diff options
author | Stefan Hajnoczi <stefanha@redhat.com> | 2017-05-05 16:52:12 +0100 |
---|---|---|
committer | Stefan Hajnoczi <stefanha@redhat.com> | 2017-05-05 16:52:35 +0100 |
commit | 4aee86c60a53a3478d9799a4464cf0bc08071148 (patch) | |
tree | a8fa7c5aba4aa18e52fd8182cce9cc5872df1fa3 | |
parent | bc56fd3a23c94302937ed023d33e17a2de1a1b2a (diff) | |
parent | 1db9d8e501fc99fa2201f228627952aee6cfc349 (diff) |
Merge remote-tracking branch 'quintela/tags/migration/20170504' into staging
migration/next for 20170504
# gpg: Signature made Thu 04 May 2017 10:35:41 AM BST
# gpg: using RSA key 0xF487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>"
# gpg: aka "Juan Quintela <quintela@trasno.org>"
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03 4B82 F487 EF18 5872 D723
* quintela/tags/migration/20170504:
migration: Extra tracing
migration: Move postcopy-ram.h to migration/
monitor: Move hmp_info_snapshots from savevm.c to hmp.c
monitor: Move hmp_delvm from savevm.c to hmp.c
monitor: Move hmp_savevm from savevm.c to hmp.c
monitor: Move hmp_loadvm from monitor.c to hmp.c
monitor: Remove monitor parameter from save_vmstate
migration: to_dst_file at that point is NULL
migration: setup bi-directional I/O channel for exec: protocol
ram: Split dirty bitmap by RAMBlock
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
-rw-r--r-- | hmp.c | 174 | ||||
-rw-r--r-- | hmp.h | 4 | ||||
-rw-r--r-- | include/exec/ram_addr.h | 13 | ||||
-rw-r--r-- | include/migration/migration.h | 3 | ||||
-rw-r--r-- | include/sysemu/sysemu.h | 5 | ||||
-rw-r--r-- | migration/exec.c | 4 | ||||
-rw-r--r-- | migration/migration.c | 2 | ||||
-rw-r--r-- | migration/postcopy-ram.c | 7 | ||||
-rw-r--r-- | migration/postcopy-ram.h (renamed from include/migration/postcopy-ram.h) | 3 | ||||
-rw-r--r-- | migration/ram.c | 269 | ||||
-rw-r--r-- | migration/savevm.c | 185 | ||||
-rw-r--r-- | migration/socket.c | 1 | ||||
-rw-r--r-- | migration/tls.c | 1 | ||||
-rw-r--r-- | migration/trace-events | 2 | ||||
-rw-r--r-- | monitor.c | 13 | ||||
-rw-r--r-- | replay/replay-snapshot.c | 2 |
16 files changed, 314 insertions, 374 deletions
@@ -19,6 +19,7 @@ #include "net/eth.h" #include "sysemu/char.h" #include "sysemu/block-backend.h" +#include "sysemu/sysemu.h" #include "qemu/config-file.h" #include "qemu/option.h" #include "qemu/timer.h" @@ -1268,6 +1269,179 @@ void hmp_snapshot_delete_blkdev_internal(Monitor *mon, const QDict *qdict) hmp_handle_error(mon, &err); } +void hmp_loadvm(Monitor *mon, const QDict *qdict) +{ + int saved_vm_running = runstate_is_running(); + const char *name = qdict_get_str(qdict, "name"); + + vm_stop(RUN_STATE_RESTORE_VM); + + if (load_vmstate(name) == 0 && saved_vm_running) { + vm_start(); + } +} + +void hmp_savevm(Monitor *mon, const QDict *qdict) +{ + save_vmstate(qdict_get_try_str(qdict, "name")); +} + +void hmp_delvm(Monitor *mon, const QDict *qdict) +{ + BlockDriverState *bs; + Error *err; + const char *name = qdict_get_str(qdict, "name"); + + if (bdrv_all_delete_snapshot(name, &bs, &err) < 0) { + error_reportf_err(err, + "Error while deleting snapshot on device '%s': ", + bdrv_get_device_name(bs)); + } +} + +void hmp_info_snapshots(Monitor *mon, const QDict *qdict) +{ + BlockDriverState *bs, *bs1; + BdrvNextIterator it1; + QEMUSnapshotInfo *sn_tab, *sn; + bool no_snapshot = true; + int nb_sns, i; + int total; + int *global_snapshots; + AioContext *aio_context; + + typedef struct SnapshotEntry { + QEMUSnapshotInfo sn; + QTAILQ_ENTRY(SnapshotEntry) next; + } SnapshotEntry; + + typedef struct ImageEntry { + const char *imagename; + QTAILQ_ENTRY(ImageEntry) next; + QTAILQ_HEAD(, SnapshotEntry) snapshots; + } ImageEntry; + + QTAILQ_HEAD(, ImageEntry) image_list = + QTAILQ_HEAD_INITIALIZER(image_list); + + ImageEntry *image_entry, *next_ie; + SnapshotEntry *snapshot_entry; + + bs = bdrv_all_find_vmstate_bs(); + if (!bs) { + monitor_printf(mon, "No available block device supports snapshots\n"); + return; + } + aio_context = bdrv_get_aio_context(bs); + + aio_context_acquire(aio_context); + nb_sns = bdrv_snapshot_list(bs, &sn_tab); + aio_context_release(aio_context); + + if (nb_sns < 0) { + monitor_printf(mon, "bdrv_snapshot_list: error %d\n", nb_sns); + return; + } + + for (bs1 = bdrv_first(&it1); bs1; bs1 = bdrv_next(&it1)) { + int bs1_nb_sns = 0; + ImageEntry *ie; + SnapshotEntry *se; + AioContext *ctx = bdrv_get_aio_context(bs1); + + aio_context_acquire(ctx); + if (bdrv_can_snapshot(bs1)) { + sn = NULL; + bs1_nb_sns = bdrv_snapshot_list(bs1, &sn); + if (bs1_nb_sns > 0) { + no_snapshot = false; + ie = g_new0(ImageEntry, 1); + ie->imagename = bdrv_get_device_name(bs1); + QTAILQ_INIT(&ie->snapshots); + QTAILQ_INSERT_TAIL(&image_list, ie, next); + for (i = 0; i < bs1_nb_sns; i++) { + se = g_new0(SnapshotEntry, 1); + se->sn = sn[i]; + QTAILQ_INSERT_TAIL(&ie->snapshots, se, next); + } + } + g_free(sn); + } + aio_context_release(ctx); + } + + if (no_snapshot) { + monitor_printf(mon, "There is no snapshot available.