diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index 909f0517f8..967159479d 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -40,6 +40,8 @@ struct BdrvDirtyBitmap { QemuMutex *mutex; HBitmap *bitmap; /* Dirty bitmap implementation */ HBitmap *meta; /* Meta dirty bitmap */ + bool qmp_locked; /* Bitmap is locked, it can't be modified + through QMP */ BdrvDirtyBitmap *successor; /* Anonymous child; implies frozen status */ char *name; /* Optional non-empty unique ID */ int64_t size; /* Size of the bitmap, in bytes */ @@ -183,6 +185,18 @@ bool bdrv_dirty_bitmap_frozen(BdrvDirtyBitmap *bitmap) return bitmap->successor; } +void bdrv_dirty_bitmap_set_qmp_locked(BdrvDirtyBitmap *bitmap, bool qmp_locked) +{ + qemu_mutex_lock(bitmap->mutex); + bitmap->qmp_locked = qmp_locked; + qemu_mutex_unlock(bitmap->mutex); +} + +bool bdrv_dirty_bitmap_qmp_locked(BdrvDirtyBitmap *bitmap) +{ + return bitmap->qmp_locked; +} + /* Called with BQL taken. */ bool bdrv_dirty_bitmap_enabled(BdrvDirtyBitmap *bitmap) { @@ -194,6 +208,8 @@ DirtyBitmapStatus bdrv_dirty_bitmap_status(BdrvDirtyBitmap *bitmap) { if (bdrv_dirty_bitmap_frozen(bitmap)) { return DIRTY_BITMAP_STATUS_FROZEN; + } else if (bdrv_dirty_bitmap_qmp_locked(bitmap)) { + return DIRTY_BITMAP_STATUS_LOCKED; } else if (!bdrv_dirty_bitmap_enabled(bitmap)) { return DIRTY_BITMAP_STATUS_DISABLED; } else { @@ -234,6 +250,59 @@ int bdrv_dirty_bitmap_create_successor(BlockDriverState *bs, return 0; } +/* Called with BQL taken. */ +void bdrv_dirty_bitmap_enable_successor(BdrvDirtyBitmap *bitmap) +{ + qemu_mutex_lock(bitmap->mutex); + bdrv_enable_dirty_bitmap(bitmap->successor); + qemu_mutex_unlock(bitmap->mutex); +} + +/* Called within bdrv_dirty_bitmap_lock..unlock */ +static void bdrv_do_release_matching_dirty_bitmap_locked( + BlockDriverState *bs, BdrvDirtyBitmap *bitmap, + bool (*cond)(BdrvDirtyBitmap *bitmap)) +{ + BdrvDirtyBitmap *bm, *next; + + QLIST_FOREACH_SAFE(bm, &bs->dirty_bitmaps, list, next) { + if ((!bitmap || bm == bitmap) && (!cond || cond(bm))) { + assert(!bm->active_iterators); + assert(!bdrv_dirty_bitmap_frozen(bm)); + assert(!bm->meta); + QLIST_REMOVE(bm, list); + hbitmap_free(bm->bitmap); + g_free(bm->name); + g_free(bm); + + if (bitmap) { + return; + } + } + } + + if (bitmap) { + abort(); + } +} + +/* Called with BQL taken. */ +static void bdrv_do_release_matching_dirty_bitmap( + BlockDriverState *bs, BdrvDirtyBitmap *bitmap, + bool (*cond)(BdrvDirtyBitmap *bitmap)) +{ + bdrv_dirty_bitmaps_lock(bs); + bdrv_do_release_matching_dirty_bitmap_locked(bs, bitmap, cond); + bdrv_dirty_bitmaps_unlock(bs); +} + +/* Called within bdrv_dirty_bitmap_lock..unlock */ +static void bdrv_release_dirty_bitmap_locked(BlockDriverState *bs, + BdrvDirtyBitmap *bitmap) +{ + bdrv_do_release_matching_dirty_bitmap_locked(bs, bitmap, NULL); +} + /** * For a bitmap with a successor, yield our name to the successor, * delete the old bitmap, and return a handle to the new bitmap. @@ -267,11 +336,11 @@ BdrvDirtyBitmap *bdrv_dirty_bitmap_abdicate(BlockDriverState *bs, * In cases of failure where we can no longer safely delete the parent, * we may wish to re-join the parent and child/successor. * The merged parent will be un-frozen, but not explicitly re-enabled. - * Called with BQL taken. + * Called within bdrv_dirty_bitmap_lock..unlock and with BQL taken. */ -BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs, - BdrvDirtyBitmap *parent, - Error **errp) +BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap_locked(BlockDriverState *bs, + BdrvDirtyBitmap *parent, + Error **errp) { BdrvDirtyBitmap *successor = parent->successor; @@ -284,12 +353,26 @@ BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs, error_setg(errp, "Merging of parent and successor bitmap failed"); return NULL; } - bdrv_release_dirty_bitmap(bs, successor); + bdrv_release_dirty_bitmap_locked(bs, successor); parent->successor = NULL; return parent; } +/* Called with BQL taken. */ +BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs, + BdrvDirtyBitmap *parent, + Error **errp) +{ + BdrvDirtyBitmap *ret; + + qemu_mutex_lock(parent->mutex); + ret = bdrv_reclaim_dirty_bitmap_locked(bs, parent, errp); + qemu_mutex_unlock(parent->mutex); + + return ret; +} + /** * Truncates _all_ bitmaps attached to a BDS. * Called with BQL taken. @@ -313,36 +396,6 @@ static bool bdrv_dirty_bitmap_has_name(BdrvDirtyBitmap *bitmap) return !!bdrv_dirty_bitmap_name(bitmap); } -/* Called with BQL taken. */ -static void bdrv_do_release_matching_dirty_bitmap( - BlockDriverState *bs, BdrvDirtyBitmap *bitmap, - bool (*cond)(BdrvDirtyBitmap *bitmap)) -{ - BdrvDirtyBitmap *bm, *next; - bdrv_dirty_bitmaps_lock(bs); - QLIST_FOREACH_SAFE(bm, &bs->dirty_bitmaps, list, next) { - if ((!bitmap || bm == bitmap) && (!cond || cond(bm))) { - assert(!bm->active_iterators); - assert(!bdrv_dirty_bitmap_frozen(bm)); - assert(!bm->meta); - QLIST_REMOVE(bm, list); - hbitmap_free(bm->bitmap); - g_free(bm->name); - g_free(bm); - - if (bitmap) { - goto out; - } - } - } - if (bitmap) { - abort(); - } - -out: - bdrv_dirty_bitmaps_unlock(bs); -} - /* Called with BQL taken. */ void bdrv_release_dirty_bitmap(BlockDriverState *bs, BdrvDirtyBitmap *bitmap) { diff --git a/blockdev.c b/blockdev.c index 1fbfd3a2c4..b9de18f3b2 100644 --- a/blockdev.c +++ b/blockdev.c @@ -2118,6 +2118,9 @@ static void block_dirty_bitmap_clear_prepare(BlkActionState *common, if (bdrv_dirty_bitmap_frozen(state->bitmap)) { error_setg(errp, "Cannot modify a frozen bitmap"); return; + } else if (bdrv_dirty_bitmap_qmp_locked(state->bitmap)) { + error_setg(errp, "Cannot modify a locked bitmap"); + return; } else if (!bdrv_dirty_bitmap_enabled(state->bitmap)) { error_setg(errp, "Cannot clear a disabled bitmap"); return; @@ -2862,6 +2865,11 @@ void qmp_block_dirty_bitmap_remove(const char *node, const char *name, "Bitmap '%s' is currently frozen and cannot be removed", name); return; + } else if (bdrv_dirty_bitmap_qmp_locked(bitmap)) { + error_setg(errp, + "Bitmap '%s' is currently locked and cannot be removed", + name); + return; } if (bdrv_dirty_bitmap_get_persistance(bitmap)) { @@ -2896,6 +2904,11 @@ void qmp_block_dirty_bitmap_clear(const char *node, const char *name, "Bitmap '%s' is currently frozen and cannot be modified", name); return; + } else if (bdrv_dirty_bitmap_qmp_locked(bitmap)) { + error_setg(errp, + "Bitmap '%s' is currently locked and cannot be modified", + name); + return; } else if (!bdrv_dirty_bitmap_enabled(bitmap)) { error_setg(errp, "Bitmap '%s' is currently disabled and cannot be cleared", @@ -3370,6 +3383,12 @@ static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn, bdrv_unref(target_bs); goto out; } + if (bdrv_dirty_bitmap_qmp_locked(bmap)) { + error_setg(errp, + "Bitmap '%s' is currently locked and cannot be used for " + "backup", backup->bitmap); + goto out; + } } job = backup_job_create(backup->job_id, bs, target_bs, backup->speed, diff --git a/hw/s390x/s390-stattrib.c b/hw/s390x/s390-stattrib.c index adf07ef312..70b95550a8 100644 --- a/hw/s390x/s390-stattrib.c +++ b/hw/s390x/s390-stattrib.c @@ -183,15 +183,16 @@ static int cmma_save_setup(QEMUFile *f, void *opaque) } static void cmma_save_pending(QEMUFile *f, void *opaque, uint64_t max_size, - uint64_t *non_postcopiable_pending, - uint64_t *postcopiable_pending) + uint64_t *res_precopy_only, + uint64_t *res_compatible, + uint64_t *res_postcopy_only) { S390StAttribState *sas = S390_STATTRIB(opaque); S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas); long long res = sac->get_dirtycount(sas); if (res >= 0) { - *non_postcopiable_pending += res; + *res_precopy_only += res; } } diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index 09efec609f..1ff8949b1b 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -21,6 +21,7 @@ BdrvDirtyBitmap *bdrv_dirty_bitmap_abdicate(BlockDriverState *bs, BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, Error **errp); +void bdrv_dirty_bitmap_enable_successor(BdrvDirtyBitmap *bitmap); BdrvDirtyBitmap *bdrv_find_dirty_bitmap(BlockDriverState *bs, const char *name); void bdrv_dirty_bitmap_make_anon(BdrvDirtyBitmap *bitmap); @@ -68,6 +69,8 @@ void bdrv_dirty_bitmap_deserialize_finish(BdrvDirtyBitmap *bitmap); void bdrv_dirty_bitmap_set_readonly(BdrvDirtyBitmap *bitmap, bool value); void bdrv_dirty_bitmap_set_persistance(BdrvDirtyBitmap *bitmap, bool persistent); +void bdrv_dirty_bitmap_set_qmp_locked(BdrvDirtyBitmap *bitmap, bool qmp_locked); + /* Functions that require manual locking. */ void bdrv_dirty_bitmap_lock(BdrvDirtyBitmap *bitmap); @@ -87,10 +90,14 @@ bool bdrv_dirty_bitmap_readonly(const BdrvDirtyBitmap *bitmap); bool bdrv_has_readonly_bitmaps(BlockDriverState *bs); bool bdrv_dirty_bitmap_get_autoload(const BdrvDirtyBitmap *bitmap); bool bdrv_dirty_bitmap_get_persistance(BdrvDirtyBitmap *bitmap); +bool bdrv_dirty_bitmap_qmp_locked(BdrvDirtyBitmap *bitmap); bool bdrv_has_changed_persistent_bitmaps(BlockDriverState *bs); BdrvDirtyBitmap *bdrv_dirty_bitmap_next(BlockDriverState *bs, BdrvDirtyBitmap *bitmap); char *bdrv_dirty_bitmap_sha256(const BdrvDirtyBitmap *bitmap, Error **errp); int64_t bdrv_dirty_bitmap_next_zero(BdrvDirtyBitmap *bitmap, uint64_t start); +BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap_locked(BlockDriverState *bs, + BdrvDirtyBitmap *bitmap, + Error **errp); #endif diff --git a/include/migration/misc.h b/include/migration/misc.h index 77fd4f587c..4ebf24c6c2 100644 --- a/include/migration/misc.h +++ b/include/migration/misc.h @@ -56,4 +56,7 @@ bool migration_has_failed(MigrationState *); bool migration_in_postcopy_after_devices(MigrationState *); void migration_global_dump(Monitor *mon); +/* migration/block-dirty-bitmap.c */ +void dirty_bitmap_mig_init(void); + #endif diff --git a/include/migration/register.h b/include/migration/register.h index f4f7bdc177..f6f12f9b1a 100644 --- a/include/migration/register.h +++ b/include/migration/register.h @@ -26,6 +26,15 @@ typedef struct SaveVMHandlers { bool (*is_active)(void *opaque); bool (*has_postcopy)(void *opaque); + /* is_active_iterate + * If it is not NULL then qemu_savevm_state_iterate will skip iteration if + * it returns false. For example, it is needed for only-postcopy-states, + * which needs to be handled by qemu_savevm_state_setup and + * qemu_savevm_state_pending, but do not need iterations until not in + * postcopy stage. + */ + bool (*is_active_iterate)(void *opaque); + /* This runs outside the iothread lock in the migration case, and * within the lock in the savevm case. The callback had better only * use data that is local to the migration thread or protected @@ -37,8 +46,21 @@ typedef struct SaveVMHandlers { int (*save_setup)(QEMUFile *f, void *opaque); void (*save_live_pending)(QEMUFile *f, void *opaque, uint64_t threshold_size, - uint64_t *non_postcopiable_pending, - uint64_t *postcopiable_pending); + uint64_t *res_precopy_only, + uint64_t *res_compatible, + uint64_t *res_postcopy_only); + /* Note for save_live_pending: + * - res_precopy_only is for data which must be migrated in precopy phase + * or in stopped state, in other words - before target vm start + * - res_compatible is for data which may be migrated in any phase + * - res_postcopy_only is for data which must be migrated in postcopy phase + * or in stopped state, in other words - after source vm stop + * + * Sum of res_postcopy_only, res_compatible and res_postcopy_only is the + * whole amount of pending data. + */ + + LoadStateHandler *load_state; int (*load_setup)(QEMUFile *f, void *opaque); int (*load_cleanup)(void *opaque); diff --git a/migration/Makefile.objs b/migration/Makefile.objs index 99e038024d..c83ec47ba8 100644 --- a/migration/Makefile.objs +++ b/migration/Makefile.objs @@ -6,6 +6,7 @@ common-obj-y += qemu-file.o global_state.o common-obj-y += qemu-file-channel.o common-obj-y += xbzrle.o postcopy-ram.o common-obj-y += qjson.o +common-obj-y += block-dirty-bitmap.o common-obj-$(CONFIG_RDMA) += rdma.o diff --git a/migration/block-dirty-bitmap.c b/migration/block-dirty-bitmap.c new file mode 100644 index 0000000000..dd04f102d8 --- /dev/null +++ b/migration/block-dirty-bitmap.c @@ -0,0 +1,746 @@ +/* + * Block dirty bitmap postcopy migration + * + * Copyright IBM, Corp. 2009 + * Copyright (c) 2016-2017 Virtuozzo International GmbH. All rights reserved. + * + * Authors: + * Liran Schour + * Vladimir Sementsov-Ogievskiy + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * This file is derived from migration/block.c, so it's author and IBM copyright + * are here, although content is quite different. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + * + * *** + * + * Here postcopy migration of dirty bitmaps is realized. Only QMP-addressable + * bitmaps are migrated. + * + * Bitmap migration implies creating bitmap with the same name and granularity + * in destination QEMU. If the bitmap with the same name (for the same node) + * already exists on destination an error will be generated. + * + * format of migration: + * + * # Header (shared for different chunk types) + * 1, 2 or 4 bytes: flags (see qemu_{put,put}_flags) + * [ 1 byte: node name size ] \ flags & DEVICE_NAME + * [ n bytes: node name ] / + * [ 1 byte: bitmap name size ] \ flags & BITMAP_NAME + * [ n bytes: bitmap name ] / + * + * # Start of bitmap migration (flags & START) + * header + * be64: granularity + * 1 byte: bitmap flags (corresponds to BdrvDirtyBitmap) + * bit 0 - bitmap is enabled + * bit 1 - bitmap is persistent + * bit 2 - bitmap is autoloading + * bits 3-7 - reserved, must be zero + * + * # Complete of bitmap migration (flags & COMPLETE) + * header + * + * # Data chunk of bitmap migration + * header + * be64: start sector + * be32: number of sectors + * [ be64: buffer size ] \ ! (flags & ZEROES) + * [ n bytes: buffer ] / + * + * The last chunk in stream should contain flags & EOS. The chunk may skip + * device and/or bitmap names, assuming them to be the same with the previous + * chunk. + */ + +#include "qemu/osdep.h" +#include "block/block.h" +#include "block/block_int.h" +#include "sysemu/block-backend.h" +#include "qemu/main-loop.h" +#include "qemu/error-report.h" +#include "migration/misc.