diff options
Diffstat (limited to 'migration/savevm.c')
| -rw-r--r-- | migration/savevm.c | 826 |
1 files changed, 744 insertions, 82 deletions
diff --git a/migration/savevm.c b/migration/savevm.c index e05158d7ba..be52314a12 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -37,6 +37,7 @@ #include "qemu/timer.h" #include "audio/audio.h" #include "migration/migration.h" +#include "migration/postcopy-ram.h" #include "qapi/qmp/qerror.h" #include "qemu/error-report.h" #include "qemu/sockets.h" @@ -45,6 +46,7 @@ #include "exec/memory.h" #include "qmp-commands.h" #include "trace.h" +#include "qemu/bitops.h" #include "qemu/iov.h" #include "block/snapshot.h" #include "block/qapi.h" @@ -57,8 +59,26 @@ #define ARP_PTYPE_IP 0x0800 #define ARP_OP_REQUEST_REV 0x3 +const unsigned int postcopy_ram_discard_version = 0; + static bool skip_section_footers; +static struct mig_cmd_args { + ssize_t len; /* -1 = variable */ + const char *name; +} mig_cmd_args[] = { + [MIG_CMD_INVALID] = { .len = -1, .name = "INVALID" }, + [MIG_CMD_OPEN_RETURN_PATH] = { .len = 0, .name = "OPEN_RETURN_PATH" }, + [MIG_CMD_PING] = { .len = sizeof(uint32_t), .name = "PING" }, + [MIG_CMD_POSTCOPY_ADVISE] = { .len = 16, .name = "POSTCOPY_ADVISE" }, + [MIG_CMD_POSTCOPY_LISTEN] = { .len = 0, .name = "POSTCOPY_LISTEN" }, + [MIG_CMD_POSTCOPY_RUN] = { .len = 0, .name = "POSTCOPY_RUN" }, + [MIG_CMD_POSTCOPY_RAM_DISCARD] = { + .len = -1, .name = "POSTCOPY_RAM_DISCARD" }, + [MIG_CMD_PACKAGED] = { .len = 4, .name = "PACKAGED" }, + [MIG_CMD_MAX] = { .len = -1, .name = "MAX" }, +}; + static int announce_self_create(uint8_t *buf, uint8_t *mac_addr) { @@ -694,6 +714,156 @@ static void save_section_footer(QEMUFile *f, SaveStateEntry *se) } } +/** + * qemu_savevm_command_send: Send a 'QEMU_VM_COMMAND' type element with the + * command and associated data. + * + * @f: File to send command on + * @command: Command type to send + * @len: Length of associated data + * @data: Data associated with command. + */ +void qemu_savevm_command_send(QEMUFile *f, + enum qemu_vm_cmd command, + uint16_t len, + uint8_t *data) +{ + trace_savevm_command_send(command, len); + qemu_put_byte(f, QEMU_VM_COMMAND); + qemu_put_be16(f, (uint16_t)command); + qemu_put_be16(f, len); + qemu_put_buffer(f, data, len); + qemu_fflush(f); +} + +void qemu_savevm_send_ping(QEMUFile *f, uint32_t value) +{ + uint32_t buf; + + trace_savevm_send_ping(value); + buf = cpu_to_be32(value); + qemu_savevm_command_send(f, MIG_CMD_PING, sizeof(value), (uint8_t *)&buf); +} + +void qemu_savevm_send_open_return_path(QEMUFile *f) +{ + trace_savevm_send_open_return_path(); + qemu_savevm_command_send(f, MIG_CMD_OPEN_RETURN_PATH, 0, NULL); +} + +/* We have a buffer of data to send; we don't want that all to be loaded + * by the command itself, so the command contains just the length of the + * extra buffer that we then send straight after it. + * TODO: Must be a better way to organise that + * + * Returns: + * 0 on success + * -ve on error + */ +int qemu_savevm_send_packaged(QEMUFile *f, const QEMUSizedBuffer *qsb) +{ + size_t cur_iov; + size_t len = qsb_get_length(qsb); + uint32_t tmp; + + if (len > MAX_VM_CMD_PACKAGED_SIZE) { + error_report("%s: Unreasonably large packaged state: %zu", + __func__, len); + return -1; + } + + tmp = cpu_to_be32(len); + + trace_qemu_savevm_send_packaged(); + qemu_savevm_command_send(f, MIG_CMD_PACKAGED, 4, (uint8_t *)&tmp); + + /* all the data follows (concatinating the iov's) */ + for (cur_iov = 0; cur_iov < qsb->n_iov; cur_iov++) { + /* The iov entries are partially filled */ + size_t towrite = MIN(qsb->iov[cur_iov].iov_len, len); + len -= towrite; + + if (!towrite) { + break; + } + + qemu_put_buffer(f, qsb->iov[cur_iov].iov_base, towrite); + } + + return 0; +} + +/* Send prior to any postcopy transfer */ +void qemu_savevm_send_postcopy_advise(QEMUFile *f) +{ + uint64_t