diff options
| -rw-r--r-- | MAINTAINERS | 1 | ||||
| -rw-r--r-- | include/migration/register.h | 15 | ||||
| -rw-r--r-- | migration/migration.c | 164 | ||||
| -rw-r--r-- | migration/multifd.c | 5 | ||||
| -rw-r--r-- | migration/multifd.h | 5 | ||||
| -rw-r--r-- | migration/options.c | 30 | ||||
| -rw-r--r-- | migration/options.h | 1 | ||||
| -rw-r--r-- | migration/ram.c | 168 | ||||
| -rw-r--r-- | migration/rdma.c | 191 | ||||
| -rw-r--r-- | migration/rdma.h | 3 | ||||
| -rw-r--r-- | migration/savevm.c | 33 | ||||
| -rw-r--r-- | migration/savevm.h | 1 | ||||
| -rwxr-xr-x | scripts/rdma-migration-helper.sh | 70 | ||||
| -rwxr-xr-x | scripts/vmstate-static-checker.py | 1 | ||||
| -rw-r--r-- | tests/qtest/migration/compression-tests.c | 22 | ||||
| -rw-r--r-- | tests/qtest/migration/cpr-tests.c | 6 | ||||
| -rw-r--r-- | tests/qtest/migration/file-tests.c | 58 | ||||
| -rw-r--r-- | tests/qtest/migration/framework.c | 75 | ||||
| -rw-r--r-- | tests/qtest/migration/framework.h | 9 | ||||
| -rw-r--r-- | tests/qtest/migration/misc-tests.c | 4 | ||||
| -rw-r--r-- | tests/qtest/migration/postcopy-tests.c | 8 | ||||
| -rw-r--r-- | tests/qtest/migration/precopy-tests.c | 91 | ||||
| -rw-r--r-- | tests/qtest/migration/tls-tests.c | 23 |
23 files changed, 614 insertions, 370 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index b3f9f2680b..8cd96269b2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3538,6 +3538,7 @@ R: Li Zhijian <lizhijian@fujitsu.com> R: Peter Xu <peterx@redhat.com> S: Odd Fixes F: migration/rdma* +F: scripts/rdma-migration-helper.sh Migration dirty limit and dirty page rate M: Hyman Huang <yong.huang@smartx.com> diff --git a/include/migration/register.h b/include/migration/register.h index c041ce32f2..b79dc81b8d 100644 --- a/include/migration/register.h +++ b/include/migration/register.h @@ -190,6 +190,21 @@ typedef struct SaveVMHandlers { /* This runs outside the BQL! */ /** + * @save_postcopy_prepare + * + * This hook will be invoked on the source side right before switching + * to postcopy (before VM stopped). + * + * @f: QEMUFile where to send the data + * @opaque: Data pointer passed to register_savevm_live() + * @errp: Error** used to report error message + * + * Returns: true if succeeded, false if error occured. When false is + * returned, @errp must be set. + */ + bool (*save_postcopy_prepare)(QEMUFile *f, void *opaque, Error **errp); + + /** * @state_pending_estimate * * This estimates the remaining data to transfer diff --git a/migration/migration.c b/migration/migration.c index 55ec4bfab6..4697732bef 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -95,6 +95,9 @@ enum mig_rp_message_type { MIG_RP_MSG_MAX }; +/* Migration channel types */ +enum { CH_MAIN, CH_MULTIFD, CH_POSTCOPY }; + /* When we add fault tolerance, we could have several migrations at once. For now we don't need to add dynamic creation of migration */ @@ -259,6 +262,24 @@ migration_channels_and_transport_compatible(MigrationAddress *addr, return true; } +static bool +migration_capabilities_and_transport_compatible(MigrationAddress *addr, + Error **errp) +{ + if (addr->transport == MIGRATION_ADDRESS_TYPE_RDMA) { + return migrate_rdma_caps_check(migrate_get_current()->capabilities, + errp); + } + + return true; +} + +static bool migration_transport_compatible(MigrationAddress *addr, Error **errp) +{ + return migration_channels_and_transport_compatible(addr, errp) && + migration_capabilities_and_transport_compatible(addr, errp); +} + static gint page_request_addr_cmp(gconstpointer ap, gconstpointer bp) { uintptr_t a = (uintptr_t) ap, b = (uintptr_t) bp; @@ -750,7 +771,7 @@ static void qemu_start_incoming_migration(const char *uri, bool has_channels, } /* transport mechanism not suitable for migration? */ - if (!migration_channels_and_transport_compatible(addr, errp)) { + if (!migration_transport_compatible(addr, errp)) { return; } @@ -769,14 +790,6 @@ static void qemu_start_incoming_migration(const char *uri, bool has_channels, } #ifdef CONFIG_RDMA } else if (addr->transport == MIGRATION_ADDRESS_TYPE_RDMA) { - if (migrate_xbzrle()) { - error_setg(errp, "RDMA and XBZRLE can't be used together"); - return; - } - if (migrate_multifd()) { - error_setg(errp, "RDMA and multifd can't be used together"); - return; - } rdma_start_incoming_migration(&addr->u.rdma, errp); #endif } else if (addr->transport == MIGRATION_ADDRESS_TYPE_EXEC) { @@ -931,9 +944,8 @@ static void migration_incoming_setup(QEMUFile *f) { MigrationIncomingState *mis = migration_incoming_get_current(); - if (!mis->from_src_file) { - mis->from_src_file = f; - } + assert(!mis->from_src_file); + mis->from_src_file = f; qemu_file_set_blocking(f, false); } @@ -985,28 +997,19 @@ void migration_fd_process_incoming(QEMUFile *f) migration_incoming_process(); } -/* - * Returns true when we want to start a new incoming migration process, - * false otherwise. - */ -static bool migration_should_start_incoming(bool main_channel) +static bool migration_has_main_and_multifd_channels(void) { - /* Multifd doesn't start unless all channels are established */ - if (migrate_multifd()) { - return migration_has_all_channels(); + MigrationIncomingState *mis = migration_incoming_get_current(); + if (!mis->from_src_file) { + /* main channel not established */ + return false; } - /* Preempt channel only starts when the main channel is created */ - if (migrate_postcopy_preempt()) { - return main_channel; + if (migrate_multifd() && !multifd_recv_all_channels_created()) { + return false; } - /* - * For all the rest types of migration, we should only reach here when - * it's the main channel that's being created, and we should always - * proceed with this channel. - */ - assert(main_channel); + /* main and all multifd channels are established */ return true; } @@ -1015,59 +1018,81 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp) MigrationIncomingState *mis = migration_incoming_get_current(); Error *local_err = NULL; QEMUFile *f; - bool default_channel = true; + uint8_t channel; uint32_t channel_magic = 0; int ret = 0; - if (migrate_multifd() && !migrate_mapped_ram() && - !migrate_postcopy_ram() && - qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) { - /* - * With multiple channels, it is possible that we receive channels - * out of order on destination side, causing incorrect mapping of - * source channels on destination side. Check channel MAGIC to - * decide type of channel. Please note this is best effort, postcopy - * preempt channel does not send any magic number so avoid it for - * postcopy live migration. Also tls live migration already does - * tls handshake while initializing main channel so with tls this - * issue is not