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "migration/vmstate.h" +#include "migration/register.h" +#include "qemu/hbitmap.h" +#include "sysemu/sysemu.h" +#include "qemu/cutils.h" +#include "qapi/error.h" +#include "trace.h" + +#define CHUNK_SIZE (1 << 10) + +/* Flags occupy one, two or four bytes (Big Endian). The size is determined as + * follows: + * in first (most significant) byte bit 8 is clear --> one byte + * in first byte bit 8 is set --> two or four bytes, depending on second + * byte: + * | in second byte bit 8 is clear --> two bytes + * | in second byte bit 8 is set --> four bytes + */ +#define DIRTY_BITMAP_MIG_FLAG_EOS 0x01 +#define DIRTY_BITMAP_MIG_FLAG_ZEROES 0x02 +#define DIRTY_BITMAP_MIG_FLAG_BITMAP_NAME 0x04 +#define DIRTY_BITMAP_MIG_FLAG_DEVICE_NAME 0x08 +#define DIRTY_BITMAP_MIG_FLAG_START 0x10 +#define DIRTY_BITMAP_MIG_FLAG_COMPLETE 0x20 +#define DIRTY_BITMAP_MIG_FLAG_BITS 0x40 + +#define DIRTY_BITMAP_MIG_EXTRA_FLAGS 0x80 + +#define DIRTY_BITMAP_MIG_START_FLAG_ENABLED 0x01 +#define DIRTY_BITMAP_MIG_START_FLAG_PERSISTENT 0x02 +/* 0x04 was "AUTOLOAD" flags on elder versions, no it is ignored */ +#define DIRTY_BITMAP_MIG_START_FLAG_RESERVED_MASK 0xf8 + +typedef struct DirtyBitmapMigBitmapState { + /* Written during setup phase. */ + BlockDriverState *bs; + const char *node_name; + BdrvDirtyBitmap *bitmap; + uint64_t total_sectors; + uint64_t sectors_per_chunk; + QSIMPLEQ_ENTRY(DirtyBitmapMigBitmapState) entry; + uint8_t flags; + + /* For bulk phase. */ + bool bulk_completed; + uint64_t cur_sector; +} DirtyBitmapMigBitmapState; + +typedef struct DirtyBitmapMigState { + QSIMPLEQ_HEAD(dbms_list, DirtyBitmapMigBitmapState) dbms_list; + + bool bulk_completed; + bool no_bitmaps; + + /* for send_bitmap_bits() */ + BlockDriverState *prev_bs; + BdrvDirtyBitmap *prev_bitmap; +} DirtyBitmapMigState; + +typedef struct DirtyBitmapLoadState { + uint32_t flags; + char node_name[256]; + char bitmap_name[256]; + BlockDriverState *bs; + BdrvDirtyBitmap *bitmap; +} DirtyBitmapLoadState; + +static DirtyBitmapMigState dirty_bitmap_mig_state; + +typedef struct DirtyBitmapLoadBitmapState { + BlockDriverState *bs; + BdrvDirtyBitmap *bitmap; + bool migrated; +} DirtyBitmapLoadBitmapState; +static GSList *enabled_bitmaps; +QemuMutex finish_lock; + +void init_dirty_bitmap_incoming_migration(void) +{ + qemu_mutex_init(&finish_lock); +} + +static uint32_t qemu_get_bitmap_flags(QEMUFile *f) +{ + uint8_t flags = qemu_get_byte(f); + if (flags & DIRTY_BITMAP_MIG_EXTRA_FLAGS) { + flags = flags << 8 | qemu_get_byte(f); + if (flags & DIRTY_BITMAP_MIG_EXTRA_FLAGS) { + flags = flags << 16 | qemu_get_be16(f); + } + } + + return flags; +} + +static void qemu_put_bitmap_flags(QEMUFile *f, uint32_t flags) +{ + /* The code currently do not send flags more than one byte */ + assert(!(flags & (0xffffff00 | DIRTY_BITMAP_MIG_EXTRA_FLAGS))); + + qemu_put_byte(f, flags); +} + +static void send_bitmap_header(QEMUFile *f, DirtyBitmapMigBitmapState *dbms, + uint32_t additional_flags) +{ + BlockDriverState *bs = dbms->bs; + BdrvDirtyBitmap *bitmap = dbms->bitmap; + uint32_t flags = additional_flags; + trace_send_bitmap_header_enter(); + + if (bs != dirty_bitmap_mig_state.prev_bs) { + dirty_bitmap_mig_state.prev_bs = bs; + flags |= DIRTY_BITMAP_MIG_FLAG_DEVICE_NAME; + } + + if (bitmap != dirty_bitmap_mig_state.prev_bitmap) { + dirty_bitmap_mig_state.prev_bitmap = bitmap; + flags |= DIRTY_BITMAP_MIG_FLAG_BITMAP_NAME; + } + + qemu_put_bitmap_flags(f, flags); + + if (flags & DIRTY_BITMAP_MIG_FLAG_DEVICE_NAME) { + qemu_put_counted_string(f, dbms->node_name); + } + + if (flags & DIRTY_BITMAP_MIG_FLAG_BITMAP_NAME) { + qemu_put_counted_string(f, bdrv_dirty_bitmap_name(bitmap)); + } +} + +static void send_bitmap_start(QEMUFile *f, DirtyBitmapMigBitmapState *dbms) +{ + send_bitmap_header(f, dbms, DIRTY_BITMAP_MIG_FLAG_START); + qemu_put_be32(f, bdrv_dirty_bitmap_granularity(dbms->bitmap)); + qemu_put_byte(f, dbms->flags); +} + +static void send_bitmap_complete(QEMUFile *f, DirtyBitmapMigBitmapState *dbms) +{ + send_bitmap_header(f, dbms, DIRTY_BITMAP_MIG_FLAG_COMPLETE); +} + +static void send_bitmap_bits(QEMUFile *f, DirtyBitmapMigBitmapState *dbms, + uint64_t start_sector, uint32_t nr_sectors) +{ + /* align for buffer_is_zero() */ + uint64_t align = 4 * sizeof(long); + uint64_t unaligned_size = + bdrv_dirty_bitmap_serialization_size( + dbms->bitmap, start_sector << BDRV_SECTOR_BITS, + (uint64_t)nr_sectors << BDRV_SECTOR_BITS); + uint64_t buf_size = QEMU_ALIGN_UP(unaligned_size, align); + uint8_t *buf = g_malloc0(buf_size); + uint32_t flags = DIRTY_BITMAP_MIG_FLAG_BITS; + + bdrv_dirty_bitmap_serialize_part( + dbms->bitmap, buf, start_sector << BDRV_SECTOR_BITS, + (uint64_t)nr_sectors << BDRV_SECTOR_BITS); + + if (buffer_is_zero(buf, buf_size)) { + g_free(buf); + buf = NULL; + flags |= DIRTY_BITMAP_MIG_FLAG_ZEROES; + } + + trace_send_bitmap_bits(flags, start_sector, nr_sectors, buf_size); + + send_bitmap_header(f, dbms, flags); + + qemu_put_be64(f, start_sector); + qemu_put_be32(f, nr_sectors); + + /* if a block is zero we need to flush here since the network + * bandwidth is now a lot higher than the storage device bandwidth. + * thus if we queue zero blocks we slow down the migration. */ + if (flags & DIRTY_BITMAP_MIG_FLAG_ZEROES) { + qemu_fflush(f); + } else { + qemu_put_be64(f, buf_size); + qemu_put_buffer(f, buf, buf_size); + } + + g_free(buf); +} + +/* Called with iothread lock taken. */ +static void dirty_bitmap_mig_cleanup(void) +{ + DirtyBitmapMigBitmapState *dbms; + + while ((dbms = QSIMPLEQ_FIRST(&dirty_bitmap_mig_state.dbms_list)) != NULL) { + QSIMPLEQ_REMOVE_HEAD(&dirty_bitmap_mig_state.dbms_list, entry); + bdrv_dirty_bitmap_set_qmp_locked(dbms->bitmap, false); + bdrv_unref(dbms->bs); + g_free(dbms); + } +} + +/* Called with iothread lock taken. */ +static int init_dirty_bitmap_migration(void) +{ + BlockDriverState *bs; + BdrvDirtyBitmap *bitmap; + DirtyBitmapMigBitmapState *dbms; + BdrvNextIterator it; + + dirty_bitmap_mig_state.bulk_completed = false; + dirty_bitmap_mig_state.prev_bs = NULL; + dirty_bitmap_mig_state.prev_bitmap = NULL; + dirty_bitmap_mig_state.no_bitmaps = false; + + for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { + const char *drive_name = bdrv_get_device_or_node_name(bs); + + /* skip automatically inserted nodes */ + while (bs && bs->drv && bs->implicit) { + bs = backing_bs(bs); + } + + for (bitmap = bdrv_dirty_bitmap_next(bs, NULL); bitmap; + bitmap = bdrv_dirty_bitmap_next(bs, bitmap)) + { + if (!bdrv_dirty_bitmap_name(bitmap)) { + continue; + } + + if (drive_name == NULL) { + error_report("Found bitmap '%s' in unnamed node %p. It can't " + "be migrated", bdrv_dirty_bitmap_name(bitmap), bs); + goto fail; + } + + if (bdrv_dirty_bitmap_frozen(bitmap)) { + error_report("Can't migrate frozen dirty bitmap: '%s", + bdrv_dirty_bitmap_name(bitmap)); + goto fail; + } + + if (bdrv_dirty_bitmap_qmp_locked(bitmap)) { + error_report("Can't migrate locked dirty bitmap: '%s", + bdrv_dirty_bitmap_name(bitmap)); + goto fail; + } + + bdrv_ref(bs); + bdrv_dirty_bitmap_set_qmp_locked(bitmap, true); + + dbms = g_new0(DirtyBitmapMigBitmapState, 1); + dbms->bs = bs; + dbms->node_name = drive_name; + dbms->bitmap = bitmap; + dbms->total_sectors = bdrv_nb_sectors(bs); + dbms->sectors_per_chunk = CHUNK_SIZE * 8 * + bdrv_dirty_bitmap_granularity(bitmap) >> BDRV_SECTOR_BITS; + if (bdrv_dirty_bitmap_enabled(bitmap)) { + dbms->flags |= DIRTY_BITMAP_MIG_START_FLAG_ENABLED; + } + if (bdrv_dirty_bitmap_get_persistance(bitmap)) { + dbms->flags |= DIRTY_BITMAP_MIG_START_FLAG_PERSISTENT; + } + + QSIMPLEQ_INSERT_TAIL(&dirty_bitmap_mig_state.dbms_list, + dbms, entry); + } + } + + /* unset persistance here, to not roll back it */ + QSIMPLEQ_FOREACH(dbms, &dirty_bitmap_mig_state.dbms_list, entry) { + bdrv_dirty_bitmap_set_persistance(dbms->bitmap, false); + } + + if (QSIMPLEQ_EMPTY(&dirty_bitmap_mig_state.dbms_list)) { + dirty_bitmap_mig_state.no_bitmaps = true; + } + + return 0; + +fail: + dirty_bitmap_mig_cleanup(); + + return -1; +} + +/* Called with no lock taken. */ +static void bulk_phase_send_chunk(QEMUFile *f, DirtyBitmapMigBitmapState *dbms) +{ + uint32_t nr_sectors = MIN(dbms->total_sectors - dbms->cur_sector, + dbms->sectors_per_chunk); + + send_bitmap_bits(f, dbms, dbms->cur_sector, nr_sectors); + + dbms->cur_sector += nr_sectors; + if (dbms->cur_sector >= dbms->total_sectors) { + dbms->bulk_completed = true; + } +} + +/* Called with no lock taken. */ +static void bulk_phase(QEMUFile *f, bool limit) +{ + DirtyBitmapMigBitmapState *dbms; + + QSIMPLEQ_FOREACH(dbms, &dirty_bitmap_mig_state.dbms_list, entry) { + while (!dbms->bulk_completed) { + bulk_phase_send_chunk(f, dbms); + if (limit && qemu_file_rate_limit(f)) { + return; + } + } + } + + dirty_bitmap_mig_state.bulk_completed = true; +} + +/* for SaveVMHandlers */ +static void dirty_bitmap_save_cleanup(void *opaque) +{ + dirty_bitmap_mig_cleanup(); +} + +static int dirty_bitmap_save_iterate(QEMUFile *f, void *opaque) +{ + trace_dirty_bitmap_save_iterate(migration_in_postcopy()); + + if (migration_in_postcopy() && !dirty_bitmap_mig_state.bulk_completed) { + bulk_phase(f, true); + } + + qemu_put_bitmap_flags(f, DIRTY_BITMAP_MIG_FLAG_EOS); + + return dirty_bitmap_mig_state.bulk_completed; +} + +/* Called with iothread lock taken. */ + +static int dirty_bitmap_save_complete(QEMUFile *f, void *opaque) +{ + DirtyBitmapMigBitmapState *dbms; + trace_dirty_bitmap_save_complete_enter(); + + if (!dirty_bitmap_mig_state.bulk_completed) { + bulk_phase(f, false); + } + + QSIMPLEQ_FOREACH(dbms, &dirty_bitmap_mig_state.dbms_list, entry) { + send_bitmap_complete(f, dbms); + } + + qemu_put_bitmap_flags(f, DIRTY_BITMAP_MIG_FLAG_EOS); + + trace_dirty_bitmap_save_complete_finish(); + + dirty_bitmap_mig_cleanup(); + return 0; +} + +static void dirty_bitmap_save_pending(QEMUFile *f, void *opaque, + uint64_t max_size, + uint64_t *res_precopy_only, + uint64_t *res_compatible, + uint64_t *res_postcopy_only) +{ + DirtyBitmapMigBitmapState *dbms; + uint64_t pending = 0; + + qemu_mutex_lock_iothread(); + + QSIMPLEQ_FOREACH(dbms, &dirty_bitmap_mig_state.dbms_list, entry) { + uint64_t gran = bdrv_dirty_bitmap_granularity(dbms->bitmap); + uint64_t sectors = dbms->bulk_completed ? 0 : + dbms->total_sectors - dbms->cur_sector; + + pending += DIV_ROUND_UP(sectors * BDRV_SECTOR_SIZE, gran); + } + + qemu_mutex_unlock_iothread(); + + trace_dirty_bitmap_save_pending(pending, max_size); + + *res_postcopy_only += pending; +} + +/* First occurrence of this bitmap. It should be created if doesn't exist */ +static int dirty_bitmap_load_start(QEMUFile *f, DirtyBitmapLoadState *s) +{ + Error *local_err = NULL; + uint32_t granularity = qemu_get_be32(f); + uint8_t flags = qemu_get_byte(f); + + if (s->bitmap) { + error_report("Bitmap with the same name ('%s') already exists on " + "destination", bdrv_dirty_bitmap_name(s->bitmap)); + return -EINVAL; + } else { + s->bitmap = bdrv_create_dirty_bitmap(s->bs, granularity, + s->bitmap_name, &local_err); + if (!s->bitmap) { + error_report_err(local_err); + return -EINVAL; + } + } + + if (flags & DIRTY_BITMAP_MIG_START_FLAG_RESERVED_MASK) { + error_report("Unknown flags in migrated dirty bitmap header: %x", + flags); + return -EINVAL; + } + + if (flags & DIRTY_BITMAP_MIG_START_FLAG_PERSISTENT) { + bdrv_dirty_bitmap_set_persistance(s->bitmap, true); + } + + bdrv_disable_dirty_bitmap(s->bitmap); + if (flags & DIRTY_BITMAP_MIG_START_FLAG_ENABLED) { + DirtyBitmapLoadBitmapState *b; + + bdrv_dirty_bitmap_create_successor(s->bs, s->bitmap, &local_err); + if (local_err) { + error_report_err(local_err); + return -EINVAL; + } + + b = g_new(DirtyBitmapLoadBitmapState, 1); + b->bs = s->bs; + b->bitmap = s->bitmap; + b->migrated = false; + enabled_bitmaps = g_slist_prepend(enabled_bitmaps, b); + } + + return 0; +} + +void dirty_bitmap_mig_before_vm_start(void) +{ + GSList *item; + + qemu_mutex_lock(&finish_lock); + + for (item = enabled_bitmaps; item; item = g_slist_next(item)) { + DirtyBitmapLoadBitmapState *b = item->data; + + if (b->migrated) { + bdrv_enable_dirty_bitmap(b->bitmap); + } else { + bdrv_dirty_bitmap_enable_successor(b->bitmap); + } + + g_free(b); + } + + g_slist_free(enabled_bitmaps); + enabled_bitmaps = NULL; + + qemu_mutex_unlock(&finish_lock); +} + +static void dirty_bitmap_load_complete(QEMUFile *f, DirtyBitmapLoadState *s) +{ + GSList *item; + trace_dirty_bitmap_load_complete(); + bdrv_dirty_bitmap_deserialize_finish(s->bitmap); + + qemu_mutex_lock(&finish_lock); + + for (item = enabled_bitmaps; item; item = g_slist_next(item)) { + DirtyBitmapLoadBitmapState *b = item->data; + + if (b->bitmap == s->bitmap) { + b->migrated = true; + break; + } + } + + if (bdrv_dirty_bitmap_frozen(s->bitmap)) { + bdrv_dirty_bitmap_lock(s->bitmap); + if (enabled_bitmaps == NULL) { + /* in postcopy */ + bdrv_reclaim_dirty_bitmap_locked(s->bs, s->bitmap, &error_abort); + bdrv_enable_dirty_bitmap(s->bitmap); + } else { + /* target not started, successor must be empty */ + int64_t count = bdrv_get_dirty_count(s->bitmap); + BdrvDirtyBitmap *ret = bdrv_reclaim_dirty_bitmap_locked(s->bs, + s->bitmap, + NULL); + /* bdrv_reclaim_dirty_bitmap can fail only on no successor (it + * must be) or on merge fail, but merge can't fail when second + * bitmap is empty + */ + assert(ret == s->bitmap && + count == bdrv_get_dirty_count(s->bitmap)); + } + bdrv_dirty_bitmap_unlock(s->bitmap); + } + + qemu_mutex_unlock(&finish_lock); +} + +static int dirty_bitmap_load_bits(QEMUFile *f, DirtyBitmapLoadState *s) +{ + uint64_t first_byte = qemu_get_be64(f) << BDRV_SECTOR_BITS; + uint64_t nr_bytes = (uint64_t)qemu_get_be32(f) << BDRV_SECTOR_BITS; + trace_dirty_bitmap_load_bits_enter(first_byte >> BDRV_SECTOR_BITS, + nr_bytes >> BDRV_SECTOR_BITS); + + if (s->flags & DIRTY_BITMAP_MIG_FLAG_ZEROES) { + trace_dirty_bitmap_load_bits_zeroes(); + bdrv_dirty_bitmap_deserialize_zeroes(s->bitmap, first_byte, nr_bytes, + false); + } else { + size_t ret; + uint8_t *buf; + uint64_t buf_size = qemu_get_be64(f); + uint64_t needed_size = + bdrv_dirty_bitmap_serialization_size(s->bitmap, + first_byte, nr_bytes); + + if (needed_size > buf_size || + buf_size > QEMU_ALIGN_UP(needed_size, 4 * sizeof(long)) + /* Here used same alignment as in send_bitmap_bits */ + ) { + error_report("Migrated bitmap granularity doesn't " + "match the destination bitmap '%s' granularity", + bdrv_dirty_bitmap_name(s->bitmap)); + return -EINVAL; + } + + buf = g_malloc(buf_size); + ret = qemu_get_buffer(f, buf, buf_size); + if (ret != buf_size) { + error_report("Failed to read bitmap bits"); + return -EIO; + } + + bdrv_dirty_bitmap_deserialize_part(s->bitmap, buf, first_byte, nr_bytes, + false); + g_free(buf); + } + + return 0; +} + +static int dirty_bitmap_load_header(QEMUFile *f, DirtyBitmapLoadState *s) +{ + Error *local_err = NULL; + bool nothing; + s->flags = qemu_get_bitmap_flags(f); + trace_dirty_bitmap_load_header(s->flags); + + nothing = s->flags == (s->flags & DIRTY_BITMAP_MIG_FLAG_EOS); + + if (s->flags & DIRTY_BITMAP_MIG_FLAG_DEVICE_NAME) { + if (!qemu_get_counted_string(f, s->node_name)) { + error_report("Unable to read node name string"); + return -EINVAL; + } + s->bs = bdrv_lookup_bs(s->node_name, s->node_name, &local_err); + if (!s->bs) { + error_report_err(local_err); + return -EINVAL; + } + } else if (!s->bs && !nothing) { + error_report("Error: block device name is not set"); + return -EINVAL; + } + + if (s->flags & DIRTY_BITMAP_MIG_FLAG_BITMAP_NAME) { + if (!qemu_get_counted_string(f, s->bitmap_name)) { + error_report("Unable to read bitmap name string"); + return -EINVAL; + } + s->bitmap = bdrv_find_dirty_bitmap(s->bs, s->bitmap_name); + + /* bitmap may be NULL here, it wouldn't be an error if it is the + * first occurrence of the bitmap */ + if (!s->bitmap && !(s->flags & DIRTY_BITMAP_MIG_FLAG_START)) { + error_report("Error: unknown dirty bitmap " + "'%s' for block device '%s'", + s->bitmap_name, s->node_name); + return -EINVAL; + } + } else if (!s->bitmap && !nothing) { + error_report("Error: block device name is not set"); + return -EINVAL; + } + + return 0; +} + +static int dirty_bitmap_load(QEMUFile *f, void *opaque, int version_id) +{ + static DirtyBitmapLoadState s; + int ret = 0; + + trace_dirty_bitmap_load_enter(); + + if (version_id != 1) { + return -EINVAL; + } + + do { + ret = dirty_bitmap_load_header(f, &s); + + if (s.flags & DIRTY_BITMAP_MIG_FLAG_START) { + ret = dirty_bitmap_load_start(f, &s); + } else if (s.flags & DIRTY_BITMAP_MIG_FLAG_COMPLETE) { + dirty_bitmap_load_complete(f, &s); + } else if (s.flags & DIRTY_BITMAP_MIG_FLAG_BITS) { + ret = dirty_bitmap_load_bits(f, &s); + } + + if (!ret) { + ret = qemu_file_get_error(f); + } + + if (ret) { + return ret; + } + } while (!(s.flags & DIRTY_BITMAP_MIG_FLAG_EOS)); + + trace_dirty_bitmap_load_success(); + return 0; +} + +static int dirty_bitmap_save_setup(QEMUFile *f, void *opaque) +{ + DirtyBitmapMigBitmapState *dbms = NULL; + if (init_dirty_bitmap_migration() < 0) { + return -1; + } + + QSIMPLEQ_FOREACH(dbms, &dirty_bitmap_mig_state.dbms_list, entry) { + send_bitmap_start(f, dbms); + } + qemu_put_bitmap_flags(f, DIRTY_BITMAP_MIG_FLAG_EOS); + + return 0; +} + +static bool dirty_bitmap_is_active(void *opaque) +{ + return migrate_dirty_bitmaps() && !dirty_bitmap_mig_state.no_bitmaps; +} + +static bool dirty_bitmap_is_active_iterate(void *opaque) +{ + return dirty_bitmap_is_active(opaque) && !runstate_is_running(); +} + +static bool dirty_bitmap_has_postcopy(void *opaque) +{ + return true; +} + +static SaveVMHandlers savevm_dirty_bitmap_handlers = { + .save_setup = dirty_bitmap_save_setup, + .save_live_complete_postcopy = dirty_bitmap_save_complete, + .save_live_complete_precopy = dirty_bitmap_save_complete, + .has_postcopy = dirty_bitmap_has_postcopy, + .save_live_pending = dirty_bitmap_save_pending, + .save_live_iterate = dirty_bitmap_save_iterate, + .is_active_iterate = dirty_bitmap_is_active_iterate, + .load_state = dirty_bitmap_load, + .save_cleanup = dirty_bitmap_save_cleanup, + .is_active = dirty_bitmap_is_active, +}; + +void dirty_bitmap_mig_init(void) +{ + QSIMPLEQ_INIT(&dirty_bitmap_mig_state.dbms_list); + + register_savevm_live(NULL, "dirty-bitmap", 0, 1, + &savevm_dirty_bitmap_handlers, + &dirty_bitmap_mig_state); +} diff --git a/migration/block.c b/migration/block.c index 41b95d1dd8..5c03632257 100644 --- a/migration/block.c +++ b/migration/block.c @@ -864,8 +864,9 @@ static int block_save_complete(QEMUFile *f, void *opaque) } static void block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size, - uint64_t *non_postcopiable_pending, - uint64_t *postcopiable_pending) + uint64_t *res_precopy_only, + uint64_t *res_compatible, + uint64_t *res_postcopy_only) { /* Estimate pending number of bytes to send */ uint64_t pending; @@ -886,7 +887,7 @@ static void block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size, DPRINTF("Enter save live pending %" PRIu64 "\n", pending); /* We don't do postcopy */ - *non_postcopiable_pending += pending; + *res_precopy_only += pending; } static int block_load(QEMUFile *f, void *opaque, int version_id) diff --git a/migration/migration.c b/migration/migration.c index 6a4780ef6f..623f373326 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -157,6 +157,9 @@ MigrationIncomingState *migration_incoming_get_current(void) memset(&mis_current, 