tmp[2]; + tmp[0] = cpu_to_be64(getpagesize()); + tmp[1] = cpu_to_be64(1ul << qemu_target_page_bits()); + + trace_qemu_savevm_send_postcopy_advise(); + qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_ADVISE, 16, (uint8_t *)tmp); +} + +/* Sent prior to starting the destination running in postcopy, discard pages + * that have already been sent but redirtied on the source. + * CMD_POSTCOPY_RAM_DISCARD consist of: + * byte version (0) + * byte Length of name field (not including 0) + * n x byte RAM block name + * byte 0 terminator (just for safety) + * n x Byte ranges within the named RAMBlock + * be64 Start of the range + * be64 Length + * + * name: RAMBlock name that these entries are part of + * len: Number of page entries + * start_list: 'len' addresses + * length_list: 'len' addresses + * + */ +void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name, + uint16_t len, + uint64_t *start_list, + uint64_t *length_list) +{ + uint8_t *buf; + uint16_t tmplen; + uint16_t t; + size_t name_len = strlen(name); + + trace_qemu_savevm_send_postcopy_ram_discard(name, len); + assert(name_len < 256); + buf = g_malloc0(1 + 1 + name_len + 1 + (8 + 8) * len); + buf[0] = postcopy_ram_discard_version; + buf[1] = name_len; + memcpy(buf + 2, name, name_len); + tmplen = 2 + name_len; + buf[tmplen++] = '\0'; + + for (t = 0; t < len; t++) { + cpu_to_be64w((uint64_t *)(buf + tmplen), start_list[t]); + tmplen += 8; + cpu_to_be64w((uint64_t *)(buf + tmplen), length_list[t]); + tmplen += 8; + } + qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_RAM_DISCARD, tmplen, buf); + g_free(buf); +} + +/* Get the destination into a state where it can receive postcopy data. */ +void qemu_savevm_send_postcopy_listen(QEMUFile *f) +{ + trace_savevm_send_postcopy_listen(); + qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_LISTEN, 0, NULL); +} + +/* Kick the destination into running */ +void qemu_savevm_send_postcopy_run(QEMUFile *f) +{ + trace_savevm_send_postcopy_run(); + qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_RUN, 0, NULL); +} + bool qemu_savevm_state_blocked(Error **errp) { SaveStateEntry *se; @@ -713,6 +883,12 @@ void qemu_savevm_state_header(QEMUFile *f) trace_savevm_state_header(); qemu_put_be32(f, QEMU_VM_FILE_MAGIC); qemu_put_be32(f, QEMU_VM_FILE_VERSION); + + if (!savevm_state.skip_configuration) { + qemu_put_byte(f, QEMU_VM_CONFIGURATION); + vmstate_save_state(f, &vmstate_configuration, &savevm_state, 0); + } + } void qemu_savevm_state_begin(QEMUFile *f, @@ -729,11 +905,6 @@ void qemu_savevm_state_begin(QEMUFile *f, se->ops->set_params(params, se->opaque); } - if (!savevm_state.skip_configuration) { - qemu_put_byte(f, QEMU_VM_CONFIGURATION); - vmstate_save_state(f, &vmstate_configuration, &savevm_state, 0); - } - QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { if (!se->ops || !se->ops->save_live_setup) { continue; @@ -760,7 +931,7 @@ void qemu_savevm_state_begin(QEMUFile *f, * 0 : We haven't finished, caller have to go again * 1 : We have finished, we can go to complete phase */ -int qemu_savevm_state_iterate(QEMUFile *f) +int qemu_savevm_state_iterate(QEMUFile *f, bool postcopy) { SaveStateEntry *se; int ret = 1; @@ -775,6 +946,15 @@ int qemu_savevm_state_iterate(QEMUFile *f) continue; } } + /* + * In the postcopy phase, any device that doesn't know how to + * do postcopy should have saved it's state in the _complete + * call that's already run, it might get confused if we call + * iterate afterwards. + */ + if (postcopy && !se->ops->save_live_complete_postcopy) { + continue; + } if (qemu_file_rate_limit(f)) { return 0; } @@ -803,22 +983,65 @@ int qemu_savevm_state_iterate(QEMUFile *f) static bool should_send_vmdesc(void) { MachineState *machine = MACHINE(qdev_get_machine()); - return !machine->suppress_vmdesc; + bool in_postcopy = migration_in_postcopy(migrate_get_current()); + return !machine->suppress_vmdesc && !in_postcopy; } -void qemu_savevm_state_complete(QEMUFile *f) +/* + * Calls the save_live_complete_postcopy methods + * causing the last few pages to be sent immediately and doing any associated + * cleanup. + * Note postcopy also calls qemu_savevm_state_complete_precopy to complete + * all the other devices, but that happens at the point we switch to postcopy. + */ +void qemu_savevm_state_complete_postcopy(QEMUFile *f) +{ + SaveStateEntry *se; + int ret; + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->ops || !se->ops->save_live_complete_postcopy) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + trace_savevm_section_start(se->idstr, se->section_id); + /* Section type */ + qemu_put_byte(f, QEMU_VM_SECTION_END); + qemu_put_be32(f, se->section_id); + + ret = se->ops->save_live_complete_postcopy(f, se->opaque); + trace_savevm_section_end(se->idstr, se->section_id, ret); + save_section_footer(f, se); + if (ret < 0) { + qemu_file_set_error(f, ret); + return; + } + } + + qemu_put_byte(f, QEMU_VM_EOF); + qemu_fflush(f); +} + +void qemu_savevm_state_complete_precopy(QEMUFile *f) { QJSON *vmdesc; int vmdesc_len; SaveStateEntry *se; int ret; + bool in_postcopy = migration_in_postcopy(migrate_get_current()); - trace_savevm_state_complete(); + trace_savevm_state_complete_precopy(); cpu_synchronize_all_states(); QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { - if (!se->ops || !se->ops->save_live_complete) { + if (!se->ops || + (in_postcopy && se->ops->save_live_complete_postcopy) || + !se->ops->save_live_complete_precopy) { continue; } if (se->ops && se->ops->is_active) { @@ -830,7 +1053,7 @@ void qemu_savevm_state_complete(QEMUFile *f) save_section_header(f, se, QEMU_VM_SECTION_END); - ret = se->ops->save_live_complete(f, se->opaque); + ret = se->ops->save_live_complete_precopy(f, se->opaque); trace_savevm_section_end(se->idstr, se->section_id, ret); save_section_footer(f, se); if (ret < 0) { @@ -867,7 +1090,10 @@ void qemu_savevm_state_complete(QEMUFile *f) save_section_footer(f, se); } - qemu_put_byte(f, QEMU_VM_EOF); + if (!in_postcopy) { + /* Postcopy stream will still be going */ + qemu_put_byte(f, QEMU_VM_EOF); + } json_end_array(vmdesc); qjson_finish(vmdesc); @@ -883,10 +1109,19 @@ void qemu_savevm_state_complete(QEMUFile *f) qemu_fflush(f); } -uint64_t qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size) +/* Give an estimate of the amount left to be transferred, + * the result is split into the amount for units that can and + * for units that can't do postcopy. + */ +void qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size, + uint64_t *res_non_postcopiable, + uint64_t *res_postcopiable) { SaveStateEntry *se; - uint64_t ret = 0; + + *res_non_postcopiable = 0; + *res_postcopiable = 0; + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { if (!se->ops || !se->ops->save_live_pending) { @@ -897,9 +1132,9 @@ uint64_t qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size) continue; } } - ret += se->ops->save_live_pending(f, se->opaque, max_size); + se->ops->save_live_pending(f, se->opaque, max_size, + res_non_postcopiable, res_postcopiable); } - return ret; } void qemu_savevm_state_cleanup(void) @@ -921,6 +1156,8 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp) .blk = 0, .shared = 0 }; + MigrationState *ms = migrate_init(¶ms); + ms->file = f; if (qemu_savevm_state_blocked(errp)) { return -EINVAL; @@ -932,18 +1169,18 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp) qemu_mutex_lock_iothread(); while (qemu_file_get_error(f) == 0) { - if (qemu_savevm_state_iterate(f) > 0) { + if (qemu_savevm_state_iterate(f, false) > 0) { break; } } ret = qemu_file_get_error(f); if (ret == 0) { - qemu_savevm_state_complete(f); + qemu_savevm_state_complete_precopy(f); ret = qemu_file_get_error(f); } + qemu_savevm_state_cleanup(); if (ret != 0) { - qemu_savevm_state_cleanup(); error_setg_errno(errp, -ret, "Error