diff options
Diffstat (limited to 'migration')
| -rw-r--r-- | migration/Makefile.objs | 2 | ||||
| -rw-r--r-- | migration/block-dirty-bitmap.c | 12 | ||||
| -rw-r--r-- | migration/colo-comm.c | 76 | ||||
| -rw-r--r-- | migration/colo-failover.c | 2 | ||||
| -rw-r--r-- | migration/colo.c | 212 | ||||
| -rw-r--r-- | migration/migration.c | 58 | ||||
| -rw-r--r-- | migration/postcopy-ram.c | 11 | ||||
| -rw-r--r-- | migration/ram.c | 166 | ||||
| -rw-r--r-- | migration/ram.h | 4 | ||||
| -rw-r--r-- | migration/savevm.c | 61 | ||||
| -rw-r--r-- | migration/savevm.h | 5 | ||||
| -rw-r--r-- | migration/trace-events | 3 |
12 files changed, 488 insertions, 124 deletions
diff --git a/migration/Makefile.objs b/migration/Makefile.objs index c83ec47ba8..a4f3bafd86 100644 --- a/migration/Makefile.objs +++ b/migration/Makefile.objs @@ -1,6 +1,6 @@ common-obj-y += migration.o socket.o fd.o exec.o common-obj-y += tls.o channel.o savevm.o -common-obj-y += colo-comm.o colo.o colo-failover.o +common-obj-y += colo.o colo-failover.o common-obj-y += vmstate.o vmstate-types.o page_cache.o common-obj-y += qemu-file.o global_state.o common-obj-y += qemu-file-channel.o diff --git a/migration/block-dirty-bitmap.c b/migration/block-dirty-bitmap.c index 477826330c..5e90f44c2f 100644 --- a/migration/block-dirty-bitmap.c +++ b/migration/block-dirty-bitmap.c @@ -301,14 +301,14 @@ static int init_dirty_bitmap_migration(void) goto fail; } - if (bdrv_dirty_bitmap_frozen(bitmap)) { - error_report("Can't migrate frozen dirty bitmap: '%s", + if (bdrv_dirty_bitmap_user_locked(bitmap)) { + error_report("Can't migrate a bitmap that is in use by another operation: '%s'", bdrv_dirty_bitmap_name(bitmap)); goto fail; } - if (bdrv_dirty_bitmap_qmp_locked(bitmap)) { - error_report("Can't migrate locked dirty bitmap: '%s", + if (bdrv_dirty_bitmap_readonly(bitmap)) { + error_report("Can't migrate read-only dirty bitmap: '%s", bdrv_dirty_bitmap_name(bitmap)); goto fail; } @@ -335,9 +335,9 @@ static int init_dirty_bitmap_migration(void) } } - /* unset persistance here, to not roll back it */ + /* unset migration flags here, to not roll back it */ QSIMPLEQ_FOREACH(dbms, &dirty_bitmap_mig_state.dbms_list, entry) { - bdrv_dirty_bitmap_set_persistance(dbms->bitmap, false); + bdrv_dirty_bitmap_set_migration(dbms->bitmap, true); } if (QSIMPLEQ_EMPTY(&dirty_bitmap_mig_state.dbms_list)) { diff --git a/migration/colo-comm.c b/migration/colo-comm.c deleted file mode 100644 index df26e4dfe7..0000000000 --- a/migration/colo-comm.c +++ /dev/null @@ -1,76 +0,0 @@ -/* - * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO) - * (a.k.a. Fault Tolerance or Continuous Replication) - * - * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD. - * Copyright (c) 2016 FUJITSU LIMITED - * Copyright (c) 2016 Intel Corporation - * - * This work is licensed under the terms of the GNU GPL, version 2 or - * later. See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "migration.h" -#include "migration/colo.h" -#include "migration/vmstate.h" -#include "trace.h" - -typedef struct { - bool colo_requested; -} COLOInfo; - -static COLOInfo colo_info; - -COLOMode get_colo_mode(void) -{ - if (migration_in_colo_state()) { - return COLO_MODE_PRIMARY; - } else if (migration_incoming_in_colo_state()) { - return COLO_MODE_SECONDARY; - } else { - return COLO_MODE_UNKNOWN; - } -} - -static int colo_info_pre_save(void *opaque) -{ - COLOInfo *s = opaque; - - s->colo_requested = migrate_colo_enabled(); - - return 0; -} - -static bool colo_info_need(void *opaque) -{ - return migrate_colo_enabled(); -} - -static const VMStateDescription colo_state = { - .name = "COLOState", - .version_id = 1, - .minimum_version_id = 