possible. - */ - ret = migration_channel_read_peek(ioc, (void *)&channel_magic, - sizeof(channel_magic), errp); + if (!migration_has_main_and_multifd_channels()) { + if (qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) { + /* + * With multiple channels, it is possible that we receive channels + * out of order on destination side, causing incorrect mapping of + * source channels on destination side. Check channel MAGIC to + * decide type of channel. Please note this is best effort, + * postcopy preempt channel does not send any magic number so + * avoid it for postcopy live migration. Also tls live migration + * already does tls handshake while initializing main channel so + * with tls this issue is not possible. + */ + ret = migration_channel_read_peek(ioc, (void *)&channel_magic, + sizeof(channel_magic), errp); + if (ret != 0) { + return; + } - if (ret != 0) { + channel_magic = be32_to_cpu(channel_magic); + if (channel_magic == QEMU_VM_FILE_MAGIC) { + channel = CH_MAIN; + } else if (channel_magic == MULTIFD_MAGIC) { + assert(migrate_multifd()); + channel = CH_MULTIFD; + } else if (!mis->from_src_file && + mis->state == MIGRATION_STATUS_POSTCOPY_PAUSED) { + /* reconnect main channel for postcopy recovery */ + channel = CH_MAIN; + } else { + error_setg(errp, "unknown channel magic: %u", channel_magic); + return; + } + } else if (mis->from_src_file && migrate_multifd()) { + /* + * Non-peekable channels like tls/file are processed as + * multifd channels when multifd is enabled. + */ + channel = CH_MULTIFD; + } else if (!mis->from_src_file) { + channel = CH_MAIN; + } else { + error_setg(errp, "non-peekable channel used without multifd"); return; } - - default_channel = (channel_magic == cpu_to_be32(QEMU_VM_FILE_MAGIC)); } else { - default_channel = !mis->from_src_file; + assert(migrate_postcopy_preempt()); + channel = CH_POSTCOPY; } if (multifd_recv_setup(errp) != 0) { return; } - if (default_channel) { + if (channel == CH_MAIN) { f = qemu_file_new_input(ioc); migration_incoming_setup(f); - } else { + } else if (channel == CH_MULTIFD) { /* Multiple connections */ - assert(migration_needs_multiple_sockets()); - if (migrate_multifd()) { - multifd_recv_new_channel(ioc, &local_err); - } else { - assert(migrate_postcopy_preempt()); - f = qemu_file_new_input(ioc); - postcopy_preempt_new_channel(mis, f); - } + multifd_recv_new_channel(ioc, &local_err); if (local_err) { error_propagate(errp, local_err); return; } + } else if (channel == CH_POSTCOPY) { + assert(!mis->postcopy_qemufile_dst); + f = qemu_file_new_input(ioc); + postcopy_preempt_new_channel(mis, f); + return; } - if (migration_should_start_incoming(default_channel)) { + if (migration_has_main_and_multifd_channels()) { /* If it's a recovery, we're done */ if (postcopy_try_recover()) { return; @@ -1084,18 +1109,13 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp) */ bool migration_has_all_channels(void) { - MigrationIncomingState *mis = migration_incoming_get_current(); - - if (!mis->from_src_file) { + if (!migration_has_main_and_multifd_channels()) { return false; } - if (migrate_multifd()) { - return multifd_recv_all_channels_created(); - } - - if (migrate_postcopy_preempt()) { - return mis->postcopy_qemufile_dst != NULL; + MigrationIncomingState *mis = migration_incoming_get_current(); + if (migrate_postcopy_preempt() && !mis->postcopy_qemufile_dst) { + return false; } return true; @@ -2208,7 +2228,7 @@ void qmp_migrate(const char *uri, bool has_channels, } /* transport mechanism not suitable for migration? */ - if (!migration_channels_and_transport_compatible(addr, errp)) { + if (!migration_transport_compatible(addr, errp)) { return; } @@ -2707,6 +2727,10 @@ static int postcopy_start(MigrationState *ms, Error **errp) } } + if (!qemu_savevm_state_postcopy_prepare(ms->to_dst_file, errp)) { + return -1; + } + trace_postcopy_start(); bql_lock(); trace_postcopy_start_set_run(); diff --git a/migration/multifd.c b/migration/multifd.c index 86c83e43c0..ec108af624 100644 --- a/migration/multifd.c +++ b/migration/multifd.c @@ -36,11 +36,6 @@ #include "io/channel-socket.h" #include "yank_functions.h" -/* Multiple fd's */ - -#define MULTIFD_MAGIC 0x11223344U -#define MULTIFD_VERSION 1 - typedef struct { uint32_t magic; uint32_t version; diff --git a/migration/multifd.h b/migration/multifd.h index 2d337e7b3b..9b6d81e7ed 100644 --- a/migration/multifd.h +++ b/migration/multifd.h @@ -49,6 +49,11 @@ bool multifd_queue_page(RAMBlock *block, ram_addr_t offset); bool multifd_recv(void); MultiFDRecvData *multifd_get_recv_data(void); +/* Multiple fd's */ + +#define MULTIFD_MAGIC 0x11223344U +#define MULTIFD_VERSION 1 + /* Multifd Compression flags */ #define MULTIFD_FLAG_SYNC (1 << 0) diff --git a/migration/options.c b/migration/options.c index b0ac2ea408..b6ae95358d 100644 --- a/migration/options.c +++ b/migration/options.c @@ -448,6 +448,24 @@ static bool migrate_incoming_started(void) return !!migration_incoming_get_current()->transport_data; } +bool migrate_rdma_caps_check(bool *caps, Error **errp) +{ + if (caps[MIGRATION_CAPABILITY_XBZRLE]) { + error_setg(errp, "RDMA and XBZRLE can't be used together"); + return false; + } + if (caps[MIGRATION_CAPABILITY_MULTIFD]) { + error_setg(errp, "RDMA and multifd can't be used together"); + return false; + } + if (caps[MIGRATION_CAPABILITY_POSTCOPY_RAM]) { + error_setg(errp, "RDMA and postcopy-ram can't be used together"); + return false; + } + + return true; +} + /** * @migration_caps_check - check capability compatibility * @@ -611,6 +629,13 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp) } } + /* + * On destination side, check the cases that capability is being set + * after incoming thread has started. + */ + if (migrate_rdma() && !migrate_rdma_caps_check(new_caps, errp)) { + return false; + } return true; } @@ -1193,6 +1218,11 @@ static void migrate_params_test_apply(MigrateSetParameters *params, dest->tls_hostname = params->tls_hostname->u.s; } + if (params->tls_authz) { + assert(params->tls_authz->type == QTYPE_QSTRING); + dest->tls_authz = params->tls_authz->u.s; + } + if (params->has_max_bandwidth) { dest->max_bandwidth = params->max_bandwidth; } diff --git a/migration/options.h b/migration/options.h index 762be4e641..82d839709e 100644 --- a/migration/options.h +++ b/migration/options.h @@ -57,6 +57,7 @@ bool migrate_tls(void); /* capabilities helpers */ +bool migrate_rdma_caps_check(bool *caps, Error **errp); bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp); /* parameters */ diff --git a/migration/ram.c b/migration/ram.c index cb8b2ed493..e12913b43e 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -91,6 +91,36 @@ XBZRLECacheStats xbzrle_counters; +/* + * This