\n"); + return; + } + + global_snapshots = g_new0(int, nb_sns); + total = 0; + for (i = 0; i < nb_sns; i++) { + SnapshotEntry *next_sn; + if (bdrv_all_find_snapshot(sn_tab[i].name, &bs1) == 0) { + global_snapshots[total] = i; + total++; + QTAILQ_FOREACH(image_entry, &image_list, next) { + QTAILQ_FOREACH_SAFE(snapshot_entry, &image_entry->snapshots, + next, next_sn) { + if (!strcmp(sn_tab[i].name, snapshot_entry->sn.name)) { + QTAILQ_REMOVE(&image_entry->snapshots, snapshot_entry, + next); + g_free(snapshot_entry); + } + } + } + } + } + + monitor_printf(mon, "List of snapshots present on all disks:\n"); + + if (total > 0) { + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, NULL); + monitor_printf(mon, "\n"); + for (i = 0; i < total; i++) { + sn = &sn_tab[global_snapshots[i]]; + /* The ID is not guaranteed to be the same on all images, so + * overwrite it. + */ + pstrcpy(sn->id_str, sizeof(sn->id_str), "--"); + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, sn); + monitor_printf(mon, "\n"); + } + } else { + monitor_printf(mon, "None\n"); + } + + QTAILQ_FOREACH(image_entry, &image_list, next) { + if (QTAILQ_EMPTY(&image_entry->snapshots)) { + continue; + } + monitor_printf(mon, + "\nList of partial (non-loadable) snapshots on '%s':\n", + image_entry->imagename); + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, NULL); + monitor_printf(mon, "\n"); + QTAILQ_FOREACH(snapshot_entry, &image_entry->snapshots, next) { + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, + &snapshot_entry->sn); + monitor_printf(mon, "\n"); + } + } + + QTAILQ_FOREACH_SAFE(image_entry, &image_list, next, next_ie) { + SnapshotEntry *next_sn; + QTAILQ_FOREACH_SAFE(snapshot_entry, &image_entry->snapshots, next, + next_sn) { + g_free(snapshot_entry); + } + g_free(image_entry); + } + g_free(sn_tab); + g_free(global_snapshots); + +} + void hmp_migrate_cancel(Monitor *mon, const QDict *qdict) { qmp_migrate_cancel(NULL); @@ -63,6 +63,10 @@ void hmp_snapshot_blkdev_internal(Monitor *mon, const QDict *qdict); void hmp_snapshot_delete_blkdev_internal(Monitor *mon, const QDict *qdict); void hmp_drive_mirror(Monitor *mon, const QDict *qdict); void hmp_drive_backup(Monitor *mon, const QDict *qdict); +void hmp_loadvm(Monitor *mon, const QDict *qdict); +void hmp_savevm(Monitor *mon, const QDict *qdict); +void hmp_delvm(Monitor *mon, const QDict *qdict); +void hmp_info_snapshots(Monitor *mon, const QDict *qdict); void hmp_migrate_cancel(Monitor *mon, const QDict *qdict); void hmp_migrate_incoming(Monitor *mon, const QDict *qdict); void hmp_migrate_set_downtime(Monitor *mon, const QDict *qdict); diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index dbe2f08d47..140efa840c 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -39,6 +39,14 @@ struct RAMBlock { QLIST_HEAD(, RAMBlockNotifier) ramblock_notifiers; int fd; size_t page_size; + /* dirty bitmap used during migration */ + unsigned long *bmap; + /* bitmap of pages that haven't been sent even once + * only maintained and used in postcopy at the moment + * where it's used to send the dirtymap at the start + * of the postcopy phase + */ + unsigned long *unsentmap; }; static inline bool offset_in_ramblock(RAMBlock *b, ram_addr_t offset) @@ -360,16 +368,15 @@ static inline void cpu_physical_memory_clear_dirty_range(ram_addr_t start, static inline -uint64_t cpu_physical_memory_sync_dirty_bitmap(unsigned long *dest, - RAMBlock *rb, +uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlock *rb, ram_addr_t start, ram_addr_t length, uint64_t *real_dirty_pages) { ram_addr_t addr; - start = rb->offset + start; unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS); uint64_t num_dirty = 0; + unsigned long *dest = rb->bmap; /* start address is aligned at the start of a word? */ if (((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) { diff --git a/include/migration/migration.h b/include/migration/migration.h index ba1a16cbc1..e29cb0144b 100644 --- a/include/migration/migration.h +++ b/include/migration/migration.h @@ -266,7 +266,8 @@ uint64_t xbzrle_mig_pages_cache_miss(void); double xbzrle_mig_cache_miss_rate(void); void ram_handle_compressed(void *host, uint8_t ch, uint64_t size); -void ram_debug_dump_bitmap(unsigned long *todump, bool expected); +void ram_debug_dump_bitmap(unsigned long *todump, bool expected, + unsigned long pages); /* For outgoing discard bitmap */ int ram_postcopy_send_discard_bitmap(MigrationState *ms); /* For incoming postcopy discard */ diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 16175f7295..15656b7c36 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -75,11 +75,8 @@ void qemu_remove_exit_notifier(Notifier *notify); void qemu_add_machine_init_done_notifier(Notifier *notify); void qemu_remove_machine_init_done_notifier(Notifier *notify); -void