1, - .pre_save = colo_info_pre_save, - .needed = colo_info_need, - .fields = (VMStateField[]) { - VMSTATE_BOOL(colo_requested, COLOInfo), - VMSTATE_END_OF_LIST() - }, -}; - -void colo_info_init(void) -{ - vmstate_register(NULL, 0, &colo_state, &colo_info); -} - -bool migration_incoming_enable_colo(void) -{ - return colo_info.colo_requested; -} - -void migration_incoming_exit_colo(void) -{ - colo_info.colo_requested = false; -} diff --git a/migration/colo-failover.c b/migration/colo-failover.c index 0ae0c41221..4854a96c92 100644 --- a/migration/colo-failover.c +++ b/migration/colo-failover.c @@ -77,7 +77,7 @@ FailoverStatus failover_get_state(void) void qmp_x_colo_lost_heartbeat(Error **errp) { - if (get_colo_mode() == COLO_MODE_UNKNOWN) { + if (get_colo_mode() == COLO_MODE_NONE) { error_setg(errp, QERR_FEATURE_DISABLED, "colo"); return; } diff --git a/migration/colo.c b/migration/colo.c index 88936f5962..956ac236b7 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -25,8 +25,16 @@ #include "qemu/error-report.h" #include "migration/failover.h" #include "replication.h" +#include "net/colo-compare.h" +#include "net/colo.h" +#include "block/block.h" +#include "qapi/qapi-events-migration.h" +#include "qapi/qmp/qerror.h" +#include "sysemu/cpus.h" +#include "net/filter.h" static bool vmstate_loading; +static Notifier packets_compare_notifier; #define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024) @@ -53,6 +61,7 @@ static void secondary_vm_do_failover(void) { int old_state; MigrationIncomingState *mis = migration_incoming_get_current(); + Error *local_err = NULL; /* Can not do failover during the process of VM's loading VMstate, Or * it will break the secondary VM. @@ -70,6 +79,17 @@ static void secondary_vm_do_failover(void) migrate_set_state(&mis->state, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED); + replication_stop_all(true, &local_err); + if (local_err) { + error_report_err(local_err); + } + + /* Notify all filters of all NIC to do checkpoint */ + colo_notify_filters_event(COLO_EVENT_FAILOVER, &local_err); + if (local_err) { + error_report_err(local_err); + } + if (!autostart) { error_report("\"-S\" qemu option will be ignored in secondary side"); /* recover runstate to normal migration finish state */ @@ -107,9 +127,15 @@ static void primary_vm_do_failover(void) { MigrationState *s = migrate_get_current(); int old_state; + Error *local_err = NULL; migrate_set_state(&s->state, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED); + /* + * kick COLO thread which might wait at + * qemu_sem_wait(&s->colo_checkpoint_sem). + */ + colo_checkpoint_notify(migrate_get_current()); /* * Wake up COLO thread which may blocked in recv() or send(), @@ -130,10 +156,28 @@ static void primary_vm_do_failover(void) FailoverStatus_str(old_state)); return; } + + replication_stop_all(true, &local_err); + if (local_err) { + error_report_err(local_err); + local_err = NULL; + } + /* Notify COLO thread that failover work is finished */ qemu_sem_post(&s->colo_exit_sem); } +COLOMode get_colo_mode(void) +{ + if (migration_in_colo_state()) { + return COLO_MODE_PRIMARY; + } else if (migration_incoming_in_colo_state()) { + return COLO_MODE_SECONDARY; + } else { + return COLO_MODE_NONE; + } +} + void colo_do_failover(MigrationState *s) { /* Make sure VM stopped while failover happened. */ @@ -207,6 +251,26 @@ void qmp_xen_colo_do_checkpoint(Error **errp) #endif } +COLOStatus *qmp_query_colo_status(Error **errp) +{ + COLOStatus *s = g_new0(COLOStatus, 1); + + s->mode = get_colo_mode(); + + switch (failover_get_state()) { + case FAILOVER_STATUS_NONE: + s->reason = COLO_EXIT_REASON_NONE; + break; + case FAILOVER_STATUS_REQUIRE: + s->reason = COLO_EXIT_REASON_REQUEST; + break; + default: + s->reason = COLO_EXIT_REASON_ERROR; + } + + return s; +} + static void colo_send_message(QEMUFile *f, COLOMessage msg, Error **errp) { @@ -343,21 +407,42 @@ static int colo_do_checkpoint_transaction(MigrationState *s, goto out; } + colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err); + if (local_err) { + goto out; + } + /* Disable block migration */ migrate_set_block_enabled(false, &local_err); - qemu_savevm_state_header(fb); - qemu_savevm_state_setup(fb); qemu_mutex_lock_iothread(); - qemu_savevm_state_complete_precopy(fb, false, false); - qemu_mutex_unlock_iothread(); - - qemu_fflush(fb); + replication_do_checkpoint_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err); if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + /* Note: device state is saved into buffer */ + ret = qemu_save_device_state(fb); + + qemu_mutex_unlock_iothread(); + if (ret < 0) { goto out; } /* + * Only save VM's live state, which not including device state. + * TODO: We may need a timeout mechanism to prevent COLO process + * to be blocked here. + */ + qemu_savevm_live_state(s->to_dst_file); + + qemu_fflush(fb); + + /* * We need the size of the VMstate data in Secondary side, * With which we can decide how much data should be read. */ @@ -400,6 +485,11 @@ out: return ret; } +static void colo_compare_notify_checkpoint(Notifier *notifier, void *data) +{ + colo_checkpoint_notify(data); +} + static void colo_process_checkpoint(MigrationState *s) { QIOChannelBuffer *bioc; @@ -416,6 +506,9 @@ static void colo_process_checkpoint(MigrationState *s) goto out; } + packets_compare_notifier.notify = colo_compare_notify_checkpoint; + colo_compare_register_notifier(&packets_compare_notifier); + /* * Wait for Secondary finish loading VM states and enter COLO * restore. @@ -430,6 +523,12 @@ static void colo_process_checkpoint(MigrationState *s) object_unref(OBJECT(bioc)); qemu_mutex_lock_iothread(); + replication_start_all(REPLICATION_MODE_PRIMARY, &local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vm_start(); qemu_mutex_unlock_iothread(); trace_colo_vm_state_change("stop", "run"); @@ -445,6 +544,9 @@ static void colo_process_checkpoint(MigrationState *s) qemu_sem_wait(&s->colo_checkpoint_sem); + if (s->state != MIGRATION_STATUS_COLO) { + goto out; + } ret = colo_do_checkpoint_transaction(s, bioc, fb); if (ret < 0) { goto out; @@ -461,11 +563,38 @@ out: qemu_fclose(fb); } - timer_del(s->colo_delay_timer); + /* + * There are only two reasons we can get here, some error happened + * or the user triggered failover. + */ + switch (failover_get_state()) { + case FAILOVER_STATUS_NONE: + qapi_event_send_colo_exit(COLO_MODE_PRIMARY, + COLO_EXIT_REASON_ERROR); + break; + case FAILOVER_STATUS_REQUIRE: + qapi_event_send_colo_exit(COLO_MODE_PRIMARY, + COLO_EXIT_REASON_REQUEST); + break; + default: + abort(); + } /* Hope this not to be too long to wait here */ qemu_sem_wait(&s->colo_exit_sem); qemu_sem_destroy(&s->colo_exit_sem); + + /* + * It is safe to unregister notifier after failover finished. + * Besides, colo_delay_timer and colo_checkpoint_sem can't be + * released befor unregister notifier, or there will be use-after-free + * error. + */ + colo_compare_unregister_notifier(&packets_compare_notifier); + timer_del(s->colo_delay_timer); + timer_free(s->colo_delay_timer); + qemu_sem_destroy(&s->colo_checkpoint_sem); + /* * Must be called after failover BH is completed, * Or the failover BH may shutdown the wrong fd that @@ -533,6 +662,7 @@ void *colo_process_incoming_thread(void *opaque) uint64_t total_size; uint64_t value; Error *local_err = NULL; + int ret; rcu_register_thread(); qemu_sem_init(&mis->colo_incoming_sem, 