/colo.c | 10 | ||||
| -rw-r--r-- | migration/cpr-exec.c | 194 | ||||
| -rw-r--r-- | migration/cpr.c | 42 | ||||
| -rw-r--r-- | migration/meson.build | 1 | ||||
| -rw-r--r-- | migration/migration-hmp-cmds.c | 44 | ||||
| -rw-r--r-- | migration/migration.c | 116 | ||||
| -rw-r--r-- | migration/multifd.c | 65 | ||||
| -rw-r--r-- | migration/options.c | 14 | ||||
| -rw-r--r-- | migration/postcopy-ram.c | 9 | ||||
| -rw-r--r-- | migration/postcopy-ram.h | 2 | ||||
| -rw-r--r-- | migration/qemu-file.c | 7 | ||||
| -rw-r--r-- | migration/ram.c | 17 | ||||
| -rw-r--r-- | migration/ram.h | 4 | ||||
| -rw-r--r-- | migration/savevm.c | 329 | ||||
| -rw-r--r-- | migration/savevm.h | 7 | ||||
| -rw-r--r-- | migration/trace-events | 1 | ||||
| -rw-r--r-- | migration/vmstate-types.c | 61 | ||||
| -rw-r--r-- | migration/vmstate.c | 103 |
18 files changed, 733 insertions, 293 deletions
diff --git a/migration/colo.c b/migration/colo.c index cf4d71d9ed..db783f6fa7 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -686,11 +686,10 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, bql_lock(); cpu_synchronize_all_states(); - ret = qemu_loadvm_state_main(mis->from_src_file, mis); + ret = qemu_loadvm_state_main(mis->from_src_file, mis, errp); bql_unlock(); if (ret < 0) { - error_setg(errp, "Load VM's live state (ram) error"); return; } @@ -729,9 +728,8 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, bql_lock(); vmstate_loading = true; colo_flush_ram_cache(); - ret = qemu_load_device_state(fb); + ret = qemu_load_device_state(fb, errp); if (ret < 0) { - error_setg(errp, "COLO: load device state failed"); vmstate_loading = false; bql_unlock(); return; @@ -849,10 +847,6 @@ static void *colo_process_incoming_thread(void *opaque) failover_init_state(); mis->to_src_file = qemu_file_get_return_path(mis->from_src_file); - if (!mis->to_src_file) { - error_report("COLO incoming thread: Open QEMUFile to_src_file failed"); - goto out; - } /* * Note: the communication between Primary side and Secondary side * should be sequential, we set the fd to unblocked in migration incoming diff --git a/migration/cpr-exec.c b/migration/cpr-exec.c new file mode 100644 index 0000000000..d57714bc5d --- /dev/null +++ b/migration/cpr-exec.c @@ -0,0 +1,194 @@ +/* + * Copyright (c) 2021-2025 Oracle and/or its affiliates. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/cutils.h" +#include "qemu/error-report.h" +#include "qemu/memfd.h" +#include "qapi/error.h" +#include "qapi/type-helpers.h" +#include "io/channel-file.h" +#include "io/channel-socket.h" +#include "block/block-global-state.h" +#include "qemu/main-loop.h" +#include "migration/cpr.h" +#include "migration/qemu-file.h" +#include "migration/migration.h" +#include "migration/misc.h" +#include "migration/vmstate.h" +#include "system/runstate.h" +#include "trace.h" + +#define CPR_EXEC_STATE_NAME "QEMU_CPR_EXEC_STATE" + +static QEMUFile *qemu_file_new_fd_input(int fd, const char *name) +{ + g_autoptr(QIOChannelFile) fioc = qio_channel_file_new_fd(fd); + QIOChannel *ioc = QIO_CHANNEL(fioc); + qio_channel_set_name(ioc, name); + return qemu_file_new_input(ioc); +} + +static QEMUFile *qemu_file_new_fd_output(int fd, const char *name) +{ + g_autoptr(QIOChannelFile) fioc = qio_channel_file_new_fd(fd); + QIOChannel *ioc = QIO_CHANNEL(fioc); + qio_channel_set_name(ioc, name); + return qemu_file_new_output(ioc); +} + +void cpr_exec_persist_state(QEMUFile *f) +{ + QIOChannelFile *fioc = QIO_CHANNEL_FILE(qemu_file_get_ioc(f)); + int mfd = dup(fioc->fd); + char val[16]; + + /* Remember mfd in environment for post-exec load */ + qemu_clear_cloexec(mfd); + snprintf(val, sizeof(val), "%d", mfd); + g_setenv(CPR_EXEC_STATE_NAME, val, 1); +} + +static int cpr_exec_find_state(void) +{ + const char *val = g_getenv(CPR_EXEC_STATE_NAME); + int mfd; + + assert(val); + g_unsetenv(CPR_EXEC_STATE_NAME); + assert(!qemu_strtoi(val, NULL, 10, &mfd)); + return mfd; +} + +bool cpr_exec_has_state(void) +{ + return g_getenv(CPR_EXEC_STATE_NAME) != NULL; +} + +void cpr_exec_unpersist_state(void) +{ + int mfd; + const char *val = g_getenv(CPR_EXEC_STATE_NAME); + + g_unsetenv(CPR_EXEC_STATE_NAME); + assert(val); + assert(!qemu_strtoi(val, NULL, 10, &mfd)); + close(mfd); +} + +QEMUFile *cpr_exec_output(Error **errp) +{ + int mfd; + +#ifdef CONFIG_LINUX + mfd = qemu_memfd_create(CPR_EXEC_STATE_NAME, 0, false, 0, 0, errp); +#else + mfd = -1; +#endif + + if (mfd < 0) { + return NULL; + } + + return qemu_file_new_fd_output(mfd, CPR_EXEC_STATE_NAME); +} + +QEMUFile *cpr_exec_input(Error **errp) +{ + int mfd = cpr_exec_find_state(); + + lseek(mfd, 0, SEEK_SET); + return qemu_file_new_fd_input(mfd, CPR_EXEC_STATE_NAME); +} + +static bool preserve_fd(int fd) +{ + qemu_clear_cloexec(fd); + return true; +} + +static bool unpreserve_fd(int fd) +{ + qemu_set_cloexec(fd); + return true; +} + +static void cpr_exec_preserve_fds(void) +{ + cpr_walk_fd(preserve_fd); +} + +void cpr_exec_unpreserve_fds(void) +{ + cpr_walk_fd(unpreserve_fd); +} + +static void cpr_exec_cb(void *opaque) +{ + MigrationState *s = migrate_get_current(); + char **argv = strv_from_str_list(s->parameters.cpr_exec_command); + Error *err = NULL; + + /* + * Clear the close-on-exec flag for all preserved fd's. We cannot do so + * earlier because they should not persist across miscellaneous fork and + * exec calls that are performed during normal operation. + */ + cpr_exec_preserve_fds(); + + trace_cpr_exec(); + execvp(argv[0], argv); + + /* + * exec should only fail if argv[0] is bogus, or has a permissions problem, + * or the system is very short on resources. + */ + g_strfreev(argv); + cpr_exec_unpreserve_fds(); + + error_setg_errno(&err, errno, "execvp %s failed", argv[0]); + error_report_err(error_copy(err)); + migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED); + migrate_set_error(s, err); + + /* Note, we can go from state COMPLETED to FAILED */ + migration_call_notifiers(s, MIG_EVENT_PRECOPY_FAILED, NULL); + + err = NULL; + if (!migration_block_activate(&err)) { + /* error was already reported */ + error_free(err); + return; + } + + if (runstate_is_live(s->vm_old_state)) { + vm_start(); + } +} + +static int cpr_exec_notifier(NotifierWithReturn *notifier, MigrationEvent *e, + Error **errp) +{ + MigrationState *s = migrate_get_current(); + + if (e->type == MIG_EVENT_PRECOPY_DONE) { + QEMUBH *cpr_exec_bh = qemu_bh_new(cpr_exec_cb, NULL); + assert(s->state == MIGRATION_STATUS_COMPLETED); + qemu_bh_schedule(cpr_exec_bh); + qemu_notify_event(); + } else if (e->type == MIG_EVENT_PRECOPY_FAILED) { + cpr_exec_unpersist_state(); + } + return 0; +} + +void cpr_exec_init(void) +{ + static NotifierWithReturn exec_notifier; + + migration_add_notifier_mode(&exec_notifier, cpr_exec_notifier, + MIG_MODE_CPR_EXEC); +} diff --git a/migration/cpr.c b/migration/cpr.c index 9848a21ea6..22dbac7c72 100644 --- a/migration/cpr.c +++ b/migration/cpr.c @@ -6,6 +6,7 @@ */ #include "qemu/osdep.h" +#include "qemu/error-report.h" #include "qapi/error.h" #include "qemu/error-report.h" #include "hw/vfio/vfio-device.h" @@ -122,6 +123,19 @@ int cpr_open_fd(const char *path, int flags, const char *name, int id, return fd; } +bool cpr_walk_fd(cpr_walk_fd_cb cb) +{ + CprFd *elem; + + QLIST_FOREACH(elem, &cpr_state.fds, next) { + g_assert(elem->fd >= 0); + if (!cb(elem->fd)) { + return false; + } + } + return true; +} + /*************************************************************************/ static const VMStateDescription vmstate_cpr_state = { .name = CPR_STATE, @@ -173,6 +187,8 @@ int cpr_state_save(MigrationChannel *channel, Error **errp) if (mode == MIG_MODE_CPR_TRANSFER) { g_assert(channel); f = cpr_transfer_output(channel, errp); + } else if (mode == MIG_MODE_CPR_EXEC) { + f = cpr_exec_output(errp); } else { return 0; } @@ -183,13 +199,16 @@ int cpr_state_save(MigrationChannel *channel, Error **errp) qemu_put_be32(f, QEMU_CPR_FILE_MAGIC); qemu_put_be32(f, QEMU_CPR_FILE_VERSION); - ret = vmstate_save_state(f, &vmstate_cpr_state, &cpr_state, 0); + ret = vmstate_save_state(f, &vmstate_cpr_state, &cpr_state, 0, errp); if (ret) { - error_setg(errp, "vmstate_save_state error %d", ret); qemu_fclose(f); return ret; } + if (migrate_mode() == MIG_MODE_CPR_EXEC) { + cpr_exec_persist_state(f); + } + /* * Close the socket only partially so