0, sizeof(MigrationIncomingState)); qemu_mutex_init(&mis_current.rp_mutex); qemu_event_init(&mis_current.main_thread_load_event, false); + + init_dirty_bitmap_incoming_migration(); + once = true; } return &mis_current; @@ -320,6 +323,8 @@ static void process_incoming_migration_bh(void *opaque) state, we need to obey autostart. Any other state is set with runstate_set. */ + dirty_bitmap_mig_before_vm_start(); + if (!global_state_received() || global_state_get_runstate() == RUN_STATE_RUNNING) { if (autostart) { @@ -1022,7 +1027,7 @@ void qmp_migrate_start_postcopy(Error **errp) { MigrationState *s = migrate_get_current(); - if (!migrate_postcopy_ram()) { + if (!migrate_postcopy()) { error_setg(errp, "Enable postcopy with migrate_set_capability before" " the start of migration"); return; @@ -1508,7 +1513,7 @@ bool migrate_postcopy_ram(void) bool migrate_postcopy(void) { - return migrate_postcopy_ram(); + return migrate_postcopy_ram() || migrate_dirty_bitmaps(); } bool migrate_auto_converge(void) @@ -1565,6 +1570,15 @@ int migrate_decompress_threads(void) return s->parameters.decompress_threads; } +bool migrate_dirty_bitmaps(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->enabled_capabilities[MIGRATION_CAPABILITY_DIRTY_BITMAPS]; +} + bool migrate_use_events(void) { MigrationState *s; @@ -2242,20 +2256,20 @@ typedef enum { */ static MigIterateState migration_iteration_run(MigrationState *s) { - uint64_t pending_size, pend_post, pend_nonpost; + uint64_t pending_size, pend_pre, pend_compat, pend_post; bool in_postcopy = s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE; - qemu_savevm_state_pending(s->to_dst_file, s->threshold_size, - &pend_nonpost, &pend_post); - pending_size = pend_nonpost + pend_post; + qemu_savevm_state_pending(s->to_dst_file, s->threshold_size, &pend_pre, + &pend_compat, &pend_post); + pending_size = pend_pre + pend_compat + pend_post; trace_migrate_pending(pending_size, s->threshold_size, - pend_post, pend_nonpost); + pend_pre, pend_compat, pend_post); if (pending_size && pending_size >= s->threshold_size) { /* Still a significant amount to transfer */ if (migrate_postcopy() && !in_postcopy && - pend_nonpost <= s->threshold_size && + pend_pre <= s->threshold_size && atomic_read(&s->start_postcopy)) { if (postcopy_start(s)) { error_report("%s: postcopy failed to start", __func__); diff --git a/migration/migration.h b/migration/migration.h index 08c5d2ded1..a79540b99c 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -205,6 +205,7 @@ bool migrate_postcopy(void); bool migrate_release_ram(void); bool migrate_postcopy_ram(void); bool migrate_zero_blocks(void); +bool migrate_dirty_bitmaps(void); bool migrate_auto_converge(void); bool migrate_use_multifd(void); @@ -234,4 +235,7 @@ void migrate_send_rp_pong(MigrationIncomingState *mis, int migrate_send_rp_req_pages(MigrationIncomingState *mis, const char* rbname, ram_addr_t start, size_t len); +void dirty_bitmap_mig_before_vm_start(void); +void init_dirty_bitmap_incoming_migration(void); + #endif diff --git a/migration/qemu-file.c b/migration/qemu-file.c index 2ab2bf362d..e85f501f86 100644 --- a/migration/qemu-file.c +++ b/migration/qemu-file.c @@ -733,6 +733,19 @@ size_t qemu_get_counted_string(QEMUFile *f, char buf[256]) return res == len ? res : 0; } +/* + * Put a string with one preceding byte containing its length. The length of + * the string should be less than 256. + */ +void qemu_put_counted_string(QEMUFile *f, const char *str) +{ + size_t len = strlen(str); + + assert(len < 256); + qemu_put_byte(f, len); + qemu_put_buffer(f, (const uint8_t *)str, len); +} + /* * Set the blocking state of the QEMUFile. * Note: On some transports the OS only keeps a single blocking state for diff --git a/migration/qemu-file.h b/migration/qemu-file.h index aae4e5ed36..f4f356ab12 100644 --- a/migration/qemu-file.h +++ b/migration/qemu-file.h @@ -174,4 +174,6 @@ size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset, ram_addr_t offset, size_t size, uint64_t *bytes_sent); +void qemu_put_counted_string(QEMUFile *f, const char *name); + #endif diff --git a/migration/ram.c b/migration/ram.c index 7266351fd0..590fceb7e9 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -2370,8 +2370,9 @@ static int ram_save_complete(QEMUFile *f, void *opaque) } static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size, - uint64_t *non_postcopiable_pending, - uint64_t *postcopiable_pending) + uint64_t *res_precopy_only, + uint64_t *res_compatible, + uint64_t *res_postcopy_only) { RAMState **temp = opaque; RAMState *rs = *temp; @@ -2391,9 +2392,9 @@ static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size, if (migrate_postcopy_ram()) { /* We can do postcopy, and all the data is postcopiable */ - *postcopiable_pending += remaining_size; + *res_compatible += remaining_size; } else { - *non_postcopiable_pending += remaining_size; + *res_precopy_only += remaining_size; } } diff --git a/migration/savevm.c b/migration/savevm.c index fbeac658c1..f417cef7d5 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1029,6 +1029,11 @@ int qemu_savevm_state_iterate(QEMUFile *f, bool postcopy) continue; } } + if (se->ops && se->ops->is_active_iterate) { + if (!se->ops->is_active_iterate(se->opaque)) { + continue; + } + } /* * In the postcopy phase, any device that doesn't know how to * do postcopy should have saved it's state in the _complete @@ -1221,13 +1226,15 @@ int qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only, * for units that can't do postcopy. */ void qemu_savevm_state_pending(QEMUFile *f, uint64_t threshold_size, - uint64_t *res_non_postcopiable, - uint64_t *res_postcopiable) + uint64_t *res_precopy_only, + uint64_t *res_compatible, + uint64_t *res_postcopy_only) { SaveStateEntry *se; - *res_non_postcopiable = 0; - *res_postcopiable = 0; + *res_precopy_only = 0; + *res_compatible = 0; + *res_postcopy_only = 0; QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { @@ -1240,7 +1247,8 @@ void qemu_savevm_state_pending(QEMUFile *f, uint64_t threshold_size, } } se->ops->save_live_pending(f, se->opaque, threshold_size, - res_non_postcopiable, res_postcopiable); + res_precopy_only, res_compatible, + res_postcopy_only); } } @@ -1686,6 +1694,8 @@ static void loadvm_postcopy_handle_run_bh(void *opaque) trace_loadvm_postcopy_handle_run_vmstart(); + dirty_bitmap_mig_before_vm_start(); + if (autostart) { /* Hold onto your hats, starting the CPU */ vm_start(); diff --git a/migration/savevm.h b/migration/savevm.h index 295c4a1f2c..cf4f0d37ca 100644 --- a/migration/savevm.h +++ b/migration/savevm.h @@ -38,8 +38,9 @@ void qemu_savevm_state_complete_postcopy(QEMUFile *f); int qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only, bool