0); @@ -559,6 +689,16 @@ void *colo_process_incoming_thread(void *opaque) fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc)); object_unref(OBJECT(bioc)); + qemu_mutex_lock_iothread(); + replication_start_all(REPLICATION_MODE_SECONDARY, &local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vm_start(); + trace_colo_vm_state_change("stop", "run"); + qemu_mutex_unlock_iothread(); + colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, &local_err); if (local_err) { @@ -578,6 +718,11 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + qemu_mutex_lock_iothread(); + vm_stop_force_state(RUN_STATE_COLO); + trace_colo_vm_state_change("run", "stop"); + qemu_mutex_unlock_iothread(); + /* FIXME: This is unnecessary for periodic checkpoint mode */ colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY, &local_err); @@ -591,6 +736,16 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + qemu_mutex_lock_iothread(); + cpu_synchronize_all_pre_loadvm(); + ret = qemu_loadvm_state_main(mis->from_src_file, mis); + qemu_mutex_unlock_iothread(); + + if (ret < 0) { + error_report("Load VM's live state (ram) error"); + goto out; + } + value = colo_receive_message_value(mis->from_src_file, COLO_MESSAGE_VMSTATE_SIZE, &local_err); if (local_err) { @@ -622,15 +777,37 @@ void *colo_process_incoming_thread(void *opaque) } qemu_mutex_lock_iothread(); - qemu_system_reset(SHUTDOWN_CAUSE_NONE); vmstate_loading = true; - if (qemu_loadvm_state(fb) < 0) { - error_report("COLO: loadvm failed"); + ret = qemu_load_device_state(fb); + if (ret < 0) { + error_report("COLO: load device state failed"); + qemu_mutex_unlock_iothread(); + goto out; + } + + replication_get_error_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + /* discard colo disk buffer */ + replication_do_checkpoint_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + + /* Notify all filters of all NIC to do checkpoint */ + colo_notify_filters_event(COLO_EVENT_CHECKPOINT, &local_err); + + if (local_err) { qemu_mutex_unlock_iothread(); goto out; } vmstate_loading = false; + vm_start(); + trace_colo_vm_state_change("stop", "run"); qemu_mutex_unlock_iothread(); if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) { @@ -654,6 +831,19 @@ out: error_report_err(local_err); } + switch (failover_get_state()) { + case FAILOVER_STATUS_NONE: + qapi_event_send_colo_exit(COLO_MODE_SECONDARY, + COLO_EXIT_REASON_ERROR); + break; + case FAILOVER_STATUS_REQUIRE: + qapi_event_send_colo_exit(COLO_MODE_SECONDARY, + COLO_EXIT_REASON_REQUEST); + break; + default: + abort(); + } + if (fb) { qemu_fclose(fb); } @@ -665,7 +855,7 @@ out: if (mis->to_src_file) { qemu_fclose(mis->to_src_file); } - migration_incoming_exit_colo(); + migration_incoming_disable_colo(); rcu_unregister_thread(); return NULL; diff --git a/migration/migration.c b/migration/migration.c index d6ae879dc8..8b36e7f184 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -76,10 +76,8 @@ /* Migration XBZRLE default cache size */ #define DEFAULT_MIGRATE_XBZRLE_CACHE_SIZE (64 * 1024 * 1024) -/* The delay time (in ms) between two COLO checkpoints - * Note: Please change this default value to 10000 when we support hybrid mode. - */ -#define DEFAULT_MIGRATE_X_CHECKPOINT_DELAY 200 +/* The delay time (in ms) between two COLO checkpoints */ +#define DEFAULT_MIGRATE_X_CHECKPOINT_DELAY (200 * 100) #define DEFAULT_MIGRATE_MULTIFD_CHANNELS 2 #define DEFAULT_MIGRATE_MULTIFD_PAGE_COUNT 16 @@ -298,6 +296,22 @@ int migrate_send_rp_req_pages(MigrationIncomingState *mis, const char *rbname, return migrate_send_rp_message(mis, msg_type, msglen, bufc); } +static bool migration_colo_enabled; +bool migration_incoming_colo_enabled(void) +{ + return migration_colo_enabled; +} + +void migration_incoming_disable_colo(void) +{ + migration_colo_enabled = false; +} + +void migration_incoming_enable_colo(void) +{ + migration_colo_enabled = true; +} + void qemu_start_incoming_migration(const char *uri, Error **errp) { const char *p; @@ -388,6 +402,7 @@ static void process_incoming_migration_co(void *opaque) MigrationIncomingState *mis = migration_incoming_get_current(); PostcopyState ps; int ret; + Error *local_err = NULL; assert(mis->from_src_file); mis->migration_incoming_co = qemu_coroutine_self(); @@ -419,7 +434,21 @@ static void process_incoming_migration_co(void *opaque) } /* we get COLO info, and know if we are in COLO mode */ - if (!ret && migration_incoming_enable_colo()) { + if (!ret && migration_incoming_colo_enabled()) { + /* Make sure all file formats flush their mutable metadata */ + bdrv_invalidate_cache_all(&local_err); + if (local_err) { + migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, + MIGRATION_STATUS_FAILED); + error_report_err(local_err); + exit(EXIT_FAILURE); + } + + if (colo_init_ram_cache() < 0) { + error_report("Init ram cache failed"); + exit(EXIT_FAILURE); + } + qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming", colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE); mis->have_colo_incoming_thread = true; @@ -427,6 +456,8 @@ static void process_incoming_migration_co(void *opaque) /* Wait checkpoint incoming thread exit before free resource */ qemu_thread_join(&mis->colo_incoming_thread); + /* We hold the global iothread lock, so it is safe here */ + colo_release_ram_cache(); } if (ret < 0) { @@ -1546,9 +1577,9 @@ static GSList *migration_blockers; int migrate_add_blocker(Error *reason, Error **errp) { if (migrate_get_current()->only_migratable) { - error_propagate(errp, error_copy(reason)); - error_prepend(errp, "disallowing migration blocker " - "(--only_migratable) for: "); + error_propagate_prepend(errp, error_copy(reason), + "disallowing migration blocker " + "(--only_migratable) for: "); return -EACCES; } @@ -1557,9 +1588,9 @@ int migrate_add_blocker(Error *reason, Error **errp) return 0; } - error_propagate(errp, error_copy(reason)); - error_prepend(errp, "disallowing migration blocker (migration in " - "progress) for: "); + error_propagate_prepend(errp, error_copy(reason), + "disallowing migration blocker " + "(migration in progress) for: "); return -EBUSY; } @@ -3017,6 +3048,11 @@ static void *migration_thread(void *opaque) qemu_savevm_send_postcopy_advise(s->to_dst_file); } + if (migrate_colo_enabled()) { + /* Notify migration destination that we enable COLO */ + qemu_savevm_send_colo_enable(s->to_dst_file); + } + qemu_savevm_state_setup(s->to_dst_file); s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start; diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 853d8b32ca..e5c02a32c5 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -533,6 +533,12 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis) if (mis->have_fault_thread) { Error *local_err = NULL; + /* Let the fault thread quit */ + atomic_set(&mis->fault_thread_quit, 1); + postcopy_fault_thread_notify(mis); + trace_postcopy_ram_incoming_cleanup_join(); + qemu_thread_join(&mis->fault_thread); + if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_END, &local_err)) { error_report_err(local_err); return -1; @@ -541,11 +547,6 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis) if (qemu_ram_foreach_migratable_block(cleanup_range, mis)) { return -1; } - /* Let the fault thread quit */ - atomic_set(&mis->fault_thread_quit, 1); - postcopy_fault_thread_notify(mis); - trace_postcopy_ram_incoming_cleanup_join(); - qemu_thread_join(&mis->fault_thread); trace_postcopy_ram_incoming_cleanup_closeuf(); close(mis->userfault_fd); diff --git a/migration/ram.c b/migration/ram.c index bc38d98cc3..7e7deec4d8 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -3447,6 +3447,29 @@ static inline void *host_from_ram_block_offset(RAMBlock *block, return block->host + offset; } +static inline void *colo_cache_from_block_offset(RAMBlock *block, + ram_addr_t offset) +{ + if (!offset_in_ramblock(block, offset)) { + return NULL; + } + if (!block->colo_cache) { + error_report("%s: colo_cache is NULL in block :%s", + __func__, block->idstr); + return NULL; + } + + /* + * During colo checkpoint, we need bitmap of these migrated pages. + * It help us to decide which pages in ram cache should be flushed + * into VM's RAM later. + */ + if (!test_and_set_bit(offset >> TARGET_PAGE_BITS, block->bmap)) { + ram_state->migration_dirty_pages++; + } + return block->colo_cache + offset; +} + /** * ram_handle_compressed: handle the zero page case * @@ -3651,6 +3674,88 @@ static void decompress_data_with_multi_threads(QEMUFile *f, qemu_mutex_unlock(&decomp_done_lock); } +/* + * 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. + */ +int colo_init_ram_cache(void) +{ + RAMBlock *block; + + rcu_read_lock(); + RAMBLOCK_FOREACH_MIGRATABLE(block) { + block->colo_cache = qemu_anon_ram_alloc(block->used_length, + NULL, + 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); + goto out_locked; + } + memcpy(block->colo_cache, block->host, block->used_length); + } + rcu_read_unlock(); + /* + * Record the dirty pages that sent by PVM, we use this dirty bitmap together + * with to decide which page in cache should be flushed into SVM's RAM. Here + * we use the same name 'ram_bitmap' as for migration. + */ + if (ram_bytes_total()) { + RAMBlock *block; + + RAMBLOCK_FOREACH_MIGRATABLE(block) { + unsigned long pages = block->max_length >> TARGET_PAGE_BITS; + + block->bmap = bitmap_new(pages); + bitmap_set(block->bmap, 0, pages); + } + } + ram_state = g_new0(RAMState, 1); + ram_state->migration_dirty_pages = 0; + memory_global_dirty_log_start(); + + return 0; + +out_locked: + + RAMBLOCK_FOREACH_MIGRATABLE(block) { + if (block->colo_cache) { + qemu_anon_ram_free(block->colo_cache, block->used_length); + block->colo_cache = NULL; + } + } + + rcu_read_unlock(); + return -errno; +} + +/* It is need to hold the global lock to call this helper */ +void colo_release_ram_cache(void) +{ + RAMBlock *block; + + memory_global_dirty_log_stop(); + RAMBLOCK_FOREACH_MIGRATABLE(block) { + g_free(block->bmap); + block->bmap = NULL; + } + + rcu_read_lock(); + + RAMBLOCK_FOREACH_MIGRATABLE(block) { + if (block->colo_cache) { + qemu_anon_ram_free(block->colo_cache, block->used_length); + block->colo_cache = NULL; + } + } + + rcu_read_unlock(); + g_free(ram_state); + ram_state = NULL; +} + /** * ram_load_setup: Setup RAM for migration incoming side * @@ -3667,6 +3772,7 @@ static int ram_load_setup(QEMUFile *f, void *opaque) xbzrle_load_setup(); ramblock_recv_map_init(); + return 0; } @@ -3687,6 +3793,7 @@ static int ram_load_cleanup(void *opaque) g_free(rb->receivedmap); rb->receivedmap = NULL; } + return 0; } @@ -3869,6 +3976,46 @@ static bool postcopy_is_running(void) return ps >= POSTCOPY_INCOMING_LISTENING && ps < POSTCOPY_INCOMING_END; } +/* + * Flush content of RAM cache into SVM's memory. + * Only flush the pages that be dirtied by PVM or SVM or both. + */ +static void colo_flush_ram_cache(void) +{ + RAMBlock *block = NULL; + void *dst_host; + void *src_host; + unsigned long offset = 0; + + memory_global_dirty_log_sync(); + rcu_read_lock(); + RAMBLOCK_FOREACH_MIGRATABLE(block) { + migration_bitmap_sync_range(ram_state, block, 