we can later detect when the other * end closes by getting a HUP event. @@ -208,7 +227,13 @@ int cpr_state_load(MigrationChannel *channel, Error **errp) QEMUFile *f; MigMode mode = 0; - if (channel) { + if (cpr_exec_has_state()) { + mode = MIG_MODE_CPR_EXEC; + f = cpr_exec_input(errp); + if (channel) { + warn_report("ignoring cpr channel for migration mode cpr-exec"); + } + } else if (channel) { mode = MIG_MODE_CPR_TRANSFER; cpr_set_incoming_mode(mode); f = cpr_transfer_input(channel, errp); @@ -220,6 +245,7 @@ int cpr_state_load(MigrationChannel *channel, Error **errp) } trace_cpr_state_load(MigMode_str(mode)); + cpr_set_incoming_mode(mode); v = qemu_get_be32(f); if (v != QEMU_CPR_FILE_MAGIC) { @@ -234,13 +260,17 @@ int cpr_state_load(MigrationChannel *channel, Error **errp) return -ENOTSUP; } - ret = vmstate_load_state(f, &vmstate_cpr_state, &cpr_state, 1); + ret = vmstate_load_state(f, &vmstate_cpr_state, &cpr_state, 1, errp); if (ret) { - error_setg(errp, "vmstate_load_state error %d", ret); qemu_fclose(f); return ret; } + if (migrate_mode() == MIG_MODE_CPR_EXEC) { + /* Set cloexec to prevent fd leaks from fork until the next cpr-exec */ + cpr_exec_unpreserve_fds(); + } + /* * Let the caller decide when to close the socket (and generate a HUP event * for the sending side). @@ -261,7 +291,7 @@ void cpr_state_close(void) bool cpr_incoming_needed(void *opaque) { MigMode mode = migrate_mode(); - return mode == MIG_MODE_CPR_TRANSFER; + return mode == MIG_MODE_CPR_TRANSFER || mode == MIG_MODE_CPR_EXEC; } /* diff --git a/migration/meson.build b/migration/meson.build index 0f71544a82..16909d54c5 100644 --- a/migration/meson.build +++ b/migration/meson.build @@ -16,6 +16,7 @@ system_ss.add(files( 'channel-block.c', 'cpr.c', 'cpr-transfer.c', + 'cpr-exec.c', 'cpu-throttle.c', 'dirtyrate.c', 'exec.c', diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c index 0fc21f0647..847d18faaa 100644 --- a/migration/migration-hmp-cmds.c +++ b/migration/migration-hmp-cmds.c @@ -306,6 +306,18 @@ void hmp_info_migrate_capabilities(Monitor *mon, const QDict *qdict) qapi_free_MigrationCapabilityStatusList(caps); } +static void monitor_print_cpr_exec_command(Monitor *mon, strList *args) +{ + monitor_printf(mon, "%s:", + MigrationParameter_str(MIGRATION_PARAMETER_CPR_EXEC_COMMAND)); + + while (args) { + monitor_printf(mon, " %s", args->value); + args = args->next; + } + monitor_printf(mon, "\n"); +} + void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) { MigrationParameters *params; @@ -353,6 +365,10 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) monitor_printf(mon, "%s: '%s'\n", MigrationParameter_str(MIGRATION_PARAMETER_TLS_HOSTNAME), params->tls_hostname); + assert(params->tls_authz); + monitor_printf(mon, "%s: '%s'\n", + MigrationParameter_str(MIGRATION_PARAMETER_TLS_AUTHZ), + params->tls_authz); assert(params->has_max_bandwidth); monitor_printf(mon, "%s: %" PRIu64 " bytes/second\n", MigrationParameter_str(MIGRATION_PARAMETER_MAX_BANDWIDTH), @@ -361,6 +377,10 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) monitor_printf(mon, "%s: %" PRIu64 " bytes/second\n", MigrationParameter_str(MIGRATION_PARAMETER_AVAIL_SWITCHOVER_BANDWIDTH), params->avail_switchover_bandwidth); + assert(params->has_max_postcopy_bandwidth); + monitor_printf(mon, "%s: %" PRIu64 " bytes/second\n", + MigrationParameter_str(MIGRATION_PARAMETER_MAX_POSTCOPY_BANDWIDTH), + params->max_postcopy_bandwidth); assert(params->has_downtime_limit); monitor_printf(mon, "%s: %" PRIu64 " ms\n", MigrationParameter_str(MIGRATION_PARAMETER_DOWNTIME_LIMIT), @@ -383,12 +403,6 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) monitor_printf(mon, "%s: %" PRIu64 " bytes\n", MigrationParameter_str(MIGRATION_PARAMETER_XBZRLE_CACHE_SIZE), params->xbzrle_cache_size); - monitor_printf(mon, "%s: %" PRIu64 "\n", - MigrationParameter_str(MIGRATION_PARAMETER_MAX_POSTCOPY_BANDWIDTH), - params->max_postcopy_bandwidth); - monitor_printf(mon, "%s: '%s'\n", - MigrationParameter_str(MIGRATION_PARAMETER_TLS_AUTHZ), - params->tls_authz); if (params->has_block_bitmap_mapping) { const BitmapMigrationNodeAliasList *bmnal; @@ -435,6 +449,9 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) MIGRATION_PARAMETER_DIRECT_IO), params->direct_io ? "on" : "off"); } + + assert(params->has_cpr_exec_command); + monitor_print_cpr_exec_command(mon, params->cpr_exec_command); } qapi_free_MigrationParameters(params); @@ -716,6 +733,21 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict) p->has_direct_io = true; visit_type_bool(v, param, &p->direct_io, &err); break; + case MIGRATION_PARAMETER_CPR_EXEC_COMMAND: { + g_autofree char **strv = NULL; + g_autoptr(GError) gerr = NULL; + strList **tail = &p->cpr_exec_command; + + if (!g_shell_parse_argv(valuestr, NULL, &strv, &gerr)) { + error_setg(&err, "%s", gerr->message); + break; + } + for (int i = 0; strv[i]; i++) { + QAPI_LIST_APPEND(tail, strv[i]); + } + p->has_cpr_exec_command = true; + break; + } default: g_assert_not_reached(); } diff --git a/migration/migration.c b/migration/migration.c index e1ac4d73c2..a63b46bbef 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 { @@ -337,6 +333,7 @@ void migration_object_init(void) ram_mig_init(); dirty_bitmap_mig_init(); + cpr_exec_init(); /* Initialize cpu throttle timers */ cpu_throttle_init(); @@ -623,22 +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; @@ -881,7 +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"); @@ -908,7 +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; } @@ -935,6 +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() */ @@ -1665,23 +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; } } @@ -1691,18 +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); } @@ -1762,7 +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) @@ -2111,6 +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; } @@ -2646,12 +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(); @@ -2660,8 +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 */ @@ -2872,8 +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(); @@ -4012,10 +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); } /* diff --git a/migration/multifd.c b/migration/multifd.c index b255778855..98873cee74 100644 --- a/migration/multifd.c +++ b/migration/multifd.c @@ -439,6 +439,39 @@ static void multifd_send_set_error(Error *err) } } +/* + * Gracefully shutdown IOChannels. Only needed for successful migrations on + * top of TLS channels. Otherwise it is same to qio_channel_shutdown(). + * + * A successful migration also guarantees multifd sender threads are + * properly flushed and halted. It is only safe to send BYE in the + * migration thread here when we know there's no other thread writting to + * the channel, because GnuTLS doesn't support concurrent writers. + */ +static void migration_ioc_shutdown_gracefully(QIOChannel *ioc) +{ + g_autoptr(Error) local_err = NULL; + + if (!migration_has_failed(migrate_get_current()) && + object_dynamic_cast((Object *)ioc, TYPE_QIO_CHANNEL_TLS)) { + + /* + * The destination expects the TLS session to always be properly + * terminated. This helps to detect a premature termination in the + * middle of the stream. Note that older QEMUs always break the + * connection on the source and the destination always sees + * GNUTLS_E_PREMATURE_TERMINATION. + */ + migration_tls_channel_end(ioc, &local_err); + if (local_err) { + warn_report("Failed to gracefully terminate TLS connection: %s", + error_get_pretty(local_err)); + } + } + + qio_channel_shutdown(ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); +} + static void multifd_send_terminate_threads(void) { int i; @@ -460,7 +493,7 @@ static void multifd_send_terminate_threads(void) qemu_sem_post(&p->sem); if (p->c) { - qio_channel_shutdown(p->c, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + migration_ioc_shutdown_gracefully(p->c); } } @@ -547,36 +580,6 @@ void multifd_send_shutdown(void) return; } - for (i = 0; i < migrate_multifd_channels(); i++) { - MultiFDSendParams *p = &multifd_send_state->params[i]; - - /* thread_created implies the TLS handshake has succeeded */ - if (p->tls_thread_created && p->thread_created) { - Error *local_err = NULL; - /* - * The destination expects the TLS session to always be - * properly terminated. This