structure locates a specific location of a guest page. In QEMU, + * it's described in a tuple of (ramblock, offset). + */ +struct PageLocation { + RAMBlock *block; + unsigned long offset; +}; +typedef struct PageLocation PageLocation; + +/** + * PageLocationHint: describes a hint to a page location + * + * @valid set if the hint is vaild and to be consumed + * @location: the hint content + * + * In postcopy preempt mode, the urgent channel may provide hints to the + * background channel, so that QEMU source can try to migrate whatever is + * right after the requested urgent pages. + * + * This is based on the assumption that the VM (already running on the + * destination side) tends to access the memory with spatial locality. + * This is also the default behavior of vanilla postcopy (preempt off). + */ +struct PageLocationHint { + bool valid; + PageLocation location; +}; +typedef struct PageLocationHint PageLocationHint; + /* used by the search for pages to send */ struct PageSearchStatus { /* The migration channel used for a specific host page */ @@ -395,6 +425,13 @@ struct RAMState { * RAM migration. */ unsigned int postcopy_bmap_sync_requested; + /* + * Page hint during postcopy when preempt mode is on. Return path + * thread sets it, while background migration thread consumes it. + * + * Protected by @bitmap_mutex. + */ + PageLocationHint page_hint; }; typedef struct RAMState RAMState; @@ -1144,32 +1181,6 @@ static int save_zero_page(RAMState *rs, PageSearchStatus *pss, } /* - * @pages: the number of pages written by the control path, - * < 0 - error - * > 0 - number of pages written - * - * Return true if the pages has been saved, otherwise false is returned. - */ -static bool control_save_page(PageSearchStatus *pss, - ram_addr_t offset, int *pages) -{ - int ret; - - ret = rdma_control_save_page(pss->pss_channel, pss->block->offset, offset, - TARGET_PAGE_SIZE); - if (ret == RAM_SAVE_CONTROL_NOT_SUPP) { - return false; - } - - if (ret == RAM_SAVE_CONTROL_DELAYED) { - *pages = 1; - return true; - } - *pages = ret; - return true; -} - -/* * directly send the page to the stream * * Returns the number of pages written. @@ -1965,7 +1976,13 @@ static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss) int res; /* Hand over to RDMA first */ - if (control_save_page(pss, offset, &res)) { + if (migrate_rdma()) { + res = rdma_control_save_page(pss->pss_channel, pss->block->offset, + offset, TARGET_PAGE_SIZE); + + if (res == RAM_SAVE_CONTROL_DELAYED) { + res = 1; + } return res; } @@ -2039,6 +2056,21 @@ static void pss_host_page_finish(PageSearchStatus *pss) pss->host_page_start = pss->host_page_end = 0; } +static void ram_page_hint_update(RAMState *rs, PageSearchStatus *pss) +{ + PageLocationHint *hint = &rs->page_hint; + + /* If there's a pending hint not consumed, don't bother */ + if (hint->valid) { + return; + } + + /* Provide a hint to the background stream otherwise */ + hint->location.block = pss->block; + hint->location.offset = pss->page; + hint->valid = true; +} + /* * Send an urgent host page specified by `pss'. Need to be called with * bitmap_mutex held. @@ -2084,6 +2116,7 @@ out: /* For urgent requests, flush immediately if sent */ if (sent) { qemu_fflush(pss->pss_channel); + ram_page_hint_update(rs, pss); } return ret; } @@ -2171,6 +2204,30 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss) return (res < 0 ? res : pages); } +static bool ram_page_hint_valid(RAMState *rs) +{ + /* There's only page hint during postcopy preempt mode */ + if (!postcopy_preempt_active()) { + return false; + } + + return rs->page_hint.valid; +} + +static void ram_page_hint_collect(RAMState *rs, RAMBlock **block, + unsigned long *page) +{ + PageLocationHint *hint = &rs->page_hint; + + assert(hint->valid); + + *block = hint->location.block; + *page = hint->location.offset; + + /* Mark the hint consumed */ + hint->valid = false; +} + /** * ram_find_and_save_block: finds a dirty page and sends it to f * @@ -2187,6 +2244,8 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss) static int ram_find_and_save_block(RAMState *rs) { PageSearchStatus *pss = &rs->pss[RAM_CHANNEL_PRECOPY]; + unsigned long next_page; + RAMBlock *next_block; int pages = 0; /* No dirty page as there is zero RAM */ @@ -2206,7 +2265,14 @@ static int ram_find_and_save_block(RAMState *rs) rs->last_page = 0; } - pss_init(pss, rs->last_seen_block, rs->last_page); + if (ram_page_hint_valid(rs)) { + ram_page_hint_collect(rs, &next_block, &next_page); + } else { + next_block = rs->last_seen_block; + next_page = rs->last_page; + } + + pss_init(pss, next_block, next_page); while (true){ if (!get_queued_page(rs, pss)) { @@ -2339,6 +2405,13 @@ static void ram_save_cleanup(void *opaque) ram_state_cleanup(rsp); } +static void ram_page_hint_reset(PageLocationHint *hint) +{ + hint->location.block = NULL; + hint->location.offset = 0; + hint->valid = false; +} + static void ram_state_reset(RAMState *rs) { int i; @@ -2351,6 +2424,8 @@ static void ram_state_reset(RAMState *rs) rs->last_page = 0; rs->last_version = ram_list.version; rs->xbzrle_started = false; + + ram_page_hint_reset(&rs->page_hint); } #define MAX_WAIT 50 /* ms, half buffered_file limit */ @@ -4418,6 +4493,42 @@ static int ram_resume_prepare(MigrationState *s, void *opaque) return 0; } +static bool ram_save_postcopy_prepare(QEMUFile *f, void *opaque, Error **errp) +{ + int ret; + + if (migrate_multifd()) { + /* + * When multifd is enabled, source QEMU needs to make sure all the + * pages queued before postcopy starts have been flushed. + * + * The load of these pages must happen before switching to postcopy. + * It's because loading of guest pages (so far) in multifd recv + * threads is still non-atomic, so the load cannot happen with vCPUs + * running on the destination side. + * + * This flush and sync will guarantee that those pages are loaded + * _before_ postcopy starts on the destination. The rationale is, + * this happens before VM stops (and before source QEMU sends all + * the rest of the postcopy messages). So when the destination QEMU + * receives the postcopy messages, it must have received the sync + * message on the main channel (either RAM_SAVE_FLAG_MULTIFD_FLUSH, + * or RAM_SAVE_FLAG_EOS), and such message would guarantee that + * all previous guest pages queued in the multifd channels are + * completely loaded. + */ + ret = multifd_ram_flush_and_sync(f); + if (ret < 0) { + error_setg(errp, "%s: multifd flush and sync failed", __func__); + return false; + } + } + + qemu_put_be64(f, RAM_SAVE_FLAG_EOS); + + return true; +} + void postcopy_preempt_shutdown_file(MigrationState *s) { qemu_put_be64(s->postcopy_qemufile_src, RAM_SAVE_FLAG_EOS); @@ -4437,6 +4548,7 @@ static SaveVMHandlers savevm_ram_handlers = { .load_setup = ram_load_setup, .load_cleanup = ram_load_cleanup, .resume_prepare = ram_resume_prepare, + .save_postcopy_prepare = ram_save_postcopy_prepare, }; static void ram_mig_ram_block_resized(RAMBlockNotifier *n, void *host, diff --git a/migration/rdma.c b/migration/rdma.c index b31652baac..2d839fce6c 100644 --- a/migration/rdma.c +++ b/migration/rdma.c @@ -768,156 +768,12 @@ static void qemu_rdma_dump_gid(const char *who, struct rdma_cm_id *id) } /* - * As of now, IPv6 over RoCE / iWARP is not supported by linux. - * We will try the next addrinfo struct, and fail if there are - * no other valid addresses to bind against. - * - * If user is listening on '[::]', then we will not have a opened a device - * yet and have no way of verifying if the device is RoCE or not. - * - * In this case, the source VM will throw an error for ALL types of - * connections (both IPv4 and IPv6) if the destination machine does not have - * a regular infiniband network available for use. - * - * The only way to guarantee that an error is thrown for broken kernels is - * for the management software to choose a *specific* interface at bind time - * and validate what time of hardware it is. - * - * Unfortunately, this puts the user in a fix: - * - * If the source VM connects with an IPv4 address without knowing that the - * destination has bound to '[::]' the migration will unconditionally fail - * unless the management software is explicitly listening on the IPv4 - * address while using a RoCE-based device. - * - * If the source VM connects with an IPv6 address, then we're OK because we can - * throw an error on the source (and similarly on the destination). - * - * But in mixed environments, this will be broken for a while until it is fixed - * inside linux. - * - * We do provide a *tiny* bit of help in this function: We can list all of the - * devices in the system and check to see if all the devices are RoCE or - * Infiniband. - * - * If we detect that we have a *pure* RoCE environment, then we can safely - * thrown an error even if the management software has specified '[::]' as the - * bind address. - * - * However, if there is are multiple hetergeneous devices, then we cannot make - * this assumption and the user just has to be sure they know what they are - * doing. - * - * Patches are being reviewed on linux-rdma. - */ -static int qemu_rdma_broken_ipv6_kernel(struct ibv_context *verbs, Error **errp) -{ - /* This bug only exists in linux, to our knowledge. */ -#ifdef CONFIG_LINUX - struct ibv_port_attr port_attr; - - /* - * Verbs are only NULL if management has bound to '[::]'. - * - * Let's iterate through all the devices and see if there any pure IB - * devices (non-ethernet). - * - * If not, then we can safely proceed with the migration. - * Otherwise, there are no guarantees until the bug is fixed in linux. - */ - if (!verbs) { - int num_devices; - struct ibv_device **dev_list = ibv_get_device_list(&num_devices); - bool roce_found = false; - bool ib_found = false; - - for (int x = 0; x < num_devices; x++) { - verbs = ibv_open_device(dev_list[x]); - /* - * ibv_open_device() is not documented to set errno. If - * it does, it's somebody else's doc bug. If it doesn't, - * the use of errno below is wrong. - * TODO Find out whether ibv_open_device() sets errno. - */ - if (!verbs) { - if (errno == EPERM) { - continue; - } else { - error_setg_errno(errp, errno, - "could not open RDMA device context"); - return -1; - } - } - - if (ibv_query_port(verbs, 1, &port_attr)) { - ibv_close_device(verbs); - error_setg(errp, - "RDMA ERROR: Could not query initial IB port"); - return -1; - } - - if (port_attr.link_layer == IBV_LINK_LAYER_INFINIBAND) { - ib_found = true; - } else if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) { - roce_found = true; - } - - ibv_close_device(verbs); - - } - - if (roce_found) { - if (ib_found) { - warn_report("migrations may fail:" - " IPv6 over RoCE / iWARP in linux" - " is broken. But since you appear to have a" - " mixed RoCE / IB environment, be sure to only" - " migrate over the IB fabric until the kernel " - " fixes the bug."); - } else { - error_setg(errp, "RDMA ERROR: " - "You only have RoCE / iWARP devices in your systems" - " and your management software has specified '[::]'" - ", but IPv6 over RoCE / iWARP is not supported in Linux."); - return -1; - } - } - - return 0; - } - - /* - * If we have a verbs context, that means that some other than '[::]' was - * used by the management software for binding. In which case we can - * actually warn the user about a potentially broken kernel. - */ - - /* IB ports start with 1, not 0 */ - if (ibv_query_port(verbs, 1, &port_attr)) { - error_setg(errp, "RDMA ERROR: Could not query initial IB port"); - return -1; - } - - if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) { - error_setg(errp, "RDMA ERROR: " - "Linux kernel's RoCE / iWARP does not support IPv6 " - "(but patches on linux-rdma in progress)"); - return -1; - } - -#endif - - return 0; -} - -/* * Figure out which RDMA device corresponds to the requested IP hostname * Also create the initial connection manager identifiers for opening * the connection. */ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp) { - Error *err = NULL; int ret; struct rdma_addrinfo *res; char port_str[16]; @@ -953,9 +809,8 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp) goto err_resolve_get_addr; } - /* Try all addresses, saving the first error in @err */ + /* Try all addresses, exit loop on first success of resolving address */ for (struct rdma_addrinfo *e = res; e != NULL; e = e->ai_next) { - Error **local_errp = err ? NULL : &err; inet_ntop(e->ai_family, &((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip); @@ -964,25 +819,12 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp) ret = rdma_resolve_addr(rdma->cm_id, NULL, e->ai_dst_addr, RDMA_RESOLVE_TIMEOUT_MS); if (ret >= 0) { - if (e->ai_family == AF_INET6) { - ret = qemu_rdma_broken_ipv6_kernel(rdma->cm_id->verbs, - local_errp); - if (ret < 0) { - continue; - } - } - error_free(err); goto route; } } rdma_freeaddrinfo(res); - if (err) { - error_propagate(errp, err); - } else { - error_setg(errp, "RDMA ERROR: could not resolve address %s", - rdma->host); - } + error_setg(errp, "RDMA ERROR: could not resolve address %s", rdma->host); goto err_resolve_get_addr; route: @@ -2611,7 +2453,6 @@ err_rdma_source_connect: static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp) { - Error *err = NULL; int ret; struct rdma_cm_id *listen_id; char ip[40] = "unknown"; @@ -2661,9 +2502,8 @@ static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp) goto