0, block->used_length); + } + rcu_read_unlock(); + + trace_colo_flush_ram_cache_begin(ram_state->migration_dirty_pages); + rcu_read_lock(); + block = QLIST_FIRST_RCU(&ram_list.blocks); + + while (block) { + offset = migration_bitmap_find_dirty(ram_state, block, offset); + + if (offset << TARGET_PAGE_BITS >= block->used_length) { + offset = 0; + block = QLIST_NEXT_RCU(block, next); + } else { + migration_bitmap_clear_dirty(ram_state, block, offset); + dst_host = block->host + (offset << TARGET_PAGE_BITS); + src_host = block->colo_cache + (offset << TARGET_PAGE_BITS); + memcpy(dst_host, src_host, TARGET_PAGE_SIZE); + } + } + + rcu_read_unlock(); + trace_colo_flush_ram_cache_end(); +} + static int ram_load(QEMUFile *f, void *opaque, int version_id) { int flags = 0, ret = 0, invalid_flags = 0; @@ -3924,13 +4071,24 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) { RAMBlock *block = ram_block_from_stream(f, flags); - host = host_from_ram_block_offset(block, addr); + /* + * After going into COLO, we should load the Page into colo_cache. + */ + if (migration_incoming_in_colo_state()) { + host = colo_cache_from_block_offset(block, addr); + } else { + host = host_from_ram_block_offset(block, addr); + } if (!host) { error_report("Illegal RAM offset " RAM_ADDR_FMT, addr); ret = -EINVAL; break; } - ramblock_recv_bitmap_set(block, host); + + if (!migration_incoming_in_colo_state()) { + ramblock_recv_bitmap_set(block, host); + } + trace_ram_load_loop(block->idstr, (uint64_t)addr, flags, host); } @@ -4034,6 +4192,10 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) ret |= wait_for_decompress_done(); rcu_read_unlock(); trace_ram_load_complete(ret, seq_iter); + + if (!ret && migration_incoming_in_colo_state()) { + colo_flush_ram_cache(); + } return ret; } diff --git a/migration/ram.h b/migration/ram.h index a139066846..83ff1bc11a 100644 --- a/migration/ram.h +++ b/migration/ram.h @@ -71,4 +71,8 @@ int64_t ramblock_recv_bitmap_send(QEMUFile *file, const char *block_name); int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb); +/* ram cache */ +int colo_init_ram_cache(void); +void colo_release_ram_cache(void); + #endif diff --git a/migration/savevm.c b/migration/savevm.c index 2d10e45582..9992af4db4 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -56,6 +56,7 @@ #include "io/channel-file.h" #include "sysemu/replay.h" #include "qjson.h" +#include "migration/colo.h" #ifndef ETH_P_RARP #define ETH_P_RARP 0x8035 @@ -82,6 +83,7 @@ enum qemu_vm_cmd { were previously sent during precopy but are dirty. */ MIG_CMD_PACKAGED, /* Send a wrapped stream within this stream */ + MIG_CMD_ENABLE_COLO, /* Enable COLO */ MIG_CMD_POSTCOPY_RESUME, /* resume postcopy on dest */ MIG_CMD_RECV_BITMAP, /* Request for recved bitmap on dst */ MIG_CMD_MAX @@ -841,6 +843,12 @@ static void qemu_savevm_command_send(QEMUFile *f, qemu_fflush(f); } +void qemu_savevm_send_colo_enable(QEMUFile *f) +{ + trace_savevm_send_colo_enable(); + qemu_savevm_command_send(f, MIG_CMD_ENABLE_COLO, 0, NULL); +} + void qemu_savevm_send_ping(QEMUFile *f, uint32_t value) { uint32_t buf; @@ -1370,13 +1378,21 @@ done: return ret; } -static int qemu_save_device_state(QEMUFile *f) +void qemu_savevm_live_state(QEMUFile *f) { - SaveStateEntry *se; + /* save QEMU_VM_SECTION_END section */ + qemu_savevm_state_complete_precopy(f, true, false); + qemu_put_byte(f, QEMU_VM_EOF); +} - qemu_put_be32(f, QEMU_VM_FILE_MAGIC); - qemu_put_be32(f, QEMU_VM_FILE_VERSION); +int qemu_save_device_state(QEMUFile *f) +{ + SaveStateEntry *se; + if (!migration_in_colo_state()) { + qemu_put_be32(f, QEMU_VM_FILE_MAGIC); + qemu_put_be32(f, QEMU_VM_FILE_VERSION); + } cpu_synchronize_all_states(); QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { @@ -1432,8 +1448,6 @@ enum LoadVMExitCodes { LOADVM_QUIT = 1, }; -static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis); - /* ------ incoming postcopy messages ------ */ /* 'advise' arrives before any transfers just to tell us that a postcopy * *might* happen - it might be skipped if precopy transferred everything @@ -1922,6 +1936,12 @@ static int loadvm_handle_recv_bitmap(MigrationIncomingState *mis, return 0; } +static int loadvm_process_enable_colo(MigrationIncomingState *mis) +{ + migration_incoming_enable_colo(); + return colo_init_ram_cache(); +} + /* * Process an incoming 'QEMU_VM_COMMAND' * 0 just a normal return @@ -2001,6 +2021,9 @@ static int loadvm_process_command(QEMUFile *f) case MIG_CMD_RECV_BITMAP: return loadvm_handle_recv_bitmap(mis, len); + + case MIG_CMD_ENABLE_COLO: + return loadvm_process_enable_colo(mis); } return 0; @@ -2230,7 +2253,7 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis) return true; } -static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) +int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) { uint8_t section_type; int ret = 0; @@ -2401,6 +2424,22 @@ int qemu_loadvm_state(QEMUFile *f) return ret; } +int qemu_load_device_state(QEMUFile *f) +{ + MigrationIncomingState *mis = migration_incoming_get_current(); + int ret; + + /* Load QEMU_VM_SECTION_FULL section */ + ret = qemu_loadvm_state_main(f, mis); + if (ret < 0) { + error_report("Failed to load device state: %d", ret); + return ret; + } + + cpu_synchronize_all_post_init(); + return 0; +} + int save_snapshot(const char *name, Error **errp) { BlockDriverState *bs, *bs1; @@ -2414,8 +2453,8 @@ int save_snapshot(const char *name, Error **errp) AioContext *aio_context; if (!replay_can_snapshot()) { - error_report("Record/replay does not allow making snapshot " - "right now. Try once more later."); + error_setg(errp, "Record/replay does not allow making snapshot " + "right now. Try once more later."); return ret; } @@ -2611,8 +2650,8 @@ int load_snapshot(const char *name, Error **errp) MigrationIncomingState *mis = migration_incoming_get_current(); if (!replay_can_snapshot()) { - error_report("Record/replay does not allow loading snapshot " - "right now. Try once more later."); + error_setg(errp, "Record/replay does not allow loading snapshot " + "right now. Try once more later."); return -EINVAL; } diff --git a/migration/savevm.h b/migration/savevm.h index a5e65b8ae3..51a4b9caa8 100644 --- a/migration/savevm.h +++ b/migration/savevm.h @@ -55,8 +55,13 @@ void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name, uint16_t len, uint64_t *start_list, uint64_t *length_list); +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); void qemu_loadvm_state_cleanup(void); +int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis); +int qemu_load_device_state(QEMUFile *f); #endif diff --git a/migration/trace-events b/migration/trace-events index 9430f3cbe0..bd2d0cd25a 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -37,6 +37,7 @@ savevm_send_ping(uint32_t val) "0x%x" savevm_send_postcopy_listen(void) "" savevm_send_postcopy_run(void) "" savevm_send_postcopy_resume(void) "" +savevm_send_colo_enable(void) "" savevm_send_recv_bitmap(char *name) "%s" savevm_state_setup(void) "" savevm_state_resume_prepare(void) "" @@ -101,6 +102,8 @@ ram_dirty_bitmap_sync_start(void) "" ram_dirty_bitmap_sync_wait(void) "" ram_dirty_bitmap_sync_complete(void) "" ram_state_resume_prepare(uint64_t v) "%" PRId64 +colo_flush_ram_cache_begin(uint64_t dirty_pages) "dirty_pages %" PRIu64 +colo_flush_ram_cache_end(void) "" # migration/migration.c await_return_path_close_on_source_close(void) "" |