helps to detect a premature - * termination in the middle of the stream. Note that - * older QEMUs always break the connection on the source - * and the destination always sees - * GNUTLS_E_PREMATURE_TERMINATION. - */ - migration_tls_channel_end(p->c, &local_err); - - /* - * The above can return an error in case the migration has - * already failed. If the migration succeeded, errors are - * not expected but there's no need to kill the source. - */ - if (local_err && !migration_has_failed(migrate_get_current())) { - warn_report( - "multifd_send_%d: Failed to terminate TLS connection: %s", - p->id, error_get_pretty(local_err)); - break; - } - } - } - multifd_send_terminate_threads(); for (i = 0; i < migrate_multifd_channels(); i++) { diff --git a/migration/options.c b/migration/options.c index 4e923a2e07..5183112775 100644 --- a/migration/options.c +++ b/migration/options.c @@ -959,6 +959,9 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp) params->zero_page_detection = s->parameters.zero_page_detection; params->has_direct_io = true; params->direct_io = s->parameters.direct_io; + params->has_cpr_exec_command = true; + params->cpr_exec_command = QAPI_CLONE(strList, + s->parameters.cpr_exec_command); return params; } @@ -993,6 +996,7 @@ void migrate_params_init(MigrationParameters *params) params->has_mode = true; params->has_zero_page_detection = true; params->has_direct_io = true; + params->has_cpr_exec_command = true; } /* @@ -1297,6 +1301,10 @@ static void migrate_params_test_apply(MigrateSetParameters *params, if (params->has_direct_io) { dest->direct_io = params->direct_io; } + + if (params->has_cpr_exec_command) { + dest->cpr_exec_command = params->cpr_exec_command; + } } static void migrate_params_apply(MigrateSetParameters *params, Error **errp) @@ -1429,6 +1437,12 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp) if (params->has_direct_io) { s->parameters.direct_io = params->direct_io; } + + if (params->has_cpr_exec_command) { + qapi_free_strList(s->parameters.cpr_exec_command); + s->parameters.cpr_exec_command = + QAPI_CLONE(strList, params->cpr_exec_command); + } } void qmp_migrate_set_parameters(MigrateSetParameters *params, Error **errp) diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 0172172343..5471efb4f0 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -681,6 +681,7 @@ out: */ static int init_range(RAMBlock *rb, void *opaque) { + Error **errp = opaque; const char *block_name = qemu_ram_get_idstr(rb); void *host_addr = qemu_ram_get_host_addr(rb); ram_addr_t offset = qemu_ram_get_offset(rb); @@ -701,6 +702,8 @@ static int init_range(RAMBlock *rb, void *opaque) * (Precopy will just overwrite this data, so doesn't need the discard) */ if (ram_discard_range(block_name, 0, length)) { + error_setg(errp, "failed to discard RAM block %s len=%zu", + block_name, length); return -1; } @@ -749,9 +752,9 @@ static int cleanup_range(RAMBlock *rb, void *opaque) * postcopy later; must be called prior to any precopy. * called from arch_init's similarly named ram_postcopy_incoming_init */ -int postcopy_ram_incoming_init(MigrationIncomingState *mis) +int postcopy_ram_incoming_init(MigrationIncomingState *mis, Error **errp) { - if (foreach_not_ignored_block(init_range, NULL)) { + if (foreach_not_ignored_block(init_range, errp)) { return -1; } @@ -1703,7 +1706,7 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState *mis, Error **errp) return false; } -int postcopy_ram_incoming_init(MigrationIncomingState *mis) +int postcopy_ram_incoming_init(MigrationIncomingState *mis, Error **errp) { error_report("postcopy_ram_incoming_init: No OS support"); return -1; diff --git a/migration/postcopy-ram.h b/migration/postcopy-ram.h index 3852141d7e..ca19433b24 100644 --- a/migration/postcopy-ram.h +++ b/migration/postcopy-ram.h @@ -30,7 +30,7 @@ int postcopy_ram_incoming_setup(MigrationIncomingState *mis); * postcopy later; must be called prior to any precopy. * called from ram.c's similarly named ram_postcopy_incoming_init */ -int postcopy_ram_incoming_init(MigrationIncomingState *mis); +int postcopy_ram_incoming_init(MigrationIncomingState *mis, Error **errp); /* * At the end of a migration where postcopy_ram_incoming_init was called. diff --git a/migration/qemu-file.c b/migration/qemu-file.c index 0f4280df21..2d4ce174a5 100644 --- a/migration/qemu-file.c +++ b/migration/qemu-file.c @@ -125,7 +125,6 @@ static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable) /* * Result: QEMUFile* for a 'return path' for comms in the opposite direction - * NULL if not available */ QEMUFile *qemu_file_get_return_path(QEMUFile *f) { @@ -349,17 +348,13 @@ static ssize_t coroutine_mixed_fn qemu_fill_buffer(QEMUFile *f) } else { qio_channel_wait(f->ioc, G_IO_IN); } - } else if (len < 0) { - len = -EIO; } } while (len == QIO_CHANNEL_ERR_BLOCK); if (len > 0) { f->buf_size += len; - } else if (len == 0) { - qemu_file_set_error_obj(f, -EIO, local_error); } else { - qemu_file_set_error_obj(f, len, local_error); + qemu_file_set_error_obj(f, -EIO, local_error); } for (int i = 0; i < nfd; i++) { diff --git a/migration/ram.c b/migration/ram.c index 7208bc114f..9aac89638a 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -228,6 +228,7 @@ bool migrate_ram_is_ignored(RAMBlock *block) MigMode mode = migrate_mode(); return !qemu_ram_is_migratable(block) || mode == MIG_MODE_CPR_TRANSFER || + mode == MIG_MODE_CPR_EXEC || (migrate_ignore_shared() && qemu_ram_is_shared(block) && qemu_ram_is_named_file(block)); } @@ -3575,8 +3576,10 @@ static void colo_init_ram_state(void) * colo cache: this is for secondary VM, we cache the whole * memory of the secondary VM, it is need to hold the global lock * to call this helper. + * + * Returns zero to indicate success or -1 on error. */ -int colo_init_ram_cache(void) +int colo_init_ram_cache(Error **errp) { RAMBlock *block; @@ -3585,16 +3588,16 @@ int colo_init_ram_cache(void) block->colo_cache = qemu_anon_ram_alloc(block->used_length, NULL, false, false); if (!block->colo_cache) { - error_report("%s: Can't alloc memory for COLO cache of block %s," - "size 0x" RAM_ADDR_FMT, __func__, block->idstr, - block->used_length); + error_setg(errp, "Can't alloc memory for COLO cache of " + "block %s, size 0x" RAM_ADDR_FMT, + block->idstr, block->used_length); RAMBLOCK_FOREACH_NOT_IGNORED(block) { if (block->colo_cache) { qemu_anon_ram_free(block->colo_cache, block->used_length); block->colo_cache = NULL; } } - return -errno; + return -1; } if (!machine_dump_guest_core(current_machine)) { qemu_madvise(block->colo_cache, block->used_length, @@ -3716,9 +3719,9 @@ static int ram_load_cleanup(void *opaque) * postcopy-ram. postcopy-ram's similarly names * postcopy_ram_incoming_init does the work. */ -int ram_postcopy_incoming_init(MigrationIncomingState *mis) +int ram_postcopy_incoming_init(MigrationIncomingState *mis, Error **errp) { - return postcopy_ram_incoming_init(mis); + return postcopy_ram_incoming_init(mis, errp); } /** diff --git a/migration/ram.h b/migration/ram.h index 921c39a2c5..24cd0bf585 100644 --- a/migration/ram.h +++ b/migration/ram.h @@ -86,7 +86,7 @@ void ram_postcopy_migrated_memory_release(MigrationState *ms); void ram_postcopy_send_discard_bitmap(MigrationState *ms); /* For incoming postcopy discard */ int ram_discard_range(const char *block_name, uint64_t start, size_t length); -int ram_postcopy_incoming_init(MigrationIncomingState *mis); +int ram_postcopy_incoming_init(MigrationIncomingState *mis, Error **errp); int ram_load_postcopy(QEMUFile *f, int channel); void ram_handle_zero(void *host, uint64_t size); @@ -109,7 +109,7 @@ void ramblock_set_file_bmap_atomic(RAMBlock *block, ram_addr_t offset, bool set); /* ram cache */ -int colo_init_ram_cache(void); +int colo_init_ram_cache(Error **errp); void colo_flush_ram_cache(void); void colo_release_ram_cache(void); void colo_incoming_start_dirty_log(void); diff --git a/migration/savevm.c b/migration/savevm.c index abe0547f9b..7b35ec4dd0 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -963,13 +963,20 @@ void vmstate_unregister(VMStateIf *obj, const VMStateDescription *vmsd, } } -static int vmstate_load(QEMUFile *f, SaveStateEntry *se) +static int vmstate_load(QEMUFile *f, SaveStateEntry *se, Error **errp) { + int ret; trace_vmstate_load(se->idstr, se->vmsd ? se->vmsd->name : "(old)"); if (!se->vmsd) { /* Old style */ - return se->ops->load_state(f, se->opaque, se->load_version_id); + ret = se->ops->load_state(f, se->opaque, se->load_version_id); + if (ret < 0) { + error_setg(errp, "Failed to load vmstate version_id: %d, ret: %d", + se->load_version_id, ret); + } + return ret; } - return vmstate_load_state(f, se->vmsd, se->opaque, se->load_version_id); + return vmstate_load_state(f, se->vmsd, se->opaque, se->load_version_id, + errp); } static void vmstate_save_old_style(QEMUFile *f, SaveStateEntry *se, @@ -1049,8 +1056,8 @@ static int vmstate_save(QEMUFile *f, SaveStateEntry *se, JSONWriter *vmdesc, if (!se->vmsd) { vmstate_save_old_style(f, se, vmdesc); } else { - ret = vmstate_save_state_with_err(f, se->vmsd, se->opaque, vmdesc, - errp); + ret = vmstate_save_state(f, se->vmsd, se->opaque, vmdesc, + errp); if (ret) { return ret; } @@ -1278,6 +1285,7 @@ void qemu_savevm_state_header(QEMUFile *f) { MigrationState *s = migrate_get_current(); JSONWriter *vmdesc = s->vmdesc; + Error *local_err = NULL; trace_savevm_state_header(); qemu_put_be32(f, QEMU_VM_FILE_MAGIC); @@ -1296,7 +1304,11 @@ void qemu_savevm_state_header(QEMUFile *f) json_writer_start_object(vmdesc, "configuration"); } - vmstate_save_state(f, &vmstate_configuration, &savevm_state, vmdesc); + vmstate_save_state(f, &vmstate_configuration, &savevm_state, + vmdesc, &local_err); + if (local_err) { + error_report_err(local_err); + } if (vmdesc) { json_writer_end_object(vmdesc); @@ -1905,39 +1917,39 @@ enum LoadVMExitCodes { * quickly. */ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis, - uint16_t len) + uint16_t len, Error **errp) { PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_ADVISE); uint64_t remote_pagesize_summary, local_pagesize_summary, remote_tps; size_t page_size = qemu_target_page_size(); - Error *local_err = NULL; trace_loadvm_postcopy_handle_advise(); if (ps != POSTCOPY_INCOMING_NONE) { - error_report("CMD_POSTCOPY_ADVISE in wrong postcopy state (%d)", ps); + error_setg(errp, "CMD_POSTCOPY_ADVISE in wrong postcopy state (%d)", + ps); return -1; } switch (len) { case 0: if (migrate_postcopy_ram()) { - error_report("RAM postcopy is enabled but have 0 byte advise"); + error_setg(errp, "RAM postcopy is enabled but have 0 byte advise"); return -EINVAL; } return 0; case 8 + 8: if (!migrate_postcopy_ram()) { - error_report("RAM postcopy is disabled but have 16 byte advise"); + error_setg(errp, + "RAM postcopy is disabled but have 16 byte advise"); return -EINVAL; } break; default: - error_report("CMD_POSTCOPY_ADVISE invalid length (%d)", len); + error_setg(errp, "CMD_POSTCOPY_ADVISE invalid length (%d)", len); return -EINVAL; } - if (!postcopy_ram_supported_by_host(mis, &local_err)) { - error_report_err(local_err); + if (!postcopy_ram_supported_by_host(mis, errp)) { postcopy_state_set(POSTCOPY_INCOMING_NONE); return -1; } @@ -1960,9 +1972,10 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis, * also fails when passed to an older qemu that doesn't * do huge pages. */ - error_report("Postcopy needs matching RAM page sizes (s=%" PRIx64 - " d=%" PRIx64 ")", - remote_pagesize_summary, local_pagesize_summary); + error_setg(errp, + "Postcopy needs matching RAM page sizes " + "(s=%" PRIx64 " d=%" PRIx64 ")", + remote_pagesize_summary, local_pagesize_summary); return -1; } @@ -1972,17 +1985,18 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis, * Again, some differences could be dealt with, but for now keep it * simple. */ - error_report("Postcopy needs matching target page sizes (s=%d d=%zd)", - (int)remote_tps, page_size); + error_setg(errp, + "Postcopy needs matching target page sizes (s=%d d=%zd)", + (int)remote_tps, page_size); return -1; } - if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_ADVISE, &local_err)) { - error_report_err(local_err); + if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_ADVISE, errp)) { return -1; } - if (ram_postcopy_incoming_init(mis)) { + if (ram_postcopy_incoming_init(mis, errp) < 0) { + error_prepend(errp, "Postcopy RAM incoming init failed: "); return -1; } @@ -1995,7 +2009,7 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis, * There can be 0..many of these messages, each encoding multiple pages. */ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, - uint16_t len) + uint16_t len, Error **errp) { int tmp; char ramid[256]; @@ -2008,6 +2022,7 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, /* 1st discard */ tmp = postcopy_ram_prepare_discard(mis); if (tmp) { + error_setg(errp, "Failed to prepare for RAM discard: %d", tmp); return tmp; } break; @@ -2017,8 +2032,9 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, break; default: - error_report("CMD_POSTCOPY_RAM_DISCARD in wrong postcopy state (%d)", - ps); + error_setg(errp, + "CMD_POSTCOPY_RAM_DISCARD in wrong postcopy state (%d)", + ps); return -1; } /* We're expecting a @@ -2027,29 +2043,30 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, * then at least 1 16 byte chunk */ if (len < (1 + 1 + 1 + 1 + 2 * 8)) { - error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len); + error_setg(errp, "CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len); return -1; } tmp = qemu_get_byte(mis->from_src_file); if (tmp != postcopy_ram_discard_version) { - error_report("CMD_POSTCOPY_RAM_DISCARD invalid version (%d)", tmp); + error_setg(errp, "CMD_POSTCOPY_RAM_DISCARD invalid version (%d)", tmp); return -1; } if (!qemu_get_counted_string(mis->from_src_file, ramid)) { - error_report("CMD_POSTCOPY_RAM_DISCARD Failed to read RAMBlock ID"); + error_setg(errp, + "CMD_POSTCOPY_RAM_DISCARD Failed to read RAMBlock ID"); return -1; } tmp = qemu_get_byte(mis->from_src_file); if (tmp != 0) { - error_report("CMD_POSTCOPY_RAM_DISCARD missing nil (%d)", tmp); + error_setg(errp, "CMD_POSTCOPY_RAM_DISCARD missing nil (%d)", tmp); return -1; } len -= 3 + strlen(ramid); if (len % 16) { - error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len); + error_setg(errp, "CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len); return -1; } trace_loadvm_postcopy_ram_handle_discard_header(ramid, len); @@ -2061,6 +2078,7 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, len -= 16; int ret = ram_discard_range(ramid, start_addr, block_length); if (ret) { + error_setg(errp, "Failed to discard RAM range %s: %d", ramid, ret); return ret; } } @@ -2082,6 +2100,7 @@ static void *postcopy_ram_listen_thread(void *opaque) QEMUFile *f = mis->from_src_file; int load_res; MigrationState *migr = migrate_get_current(); + Error *local_err = NULL; object_ref(OBJECT(migr)); @@ -2098,7 +2117,7 @@ static void *postcopy_ram_listen_thread(void *opaque) 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); + load_res = qemu_loadvm_state_main(f, mis, &local_err); /* * This is tricky, but, mis->from_src_file can change after it @@ -2124,7 +2143,10 @@ static void *postcopy_ram_listen_thread(void *opaque) __func__, load_res); load_res = 0; /* prevent further exit() */ } else { - error_report("%s: loadvm failed: %d", __func__, load_res); + error_prepend(&local_err, + "loadvm failed during postcopy: %d: ", load_res); + migrate_set_error(migr, local_err); + error_report_err(local_err); migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE, MIGRATION_STATUS_FAILED); } @@ -2172,15 +2194,16 @@ static void *postcopy_ram_listen_thread(void *opaque) } /* After this message we must be able to immediately receive postcopy data */ -static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) +static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis, + Error **errp) { PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_LISTENING); - Error *local_err = NULL; trace_loadvm_postcopy_handle_listen("enter"); if (ps != POSTCOPY_INCOMING_ADVISE && ps != POSTCOPY_INCOMING_DISCARD) { - error_report("CMD_POSTCOPY_LISTEN in wrong postcopy state (%d)", ps); + error_setg(errp, + "CMD_POSTCOPY_LISTEN in wrong postcopy state (%d)", ps); return -1; } if (ps == POSTCOPY_INCOMING_ADVISE) { @@ -2203,14 +2226,14 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) if (migrate_postcopy_ram()) { if (postcopy_ram_incoming_setup(mis)) { postcopy_ram_incoming_cleanup(mis); + error_setg(errp, "Failed to setup incoming postcopy RAM blocks"); return -1; } } trace_loadvm_postcopy_handle_listen("after