inactivate_disks); void qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size, - uint64_t *res_non_postcopiable, - uint64_t *res_postcopiable); + uint64_t *res_precopy_only, + uint64_t *res_compatible, + uint64_t *res_postcopy_only); 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/migration/trace-events b/migration/trace-events index 93961dea16..314e1be6bc 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -86,7 +86,7 @@ migrate_fd_cleanup(void) "" migrate_fd_error(const char *error_desc) "error=%s" migrate_fd_cancel(void) "" migrate_handle_rp_req_pages(const char *rbname, size_t start, size_t len) "in %s at 0x%zx len 0x%zx" -migrate_pending(uint64_t size, uint64_t max, uint64_t post, uint64_t nonpost) "pending size %" PRIu64 " max %" PRIu64 " (post=%" PRIu64 " nonpost=%" PRIu64 ")" +migrate_pending(uint64_t size, uint64_t max, uint64_t pre, uint64_t compat, uint64_t post) "pending size %" PRIu64 " max %" PRIu64 " (pre = %" PRIu64 " compat=%" PRIu64 " post=%" PRIu64 ")" migrate_send_rp_message(int msg_type, uint16_t len) "%d: len %d" migration_completion_file_err(void) "" migration_completion_postcopy_end(void) "" @@ -227,3 +227,17 @@ colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'" colo_send_message(const char *msg) "Send '%s' message" colo_receive_message(const char *msg) "Receive '%s' message" colo_failover_set_state(const char *new_state) "new state %s" + +# migration/block-dirty-bitmap.c +send_bitmap_header_enter(void) "" +send_bitmap_bits(uint32_t flags, uint64_t start_sector, uint32_t nr_sectors, uint64_t data_size) "flags: 0x%x, start_sector: %" PRIu64 ", nr_sectors: %" PRIu32 ", data_size: %" PRIu64 +dirty_bitmap_save_iterate(int in_postcopy) "in postcopy: %d" +dirty_bitmap_save_complete_enter(void) "" +dirty_bitmap_save_complete_finish(void) "" +dirty_bitmap_save_pending(uint64_t pending, uint64_t max_size) "pending %" PRIu64 " max: %" PRIu64 +dirty_bitmap_load_complete(void) "" +dirty_bitmap_load_bits_enter(uint64_t first_sector, uint32_t nr_sectors) "chunk: %" PRIu64 " %" PRIu32 +dirty_bitmap_load_bits_zeroes(void) "" +dirty_bitmap_load_header(uint32_t flags) "flags 0x%x" +dirty_bitmap_load_enter(void) "" +dirty_bitmap_load_success(void) "" diff --git a/qapi/block-core.json b/qapi/block-core.json index 524d51567a..2b378f510a 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -426,10 +426,13 @@ # @active: The bitmap is actively monitoring for new writes, and can be cleared, # deleted, or used for backup operations. # +# @locked: The bitmap is currently in-use by some operation and can not be +# cleared, deleted, or used for backup operations. (Since 2.12) +# # Since: 2.4 ## { 'enum': 'DirtyBitmapStatus', - 'data': ['active', 'disabled', 'frozen'] } + 'data': ['active', 'disabled', 'frozen', 'locked'] } ## # @BlockDirtyInfo: diff --git a/qapi/migration.json b/qapi/migration.json index 7f465a1902..9d0bf82cf4 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -354,12 +354,16 @@ # # @x-multifd: Use more than one fd for migration (since 2.11) # +# @dirty-bitmaps: If enabled, QEMU will migrate named dirty bitmaps. +# (since 2.12) +# # Since: 1.2 ## { 'enum': 'MigrationCapability', 'data': ['xbzrle', 'rdma-pin-all', 'auto-converge', 'zero-blocks', 'compress', 'events', 'postcopy-ram', 'x-colo', 'release-ram', - 'block', 'return-path', 'pause-before-switchover', 'x-multifd' ] } + 'block', 'return-path', 'pause-before-switchover', 'x-multifd', + 'dirty-bitmaps' ] } ## # @MigrationCapabilityStatus: diff --git a/tests/qemu-iotests/169 b/tests/qemu-iotests/169 new file mode 100755 index 0000000000..3a8db91f6f --- /dev/null +++ b/tests/qemu-iotests/169 @@ -0,0 +1,156 @@ +#!/usr/bin/env python +# +# Tests for dirty bitmaps migration. +# +# Copyright (c) 2016-2017 Virtuozzo International GmbH. All rights reserved. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . +# + +import os +import iotests +import time +import itertools +import operator +import new +from iotests import qemu_img + + +disk_a = os.path.join(iotests.test_dir, 'disk_a') +disk_b = os.path.join(iotests.test_dir, 'disk_b') +size = '1M' +mig_file = os.path.join(iotests.test_dir, 'mig_file') + + +class TestDirtyBitmapMigration(iotests.QMPTestCase): + def tearDown(self): + self.vm_a.shutdown() + self.vm_b.shutdown() + os.remove(disk_a) + os.remove(disk_b) + os.remove(mig_file) + + def setUp(self): + qemu_img('create', '-f', iotests.imgfmt, disk_a, size) + qemu_img('create', '-f', iotests.imgfmt, disk_b, size) + + self.vm_a = iotests.VM(path_suffix='a').add_drive(disk_a) + self.vm_a.launch() + + self.vm_b = iotests.VM(path_suffix='b') + self.vm_b.add_incoming("exec: cat '" + mig_file + "'") + + def add_bitmap(self, vm, granularity, persistent): + params = {'node': 'drive0', + 'name': 'bitmap0', + 'granularity': granularity} + if persistent: + params['persistent'] = True + params['autoload'] = True + + result = vm.qmp('block-dirty-bitmap-add', **params) + self.assert_qmp(result, 'return', {}); + + def get_bitmap_hash(self, vm): + result = vm.qmp('x-debug-block-dirty-bitmap-sha256', + node='drive0', name='bitmap0') + return result['return']['sha256'] + + def check_bitmap(self, vm, sha256): + result = vm.qmp('x-debug-block-dirty-bitmap-sha256', + node='drive0', name='bitmap0') + if sha256: + self.assert_qmp(result, 'return/sha256', sha256); + else: + self.assert_qmp(result, 'error/desc', + "Dirty bitmap 'bitmap0' not found"); + + def do_test_migration(self, persistent, migrate_bitmaps, online, + shared_storage): + granularity = 512 + + # regions = ((start, count), ...) + regions = ((0, 0x10000), + (0xf0000, 0x10000), + (0xa0201, 0x1000)) + + should_migrate = migrate_bitmaps or persistent and shared_storage + + self.vm_b.add_drive(disk_a if shared_storage else disk_b) + + if online: + os.mkfifo(mig_file) + self.vm_b.launch() + + self.add_bitmap(self.vm_a, granularity, persistent) + for r in regions: + self.vm_a.hmp_qemu_io('drive0', 'write %d %d' % r) + sha256 = self.get_bitmap_hash(self.vm_a) + + if migrate_bitmaps: + capabilities = [{'capability': 'dirty-bitmaps', 'state': True}] + + result = self.vm_a.qmp('migrate-set-capabilities', + capabilities=capabilities) + self.assert_qmp(result, 'return', {}) + + if online: + result = self.vm_b.qmp('migrate-set-capabilities', + capabilities=capabilities) + self.assert_qmp(result, 'return', {}) + + result = self.vm_a.qmp('migrate-set-capabilities', + capabilities=[{'capability': 'events', + 'state': True}]) + self.assert_qmp(result, 'return', {}) + + result = self.vm_a.qmp('migrate', uri='exec:cat>' + mig_file) + while True: + event = self.vm_a.event_wait('MIGRATION') + if event['data']['status'] == 'completed': + break + + if not online: + self.vm_a.shutdown() + self.vm_b.launch() + # TODO enable bitmap capability for vm_b in this case + + self.vm_b.event_wait("RESUME", timeout=10.0) + + self.check_bitmap(self.vm_b, sha256 if should_migrate else False) + + if should_migrate: + self.vm_b.shutdown() + self.vm_b.launch() + self.check_bitmap(self.vm_b, sha256 if persistent else False) + + +def inject_test_case(klass, name, method, *args, **kwargs): + mc = operator.methodcaller(method, *args, **kwargs) + setattr(klass, 'test_' + name, new.instancemethod(mc, None, klass)) + +for cmb in list(itertools.product((True, False), repeat=3)): + name = ('_' if cmb[0] else '_not_') + 'persistent_' + name += ('_' if cmb[1] else '_not_') + 'migbitmap_' + name += '_online' if cmb[2] else '_offline' + + # TODO fix shared-storage bitmap migration and enable cases for it + args = list(cmb) + [False] + + inject_test_case(TestDirtyBitmapMigration, name, 'do_test_migration', + *args) + + +if __name__ == '__main__': + iotests.main(supported_fmts=['qcow2']) diff --git a/tests/qemu-iotests/169.out b/tests/qemu-iotests/169.out new file mode 100644 index 0000000000..594c16f49f --- /dev/null +++ b/tests/qemu-iotests/169.out @@ -0,0 +1,5 @@ +........ +---------------------------------------------------------------------- +Ran 8 tests + +OK diff --git a/tests/qemu-iotests/199 b/tests/qemu-iotests/199 new file mode 100755 index 0000000000..651e8df5d9 --- /dev/null +++ b/tests/qemu-iotests/199 @@ -0,0 +1,118 @@ +#!/usr/bin/env python +# +# Tests for dirty bitmaps postcopy migration. +# +# Copyright (c) 2016-2017 Virtuozzo International GmbH. All rights reserved. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . +# + +import os +import iotests +import time +from iotests import qemu_img + +disk_a = os.path.join(iotests.test_dir, 'disk_a') +disk_b = os.path.join(iotests.test_dir, 'disk_b') +size = '256G' +fifo = os.path.join(iotests.test_dir, 'mig_fifo') + +class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): + + def tearDown(self): + self.vm_a.shutdown() + self.vm_b.shutdown() + os.remove(disk_a) + os.remove(disk_b) + os.remove(fifo) + + def setUp(self): + os.mkfifo(fifo) + qemu_img('create', '-f', iotests.imgfmt, disk_a, size) + qemu_img('create', '-f', iotests.imgfmt, disk_b, size) + self.vm_a = iotests.VM(path_suffix='a').add_drive(disk_a) + self.vm_b = iotests.VM(path_suffix='b').add_drive(disk_b) + self.vm_b.add_incoming("exec: cat '" + fifo + "'") + self.vm_a.launch() + self.vm_b.launch() + + def test_postcopy(self): + write_size = 0x40000000 + granularity = 512 + chunk = 4096 + + result = self.vm_a.qmp('block-dirty-bitmap-add', node='drive0', + name='bitmap', granularity=granularity) + self.assert_qmp(result, 'return', {}); + + s = 0 + while s < write_size: + self.vm_a.hmp_qemu_io('drive0', 'write %d %d' % (s, chunk)) + s += 0x10000 + s = 0x8000 + while s < write_size: + self.vm_a.hmp_qemu_io('drive0', 'write %d %d' % (s, chunk)) + s += 0x10000 + + result = self.vm_a.qmp('x-debug-block-dirty-bitmap-sha256', + node='drive0', name='bitmap') + sha256 = result['return']['sha256'] + + result = self.vm_a.qmp('block-dirty-bitmap-clear', node='drive0', + name='bitmap') + self.assert_qmp(result, 'return', {}); + s = 0 + while s < write_size: + self.vm_a.hmp_qemu_io('drive0', 'write %d %d' % (s, chunk)) + s += 0x10000 + + bitmaps_cap = {'capability': 'dirty-bitmaps', 'state': True} + events_cap = {'capability': 'events', 'state': True} + + result = self.vm_a.qmp('migrate-set-capabilities', + capabilities=[bitmaps_cap, events_cap]) + self.assert_qmp(result, 'return', {}) + + result = self.vm_b.qmp('migrate-set-capabilities', + capabilities=[bitmaps_cap]) + self.assert_qmp(result, 'return', {}) + + result = self.vm_a.qmp('migrate', uri='exec:cat>' + fifo) + self.assert_qmp(result, 'return', {}) + + result = self.vm_a.qmp('migrate-start-postcopy') + self.assert_qmp(result, 'return', {}) + + while True: + event = self.vm_a.event_wait('MIGRATION') + if event['data']['status'] == 'completed': + break + + s = 0x8000 + while s < write_size: + self.vm_b.hmp_qemu_io('drive0', 'write %d %d' % (s, chunk)) + s += 0x10000 + + result = self.vm_b.qmp('query-block'); + while len(result['return'][0]['dirty-bitmaps']) > 1: + time.sleep(2) + result = self.vm_b.qmp('query-block'); + + result = self.vm_b.qmp('x-debug-block-dirty-bitmap-sha256', + node='drive0', name='bitmap') + + self.assert_qmp(result, 'return/sha256', sha256); + +if __name__ == '__main__': + iotests.main(supported_fmts=['qcow2'], supported_cache_modes=['none']) diff --git a/tests/qemu-iotests/199.out b/tests/qemu-iotests/199.out new file mode 100644 index 0000000000..ae1213e6f8 --- /dev/null +++ b/tests/qemu-iotests/199.out @@ -0,0 +1,5 @@ +. +---------------------------------------------------------------------- +Ran 1 tests + +OK diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index 624e1fbd4f..0f912e17b0 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -169,6 +169,7 @@ 162 auto quick 163 rw auto quick 165 rw auto quick +169 rw auto quick 170 rw auto quick 171 rw auto quick 172 auto @@ -196,6 +197,7 @@ 196 rw auto quick 197 rw auto quick 198 rw auto +199 rw auto 200 rw auto 201 rw auto migration 202 rw auto quick diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index 90cd751e2a..845be3ad01 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -537,6 +537,10 @@ def verify_platform(supported_oses=['linux']): if True not in [sys.platform.startswith(x) for x in supported_oses]: notrun('not suitable for this OS: %s' % sys.platform) +def verify_cache_mode(supported_cache_modes=[]): + if supported_cache_modes and (cachemode not in supported_cache_modes): + notrun('not suitable for this cache mode: %s' % cachemode) + def supports_quorum(): return 'quorum' in qemu_img_pipe('--help') @@ -545,7 +549,7 @@ def verify_quorum(): if not supports_quorum(): notrun('quorum support missing') -def main(supported_fmts=[], supported_oses=['linux']): +def main(supported_fmts=[], supported_oses=['linux'], supported_cache_modes=[]): '''Run tests''' global debug @@ -562,6 +566,7 @@ def main(supported_fmts=[], supported_oses=['linux']): verbosity = 1 verify_image_format(supported_fmts) verify_platform(supported_oses) + verify_cache_mode(supported_cache_modes) # We need to filter out the time taken from the output so that qemu-iotest # can reliably diff the results against master output. diff --git a/vl.c b/vl.c index 5925a4b502..19340a324a 100644 --- a/vl.c +++ b/vl.c @@ -4503,6 +4503,7 @@ int main(int argc, char **argv, char **envp) blk_mig_init(); ram_mig_init(); + dirty_bitmap_mig_init(); /* If the currently selected machine wishes to override the units-per-bus * property of its default HBA interface type, do so now. */