hmp_savevm(Monitor *mon, const QDict *qdict); -int save_vmstate(Monitor *mon, const char *name); +int save_vmstate(const char *name); int load_vmstate(const char *name); -void hmp_delvm(Monitor *mon, const QDict *qdict); -void hmp_info_snapshots(Monitor *mon, const QDict *qdict); void qemu_announce_self(void); diff --git a/migration/exec.c b/migration/exec.c index 9157721dfe..aba9089466 100644 --- a/migration/exec.c +++ b/migration/exec.c @@ -32,7 +32,7 @@ void exec_start_outgoing_migration(MigrationState *s, const char *command, Error trace_migration_exec_outgoing(command); ioc = QIO_CHANNEL(qio_channel_command_new_spawn(argv, - O_WRONLY, + O_RDWR, errp)); if (!ioc) { return; @@ -59,7 +59,7 @@ void exec_start_incoming_migration(const char *command, Error **errp) trace_migration_exec_incoming(command); ioc = QIO_CHANNEL(qio_channel_command_new_spawn(argv, - O_RDONLY, + O_RDWR, errp)); if (!ioc) { return; diff --git a/migration/migration.c b/migration/migration.c index 353f2728cf..799952ce99 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -26,7 +26,7 @@ #include "qemu/sockets.h" #include "qemu/rcu.h" #include "migration/block.h" -#include "migration/postcopy-ram.h" +#include "postcopy-ram.h" #include "qemu/thread.h" #include "qmp-commands.h" #include "trace.h" diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 85fd8d72b3..cdadaf6578 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -20,7 +20,7 @@ #include "qemu-common.h" #include "migration/migration.h" -#include "migration/postcopy-ram.h" +#include "postcopy-ram.h" #include "sysemu/sysemu.h" #include "sysemu/balloon.h" #include "qemu/error-report.h" @@ -33,7 +33,6 @@ struct PostcopyDiscardState { const char *ramblock_name; - uint64_t offset; /* Bitmap entry for the 1st bit of this RAMBlock */ uint16_t cur_entry; /* * Start and length of a discard range (bytes) @@ -717,14 +716,12 @@ void *postcopy_get_tmp_page(MigrationIncomingState *mis) * returns: a new PDS. */ PostcopyDiscardState *postcopy_discard_send_init(MigrationState *ms, - unsigned long offset, const char *name) { PostcopyDiscardState *res = g_malloc0(sizeof(PostcopyDiscardState)); if (res) { res->ramblock_name = name; - res->offset = offset; } return res; @@ -745,7 +742,7 @@ void postcopy_discard_send_range(MigrationState *ms, PostcopyDiscardState *pds, { size_t tp_size = qemu_target_page_size(); /* Convert to byte offsets within the RAM block */ - pds->start_list[pds->cur_entry] = (start - pds->offset) * tp_size; + pds->start_list[pds->cur_entry] = start * tp_size; pds->length_list[pds->cur_entry] = length * tp_size; trace_postcopy_discard_send_range(pds->ramblock_name, start, length); pds->cur_entry++; diff --git a/include/migration/postcopy-ram.h b/migration/postcopy-ram.h index 8e036b95a2..4c25f03be2 100644 --- a/include/migration/postcopy-ram.h +++ b/migration/postcopy-ram.h @@ -43,12 +43,9 @@ int postcopy_ram_prepare_discard(MigrationIncomingState *mis); /* * Called at the start of each RAMBlock by the bitmap code. - * 'offset' is the bitmap offset of the named RAMBlock in the migration - * bitmap. * Returns a new PDS */ PostcopyDiscardState *postcopy_discard_send_init(MigrationState *ms, - unsigned long offset, const char *name); /* diff --git a/migration/ram.c b/migration/ram.c index f48664ec62..293d27ce83 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -36,7 +36,7 @@ #include "qemu/timer.h" #include "qemu/main-loop.h" #include "migration/migration.h" -#include "migration/postcopy-ram.h" +#include "postcopy-ram.h" #include "exec/address-spaces.h" #include "migration/page_cache.h" #include "qemu/error-report.h" @@ -138,19 +138,6 @@ out: return ret; } -struct RAMBitmap { - struct rcu_head rcu; - /* Main migration bitmap */ - unsigned long *bmap; - /* bitmap of pages that haven't been sent even once - * only maintained and used in postcopy at the moment - * where it's used to send the dirtymap at the start - * of the postcopy phase - */ - unsigned long *unsentmap; -}; -typedef struct RAMBitmap RAMBitmap; - /* * An outstanding page request, on the source, having been received * and queued @@ -220,8 +207,6 @@ struct RAMState { uint64_t postcopy_requests; /* protects modification of the bitmap */ QemuMutex bitmap_mutex; - /* Ram Bitmap protected by RCU */ - RAMBitmap *ram_bitmap; /* The RAMBlock used in the last src_page_requests */ RAMBlock *last_req_rb; /* Queue of outstanding page requests from the destination */ @@ -614,22 +599,17 @@ static inline unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb, unsigned long start) { - unsigned long base = rb->offset >> TARGET_PAGE_BITS; - unsigned long nr = base + start; - uint64_t rb_size = rb->used_length; - unsigned long size = base + (rb_size >> TARGET_PAGE_BITS); - unsigned long *bitmap; - + unsigned long size = rb->used_length >> TARGET_PAGE_BITS; + unsigned long *bitmap = rb->bmap; unsigned long next; - bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap; - if (rs->ram_bulk_stage && nr > base) { - next = nr + 1; + if (rs->ram_bulk_stage && start > 0) { + next = start + 1; } else { - next = find_next_bit(bitmap, size, nr); + next = find_next_bit(bitmap, size, start); } - return next - base; + return next; } static inline bool migration_bitmap_clear_dirty(RAMState *rs, @@ -637,10 +617,8 @@ static inline bool migration_bitmap_clear_dirty(RAMState *rs, unsigned long page) { bool ret; - unsigned long *bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap; - unsigned long nr = (rb->offset >> TARGET_PAGE_BITS) + page; - ret = test_and_clear_bit(nr, bitmap); + ret = test_and_clear_bit(page, rb->bmap); if (ret) { rs->migration_dirty_pages--; @@ -651,10 +629,8 @@ static inline bool migration_bitmap_clear_dirty(RAMState *rs, static void migration_bitmap_sync_range(RAMState *rs, RAMBlock *rb, ram_addr_t start, ram_addr_t length) { - unsigned long *bitmap; - bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap; rs->migration_dirty_pages += - cpu_physical_memory_sync_dirty_bitmap(bitmap, rb, start, length, + cpu_physical_memory_sync_dirty_bitmap(rb, start, length, &rs->num_dirty_pages_period); } @@ -812,6 +788,7 @@ static int ram_save_page(RAMState *rs, PageSearchStatus *pss, bool last_stage) ram_addr_t offset = pss->page << TARGET_PAGE_BITS; p = block->host + offset; + trace_ram_save_page(block->idstr, (uint64_t)offset, p); /* In doubt sent page as normal */ bytes_xmit = 0; @@ -1153,17 +1130,13 @@ static bool get_queued_page(RAMState *rs, PageSearchStatus *pss) * search already sent it. */ if (block) { - unsigned long *bitmap; unsigned long page; - bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap; - page = (block->offset + offset) >> TARGET_PAGE_BITS; - dirty = test_bit(page, bitmap); + page = offset >> TARGET_PAGE_BITS; + dirty = test_bit(page, block->bmap); if (!dirty) { trace_get_queued_page_not_dirty(block->idstr, (uint64_t)offset, - page, - test_bit(page, - atomic_rcu_read(&rs->ram_bitmap)->unsentmap)); + page, test_bit(page, block->unsentmap)); } else { trace_get_queued_page(block->idstr, (uint64_t)offset, page); } @@ -1301,16 +1274,13 @@ static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss, /* Check the pages is dirty and if it is send it */ if (migration_bitmap_clear_dirty(rs, pss->block, pss->page)) { - unsigned long *unsentmap; /* * If xbzrle is on, stop using the data compression after first * round of migration even if compression is enabled. In theory, * xbzrle can do better than compression. */ - unsigned long page = - (pss->block->offset >> TARGET_PAGE_BITS) + pss->page; - if (migrate_use_compression() - && (rs->ram_bulk_stage || !migrate_use_xbzrle())) { + if (migrate_use_compression() && + (rs->ram_bulk_stage || !migrate_use_xbzrle())) { res = ram_save_compressed_page(rs, pss, last_stage); } else { res = ram_save_page(rs, pss, last_stage); @@ -1319,9 +1289,8 @@ static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss, if (res < 0) { return res; } - unsentmap = atomic_rcu_read(&rs->ram_bitmap)->unsentmap; - if (unsentmap) { - clear_bit(page, unsentmap); + if (pss->block->unsentmap) { + clear_bit(pss->page, pss->block->unsentmap); } } @@ -1451,25 +1420,20 @@ void free_xbzrle_decoded_buf(void) xbzrle_decoded_buf = NULL; } -static void migration_bitmap_free(RAMBitmap *bmap) -{ - g_free(bmap->bmap); - g_free(bmap->unsentmap); - g_free(bmap); -} - static void ram_migration_cleanup(void *opaque) { - RAMState *rs = opaque; + RAMBlock *block; /* caller have hold iothread lock or is in a bh, so there is * no writing race against this migration_bitmap */ - RAMBitmap *bitmap = rs->ram_bitmap; - atomic_rcu_set(&rs->ram_bitmap, NULL); - if (bitmap) { - memory_global_dirty_log_stop(); - call_rcu(bitmap, migration_bitmap_free, rcu); + memory_global_dirty_log_stop(); + + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { + g_free(block->bmap); + block->bmap = NULL; + g_free(block->unsentmap); + block->unsentmap = NULL; } XBZRLE_cache_lock(); @@ -1501,27 +1465,22 @@ static void ram_state_reset(RAMState *rs) * of; it won't bother printing lines that are all this value. * If 'todump' is null the migration bitmap is dumped. */ -void ram_debug_dump_bitmap(unsigned long *todump, bool expected) +void ram_debug_dump_bitmap(unsigned long *todump, bool expected, + unsigned long pages) { - unsigned long ram_pages = last_ram_page(); - RAMState *rs = &ram_state; int64_t cur; int64_t linelen = 128; char linebuf[129]; - if (!todump) { - todump = atomic_rcu_read(&rs->ram_bitmap)->bmap; - } - - for (cur = 0; cur < ram_pages; cur += linelen) { + for (cur = 0; cur < pages; cur += linelen) { int64_t curb; bool found = false; /* * Last line; catch the case where the line length * is longer than remaining ram */ - if (cur + linelen > ram_pages) { - linelen = ram_pages - cur; + if (cur + linelen > pages) { + linelen = pages - cur; } for (curb = 0; curb < linelen; curb++) { bool thisbit = test_bit(cur + curb, todump); @@ -1539,14 +1498,12 @@ void ram_debug_dump_bitmap(unsigned long *todump, bool expected) void ram_postcopy_migrated_memory_release(MigrationState *ms) { - RAMState *rs = &ram_state; struct RAMBlock *block; - unsigned long *bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap; QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { - unsigned long first = block->offset >> TARGET_PAGE_BITS; - unsigned long range = first + (block->used_length >> TARGET_PAGE_BITS); - unsigned long run_start = find_next_zero_bit(bitmap, range, first); + unsigned long *bitmap = block->bmap; + unsigned long range = block->used_length >> TARGET_PAGE_BITS; + unsigned long run_start = find_next_zero_bit(bitmap, range, 0); while (run_start < range) { unsigned long run_end = find_next_bit(bitmap, range, run_start + 1); @@ -1573,16 +1530,13 @@ void ram_postcopy_migrated_memory_release(MigrationState *ms) */ static int postcopy_send_discard_bm_ram(MigrationState *ms, PostcopyDiscardState *pds, - unsigned long start, - unsigned long length) + RAMBlock *block) { - RAMState *rs = &ram_state; - unsigned long end = start + length; /* one after the end */ + unsigned long end = block->used_length >> TARGET_PAGE_BITS; unsigned long current; - unsigned long *unsentmap; + unsigned long *unsentmap = block->unsentmap; - unsentmap = atomic_rcu_read(&rs->ram_bitmap)->unsentmap; - for (current = start; current < end; ) { + for (current = 0; current < end; ) { unsigned long one = find_next_bit(unsentmap, end, current); if (one <= end) { @@ -1625,18 +1579,15 @@ static int postcopy_each_ram_send_discard(MigrationState *ms) int ret; QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { - unsigned long first = block->offset >> TARGET_PAGE_BITS; - PostcopyDiscardState *pds = postcopy_discard_send_init(ms, - first, - block->idstr); + PostcopyDiscardState *pds = + postcopy_discard_send_init(ms, block->idstr); /* * Postcopy sends chunks of bitmap over the wire, but it * just needs indexes at this point, avoids it having * target page specific code. */ - ret = postcopy_send_discard_bm_ram(ms, pds, first, - block->used_length >> TARGET_PAGE_BITS); + ret = postcopy_send_discard_bm_ram(ms, pds, block); postcopy_discard_send_finish(ms, pds); if (ret) { return ret; @@ -1667,12 +1618,10 @@ static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass, PostcopyDiscardState *pds) { RAMState *rs = &ram_state; - unsigned long *bitmap; - unsigned long *unsentmap; + unsigned long *bitmap = block->bmap; + unsigned long *unsentmap = block->unsentmap; unsigned int host_ratio = block->page_size / TARGET_PAGE_SIZE; - unsigned long first = block->offset >> TARGET_PAGE_BITS; - unsigned long len = block->used_length >> TARGET_PAGE_BITS; - unsigned long last = first + (len - 1); + unsigned long pages = block->used_length >> TARGET_PAGE_BITS; unsigned long run_start; if (block->page_size == TARGET_PAGE_SIZE) { @@ -1680,18 +1629,15 @@ static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass, return; } - bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap; - unsentmap = atomic_rcu_read(&rs->ram_bitmap)->unsentmap; - if (unsent_pass) { /* Find a sent page */ - run_start = find_next_zero_bit(unsentmap, last + 1, first); + run_start = find_next_zero_bit(unsentmap, pages, 0); } else { /* Find a dirty page */ - run_start = find_next_bit(bitmap, last + 1, first); + run_start = find_next_bit(bitmap, pages, 0); } - while (run_start <= last) { + while (run_start < pages) { bool do_fixup = false; unsigned long fixup_start_addr; unsigned long host_offset; @@ -1711,9 +1657,9 @@ static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass, /* Find the end of this run */ unsigned long run_end; if (unsent_pass) { - run_end = find_next_bit(unsentmap, last + 1, run_start + 1); + run_end = find_next_bit(unsentmap, pages, run_start + 1); } else { - run_end = find_next_zero_bit(bitmap, last + 1, run_start + 1); + run_end = find_next_zero_bit(bitmap, pages, run_start + 1); } /* * If the end isn't at the start of a host page, then the @@ -1770,11 +1716,10 @@ static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass, if (unsent_pass) { /* Find the next sent page for the next iteration */ - run_start = find_next_zero_bit(unsentmap, last + 1, - run_start); + run_start = find_next_zero_bit(unsentmap, pages, run_start); } else { /* Find the next dirty page for the next iteration */ - run_start = find_next_bit(bitmap, last + 1, run_start); + run_start = find_next_bit(bitmap, pages, run_start); } } } @@ -1791,34 +1736,22 @@ static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass, * Returns zero on success * * @ms: current migration state + * @block: block we want to work with */ -static int postcopy_chunk_hostpages(MigrationState *ms) +static int postcopy_chunk_hostpages(MigrationState *ms, RAMBlock *block) { - RAMState *rs = &ram_state; - struct RAMBlock *block; - - /* Easiest way to make sure we don't resume in the middle of a host-page */ - rs->last_seen_block = NULL; - rs->last_sent_block = NULL; - rs->last_page = 0; - - QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { - unsigned long first = block->offset >> TARGET_PAGE_BITS; - - PostcopyDiscardState *pds = - postcopy_discard_send_init(ms, first, block->idstr); - - /* First pass: Discard all partially sent host pages */ - postcopy_chunk_hostpages_pass(ms, true, block, pds); - /* - * Second pass: Ensure that all partially dirty host pages are made - * fully dirty. - */ - postcopy_chunk_hostpages_pass(ms, false, block, pds); + PostcopyDiscardState *pds = + postcopy_discard_send_init(ms, block->idstr); - postcopy_discard_send_finish(ms, pds); - } /* ram_list loop */ + /* First pass: Discard all partially sent host pages */ + postcopy_chunk_hostpages_pass(ms, true, block, pds); + /* + * Second pass: Ensure that all partially dirty host pages are made + * fully dirty. + */ + postcopy_chunk_hostpages_pass(ms, false, block, pds); + postcopy_discard_send_finish(ms, pds); return 0; } @@ -1840,43 +1773,49 @@ static int postcopy_chunk_hostpages(MigrationState *ms) int ram_postcopy_send_discard_bitmap(MigrationState *ms) { RAMState *rs = &ram_state; + RAMBlock *block; int ret; - unsigned long *bitmap, *unsentmap; rcu_read_lock(); /* This should be our last sync, the src is now paused */ migration_bitmap_sync(rs); - unsentmap = atomic_rcu_read(&rs->ram_bitmap)->unsentmap; - if (!unsentmap) { - /* We don't have a safe way to resize the sentmap, so - * if the bitmap was resized it will be NULL at this - * point. - */ - error_report("migration ram resized during precopy phase"); - rcu_read_unlock(); - return -EINVAL; - } - - /* Deal with TPS != HPS and huge pages */ - ret = postcopy_chunk_hostpages(ms); - if (ret) { - rcu_read_unlock(); - return ret; - } - - /* - * Update the unsentmap to be unsentmap = unsentmap | dirty - */ - bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap; - bitmap_or(unsentmap, unsentmap, bitmap, last_ram_page()); + /* Easiest way to make sure we don't resume in the middle of a host-page */ + rs->last_seen_block = NULL; + rs->last_sent_block = NULL; + rs->last_page = 0; + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { + unsigned long pages = block->used_length >> TARGET_PAGE_BITS; + unsigned long *bitmap = block->bmap; + unsigned long *unsentmap = block->unsentmap; + + if (!unsentmap) { + /* We don't have a safe way to resize the sentmap, so + * if the bitmap was resized it will be NULL at this + * point. + */ + error_report("migration ram resized during precopy phase"); + rcu_read_unlock(); + return -EINVAL; + } + /* Deal with TPS != HPS and huge pages */ + ret = postcopy_chunk_hostpages(ms, block); + if (ret) { + rcu_read_unlock(); + return ret; + } - trace_ram_postcopy_send_discard_bitmap(); + /* + * Update the unsentmap to be unsentmap = unsentmap | dirty + */ + bitmap_or(unsentmap, unsentmap, bitmap, pages); #ifdef DEBUG_POSTCOPY - ram_debug_dump_bitmap(unsentmap, true); + ram_debug_dump_bitmap(unsentmap, true, pages); #endif + } + trace_ram_postcopy_send_discard_bitmap(); ret = postcopy_each_ram_send_discard(ms); rcu_read_unlock(); @@ -1918,8 +1857,6 @@ err: static int ram_state_init(RAMState *rs) { - unsigned long ram_bitmap_pages; - memset(rs, 0, sizeof(*rs)); qemu_mutex_init(&rs->bitmap_mutex); qemu_mutex_init(&rs->src_page_req_mutex); @@ -1961,16 +1898,19 @@ static int ram_state_init(RAMState *rs) rcu_read_lock(); ram_state_reset(rs); - rs->ram_bitmap = g_new0(RAMBitmap, 1); /* Skip setting bitmap if there is no RAM */ if (ram_bytes_total()) { - ram_bitmap_pages = last_ram_page(); - rs->ram_bitmap->bmap = bitmap_new(ram_bitmap_pages); - bitmap_set(rs->ram_bitmap->bmap, 0, ram_bitmap_pages); + RAMBlock *block; - if (migrate_postcopy_ram()) { - rs->ram_bitmap->unsentmap = bitmap_new(ram_bitmap_pages); - bitmap_set(rs->ram_bitmap->unsentmap, 0, ram_bitmap_pages); + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { + unsigned long pages = block->max_length >> TARGET_PAGE_BITS; + + block->bmap = bitmap_new(pages); + bitmap_set(block->bmap, 0, pages); + if (migrate_postcopy_ram()) { + block->unsentmap = bitmap_new(pages); + bitmap_set(block->unsentmap, 0, pages); + } } } @@ -2611,6 +2551,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) ret = -EINVAL; break; } + trace_ram_load_loop(block->idstr, (uint64_t)addr, flags, host); } switch (flags & ~RAM_SAVE_FLAG_CONTINUE) { diff --git a/migration/savevm.c b/migration/savevm.c index a00c1ab0af..352a8f23b5 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -33,15 +33,12 @@ #include "hw/qdev.h" #include "hw/xen/xen.h" #include "net/net.h" -#include "monitor/monitor.h" #include "sysemu/sysemu.h" #include "qemu/timer.h" -#include "audio/audio.h" #include "migration/migration.h" -#include "migration/postcopy-ram.h" +#include "postcopy-ram.h" #include "qapi/qmp/qerror.h" #include "qemu/error-report.h" -#include "qemu/sockets.h" #include "qemu/queue.h" #include "sysemu/cpus.h" #include "exec/memory.h" @@ -50,7 +47,6 @@ #include "qemu/bitops.h" #include "qemu/iov.h" #include "block/snapshot.h" -#include "block/qapi.h" #include "qemu/cutils.h" #include "io/channel-buffer.h" #include "io/channel-file.h" @@ -2078,7 +2074,7 @@ int qemu_loadvm_state(QEMUFile *f) return ret; } -int save_vmstate(Monitor *mon, const char *name) +int save_vmstate(const char *name) { BlockDriverState *bs, *bs1; QEMUSnapshotInfo sn1, *sn = &sn1, old_sn1, *old_sn = &old_sn1; @@ -2092,8 +2088,8 @@ int save_vmstate(Monitor *mon, const char *name) AioContext *aio_context; if (!bdrv_all_can_snapshot(&bs)) { - monitor_printf(mon, "Device '%s' is writable but does not " - "support snapshots.\n", bdrv_get_device_name(bs)); + error_report("Device '%s' is writable but does not support snapshots", + bdrv_get_device_name(bs)); return ret; } @@ -2110,7 +2106,7 @@ int save_vmstate(Monitor *mon, const char *name) bs = bdrv_all_find_vmstate_bs(); if (bs == NULL) { - monitor_printf(mon, "No block device can accept snapshots\n"); + error_report("No block device can accept snapshots"); return ret; } aio_context = bdrv_get_aio_context(bs); @@ -2119,7 +2115,7 @@ int save_vmstate(Monitor *mon, const char *name) ret = global_state_store(); if (ret) { - monitor_printf(mon, "Error saving global state\n"); + error_report("Error saving global state"); return ret; } vm_stop(RUN_STATE_SAVE_VM); @@ -2151,7 +2147,7 @@ int save_vmstate(Monitor *mon, const char *name) /* save the VM state */ f = qemu_fopen_bdrv(bs, 1); if (!f) { - monitor_printf(mon, "Could not open VM state file\n"); + error_report("Could not open VM state file"); goto the_end; } ret = qemu_savevm_state(f, &local_err); @@ -2164,8 +2160,8 @@ int save_vmstate(Monitor *mon, const char *name) ret = bdrv_all_create_snapshot(sn, bs, vm_state_size, &bs); if (ret < 0) { - monitor_printf(mon, "Error while creating snapshot on '%s'\n", - bdrv_get_device_name(bs)); + error_report("Error while creating snapshot on '%s'", + bdrv_get_device_name(bs)); goto the_end; } @@ -2179,11 +2175,6 @@ int save_vmstate(Monitor *mon, const char *name) return ret; } -void hmp_savevm(Monitor *mon, const QDict *qdict) -{ - save_vmstate(mon, qdict_get_try_str(qdict, "name")); -} - void qmp_xen_save_devices_state(const char *filename, Error **errp) { QEMUFile *f; @@ -2253,7 +2244,7 @@ int load_vmstate(const char *name) MigrationIncomingState *mis = migration_incoming_get_current(); if (!bdrv_all_can_snapshot(&bs)) { - error_report("Device '%s' is writable but does not support snapshots.", + error_report("Device '%s' is writable but does not support snapshots", bdrv_get_device_name(bs)); return -ENOTSUP; } @@ -2317,162 +2308,6 @@ int load_vmstate(const char *name) return 0; } -void hmp_delvm(Monitor *mon, const QDict *qdict) -{ - BlockDriverState *bs; - Error *err; - const char *name = qdict_get_str(qdict, "name"); - - if (bdrv_all_delete_snapshot(name, &bs, &err) < 0) { - error_reportf_err(err, - "Error while deleting snapshot on device '%s': ", - bdrv_get_device_name(bs)); - } -} - -void hmp_info_snapshots(Monitor *mon, const QDict *qdict) -{ - BlockDriverState *bs, *bs1; - BdrvNextIterator it1; - QEMUSnapshotInfo *sn_tab, *sn; - bool no_snapshot = true; - int nb_sns, i; - int total; - int *global_snapshots; - AioContext *aio_context; - - typedef struct SnapshotEntry { - QEMUSnapshotInfo sn; - QTAILQ_ENTRY(SnapshotEntry) next; - } SnapshotEntry; - - typedef struct ImageEntry { - const char *imagename; - QTAILQ_ENTRY(ImageEntry) next; - QTAILQ_HEAD(, SnapshotEntry) snapshots; - } ImageEntry; - - QTAILQ_HEAD(, ImageEntry) image_list = - QTAILQ_HEAD_INITIALIZER(image_list); - - ImageEntry *image_entry, *next_ie; - SnapshotEntry *snapshot_entry; - - bs = bdrv_all_find_vmstate_bs(); - if (!bs) { - monitor_printf(mon, "No available block device supports snapshots\n"); - return; - } - aio_context = bdrv_get_aio_context(bs); - - aio_context_acquire(aio_context); - nb_sns = bdrv_snapshot_list(bs, &sn_tab); - aio_context_release(aio_context); - - if (nb_sns < 0) { - monitor_printf(mon, "bdrv_snapshot_list: error %d\n", nb_sns); - return; - } - - for (bs1 = bdrv_first(&it1); bs1; bs1 = bdrv_next(&it1)) { - int bs1_nb_sns = 0; - ImageEntry *ie; - SnapshotEntry *se; - AioContext *ctx = bdrv_get_aio_context(bs1); - - aio_context_acquire(ctx); - if (bdrv_can_snapshot(bs1)) { - sn = NULL; - bs1_nb_sns = bdrv_snapshot_list(bs1, &sn); - if (bs1_nb_sns > 0) { - no_snapshot = false; - ie = g_new0(ImageEntry, 1); - ie->imagename = bdrv_get_device_name(bs1); - QTAILQ_INIT(&ie->snapshots); - QTAILQ_INSERT_TAIL(&image_list, ie, next); - for (i = 0; i < bs1_nb_sns; i++) { - se = g_new0(SnapshotEntry, 1); - se->sn = sn[i]; - QTAILQ_INSERT_TAIL(&ie->snapshots, se, next); - } - } - g_free(sn); - } - aio_context_release(ctx); - } - - if (no_snapshot) { - monitor_printf(mon, "There is no snapshot available.