uffd"); - if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_LISTEN, &local_err)) { - error_report_err(local_err); + if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_LISTEN, errp)) { return -1; } @@ -2263,13 +2286,13 @@ static void loadvm_postcopy_handle_run_bh(void *opaque) } /* After all discards we can start running and asking for pages */ -static int loadvm_postcopy_handle_run(MigrationIncomingState *mis) +static int loadvm_postcopy_handle_run(MigrationIncomingState *mis, Error **errp) { PostcopyState ps = postcopy_state_get(); trace_loadvm_postcopy_handle_run(); if (ps != POSTCOPY_INCOMING_LISTENING) { - error_report("CMD_POSTCOPY_RUN in wrong postcopy state (%d)", ps); + error_setg(errp, "CMD_POSTCOPY_RUN in wrong postcopy state (%d)", ps); return -1; } @@ -2327,12 +2350,12 @@ static void migrate_send_rp_req_pages_pending(MigrationIncomingState *mis) } } -static int loadvm_postcopy_handle_resume(MigrationIncomingState *mis) +static void loadvm_postcopy_handle_resume(MigrationIncomingState *mis) { if (mis->state != MIGRATION_STATUS_POSTCOPY_RECOVER) { - error_report("%s: illegal resume received", __func__); + warn_report("%s: illegal resume received", __func__); /* Don't fail the load, only for this. */ - return 0; + return; } /* @@ -2384,8 +2407,6 @@ static int loadvm_postcopy_handle_resume(MigrationIncomingState *mis) /* Kick the fast ram load thread too */ qemu_sem_post(&mis->postcopy_pause_sem_fast_load); } - - return 0; } /** @@ -2398,7 +2419,7 @@ static int loadvm_postcopy_handle_resume(MigrationIncomingState *mis) * Returns: Negative values on error * */ -static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis) +static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis, Error **errp) { int ret; size_t length; @@ -2408,7 +2429,7 @@ static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis) trace_loadvm_handle_cmd_packaged(length); if (length > MAX_VM_CMD_PACKAGED_SIZE) { - error_report("Unreasonably large packaged state: %zu", length); + error_setg(errp, "Unreasonably large packaged state: %zu", length); return -1; } @@ -2419,8 +2440,8 @@ static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis) length); if (ret != length) { object_unref(OBJECT(bioc)); - error_report("CMD_PACKAGED: Buffer receive fail ret=%d length=%zu", - ret, length); + error_setg(errp, "CMD_PACKAGED: Buffer receive fail ret=%d length=%zu", + ret, length); return (ret < 0) ? ret : -EAGAIN; } bioc->usage += length; @@ -2449,7 +2470,7 @@ static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis) qemu_coroutine_yield(); } while (1); - ret = qemu_loadvm_state_main(packf, mis); + ret = qemu_loadvm_state_main(packf, mis, errp); trace_loadvm_handle_cmd_packaged_main(ret); qemu_fclose(packf); object_unref(OBJECT(bioc)); @@ -2464,32 +2485,35 @@ static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis) * len (1 byte) + ramblock_name (<255 bytes) */ static int loadvm_handle_recv_bitmap(MigrationIncomingState *mis, - uint16_t len) + uint16_t len, Error **errp) { QEMUFile *file = mis->from_src_file; RAMBlock *rb; char block_name[256]; size_t cnt; + int ret; cnt = qemu_get_counted_string(file, block_name); if (!cnt) { - error_report("%s: failed to read block name", __func__); + error_setg(errp, "failed to read block name"); return -EINVAL; } /* Validate before using the data */ - if (qemu_file_get_error(file)) { - return qemu_file_get_error(file); + ret = qemu_file_get_error(file); + if (ret < 0) { + error_setg(errp, "loadvm failed: stream error: %d", ret); + return ret; } if (len != cnt + 1) { - error_report("%s: invalid payload length (%d)", __func__, len); + error_setg(errp, "invalid payload length (%d)", len); return -EINVAL; } rb = qemu_ram_block_by_name(block_name); if (!rb) { - error_report("%s: block '%s' not found", __func__, block_name); + error_setg(errp, "block '%s' not found", block_name); return -EINVAL; } @@ -2500,20 +2524,26 @@ static int loadvm_handle_recv_bitmap(MigrationIncomingState *mis, return 0; } -static int loadvm_process_enable_colo(MigrationIncomingState *mis) +static int loadvm_process_enable_colo(MigrationIncomingState *mis, + Error **errp) { - int ret = migration_incoming_enable_colo(); + ERRP_GUARD(); + int ret; - if (!ret) { - ret = colo_init_ram_cache(); - if (ret) { - migration_incoming_disable_colo(); - } + ret = migration_incoming_enable_colo(errp); + if (ret < 0) { + return ret; + } + + ret = colo_init_ram_cache(errp); + if (ret) { + error_prepend(errp, "failed to init colo RAM cache: %d: ", ret); + migration_incoming_disable_colo(); } return ret; } -static int loadvm_postcopy_handle_switchover_start(void) +static int loadvm_postcopy_handle_switchover_start(Error **errp) { SaveStateEntry *se; @@ -2526,6 +2556,7 @@ static int loadvm_postcopy_handle_switchover_start(void) ret = se->ops->switchover_start(se->opaque); if (ret < 0) { + error_setg(errp, "Switchover start failed: %d", ret); return ret; } } @@ -2539,32 +2570,37 @@ static int loadvm_postcopy_handle_switchover_start(void) * LOADVM_QUIT All good, but exit the loop * <0 Error */ -static int loadvm_process_command(QEMUFile *f) +static int loadvm_process_command(QEMUFile *f, Error **errp) { MigrationIncomingState *mis = migration_incoming_get_current(); uint16_t cmd; uint16_t len; uint32_t tmp32; + int ret; cmd = qemu_get_be16(f); len = qemu_get_be16(f); /* Check validity before continue processing of cmds */ - if (qemu_file_get_error(f)) { - return qemu_file_get_error(f); + ret = qemu_file_get_error(f); + if (ret) { + error_setg(errp, + "Failed to load VM process command: stream error: %d", + ret); + return ret; } if (cmd >= MIG_CMD_MAX || cmd == MIG_CMD_INVALID) { - error_report("MIG_CMD 0x%x unknown (len 0x%x)", cmd, len); + error_setg(errp, "MIG_CMD 0x%x unknown (len 0x%x)", cmd, len); return -EINVAL; } trace_loadvm_process_command(mig_cmd_args[cmd].name, len); if (mig_cmd_args[cmd].len != -1 && mig_cmd_args[cmd].len != len) { - error_report("%s received with bad length - expecting %zu, got %d", - mig_cmd_args[cmd].name, - (size_t)mig_cmd_args[cmd].len, len); + error_setg(errp, "%s received with bad length - expecting %zu, got %d", + mig_cmd_args[cmd].name, + (size_t)mig_cmd_args[cmd].len, len); return -ERANGE; } @@ -2576,10 +2612,6 @@ static int loadvm_process_command(QEMUFile *f) return 0; } mis->to_src_file = qemu_file_get_return_path(f); - if (!mis->to_src_file) { - error_report("CMD_OPEN_RETURN_PATH failed"); - return -1; - } /* * Switchover ack is enabled but no device uses it, so send an ACK to @@ -2587,11 +2619,10 @@ static int loadvm_process_command(QEMUFile *f) * been created. */ if (migrate_switchover_ack() && !mis->switchover_ack_pending_num) { - int ret = migrate_send_rp_switchover_ack(mis); + ret = migrate_send_rp_switchover_ack(mis); if (ret) { - error_report( - "Could not send switchover ack RP MSG, err %d (%s)", ret, - strerror(-ret)); + error_setg_errno(errp, -ret, + "Could not send switchover ack RP MSG"); return ret; } } @@ -2601,39 +2632,40 @@ static int loadvm_process_command(QEMUFile *f) tmp32 = qemu_get_be32(f); trace_loadvm_process_command_ping(tmp32); if (!mis->to_src_file) { - error_report("CMD_PING (0x%x) received with no return path", - tmp32); + error_setg(errp, "CMD_PING (0x%x) received with no return path", + tmp32); return -1; } migrate_send_rp_pong(mis, tmp32); break; case MIG_CMD_PACKAGED: - return loadvm_handle_cmd_packaged(mis); + return loadvm_handle_cmd_packaged(mis, errp); case MIG_CMD_POSTCOPY_ADVISE: - return loadvm_postcopy_handle_advise(mis, len); + return loadvm_postcopy_handle_advise(mis, len, errp); case MIG_CMD_POSTCOPY_LISTEN: - return loadvm_postcopy_handle_listen(mis); + return loadvm_postcopy_handle_listen(mis, errp); case MIG_CMD_POSTCOPY_RUN: - return loadvm_postcopy_handle_run(mis); + return loadvm_postcopy_handle_run(mis, errp); case MIG_CMD_POSTCOPY_RAM_DISCARD: - return loadvm_postcopy_ram_handle_discard(mis, len); + return loadvm_postcopy_ram_handle_discard(mis, len, errp); case MIG_CMD_POSTCOPY_RESUME: - return loadvm_postcopy_handle_resume(mis); + loadvm_postcopy_handle_resume(mis); + return 0; case MIG_CMD_RECV_BITMAP: - return loadvm_handle_recv_bitmap(mis, len); + return loadvm_handle_recv_bitmap(mis, len, errp); case MIG_CMD_ENABLE_COLO: - return