while writing VM state"); } return ret; @@ -1001,6 +1238,420 @@ static SaveStateEntry *find_se(const char *idstr, int instance_id) return NULL; } +enum LoadVMExitCodes { + /* Allow a command to quit all layers of nested loadvm loops */ + 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 + * quickly. + */ +static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis) +{ + PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_ADVISE); + uint64_t remote_hps, remote_tps; + + trace_loadvm_postcopy_handle_advise(); + if (ps != POSTCOPY_INCOMING_NONE) { + error_report("CMD_POSTCOPY_ADVISE in wrong postcopy state (%d)", ps); + return -1; + } + + if (!postcopy_ram_supported_by_host()) { + return -1; + } + + remote_hps = qemu_get_be64(mis->from_src_file); + if (remote_hps != getpagesize()) { + /* + * Some combinations of mismatch are probably possible but it gets + * a bit more complicated. In particular we need to place whole + * host pages on the dest at once, and we need to ensure that we + * handle dirtying to make sure we never end up sending part of + * a hostpage on it's own. + */ + error_report("Postcopy needs matching host page sizes (s=%d d=%d)", + (int)remote_hps, getpagesize()); + return -1; + } + + remote_tps = qemu_get_be64(mis->from_src_file); + if (remote_tps != (1ul << qemu_target_page_bits())) { + /* + * Again, some differences could be dealt with, but for now keep it + * simple. + */ + error_report("Postcopy needs matching target page sizes (s=%d d=%d)", + (int)remote_tps, 1 << qemu_target_page_bits()); + return -1; + } + + if (ram_postcopy_incoming_init(mis)) { + return -1; + } + + postcopy_state_set(POSTCOPY_INCOMING_ADVISE); + + return 0; +} + +/* After postcopy we will be told to throw some pages away since they're + * dirty and will have to be demand fetched. Must happen before CPU is + * started. + * There can be 0..many of these messages, each encoding multiple pages. + */ +static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, + uint16_t len) +{ + int tmp; + char ramid[256]; + PostcopyState ps = postcopy_state_get(); + + trace_loadvm_postcopy_ram_handle_discard(); + + switch (ps) { + case POSTCOPY_INCOMING_ADVISE: + /* 1st discard */ + tmp = postcopy_ram_prepare_discard(mis); + if (tmp) { + return tmp; + } + break; + + case POSTCOPY_INCOMING_DISCARD: + /* Expected state */ + break; + + default: + error_report("CMD_POSTCOPY_RAM_DISCARD in wrong postcopy state (%d)", + ps); + return -1; + } + /* We're expecting a + * Version (0) + * a RAM ID string (length byte, name, 0 term) + * 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); + 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); + return -1; + } + + if (!qemu_get_counted_string(mis->from_src_file, ramid)) { + error_report("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); + return -1; + } + + len -= 3 + strlen(ramid); + if (len % 16) { + error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len); + return -1; + } + trace_loadvm_postcopy_ram_handle_discard_header(ramid, len); + while (len) { + uint64_t start_addr, block_length; + start_addr = qemu_get_be64(mis->from_src_file); + block_length = qemu_get_be64(mis->from_src_file); + + len -= 16; + int ret = ram_discard_range(mis, ramid, start_addr, + block_length); + if (ret) { + return ret; + } + } + trace_loadvm_postcopy_ram_handle_discard_end(); + + return 0; +} + +/* + * Triggered by a postcopy_listen command; this thread takes over reading + * the input stream, leaving the main thread free to carry on loading the rest + * of the device state (from RAM). + * (TODO:This could do with being in a postcopy file - but there again it's + * just another input loop, not that postcopy specific) + */ +static void *postcopy_ram_listen_thread(void *opaque) +{ + QEMUFile *f = opaque; + MigrationIncomingState *mis = migration_incoming_get_current(); + int