err_dest_init_bind_addr; } - /* Try all addresses, saving the first error in @err */ + /* Try all addresses */ for (e = res; e != NULL; e = e->ai_next) { - Error **local_errp = err ? NULL : &err; inet_ntop(e->ai_family, &((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip); @@ -2672,24 +2512,12 @@ static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp) if (ret < 0) { continue; } - if (e->ai_family == AF_INET6) { - ret = qemu_rdma_broken_ipv6_kernel(listen_id->verbs, - local_errp); - if (ret < 0) { - continue; - } - } - error_free(err); break; } rdma_freeaddrinfo(res); if (!e) { - if (err) { - error_propagate(errp, err); - } else { - error_setg(errp, "RDMA ERROR: Error: could not rdma_bind_addr!"); - } + error_setg(errp, "RDMA ERROR: Error: could not rdma_bind_addr!"); goto err_dest_init_bind_addr; } @@ -3284,14 +3112,11 @@ err: int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset, ram_addr_t offset, size_t size) { - if (!migrate_rdma() || migration_in_postcopy()) { - return RAM_SAVE_CONTROL_NOT_SUPP; - } + assert(migrate_rdma()); int ret = qemu_rdma_save_page(f, block_offset, offset, size); - if (ret != RAM_SAVE_CONTROL_DELAYED && - ret != RAM_SAVE_CONTROL_NOT_SUPP) { + if (ret != RAM_SAVE_CONTROL_DELAYED) { if (ret < 0) { qemu_file_set_error(f, ret); } @@ -3829,7 +3654,7 @@ int rdma_block_notification_handle(QEMUFile *f, const char *name) int rdma_registration_start(QEMUFile *f, uint64_t flags) { - if (!migrate_rdma() || migration_in_postcopy()) { + if (!migrate_rdma()) { return 0; } @@ -3861,7 +3686,7 @@ int rdma_registration_stop(QEMUFile *f, uint64_t flags) RDMAControlHeader head = { .len = 0, .repeat = 1 }; int ret; - if (!migrate_rdma() || migration_in_postcopy()) { + if (!migrate_rdma()) { return 0; } diff --git a/migration/rdma.h b/migration/rdma.h index 4d3386b84a..f74f16a459 100644 --- a/migration/rdma.h +++ b/migration/rdma.h @@ -33,7 +33,6 @@ void rdma_start_incoming_migration(InetSocketAddress *host_port, Error **errp); #define RAM_CONTROL_ROUND 1 #define RAM_CONTROL_FINISH 3 -#define RAM_SAVE_CONTROL_NOT_SUPP -1000 #define RAM_SAVE_CONTROL_DELAYED -2000 #ifdef CONFIG_RDMA @@ -56,7 +55,7 @@ static inline int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset, ram_addr_t offset, size_t size) { - return RAM_SAVE_CONTROL_NOT_SUPP; + g_assert_not_reached(); } #endif #endif diff --git a/migration/savevm.c b/migration/savevm.c index 0c12e373b4..006514c3e3 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1523,6 +1523,39 @@ void qemu_savevm_state_complete_postcopy(QEMUFile *f) qemu_fflush(f); } +bool qemu_savevm_state_postcopy_prepare(QEMUFile *f, Error **errp) +{ + SaveStateEntry *se; + bool ret; + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->ops || !se->ops->save_postcopy_prepare) { + continue; + } + + if (se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + + trace_savevm_section_start(se->idstr, se->section_id); + + save_section_header(f, se, QEMU_VM_SECTION_PART); + ret = se->ops->save_postcopy_prepare(f, se->opaque, errp); + save_section_footer(f, se); + + trace_savevm_section_end(se->idstr, se->section_id, ret); + + if (!ret) { + assert(*errp); + return false; + } + } + + return true; +} + int qemu_savevm_state_complete_precopy_iterable(QEMUFile *f, bool in_postcopy) { int64_t start_ts_each, end_ts_each; diff --git a/migration/savevm.h b/migration/savevm.h index 138c39a7f9..2d5e9c7166 100644 --- a/migration/savevm.h +++ b/migration/savevm.h @@ -45,6 +45,7 @@ void qemu_savevm_state_pending_exact(uint64_t *must_precopy, void qemu_savevm_state_pending_estimate(uint64_t *must_precopy, uint64_t *can_postcopy); int qemu_savevm_state_complete_precopy_iterable(QEMUFile *f, bool in_postcopy); +bool qemu_savevm_state_postcopy_prepare(QEMUFile *f, Error **errp); void qemu_savevm_send_ping(QEMUFile *f, uint32_t value); void qemu_savevm_send_open_return_path(QEMUFile *f); int qemu_savevm_send_packaged(QEMUFile *f, const uint8_t *buf, size_t len); diff --git a/scripts/rdma-migration-helper.sh b/scripts/rdma-migration-helper.sh new file mode 100755 index 0000000000..a39f2fb0e5 --- /dev/null +++ b/scripts/rdma-migration-helper.sh @@ -0,0 +1,70 @@ +#!/bin/bash + +# Copied from blktests +get_ipv4_addr() +{ + ip -4 -o addr show dev "$1" | + sed -n 's/.*[[:blank:]]inet[[:blank:]]*\([^[:blank:]/]*\).*/\1/p' | + head -1 | tr -d '\n' +} + +# existing rdma interfaces +rdma_interfaces() +{ + rdma link show | sed -nE 's/^link .* netdev ([^ ]+).*$/\1 /p' +} + +# existing valid ipv4 interfaces +ipv4_interfaces() +{ + ip -o addr show | awk '/inet / {print $2}' | grep -v -w lo +} + +rdma_rxe_detect() +{ + for r in $(rdma_interfaces) + do + ipv4_interfaces | grep -qw $r && get_ipv4_addr $r && return + done + + return 1 +} + +rdma_rxe_setup() +{ + for i in $(ipv4_interfaces) + do + rdma_interfaces | grep -qw $i && continue + rdma link add "${i}_rxe" type rxe netdev "$i" && { + echo "Setup new rdma/rxe ${i}_rxe for $i with $(get_ipv4_addr $i)" + return + } + done + + echo "Failed to setup any new rdma/rxe link" >&2 + return 1 +} + +rdma_rxe_clean() +{ + modprobe -r rdma_rxe +} + +operation=${1:-detect} + +command -v rdma >/dev/null || { + echo "Command 'rdma' is not available, please install it first." >&2 + exit 1 +} + +if [ "$operation" == "setup" ] || [ "$operation" == "clean" ]; then + [ "$UID" == 0 ] || { + echo "Root privilege is required to setup/clean a rdma/rxe link" >&2 + exit 1 + } + rdma_rxe_"$operation" +elif [ "$operation" == "detect" ]; then + rdma_rxe_detect +else + echo "Usage: $0 [setup | detect | clean]" +fi diff --git a/scripts/vmstate-static-checker.py b/scripts/vmstate-static-checker.py index 9c0e6b81f2..25aca839a0 100755 --- a/scripts/vmstate-static-checker.py +++ b/scripts/vmstate-static-checker.py @@ -42,6 +42,7 @@ def check_fields_match(name, s_field, d_field): # Some fields changed names between qemu versions. This list # is used to allow such changes in each section / description. changed_names = { + 'acpi-ghes': ['ghes_addr_le', 'hw_error_le'], 'apic': ['timer', 'timer_expiry'], 'e1000': ['dev', 'parent_obj'], 'ehci': ['dev', 'pcidev'], diff --git a/tests/qtest/migration/compression-tests.c b/tests/qtest/migration/compression-tests.c index 8b58401b84..41e79f031b 100644 --- a/tests/qtest/migration/compression-tests.c +++ b/tests/qtest/migration/compression-tests.c @@ -35,6 +35,9 @@ static void test_multifd_tcp_zstd(void) { MigrateCommon args = { .listen_uri = "defer", + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, .start_hook = migrate_hook_start_precopy_tcp_multifd_zstd, }; test_precopy_common(&args); @@ -56,6 +59,9 @@ static void test_multifd_tcp_qatzip(void) { MigrateCommon args = { .listen_uri = "defer", + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, .start_hook = migrate_hook_start_precopy_tcp_multifd_qatzip, }; test_precopy_common(&args); @@ -74,6 +80,9 @@ static void test_multifd_tcp_qpl(void) { MigrateCommon args = { .listen_uri = "defer", + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, .start_hook = migrate_hook_start_precopy_tcp_multifd_qpl, }; test_precopy_common(&args); @@ -92,6 +101,9 @@ static void test_multifd_tcp_uadk(void) { MigrateCommon args = { .listen_uri = "defer", + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, .start_hook = migrate_hook_start_precopy_tcp_multifd_uadk, }; test_precopy_common(&args); @@ -103,10 +115,6 @@ migrate_hook_start_xbzrle(QTestState *from, QTestState *to) { migrate_set_parameter_int(from, "xbzrle-cache-size", 33554432); - - migrate_set_capability(from, "xbzrle", true); - migrate_set_capability(to, "xbzrle", true); - return NULL; } @@ -118,6 +126,9 @@ static void test_precopy_unix_xbzrle(void) .listen_uri = uri, .start_hook = migrate_hook_start_xbzrle, .iterations = 2, + .start = { + .caps[MIGRATION_CAPABILITY_XBZRLE] = true, + }, /* * XBZRLE needs pages to be modified when doing the 2nd+ round * iteration to have real data pushed to the stream. @@ -146,6 +157,9 @@ static void test_multifd_tcp_zlib(void) { MigrateCommon args = { .listen_uri = "defer", + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, .start_hook = migrate_hook_start_precopy_tcp_multifd_zlib, }; test_precopy_common(&args); diff --git a/tests/qtest/migration/cpr-tests.c b/tests/qtest/migration/cpr-tests.c index 4758841824..5536e14610 100644 --- a/tests/qtest/migration/cpr-tests.c +++ b/tests/qtest/migration/cpr-tests.c @@ -24,9 +24,6 @@ static void *migrate_hook_start_mode_reboot(QTestState *from, QTestState *to) migrate_set_parameter_str(from, "mode", "cpr-reboot"); migrate_set_parameter_str(to, "mode", "cpr-reboot"); - migrate_set_capability(from, "x-ignore-shared", true); - migrate_set_capability(to, "x-ignore-shared", true); - return NULL; } @@ -39,6 +36,9 @@ static void test_mode_reboot(void) .connect_uri = uri, .listen_uri = "defer", .start_hook = migrate_hook_start_mode_reboot, + .start = { + .caps[MIGRATION_CAPABILITY_X_IGNORE_SHARED] = true, + }, }; test_file_common(&args, true); diff --git a/tests/qtest/migration/file-tests.c b/tests/qtest/migration/file-tests.c index f260e2871d..4d78ce0855 100644 --- a/tests/qtest/migration/file-tests.c +++ b/tests/qtest/migration/file-tests.c @@ -107,15 +107,6 @@ static void test_precopy_file_offset_bad(void) test_file_common(&args, false); } -static void *migrate_hook_start_mapped_ram(QTestState *from, - QTestState *to) -{ - migrate_set_capability(from, "mapped-ram", true); - migrate_set_capability(to, "mapped-ram", true); - - return NULL; -} - static void test_precopy_file_mapped_ram_live(void) { g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs, @@ -123,7 +114,9 @@ static void test_precopy_file_mapped_ram_live(void) MigrateCommon args = { .connect_uri = uri, .listen_uri = "defer", - .start_hook = migrate_hook_start_mapped_ram, + .start = { + .caps[MIGRATION_CAPABILITY_MAPPED_RAM] = true, + }, }; test_file_common(&args, false); @@ -136,26 +129,14 @@ static void test_precopy_file_mapped_ram(void) MigrateCommon args = { .connect_uri = uri, .listen_uri = "defer", - .start_hook = migrate_hook_start_mapped_ram, + .start = { + .caps[MIGRATION_CAPABILITY_MAPPED_RAM] = true, + }, }; test_file_common(&args, true); } -static void *migrate_hook_start_multifd_mapped_ram(QTestState *from, - QTestState *to) -{ - migrate_hook_start_mapped_ram(from, to); - - migrate_set_parameter_int(from, "multifd-channels", 4); - migrate_set_parameter_int(to, "multifd-channels", 4); - - migrate_set_capability(from, "multifd", true); - migrate_set_capability(to, "multifd", true); - - return NULL; -} - static void test_multifd_file_mapped_ram_live(void) { g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs, @@ -163,7 +144,10 @@ static void test_multifd_file_mapped_ram_live(void) MigrateCommon args = { .connect_uri = uri, .listen_uri = "defer", - .start_hook = migrate_hook_start_multifd_mapped_ram, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + .caps[MIGRATION_CAPABILITY_MAPPED_RAM] = true, + }, }; test_file_common(&args, false); @@ -176,7 +160,10 @@ static void test_multifd_file_mapped_ram(void) MigrateCommon args = { .connect_uri = uri, .listen_uri = "defer", - .start_hook = migrate_hook_start_multifd_mapped_ram, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + .caps[MIGRATION_CAPABILITY_MAPPED_RAM] = true, + }, }; test_file_common(&args, true); @@ -185,8 +172,6 @@ static void test_multifd_file_mapped_ram(void) static void *migrate_hook_start_multifd_mapped_ram_dio(QTestState *from, QTestState *to) { - migrate_hook_start_multifd_mapped_ram(from, to); - migrate_set_parameter_bool(from, "direct-io", true); migrate_set_parameter_bool(to, "direct-io", true); @@ -201,6 +186,10 @@ static void test_multifd_file_mapped_ram_dio(void) .connect_uri = uri, .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_mapped_ram_dio, + .start = { + .caps[MIGRATION_CAPABILITY_MAPPED_RAM] = true, + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, }; if (!probe_o_direct_support(tmpfs)) { @@ -246,7 +235,6 @@ static void *migrate_hook_start_multifd_mapped_ram_fdset_dio(QTestState *from, fdset_add_fds(from, file, O_WRONLY, 2, true); fdset_add_fds(to, file, O_RDONLY, 2, true); - migrate_hook_start_multifd_mapped_ram(from, to); migrate_set_parameter_bool(from, "direct-io", true); migrate_set_parameter_bool(to, "direct-io", true); @@ -261,8 +249,6 @@ static void *migrate_hook_start_multifd_mapped_ram_fdset(QTestState *from, fdset_add_fds(from, file, O_WRONLY, 2, false); fdset_add_fds(to, file, O_RDONLY, 2, false); - migrate_hook_start_multifd_mapped_ram(from, to); - return NULL; } @@ -275,6 +261,10 @@ static void test_multifd_file_mapped_ram_fdset(void) .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_mapped_ram_fdset, .end_hook = migrate_hook_end_multifd_mapped_ram_fdset, + .start = { + .caps[MIGRATION_CAPABILITY_MAPPED_RAM] = true, + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, }; test_file_common(&args, true); @@ -289,6 +279,10 @@ static void test_multifd_file_mapped_ram_fdset_dio(void) .