\n"); - return; - } - - global_snapshots = g_new0(int, nb_sns); - total = 0; - for (i = 0; i < nb_sns; i++) { - SnapshotEntry *next_sn; - if (bdrv_all_find_snapshot(sn_tab[i].name, &bs1) == 0) { - global_snapshots[total] = i; - total++; - QTAILQ_FOREACH(image_entry, &image_list, next) { - QTAILQ_FOREACH_SAFE(snapshot_entry, &image_entry->snapshots, - next, next_sn) { - if (!strcmp(sn_tab[i].name, snapshot_entry->sn.name)) { - QTAILQ_REMOVE(&image_entry->snapshots, snapshot_entry, - next); - g_free(snapshot_entry); - } - } - } - } - } - - monitor_printf(mon, "List of snapshots present on all disks:\n"); - - if (total > 0) { - bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, NULL); - monitor_printf(mon, "\n"); - for (i = 0; i < total; i++) { - sn = &sn_tab[global_snapshots[i]]; - /* The ID is not guaranteed to be the same on all images, so - * overwrite it. - */ - pstrcpy(sn->id_str, sizeof(sn->id_str), "--"); - bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, sn); - monitor_printf(mon, "\n"); - } - } else { - monitor_printf(mon, "None\n"); - } - - QTAILQ_FOREACH(image_entry, &image_list, next) { - if (QTAILQ_EMPTY(&image_entry->snapshots)) { - continue; - } - monitor_printf(mon, - "\nList of partial (non-loadable) snapshots on '%s':\n", - image_entry->imagename); - bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, NULL); - monitor_printf(mon, "\n"); - QTAILQ_FOREACH(snapshot_entry, &image_entry->snapshots, next) { - bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, - &snapshot_entry->sn); - monitor_printf(mon, "\n"); - } - } - - QTAILQ_FOREACH_SAFE(image_entry, &image_list, next, next_ie) { - SnapshotEntry *next_sn; - QTAILQ_FOREACH_SAFE(snapshot_entry, &image_entry->snapshots, next, - next_sn) { - g_free(snapshot_entry); - } - g_free(image_entry); - } - g_free(sn_tab); - g_free(global_snapshots); - -} - void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev) { qemu_ram_set_idstr(mr->ram_block, diff --git a/migration/socket.c b/migration/socket.c index 13966f1d26..dc88812048 100644 --- a/migration/socket.c +++ b/migration/socket.c @@ -79,7 +79,6 @@ static void socket_outgoing_migration(QIOTask *task, if (qio_task_propagate_error(task, &err)) { trace_migration_socket_outgoing_error(error_get_pretty(err)); - data->s->to_dst_file = NULL; migrate_fd_error(data->s, err); error_free(err); } else { diff --git a/migration/tls.c b/migration/tls.c index 45bec44ca4..a33ecb767e 100644 --- a/migration/tls.c +++ b/migration/tls.c @@ -116,7 +116,6 @@ static void migration_tls_outgoing_handshake(QIOTask *task, if (qio_task_propagate_error(task, &err)) { trace_migration_tls_outgoing_handshake_error(error_get_pretty(err)); - s->to_dst_file = NULL; migrate_fd_error(s, err); error_free(err); } else { diff --git a/migration/trace-events b/migration/trace-events index b8f01a218c..5b8ccf301c 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -69,8 +69,10 @@ migration_bitmap_sync_start(void) "" migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64 migration_throttle(void) "" ram_discard_range(const char *rbname, uint64_t start, size_t len) "%s: start: %" PRIx64 " %zx" +ram_load_loop(const char *rbname, uint64_t addr, int flags, void *host) "%s: addr: %" PRIx64 " flags: %x host: %p" ram_load_postcopy_loop(uint64_t addr, int flags) "@%" PRIx64 " %x" ram_postcopy_send_discard_bitmap(void) "" +ram_save_page(const char *rbname, uint64_t offset, void *host) "%s: offset: %" PRIx64 " host: %p" ram_save_queue_pages(const char *rbname, size_t start, size_t len) "%s: start: %zx len: %zx" # migration/migration.c @@ -37,7 +37,6 @@ #include "net/slirp.h" #include "sysemu/char.h" #include "ui/qemu-spice.h" -#include "sysemu/sysemu.h" #include "sysemu/numa.h" #include "monitor/monitor.h" #include "qemu/config-file.h" @@ -1954,18 +1953,6 @@ void qmp_closefd(const char *fdname, Error **errp) error_setg(errp, QERR_FD_NOT_FOUND, fdname); } -static void hmp_loadvm(Monitor *mon, const QDict *qdict) -{ - int saved_vm_running = runstate_is_running(); - const char *name = qdict_get_str(qdict, "name"); - - vm_stop(RUN_STATE_RESTORE_VM); - - if (load_vmstate(name) == 0 && saved_vm_running) { - vm_start(); - } -} - int monitor_get_fd(Monitor *mon, const char *fdname, Error **errp) { mon_fd_t *monfd; diff --git a/replay/replay-snapshot.c b/replay/replay-snapshot.c index 65e2d375c2..8cced4604f 100644 --- a/replay/replay-snapshot.c +++ b/replay/replay-snapshot.c @@ -64,7 +64,7 @@ void replay_vmstate_init(void) { if (replay_snapshot) { if (replay_mode == REPLAY_MODE_RECORD) { - if (save_vmstate(cur_mon, replay_snapshot) != 0) { + if (save_vmstate(replay_snapshot) != 0) { error_report("Could not create snapshot for icount record"); exit(1); } |