load_res; + + qemu_sem_post(&mis->listen_thread_sem); + trace_postcopy_ram_listen_thread_start(); + + /* + * Because we're a thread and not a coroutine we can't yield + * in qemu_file, and thus we must be blocking now. + */ + qemu_file_set_blocking(f, true); + load_res = qemu_loadvm_state_main(f, mis); + /* And non-blocking again so we don't block in any cleanup */ + qemu_file_set_blocking(f, false); + + trace_postcopy_ram_listen_thread_exit(); + if (load_res < 0) { + error_report("%s: loadvm failed: %d", __func__, load_res); + qemu_file_set_error(f, load_res); + } else { + /* + * This looks good, but it's possible that the device loading in the + * main thread hasn't finished yet, and so we might not be in 'RUN' + * state yet; wait for the end of the main thread. + */ + qemu_event_wait(&mis->main_thread_load_event); + } + postcopy_ram_incoming_cleanup(mis); + /* + * If everything has worked fine, then the main thread has waited + * for us to start, and we're the last use of the mis. + * (If something broke then qemu will have to exit anyway since it's + * got a bad migration state). + */ + migration_incoming_state_destroy(); + + if (load_res < 0) { + /* + * If something went wrong then we have a bad state so exit; + * depending how far we got it might be possible at this point + * to leave the guest running and fire MCEs for pages that never + * arrived as a desperate recovery step. + */ + exit(EXIT_FAILURE); + } + + return NULL; +} + +/* After this message we must be able to immediately receive postcopy data */ +static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) +{ + PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_LISTENING); + trace_loadvm_postcopy_handle_listen(); + if (ps != POSTCOPY_INCOMING_ADVISE && ps != POSTCOPY_INCOMING_DISCARD) { + error_report("CMD_POSTCOPY_LISTEN in wrong postcopy state (%d)", ps); + return -1; + } + if (ps == POSTCOPY_INCOMING_ADVISE) { + /* + * A rare case, we entered listen without having to do any discards, + * so do the setup that's normally done at the time of the 1st discard. + */ + postcopy_ram_prepare_discard(mis); + } + + /* + * Sensitise RAM - can now generate requests for blocks that don't exist + * However, at this point the CPU shouldn't be running, and the IO + * shouldn't be doing anything yet so don't actually expect requests + */ + if (postcopy_ram_enable_notify(mis)) { + return -1; + } + + if (mis->have_listen_thread) { + error_report("CMD_POSTCOPY_RAM_LISTEN already has a listen thread"); + return -1; + } + + mis->have_listen_thread = true; + /* Start up the listening thread and wait for it to signal ready */ + qemu_sem_init(&mis->listen_thread_sem, 0); + qemu_thread_create(&mis->listen_thread, "postcopy/listen", + postcopy_ram_listen_thread, mis->from_src_file, + QEMU_THREAD_JOINABLE); + qemu_sem_wait(&mis->listen_thread_sem); + qemu_sem_destroy(&mis->listen_thread_sem); + + return 0; +} + +/* After all discards we can start running and asking for pages */ +static int loadvm_postcopy_handle_run(MigrationIncomingState *mis) +{ + PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_RUNNING); + Error *local_err = NULL; + + trace_loadvm_postcopy_handle_run(); + if (ps != POSTCOPY_INCOMING_LISTENING) { + error_report("CMD_POSTCOPY_RUN in wrong postcopy state (%d)", ps); + return -1; + } + + /* TODO we should move all of this lot into postcopy_ram.c or a shared code + * in migration.c + */ + cpu_synchronize_all_post_init(); + + qemu_announce_self(); + + /* Make sure all file formats flush their mutable metadata */ + bdrv_invalidate_cache_all(&local_err); + if (local_err) { + error_report_err(local_err); + return -1; + } + + trace_loadvm_postcopy_handle_run_cpu_sync(); + cpu_synchronize_all_post_init(); + + trace_loadvm_postcopy_handle_run_vmstart(); + + if (autostart) { + /* Hold onto your hats, starting the CPU */ + vm_start(); + } else { + /* leave it paused and let management decide when to start the CPU */ + runstate_set(RUN_STATE_PAUSED); + } + + /* We need to finish reading the stream from the package + * and also stop reading anything more from the stream that loaded the + * package (since it's now being read by the listener thread). + * LOADVM_QUIT will quit all the layers of nested loadvm loops. + */ + return LOADVM_QUIT; +} + +/** + * Immediately following this command is a blob of data containing an embedded + * chunk of migration stream; read it and load it. + * + * @mis: Incoming state + * @length: Length of packaged data to read + * + * Returns: Negative values on error + * + */ +static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis) +{ + int ret; + uint8_t *buffer; + uint32_t length; + QEMUSizedBuffer *qsb; + + length = qemu_get_be32(mis->from_src_file); + trace_loadvm_handle_cmd_packaged(length); + + if (length > MAX_VM_CMD_PACKAGED_SIZE) { + error_report("Unreasonably large packaged state: %u", length); + return -1; + } + buffer = g_malloc0(length); + ret = qemu_get_buffer(mis->from_src_file, buffer, (int)length); + if (ret != length) { + g_free(buffer); + error_report("CMD_PACKAGED: Buffer receive fail ret=%d length=%d\n", + ret, length); + return (ret < 0) ? ret : -EAGAIN; + } + trace_loadvm_handle_cmd_packaged_received(ret); + + /* Setup a dummy QEMUFile that actually reads from the buffer */ + qsb = qsb_create(buffer, length); + g_free(buffer); /* Because qsb_create copies */ + if (!qsb) { + error_report("Unable to create qsb"); + } + QEMUFile *packf = qemu_bufopen("r", qsb); + + ret = qemu_loadvm_state_main(packf, mis); + trace_loadvm_handle_cmd_packaged_main(ret); + qemu_fclose(packf); + qsb_free(qsb); + + return ret; +} + +/* + * Process an incoming 'QEMU_VM_COMMAND' + * 0 just a normal return + * LOADVM_QUIT All good, but exit the loop + * <0 Error + */ +static int loadvm_process_command(QEMUFile *f) +{ + MigrationIncomingState *mis = migration_incoming_get_current(); + uint16_t cmd; + uint16_t len; + uint32_t tmp32; + + cmd = qemu_get_be16(f); + len = qemu_get_be16(f); + + trace_loadvm_process_command(cmd, len); + if (cmd >= MIG_CMD_MAX || cmd == MIG_CMD_INVALID) { + error_report("MIG_CMD 0x%x unknown (len 0x%x)", cmd, len); + return -EINVAL; + } + + 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); + return -ERANGE; + } + + switch (cmd) { + case MIG_CMD_OPEN_RETURN_PATH: + if (mis->to_src_file) { + error_report("CMD_OPEN_RETURN_PATH called when RP already open"); + /* Not really a problem, so don't give up */ + 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; + } + break; + + case MIG_CMD_PING: + 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); + return -1; + } + migrate_send_rp_pong(mis, tmp32); + break; + + case MIG_CMD_PACKAGED: + return loadvm_handle_cmd_packaged(mis); + + case MIG_CMD_POSTCOPY_ADVISE: + return loadvm_postcopy_handle_advise(mis); + + case MIG_CMD_POSTCOPY_LISTEN: + return loadvm_postcopy_handle_listen(mis); + + case MIG_CMD_POSTCOPY_RUN: + return loadvm_postcopy_handle_run(mis); + + case MIG_CMD_POSTCOPY_RAM_DISCARD: + return loadvm_postcopy_ram_handle_discard(mis, len); + } + + return 0; +} + struct LoadStateEntry { QLIST_ENTRY(LoadStateEntry) entry; SaveStateEntry *se; @@ -1053,47 +1704,10 @@ void loadvm_free_handlers(MigrationIncomingState *mis) } } -int qemu_loadvm_state(QEMUFile *f) +static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) { - MigrationIncomingState *mis = migration_incoming_get_current(); - Error *local_err = NULL; uint8_t section_type; - unsigned int v; int ret; - int file_error_after_eof = -1; - - if (qemu_savevm_state_blocked(&local_err)) { - error_report_err(local_err); - return -EINVAL; - } - - v = qemu_get_be32(f); - if (v != QEMU_VM_FILE_MAGIC) { - error_report("Not a migration stream"); - 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"); - return -ENOTSUP; - } - if (v != QEMU_VM_FILE_VERSION) { - error_report("Unsupported migration stream version"); - return -ENOTSUP; - } - - if (!savevm_state.skip_configuration) { - if (qemu_get_byte(f) != QEMU_VM_CONFIGURATION) { - error_report("Configuration section missing"); - return -EINVAL; - } - ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0); - - if (ret) { - return ret; - } - } while ((section_type = qemu_get_byte(f)) != QEMU_VM_EOF) { uint32_t instance_id, version_id, section_id; @@ -1122,16 +1736,14 @@ int qemu_loadvm_state(QEMUFile *f) if (se == NULL) { error_report("Unknown savevm section or instance '%s' %d", idstr, instance_id); - ret = -EINVAL; - goto out; + 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); - ret = -EINVAL; - goto out; + return -EINVAL; } /* Add entry */ @@ -1146,11 +1758,10 @@ int qemu_loadvm_state(QEMUFile *f) if (ret < 0) { error_report("error while loading state for instance 0x%x of" " device '%s'", instance_id, idstr); - goto out; + return ret; } if (!check_section_footer(f, le)) { - ret = -EINVAL; - goto out; + return -EINVAL; } break; case QEMU_VM_SECTION_PART: @@ -1165,29 +1776,88 @@ int qemu_loadvm_state(QEMUFile *f) } if (le == NULL) { error_report("Unknown savevm section %d", section_id); - ret = -EINVAL; - goto out; + return -EINVAL; } ret = vmstate_load(f, le->se, le->version_id); if (ret < 0) { error_report("error while loading state section id %d(%s)", section_id, le->se->idstr); - goto out; + return ret; } if (!check_section_footer(f, le)) { - ret = -EINVAL; - goto out; + return -EINVAL; + } + break; + case QEMU_VM_COMMAND: + ret = loadvm_process_command(f); + trace_qemu_loadvm_state_section_command(ret); + if ((ret < 0) || (ret & LOADVM_QUIT)) { + return ret; } break; default: error_report("Unknown savevm section type %d", section_type); - ret = -EINVAL; - goto out; + return -EINVAL; } } - file_error_after_eof = qemu_file_get_error(f); + return 0; +} + +int qemu_loadvm_state(QEMUFile *f) +{ + MigrationIncomingState *mis = migration_incoming_get_current(); + Error *local_err = NULL; + unsigned int v; + int ret; + + if (qemu_savevm_state_blocked(&local_err)) { + error_report_err(local_err); + return -EINVAL; + } + + v = qemu_get_be32(f); + if (v != QEMU_VM_FILE_MAGIC) { + error_report("Not a migration stream"); + 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"); + return -ENOTSUP; + } + if (v != QEMU_VM_FILE_VERSION) { + error_report("Unsupported migration stream version"); + return -ENOTSUP; + } + + if (!savevm_state.skip_configuration) { + if (qemu_get_byte(f) != QEMU_VM_CONFIGURATION) { + error_report("Configuration section missing"); + return -EINVAL; + } + ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0); + + if (ret) { + return ret; + } + } + + ret = qemu_loadvm_state_main(f, mis); + qemu_event_set(&mis->main_thread_load_event); + + trace_qemu_loadvm_state_post_main(ret); + + if (mis->have_listen_thread) { + /* Listen thread still going, can't clean up yet */ + return ret; + } + + if (ret == 0) { + ret = qemu_file_get_error(f); + } /* * Try to read in the VMDESC section as well, so that dumping tools that @@ -1199,10 +1869,10 @@ int qemu_loadvm_state(QEMUFile *f) * We also mustn't read data that isn't there; some transports (RDMA) * will stall waiting for that data when the source has already closed. */ - if (should_send_vmdesc()) { + if (ret == 0 && should_send_vmdesc()) { uint8_t *buf; uint32_t size; - section_type = qemu_get_byte(f); + uint8_t section_type = qemu_get_byte(f); if (section_type != QEMU_VM_VMDESCRIPTION) { error_report("Expected vmdescription section, but got %d", @@ -1226,14 +1896,6 @@ int qemu_loadvm_state(QEMUFile *f) cpu_synchronize_all_post_init(); - ret = 0; - -out: - if (ret == 0) { - /* We may not have a VMDESC section, so ignore relative errors */ - ret = file_error_after_eof; - } - return ret; } |