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_mapped_ram_fdset_dio, .end_hook = migrate_hook_end_multifd_mapped_ram_fdset, + .start = { + .caps[MIGRATION_CAPABILITY_MAPPED_RAM] = true, + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, }; if (!probe_o_direct_support(tmpfs)) { diff --git a/tests/qtest/migration/framework.c b/tests/qtest/migration/framework.c index 10e1d04b58..e48b80a127 100644 --- a/tests/qtest/migration/framework.c +++ b/tests/qtest/migration/framework.c @@ -30,6 +30,7 @@ #define QEMU_VM_FILE_MAGIC 0x5145564d #define QEMU_ENV_SRC "QTEST_QEMU_BINARY_SRC" #define QEMU_ENV_DST "QTEST_QEMU_BINARY_DST" +#define MULTIFD_TEST_CHANNELS 4 unsigned start_address; unsigned end_address; @@ -207,6 +208,51 @@ static QList *migrate_start_get_qmp_capabilities(const MigrateStart *args) return capabilities; } +static void migrate_start_set_capabilities(QTestState *from, QTestState *to, + MigrateStart *args) +{ + /* + * MigrationCapability_lookup and MIGRATION_CAPABILITY_ constants + * are from qapi-types-migration.h. + */ + for (uint8_t i = 0; i < MIGRATION_CAPABILITY__MAX; i++) { + if (!args->caps[i]) { + continue; + } + if (from) { + migrate_set_capability(from, + MigrationCapability_lookup.array[i], true); + } + if (to) { + migrate_set_capability(to, + MigrationCapability_lookup.array[i], true); + } + } + + /* + * Always enable migration events. Libvirt always uses it, let's try + * to mimic as closer as that. + */ + migrate_set_capability(from, "events", true); + if (!args->defer_target_connect) { + migrate_set_capability(to, "events", true); + } + + /* + * Default number of channels should be fine for most + * tests. Individual tests can override by calling + * migrate_set_parameter() directly. + */ + if (args->caps[MIGRATION_CAPABILITY_MULTIFD]) { + migrate_set_parameter_int(from, "multifd-channels", + MULTIFD_TEST_CHANNELS); + migrate_set_parameter_int(to, "multifd-channels", + MULTIFD_TEST_CHANNELS); + } + + return; +} + int migrate_start(QTestState **from, QTestState **to, const char *uri, MigrateStart *args) { @@ -379,14 +425,7 @@ int migrate_start(QTestState **from, QTestState **to, const char *uri, unlink(shmem_path); } - /* - * Always enable migration events. Libvirt always uses it, let's try - * to mimic as closer as that. - */ - migrate_set_capability(*from, "events", true); - if (!args->defer_target_connect) { - migrate_set_capability(*to, "events", true); - } + migrate_start_set_capabilities(*from, *to, args); return 0; } @@ -432,6 +471,10 @@ static int migrate_postcopy_prepare(QTestState **from_ptr, { QTestState *from, *to; + /* set postcopy capabilities */ + args->start.caps[MIGRATION_CAPABILITY_POSTCOPY_BLOCKTIME] = true; + args->start.caps[MIGRATION_CAPABILITY_POSTCOPY_RAM] = true; + if (migrate_start(&from, &to, "defer", &args->start)) { return -1; } @@ -440,17 +483,7 @@ static int migrate_postcopy_prepare(QTestState **from_ptr, args->postcopy_data = args->start_hook(from, to); } - migrate_set_capability(from, "postcopy-ram", true); - migrate_set_capability(to, "postcopy-ram", true); - migrate_set_capability(to, "postcopy-blocktime", true); - - if (args->postcopy_preempt) { - migrate_set_capability(from, "postcopy-preempt", true); - migrate_set_capability(to, "postcopy-preempt", true); - } - migrate_ensure_non_converge(from); - migrate_prepare_for_dirty_mem(from); qtest_qmp_assert_success(to, "{ 'execute': 'migrate-incoming'," " 'arguments': { " @@ -948,15 +981,9 @@ void *migrate_hook_start_precopy_tcp_multifd_common(QTestState *from, QTestState *to, const char *method) { - migrate_set_parameter_int(from, "multifd-channels", 16); - migrate_set_parameter_int(to, "multifd-channels", 16); - migrate_set_parameter_str(from, "multifd-compression", method); migrate_set_parameter_str(to, "multifd-compression", method); - migrate_set_capability(from, "multifd", true); - migrate_set_capability(to, "multifd", true); - /* Start incoming migration from the 1st socket */ migrate_incoming_qmp(to, "tcp:127.0.0.1:0", NULL, "{}"); diff --git a/tests/qtest/migration/framework.h b/tests/qtest/migration/framework.h index e4a11870f6..01e425e64e 100644 --- a/tests/qtest/migration/framework.h +++ b/tests/qtest/migration/framework.h @@ -12,6 +12,7 @@ #define TEST_FRAMEWORK_H #include "libqtest.h" +#include <qapi/qapi-types-migration.h> #define FILE_TEST_FILENAME "migfile" #define FILE_TEST_OFFSET 0x1000 @@ -120,6 +121,13 @@ typedef struct { /* Do not connect to target monitor and qtest sockets in qtest_init */ bool defer_target_connect; + + /* + * Migration capabilities to be set in both source and + * destination. For unilateral capabilities, use + * migration_set_capabilities(). + */ + bool caps[MIGRATION_CAPABILITY__MAX]; } MigrateStart; typedef enum PostcopyRecoveryFailStage { @@ -207,7 +215,6 @@ typedef struct { /* Postcopy specific fields */ void *postcopy_data; - bool postcopy_preempt; PostcopyRecoveryFailStage postcopy_recovery_fail_stage; } MigrateCommon; diff --git a/tests/qtest/migration/misc-tests.c b/tests/qtest/migration/misc-tests.c index 2e612d9e38..54995256d8 100644 --- a/tests/qtest/migration/misc-tests.c +++ b/tests/qtest/migration/misc-tests.c @@ -98,6 +98,7 @@ static void test_ignore_shared(void) QTestState *from, *to; MigrateStart args = { .use_shmem = true, + .caps[MIGRATION_CAPABILITY_X_IGNORE_SHARED] = true, }; if (migrate_start(&from, &to, uri, &args)) { @@ -107,9 +108,6 @@ static void test_ignore_shared(void) migrate_ensure_non_converge(from); migrate_prepare_for_dirty_mem(from); - migrate_set_capability(from, "x-ignore-shared", true); - migrate_set_capability(to, "x-ignore-shared", true); - /* Wait for the first serial output from the source */ wait_for_serial("src_serial"); diff --git a/tests/qtest/migration/postcopy-tests.c b/tests/qtest/migration/postcopy-tests.c index 982457bed1..483e3ff99f 100644 --- a/tests/qtest/migration/postcopy-tests.c +++ b/tests/qtest/migration/postcopy-tests.c @@ -39,7 +39,9 @@ static void test_postcopy_suspend(void) static void test_postcopy_preempt(void) { MigrateCommon args = { - .postcopy_preempt = true, + .start = { + .caps[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT] = true, + }, }; test_postcopy_common(&args); @@ -73,7 +75,9 @@ static void test_postcopy_recovery_fail_reconnect(void) static void test_postcopy_preempt_recovery(void) { MigrateCommon args = { - .postcopy_preempt = true, + .start = { + .caps[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT] = true, + }, }; test_postcopy_recovery_common(&args); diff --git a/tests/qtest/migration/precopy-tests.c b/tests/qtest/migration/precopy-tests.c index ba273d10b9..87b0a7e8ef 100644 --- a/tests/qtest/migration/precopy-tests.c +++ b/tests/qtest/migration/precopy-tests.c @@ -99,32 +99,85 @@ static void test_precopy_unix_dirty_ring(void) test_precopy_common(&args); } -static void test_precopy_tcp_plain(void) +#ifdef CONFIG_RDMA + +#define RDMA_MIGRATION_HELPER "scripts/rdma-migration-helper.sh" +static int new_rdma_link(char *buffer) { + char cmd[256]; + bool verbose = g_getenv("QTEST_LOG"); + + snprintf(cmd, sizeof(cmd), "%s