loadvm_process_enable_colo(mis); + return loadvm_process_enable_colo(mis, errp); case MIG_CMD_SWITCHOVER_START: - return loadvm_postcopy_handle_switchover_start(); + return loadvm_postcopy_handle_switchover_start(errp); } return 0; @@ -2683,8 +2715,9 @@ static bool check_section_footer(QEMUFile *f, SaveStateEntry *se) } static int -qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type) +qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type, Error **errp) { + ERRP_GUARD(); bool trace_downtime = (type == QEMU_VM_SECTION_FULL); uint32_t instance_id, version_id, section_id; int64_t start_ts, end_ts; @@ -2695,8 +2728,8 @@ qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type) /* Read section start */ section_id = qemu_get_be32(f); if (!qemu_get_counted_string(f, idstr)) { - error_report("Unable to read ID string for section %u", - section_id); + error_setg(errp, "Unable to read ID string for section %u", + section_id); return -EINVAL; } instance_id = qemu_get_be32(f); @@ -2704,8 +2737,7 @@ qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type) ret = qemu_file_get_error(f); if (ret) { - error_report("%s: Failed to read instance/version ID: %d", - __func__, ret); + error_setg(errp, "Failed to read instance/version ID: %d", ret); return ret; } @@ -2714,17 +2746,17 @@ qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type) /* Find savevm section */ se = find_se(idstr, instance_id); if (se == NULL) { - error_report("Unknown savevm section or instance '%s' %"PRIu32". " - "Make sure that your current VM setup matches your " - "saved VM setup, including any hotplugged devices", - idstr, instance_id); + error_setg(errp, "Unknown section or instance '%s' %"PRIu32". " + "Make sure that your current VM setup matches your " + "saved VM setup, including any hotplugged devices", + idstr, instance_id); return -EINVAL; } /* Validate version */ if (version_id > se->version_id) { - error_report("savevm: unsupported version %d for '%s' v%d", - version_id, idstr, se->version_id); + error_setg(errp, "unsupported version %d for '%s' v%d", + version_id, idstr, se->version_id); return -EINVAL; } se->load_version_id = version_id; @@ -2732,7 +2764,7 @@ qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type) /* Validate if it is a device's state */ if (xen_enabled() && se->is_ram) { - error_report("loadvm: %s RAM loading not allowed on Xen", idstr); + error_setg(errp, "loadvm: %s RAM loading not allowed on Xen", idstr); return -EINVAL; } @@ -2740,10 +2772,11 @@ qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type) start_ts = qemu_clock_get_us(QEMU_CLOCK_REALTIME); } - ret = vmstate_load(f, se); + ret = vmstate_load(f, se, errp); if (ret < 0) { - error_report("error while loading state for instance 0x%"PRIx32" of" - " device '%s'", instance_id, idstr); + error_prepend(errp, + "error while loading state for instance 0x%"PRIx32" of" + " device '%s': ", instance_id, idstr); return ret; } @@ -2754,6 +2787,8 @@ qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type) } if (!check_section_footer(f, se)) { + error_setg(errp, "Section footer error, section_id: %d", + section_id); return -EINVAL; } @@ -2761,7 +2796,7 @@ qemu_loadvm_section_start_full(QEMUFile *f, uint8_t type) } static int -qemu_loadvm_section_part_end(QEMUFile *f, uint8_t type) +qemu_loadvm_section_part_end(QEMUFile *f, uint8_t type, Error **errp) { bool trace_downtime = (type == QEMU_VM_SECTION_END); int64_t start_ts, end_ts; @@ -2773,8 +2808,7 @@ qemu_loadvm_section_part_end(QEMUFile *f, uint8_t type) ret = qemu_file_get_error(f); if (ret) { - error_report("%s: Failed to read section ID: %d", - __func__, ret); + error_setg(errp, "Failed to read section ID: %d", ret); return ret; } @@ -2785,7 +2819,7 @@ qemu_loadvm_section_part_end(QEMUFile *f, uint8_t type) } } if (se == NULL) { - error_report("Unknown savevm section %d", section_id); + error_setg(errp, "Unknown section %d", section_id); return -EINVAL; } @@ -2793,10 +2827,8 @@ qemu_loadvm_section_part_end(QEMUFile *f, uint8_t type) start_ts = qemu_clock_get_us(QEMU_CLOCK_REALTIME); } - ret = vmstate_load(f, se); + ret = vmstate_load(f, se, errp); if (ret < 0) { - error_report("error while loading state section id %d(%s)", - section_id, se->idstr); return ret; } @@ -2807,40 +2839,50 @@ qemu_loadvm_section_part_end(QEMUFile *f, uint8_t type) } if (!check_section_footer(f, se)) { + error_setg(errp, "Section footer error, section_id: %d", + section_id); return -EINVAL; } return 0; } -static int qemu_loadvm_state_header(QEMUFile *f) +static int qemu_loadvm_state_header(QEMUFile *f, Error **errp) { unsigned int v; int ret; v = qemu_get_be32(f); if (v != QEMU_VM_FILE_MAGIC) { - error_report("Not a migration stream"); + error_setg(errp, "Not a migration stream, magic: %x != %x", + v, QEMU_VM_FILE_MAGIC); return -EINVAL; } v = qemu_get_be32(f); if (v == QEMU_VM_FILE_VERSION_COMPAT) { - error_report("SaveVM v2 format is obsolete and don't work anymore"); + error_setg(errp, + "SaveVM v2 format is obsolete and no longer supported"); + return -ENOTSUP; } if (v != QEMU_VM_FILE_VERSION) { - error_report("Unsupported migration stream version"); + error_setg(errp, "Unsupported migration stream version, " + "file version %x != %x", + v, QEMU_VM_FILE_VERSION); return -ENOTSUP; } if (migrate_get_current()->send_configuration) { - if (qemu_get_byte(f) != QEMU_VM_CONFIGURATION) { - error_report("Configuration section missing"); + v = qemu_get_byte(f); + if (v != QEMU_VM_CONFIGURATION) { + error_setg(errp, "Configuration section missing, %x != %x", + v, QEMU_VM_CONFIGURATION); return -EINVAL; } - ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0); + ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0, + errp); if (ret) { return ret; } @@ -3028,8 +3070,10 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis) return true; } -int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) +int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis, + Error **errp) { + ERRP_GUARD(); uint8_t section_type; int ret = 0; @@ -3037,8 +3081,11 @@ retry: while (true) { section_type = qemu_get_byte(f); - ret = qemu_file_get_error_obj_any(f, mis->postcopy_qemufile_dst, NULL); + ret = qemu_file_get_error_obj_any(f, mis->postcopy_qemufile_dst, errp); if (ret) { + error_prepend(errp, + "Failed to load section ID: stream error: %d: ", + ret); break; } @@ -3046,20 +3093,20 @@ retry: switch (section_type) { case QEMU_VM_SECTION_START: case QEMU_VM_SECTION_FULL: - ret = qemu_loadvm_section_start_full(f, section_type); + ret = qemu_loadvm_section_start_full(f, section_type, errp); if (ret < 0) { goto out; } break; case QEMU_VM_SECTION_PART: case QEMU_VM_SECTION_END: - ret = qemu_loadvm_section_part_end(f, section_type); + ret = qemu_loadvm_section_part_end(f, section_type, errp); if (ret < 0) { goto out; } break; case QEMU_VM_COMMAND: - ret = loadvm_process_command(f); + ret = loadvm_process_command(f, errp); trace_qemu_loadvm_state_section_command(ret); if ((ret < 0) || (ret == LOADVM_QUIT)) { goto out; @@ -3069,7 +3116,7 @@ retry: /* This is the end of migration */ goto out; default: - error_report("Unknown savevm section type %d", section_type); + error_setg(errp, "Unknown section type %d", section_type); ret = -EINVAL; goto out; } @@ -3097,33 +3144,31 @@ out: migrate_postcopy_ram() && postcopy_pause_incoming(mis)) { /* Reset f to point to the newly created channel */ f = mis->from_src_file; + error_free_or_abort(errp); goto retry; } } return ret; } -int qemu_loadvm_state(QEMUFile *f) +int qemu_loadvm_state(QEMUFile *f, Error **errp) { MigrationState *s = migrate_get_current(); MigrationIncomingState *mis = migration_incoming_get_current(); - Error *local_err = NULL; int ret; - if (qemu_savevm_state_blocked(&local_err)) { - error_report_err(local_err); + if (qemu_savevm_state_blocked(errp)) { return -EINVAL; } qemu_loadvm_thread_pool_create(mis); - ret = qemu_loadvm_state_header(f); + ret = qemu_loadvm_state_header(f, errp); if (ret) { return ret; } - if (qemu_loadvm_state_setup(f, &local_err) != 0) { - error_report_err(local_err); + if (qemu_loadvm_state_setup(f, errp) != 0) { return -EINVAL; } @@ -3133,7 +3178,7 @@ int qemu_loadvm_state(QEMUFile *f) cpu_synchronize_all_pre_loadvm(); - ret = qemu_loadvm_state_main(f, mis); + ret = qemu_loadvm_state_main(f, mis, errp); qemu_event_set(&mis->main_thread_load_event); trace_qemu_loadvm_state_post_main(ret); @@ -3151,8 +3196,15 @@ int qemu_loadvm_state(QEMUFile *f) if (migrate_has_error(migrate_get_current()) || !qemu_loadvm_thread_pool_wait(s, mis)) { ret = -EINVAL; + error_setg(errp, + "Error while loading vmstate"); } else { ret = qemu_file_get_error(f); + if (ret < 0) { + error_setg(errp, + "Error while loading vmstate: stream error: %d", + ret); + } } } /* @@ -3201,15 +3253,14 @@ int qemu_loadvm_state(QEMUFile *f) return ret; } -int qemu_load_device_state(QEMUFile *f) +int qemu_load_device_state(QEMUFile *f, Error **errp) { MigrationIncomingState *mis = migration_incoming_get_current(); int ret; /* Load QEMU_VM_SECTION_FULL section */ - ret = qemu_loadvm_state_main(f, mis); + ret = qemu_loadvm_state_main(f, mis, errp); if (ret < 0) { - error_report("Failed to load device state: %d", ret); return ret; } @@ -3417,6 +3468,7 @@ void qmp_xen_save_devices_state(const char *filename, bool has_live, bool live, void qmp_xen_load_devices_state(const char *filename, Error **errp) { + ERRP_GUARD(); QEMUFile *f; QIOChannelFile *ioc; int ret; @@ -3438,10 +3490,10 @@ void qmp_xen_load_devices_state(const char *filename, Error **errp) f = qemu_file_new_input(QIO_CHANNEL(ioc)); object_unref(OBJECT(ioc)); - ret = qemu_loadvm_state(f); + ret = qemu_loadvm_state(f, errp); qemu_fclose(f); if (ret < 0) { - error_setg(errp, "loading Xen device state failed"); + error_prepend(errp, "loading Xen device state failed: "); } migration_incoming_state_destroy(); } @@ -3512,13 +3564,12 @@ bool load_snapshot(const char *name, const char *vmstate, ret = -EINVAL; goto err_drain; } - ret = qemu_loadvm_state(f); + ret = qemu_loadvm_state(f, errp); migration_incoming_state_destroy(); bdrv_drain_all_end(); if (ret < 0) { - error_setg(errp, "Error %d while loading VM state", ret); return false; } diff --git a/migration/savevm.h b/migration/savevm.h index 2d5e9c7166..c337e3e3d1 100644 --- a/migration/savevm.h +++ b/migration/savevm.h @@ -64,10 +64,11 @@ void qemu_savevm_send_colo_enable(QEMUFile *f); void qemu_savevm_live_state(QEMUFile *f); int qemu_save_device_state(QEMUFile *f); -int qemu_loadvm_state(QEMUFile *f); +int qemu_loadvm_state(QEMUFile *f, Error **errp); void qemu_loadvm_state_cleanup(MigrationIncomingState *mis); -int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis); -int qemu_load_device_state(QEMUFile *f); +int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis, + Error **errp); +int qemu_load_device_state(QEMUFile *f, Error **errp); int qemu_loadvm_approve_switchover(void); int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f, bool in_postcopy); diff --git a/migration/trace-events b/migration/trace-events index 706db97def..e8edd1fbba 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -354,6 +354,7 @@ cpr_state_save(const char *mode) "%s mode" cpr_state_load(const char *mode) "%s mode" cpr_transfer_input(const char *path) "%s" cpr_transfer_output(const char *path) "%s" +cpr_exec(void) "" # block-dirty-bitmap.c send_bitmap_header_enter(void) "" diff --git a/migration/vmstate-types.c b/migration/vmstate-types.c index 741a588b7e..4b01dc19c2 100644 --- a/migration/vmstate-types.c +++ b/migration/vmstate-types.c @@ -19,6 +19,7 @@ #include "qemu/error-report.h" #include "qemu/queue.h" #include "trace.h" +#include "qapi/error.h" /* bool */ @@ -321,6 +322,10 @@ static int get_fd(QEMUFile *f, void *pv, size_t size, const VMStateField *field) { int32_t *v = pv; + if (migrate_mode() == MIG_MODE_CPR_EXEC) { + qemu_get_sbe32s(f, v); + return 0; + } *v = qemu_file_get_fd(f); return 0; } @@ -329,6 +334,10 @@ static int put_fd(QEMUFile *f, void *pv, size_t size, const VMStateField *field, JSONWriter *vmdesc) { int32_t *v = pv; + if (migrate_mode() == MIG_MODE_CPR_EXEC) { + qemu_put_sbe32s(f, v); + return 0; + } return qemu_file_put_fd(f, *v); } @@ -543,13 +552,17 @@ static int get_tmp(QEMUFile *f, void *pv, size_t size, const VMStateField *field) { int ret; + Error *local_err = NULL; const VMStateDescription *vmsd = field->vmsd; int version_id = field->version_id; void *tmp = g_malloc(size); /* Writes the parent field which is at the start of the tmp */ *(void **)tmp = pv; - ret = vmstate_load_state(f, vmsd, tmp, version_id); + ret = vmstate_load_state(f, vmsd, tmp, version_id, &local_err); + if (ret < 0) { + error_report_err(local_err); + } g_free(tmp); return ret; } @@ -560,10 +573,14 @@ static int put_tmp(QEMUFile *f, void *pv, size_t size, const VMStateDescription *vmsd = field->vmsd; void *tmp = g_malloc(size); int ret; + Error *local_err = NULL; /* Writes the parent field which is at the start of the tmp */ *(void **)tmp = pv; - ret = vmstate_save_state(f, vmsd, tmp, vmdesc); + ret = vmstate_save_state(f, vmsd, tmp, vmdesc, &local_err); + if (ret) { + error_report_err(local_err); + } g_free(tmp); return ret; @@ -626,6 +643,7 @@ static int get_qtailq(QEMUFile *f, void *pv, size_t unused_size, const VMStateField *field) { int ret = 0; + Error *local_err = NULL; const VMStateDescription *vmsd = field->vmsd; /* size of a QTAILQ element */ size_t size = field->size; @@ -649,8 +667,9 @@ static int get_qtailq(QEMUFile *f, void *pv, size_t unused_size, while (qemu_get_byte(f)) { elm = g_malloc(size); - ret = vmstate_load_state(f, vmsd, elm, version_id); + ret = vmstate_load_state(f, vmsd, elm, version_id, &local_err); if (ret) { + error_report_err(local_err); return ret; } QTAILQ_RAW_INSERT_TAIL(pv, elm, entry_offset); @@ -669,13 +688,15 @@ static int put_qtailq(QEMUFile *f, void *pv, size_t unused_size, size_t entry_offset = field->start; void *elm; int ret; + Error *local_err = NULL; trace_put_qtailq(vmsd->name, vmsd->version_id); QTAILQ_RAW_FOREACH(elm, pv, entry_offset) { qemu_put_byte(f, true); - ret = vmstate_save_state(f, vmsd, elm, vmdesc); + ret = vmstate_save_state(f, vmsd, elm, vmdesc, &local_err); if (ret) { + error_report_err(local_err); return ret; } } @@ -704,6 +725,7 @@ static gboolean put_gtree_elem(gpointer key, gpointer value, gpointer data) struct put_gtree_data *capsule = (struct put_gtree_data *)data; QEMUFile *f = capsule->f; int ret; + Error *local_err = NULL; qemu_put_byte(f, true); @@ -711,16 +733,20 @@ static gboolean put_gtree_elem(gpointer key, gpointer value, gpointer data) if (!capsule->key_vmsd) { qemu_put_be64(f, (uint64_t)(uintptr_t)(key)); /* direct key */ } else { - ret = vmstate_save_state(f, capsule->key_vmsd, key, capsule->vmdesc); + ret = vmstate_save_state(f, capsule->key_vmsd, key, capsule->vmdesc, + &local_err); if (ret) { + error_report_err(local_err); capsule->ret = ret; return true; } } /* put the data */ - ret = vmstate_save_state(f, capsule->val_vmsd, value, capsule->vmdesc); + ret = vmstate_save_state(f, capsule->val_vmsd, value, capsule->vmdesc, + &local_err); if (ret) { + error_report_err(local_err); capsule->ret = ret; return true; } @@ -772,6 +798,7 @@ static int get_gtree(QEMUFile *f, void *pv, size_t unused_size, GTree *tree = *pval; void *key, *val; int ret = 0; + Error *local_err = NULL; /* in case of direct key, the key vmsd can be {}, ie. check fields */ if (!direct_key && version_id > key_vmsd->version_id) { @@ -803,18 +830,16 @@ static int get_gtree(QEMUFile *f, void *pv, size_t unused_size, key = (void *)(uintptr_t)qemu_get_be64(f); } else { key = g_malloc0(key_size); - ret = vmstate_load_state(f, key_vmsd, key, version_id); + ret = vmstate_load_state(f, key_vmsd, key, version_id, &local_err); if (ret) { - error_report("%s : failed to load %s (%d)", - field->name, key_vmsd->name, ret); + error_report_err(local_err); goto key_error; } } val = g_malloc0(val_size); - ret = vmstate_load_state(f, val_vmsd, val, version_id); + ret = vmstate_load_state(f, val_vmsd, val, version_id, &local_err); if (ret) { - error_report("%s : failed to load %s (%d)", - field->name, val_vmsd->name, ret); + error_report_err(local_err); goto val_error; } g_tree_insert(tree, key, val); @@ -851,14 +876,14 @@ static int put_qlist(QEMUFile *f, void *pv, size_t unused_size, size_t entry_offset = field->start; void *elm; int ret; + Error *local_err = NULL; trace_put_qlist(field->name, vmsd->name, vmsd->version_id); QLIST_RAW_FOREACH(elm, pv, entry_offset) { qemu_put_byte(f, true); - ret = vmstate_save_state(f, vmsd, elm, vmdesc); + ret = vmstate_save_state(f, vmsd, elm, vmdesc, &local_err); if (ret) { - error_report("%s: failed to save %s (%d)", field->name, - vmsd->name, ret); + error_report_err(local_err); return ret; } } @@ -872,6 +897,7 @@ static int get_qlist(QEMUFile *f, void *pv, size_t unused_size, const VMStateField *field) { int ret = 0; + Error *local_err = NULL; const VMStateDescription *vmsd = field->vmsd; /* size of a QLIST element */ size_t size = field->size; @@ -892,10 +918,9 @@ static int get_qlist(QEMUFile *f, void *pv, size_t unused_size, while (qemu_get_byte(f)) { elm = g_malloc(size); - ret = vmstate_load_state(f, vmsd, elm, version_id); + ret = vmstate_load_state(f, vmsd, elm, version_id, &local_err); if (ret) { - error_report("%s: failed to load %s (%d)", field->name, - vmsd->name, ret); + error_report_err(local_err); g_free(elm); return ret; } diff --git a/migration/vmstate.c b/migration/vmstate.c index 5feaa3244d..81eadde553 100644 --- a/migration/vmstate.c +++ b/migration/vmstate.c @@ -25,7 +25,7 @@ static int vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd, void *opaque, JSONWriter *vmdesc, Error **errp); static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd, - void *opaque); + void *opaque, Error **errp); /* Whether this field should exist for either save or load the VM? */ static bool @@ -132,29 +132,43 @@ static void vmstate_handle_alloc(void *ptr, const VMStateField *field, } int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd, - void *opaque, int version_id) + void *opaque, int version_id, Error **errp) { + ERRP_GUARD(); const VMStateField *field = vmsd->fields; int ret = 0; trace_vmstate_load_state(vmsd->name, version_id); if (version_id > vmsd->version_id) { - error_report("%s: incoming version_id %d is too new " - "for local version_id %d", - vmsd->name, version_id, vmsd->version_id); + error_setg(errp, "%s: incoming version_id %d is too new " + "for local version_id %d", + vmsd->name, version_id, vmsd->version_id); trace_vmstate_load_state_end(vmsd->name, "too new", -EINVAL); return -EINVAL; } if (version_id < vmsd->minimum_version_id) { - error_report("%s: incoming version_id %d is too old " - "for local minimum version_id %d", - vmsd->name, version_id, vmsd->minimum_version_id); + error_setg(errp, "%s: incoming version_id %d is too old " + "for local minimum version_id %d", + vmsd->name, version_id, vmsd->minimum_version_id); trace_vmstate_load_state_end(vmsd->name, "too old", -EINVAL); return -EINVAL; } - if (vmsd->pre_load) { + if (vmsd->pre_load_errp) { + ret = vmsd->pre_load_errp(opaque, errp); + if (ret < 0) { + error_prepend(errp, "pre load hook failed for: '%s', " + "version_id: %d, minimum version_id: %d, " + "ret: %d: ", vmsd->name, vmsd->version_id, + vmsd->minimum_version_id, ret); + return ret; + } + } else if (vmsd->pre_load) { ret = vmsd->pre_load(opaque); if (ret) { + error_setg(errp, "pre load hook failed for: '%s', " + "version_id: %d, minimum version_id: %d, ret: %d", + vmsd->name, vmsd->version_id, vmsd->minimum_version_id, + ret); return ret; } } @@ -192,13 +206,21 @@ int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd, if (inner_field->flags & VMS_STRUCT) { ret = vmstate_load_state(f, inner_field->vmsd, curr_elem, - inner_field->vmsd->version_id); + inner_field->vmsd->version_id, + errp); } else if (inner_field->flags & VMS_VSTRUCT) { ret = vmstate_load_state(f, inner_field->vmsd, curr_elem, - inner_field->struct_version_id); + inner_field->struct_version_id, + errp); } else { ret = inner_field->info->get(f, curr_elem, size, inner_field); + if (ret < 0) { + error_setg(errp, + "Failed to load element of type %s for %s: " + "%d", inner_field->info->name, + inner_field->name, ret); + } } /* If we used a fake temp field.. free it now */ @@ -208,30 +230,47 @@ int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd, if (ret >= 0) { ret = qemu_file_get_error(f); + if (ret < 0) { + error_setg(errp, + "Failed to load %s state: stream error: %d", + vmsd->name, ret); + } } if (ret < 0) { qemu_file_set_error(f, ret); - error_report("Failed to load %s:%s", vmsd->name, - field->name); trace_vmstate_load_field_error(field->name, ret); return ret; } } } else if (field->flags & VMS_MUST_EXIST) { - error_report("Input validation failed: %s/%s", - vmsd->name, field->name); + error_setg(errp, "Input validation failed: %s/%s version_id: %d", + vmsd->name, field->name, vmsd->version_id); return -1; } field++; } assert(field->flags == VMS_END); - ret = vmstate_subsection_load(f, vmsd, opaque); + ret = vmstate_subsection_load(f, vmsd, opaque, errp); if (ret != 0) { qemu_file_set_error(f, ret); return ret; } - if (vmsd->post_load) { + if (vmsd->post_load_errp) { + ret = vmsd->post_load_errp(opaque, version_id, errp); + if (ret < 0) { + error_prepend(errp, "post load hook failed for: %s, version_id: " + "%d, minimum_version: %d, ret: %d: ", vmsd->name, + vmsd->version_id, vmsd->minimum_version_id, ret); + } + } else if (vmsd->post_load) { ret = vmsd->post_load(opaque, version_id); + if (ret < 0) { + error_setg(errp, + "post load hook failed for: %s, version_id: %d, " + "minimum_version: %d, ret: %d", + vmsd->name, vmsd->version_id, vmsd->minimum_version_id, + ret); + } } trace_vmstate_load_state_end(vmsd->name, "end", ret); return ret; @@ -384,12 +423,6 @@ bool vmstate_section_needed(const VMStateDescription *vmsd, void *opaque) int vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd, - void *opaque, JSONWriter *vmdesc_id) -{ - return vmstate_save_state_v(f, vmsd, opaque, vmdesc_id, vmsd->version_id, NULL); -} - -int vmstate_save_state_with_err(QEMUFile *f, const VMStateDescription *vmsd, void *opaque, JSONWriter *vmdesc_id, Error **errp) { return vmstate_save_state_v(f, vmsd, opaque, vmdesc_id, vmsd->version_id, errp); @@ -398,12 +431,20 @@ int vmstate_save_state_with_err(QEMUFile *f, const VMStateDescription *vmsd, int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, void *opaque, JSONWriter *vmdesc, int version_id, Error **errp) { + ERRP_GUARD(); int ret = 0; const VMStateField *field = vmsd->fields; trace_vmstate_save_state_top(vmsd->name); - if (vmsd->pre_save) { + if (vmsd->pre_save_errp) { + ret = vmsd->pre_save_errp(opaque, errp); + trace_vmstate_save_state_pre_save_res(vmsd->name, ret); + if (ret < 0) { + error_prepend(errp, "pre-save for %s failed, ret: %d: ", + vmsd->name, ret); + } + } else if (vmsd->pre_save) { ret = vmsd->pre_save(opaque); trace_vmstate_save_state_pre_save_res(vmsd->name, ret); if (ret) { @@ -490,7 +531,7 @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, if (inner_field->flags & VMS_STRUCT) { ret = vmstate_save_state(f, inner_field->vmsd, - curr_elem, vmdesc_loop); + curr_elem, vmdesc_loop, errp); } else if (inner_field->flags & VMS_VSTRUCT) { ret = vmstate_save_state_v(f, inner_field->vmsd, curr_elem, vmdesc_loop, @@ -566,8 +607,9 @@ vmstate_get_subsection(const VMStateDescription * const *sub, } static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd, - void *opaque) + void *opaque, Error **errp) { + ERRP_GUARD(); trace_vmstate_subsection_load(vmsd->name); while (qemu_peek_byte(f, 0) == QEMU_VM_SUBSECTION) { @@ -598,6 +640,8 @@ static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd, sub_vmsd = vmstate_get_subsection(vmsd->subsections, idstr); if (sub_vmsd == NULL) { trace_vmstate_subsection_load_bad(vmsd->name, idstr, "(lookup)"); + error_setg(errp, "VM subsection '%s' in '%s' does not exist", + idstr, vmsd->name); return -ENOENT; } qemu_file_skip(f, 1); /* subsection */ @@ -605,9 +649,12 @@ static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd, qemu_file_skip(f, len); /* idstr */ version_id = qemu_get_be32(f); - ret = vmstate_load_state(f, sub_vmsd, opaque, version_id); + ret = vmstate_load_state(f, sub_vmsd, opaque, version_id, errp); if (ret) { trace_vmstate_subsection_load_bad(vmsd->name, idstr, "(child)"); + error_prepend(errp, + "Loading VM subsection '%s' in '%s' failed: %d: ", + idstr, vmsd->name, ret); return ret; } } @@ -646,7 +693,7 @@ static int vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd, qemu_put_byte(f, len); qemu_put_buffer(f, (uint8_t *)vmsdsub->name, len); qemu_put_be32(f, vmsdsub->version_id); - ret = vmstate_save_state_with_err(f, vmsdsub, opaque, vmdesc, errp); + ret = vmstate_save_state(f, vmsdsub, opaque, vmdesc, errp); if (ret) { return ret; } |