detect %s", RDMA_MIGRATION_HELPER, + verbose ? "" : "2>/dev/null"); + + FILE *pipe = popen(cmd, "r"); + if (pipe == NULL) { + perror("Failed to run script"); + return -1; + } + + int idx = 0; + while (fgets(buffer + idx, 128 - idx, pipe) != NULL) { + idx += strlen(buffer); + } + + int status = pclose(pipe); + if (status == -1) { + perror("Error reported by pclose()"); + return -1; + } else if (WIFEXITED(status)) { + return WEXITSTATUS(status); + } + + return -1; +} + +static void test_precopy_rdma_plain(void) +{ + char buffer[128] = {}; + + if (new_rdma_link(buffer)) { + g_test_skip("No rdma link available\n" + "# To enable the test:\n" + "# Run \'" RDMA_MIGRATION_HELPER " setup\' with root to " + "setup a new rdma/rxe link and rerun the test\n" + "# Optional: run 'scripts/rdma-migration-helper.sh clean' " + "to revert the 'setup'"); + return; + } + + /* + * TODO: query a free port instead of hard code. + * 29200=('R'+'D'+'M'+'A')*100 + **/ + g_autofree char *uri = g_strdup_printf("rdma:%s:29200", buffer); + MigrateCommon args = { - .listen_uri = "tcp:127.0.0.1:0", + .listen_uri = uri, + .connect_uri = uri, }; test_precopy_common(&args); } +#endif -static void *migrate_hook_start_switchover_ack(QTestState *from, QTestState *to) +static void test_precopy_tcp_plain(void) { + MigrateCommon args = { + .listen_uri = "tcp:127.0.0.1:0", + }; - migrate_set_capability(from, "return-path", true); - migrate_set_capability(to, "return-path", true); - - migrate_set_capability(from, "switchover-ack", true); - migrate_set_capability(to, "switchover-ack", true); - - return NULL; + test_precopy_common(&args); } static void test_precopy_tcp_switchover_ack(void) { MigrateCommon args = { .listen_uri = "tcp:127.0.0.1:0", - .start_hook = migrate_hook_start_switchover_ack, + .start = { + .caps[MIGRATION_CAPABILITY_RETURN_PATH] = true, + .caps[MIGRATION_CAPABILITY_SWITCHOVER_ACK] = true, + }, /* * Source VM must be running in order to consider the switchover ACK * when deciding to do switchover or not. @@ -393,6 +446,9 @@ static void test_multifd_tcp_uri_none(void) MigrateCommon args = { .listen_uri = "defer", .start_hook = migrate_hook_start_precopy_tcp_multifd, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, /* * Multifd is more complicated than most of the features, it * directly takes guest page buffers when sending, make sure @@ -408,6 +464,9 @@ static void test_multifd_tcp_zero_page_legacy(void) MigrateCommon args = { .listen_uri = "defer", .start_hook = migrate_hook_start_precopy_tcp_multifd_zero_page_legacy, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, /* * Multifd is more complicated than most of the features, it * directly takes guest page buffers when sending, make sure @@ -423,6 +482,9 @@ static void test_multifd_tcp_no_zero_page(void) MigrateCommon args = { .listen_uri = "defer", .start_hook = migrate_hook_start_precopy_tcp_multifd_no_zero_page, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, /* * Multifd is more complicated than most of the features, it * directly takes guest page buffers when sending, make sure @@ -439,6 +501,9 @@ static void test_multifd_tcp_channels_none(void) .listen_uri = "defer", .start_hook = migrate_hook_start_precopy_tcp_multifd, .live = true, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, .connect_channels = ("[ { 'channel-type': 'main'," " 'addr': { 'transport': 'socket'," " 'type': 'inet'," @@ -1124,6 +1189,10 @@ static void migration_test_add_precopy_smoke(MigrationTestEnv *env) test_multifd_tcp_uri_none); migration_test_add("/migration/multifd/tcp/plain/cancel", test_multifd_tcp_cancel); +#ifdef CONFIG_RDMA + migration_test_add("/migration/precopy/rdma/plain", + test_precopy_rdma_plain); +#endif } void migration_test_add_precopy(MigrationTestEnv *env) diff --git a/tests/qtest/migration/tls-tests.c b/tests/qtest/migration/tls-tests.c index 2cb4a44bcd..72f44defbb 100644 --- a/tests/qtest/migration/tls-tests.c +++ b/tests/qtest/migration/tls-tests.c @@ -375,9 +375,11 @@ static void test_postcopy_tls_psk(void) static void test_postcopy_preempt_tls_psk(void) { MigrateCommon args = { - .postcopy_preempt = true, .start_hook = migrate_hook_start_tls_psk_match, .end_hook = migrate_hook_end_tls_psk, + .start = { + .caps[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT] = true, + }, }; test_postcopy_common(&args); @@ -397,9 +399,11 @@ static void test_postcopy_recovery_tls_psk(void) static void test_postcopy_preempt_all(void) { MigrateCommon args = { - .postcopy_preempt = true, .start_hook = migrate_hook_start_tls_psk_match, .end_hook = migrate_hook_end_tls_psk, + .start = { + .caps[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT] = true, + }, }; test_postcopy_recovery_common(&args); @@ -631,6 +635,9 @@ static void test_multifd_tcp_tls_psk_match(void) .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_tcp_tls_psk_match, .end_hook = migrate_hook_end_tls_psk, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, }; test_precopy_common(&args); } @@ -640,6 +647,7 @@ static void test_multifd_tcp_tls_psk_mismatch(void) MigrateCommon args = { .start = { .hide_stderr = true, + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, }, .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_tcp_tls_psk_mismatch, @@ -656,6 +664,9 @@ static void test_multifd_tcp_tls_x509_default_host(void) .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_tls_x509_default_host, .end_hook = migrate_hook_end_tls_x509, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, }; test_precopy_common(&args); } @@ -666,6 +677,9 @@ static void test_multifd_tcp_tls_x509_override_host(void) .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_tls_x509_override_host, .end_hook = migrate_hook_end_tls_x509, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, }; test_precopy_common(&args); } @@ -688,6 +702,7 @@ static void test_multifd_tcp_tls_x509_mismatch_host(void) MigrateCommon args = { .start = { .hide_stderr = true, + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, }, .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_tls_x509_mismatch_host, @@ -703,6 +718,9 @@ static void test_multifd_tcp_tls_x509_allow_anon_client(void) .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_tls_x509_allow_anon_client, .end_hook = migrate_hook_end_tls_x509, + .start = { + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, + }, }; test_precopy_common(&args); } @@ -712,6 +730,7 @@ static void test_multifd_tcp_tls_x509_reject_anon_client(void) MigrateCommon args = { .start = { .hide_stderr = true, + .caps[MIGRATION_CAPABILITY_MULTIFD] = true, }, .listen_uri = "defer", .start_hook = migrate_hook_start_multifd_tls_x509_reject_anon_client, |