diff options
| -rw-r--r-- | migration/block.c | 65 |
1 files changed, 52 insertions, 13 deletions
diff --git a/migration/block.c b/migration/block.c index 3a8330a4b3..72883d7c64 100644 --- a/migration/block.c +++ b/migration/block.c @@ -54,17 +54,25 @@ typedef struct BlkMigDevState { int shared_base; int64_t total_sectors; QSIMPLEQ_ENTRY(BlkMigDevState) entry; + Error *blocker; /* Only used by migration thread. Does not need a lock. */ int bulk_completed; int64_t cur_sector; int64_t cur_dirty; - /* Protected by block migration lock. */ + /* Data in the aio_bitmap is protected by block migration lock. + * Allocation and free happen during setup and cleanup respectively. + */ unsigned long *aio_bitmap; + + /* Protected by block migration lock. */ int64_t completed_sectors; + + /* During migration this is protected by iothread lock / AioContext. + * Allocation and free happen during setup and cleanup respectively. + */ BdrvDirtyBitmap *dirty_bitmap; - Error *blocker; } BlkMigDevState; typedef struct BlkMigBlock { @@ -100,7 +108,7 @@ typedef struct BlkMigState { int prev_progress; int bulk_completed; - /* Lock must be taken _inside_ the iothread lock. */ + /* Lock must be taken _inside_ the iothread lock and any AioContexts. */ QemuMutex lock; } BlkMigState; @@ -264,11 +272,13 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds) if (bmds->shared_base) { qemu_mutex_lock_iothread(); + aio_context_acquire(bdrv_get_aio_context(bs)); while (cur_sector < total_sectors && !bdrv_is_allocated(bs, cur_sector, MAX_IS_ALLOCATED_SEARCH, &nr_sectors)) { cur_sector += nr_sectors; } + aio_context_release(bdrv_get_aio_context(bs)); qemu_mutex_unlock_iothread(); } @@ -302,11 +312,21 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds) block_mig_state.submitted++; blk_mig_unlock(); + /* We do not know if bs is under the main thread (and thus does + * not acquire the AioContext when doing AIO) or rather under + * dataplane. Thus acquire both the iothread mutex and the + * AioContext. + * + * This is ugly and will disappear when we make bdrv_* thread-safe, + * without the need to acquire the AioContext. + */ qemu_mutex_lock_iothread(); + aio_context_acquire(bdrv_get_aio_context(bmds->bs)); blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov, nr_sectors, blk_mig_read_cb, blk); bdrv_reset_dirty_bitmap(bmds->dirty_bitmap, cur_sector, nr_sectors); + aio_context_release(bdrv_get_aio_context(bmds->bs)); qemu_mutex_unlock_iothread(); bmds->cur_sector = cur_sector + nr_sectors; @@ -321,8 +341,10 @@ static int set_dirty_tracking(void) int ret; QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + aio_context_acquire(bdrv_get_aio_context(bmds->bs)); bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE, NULL, NULL); + aio_context_release(bdrv_get_aio_context(bmds->bs)); if (!bmds->dirty_bitmap) { ret = -errno; goto fail; @@ -333,18 +355,24 @@ static int set_dirty_tracking(void) fail: QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { if (bmds->dirty_bitmap) { + aio_context_acquire(bdrv_get_aio_context(bmds->bs)); bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap); + aio_context_release(bdrv_get_aio_context(bmds->bs)); } } return ret; } +/* Called with iothread lock taken. */ + static void unset_dirty_tracking(void) { BlkMigDevState *bmds; QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + aio_context_acquire(bdrv_get_aio_context(bmds->bs)); bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap); + aio_context_release(bdrv_get_aio_context(bmds->bs)); } } @@ -444,7 +472,7 @@ static void blk_mig_reset_dirty_cursor(void) } } -/* Called with iothread lock taken. */ +/* Called with iothread lock and AioContext taken. */ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds, int is_async) @@ -527,7 +555,9 @@ static int blk_mig_save_dirty_block(QEMUFile *f, int is_async) int ret = 1; QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + aio_context_acquire(bdrv_get_aio_context(bmds->bs)); ret = mig_save_device_dirty(f, bmds, is_async); + aio_context_release(bdrv_get_aio_context(bmds->bs)); if (ret <= 0) { break; } @@ -585,7 +615,9 @@ static int64_t get_remaining_dirty(void) int64_t dirty = 0; QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + aio_context_acquire(bdrv_get_aio_context(bmds->bs)); dirty += bdrv_get_dirty_count(bmds->dirty_bitmap); + aio_context_release(bdrv_get_aio_context(bmds->bs)); } return dirty << BDRV_SECTOR_BITS; @@ -597,21 +629,28 @@ static void block_migration_cleanup(void *opaque) { BlkMigDevState *bmds; BlkMigBlock *blk; + AioContext *ctx; bdrv_drain_all(); unset_dirty_tracking(); - blk_mig_lock(); while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) { QSIMPLEQ_REMOVE_HEAD(&block_mig_state.bmds_list, entry); bdrv_op_unblock_all(bmds->bs, bmds->blocker); error_free(bmds->blocker); + + /* Save ctx, because bmds->bs can disappear during bdrv_unref. */ + ctx = bdrv_get_aio_context(bmds->bs); + aio_context_acquire(ctx); bdrv_unref(bmds->bs); + aio_context_release(ctx); + g_free(bmds->aio_bitmap); g_free(bmds); } + blk_mig_lock(); while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) { QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry); g_free(blk->buf); @@ -633,13 +672,12 @@ static int block_save_setup(QEMUFile *f, void *opaque) /* start track dirty blocks */ ret = set_dirty_tracking(); + qemu_mutex_unlock_iothread(); + if (ret) { - qemu_mutex_unlock_iothread(); return ret; } - qemu_mutex_unlock_iothread(); - ret = flush_blks(f); blk_mig_reset_dirty_cursor(); qemu_put_be64(f, BLK_MIG_FLAG_EOS); @@ -761,17 +799,18 @@ static void block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size, uint64_t pending; qemu_mutex_lock_iothread(); + pending = get_remaining_dirty(); + qemu_mutex_unlock_iothread(); + blk_mig_lock(); - pending = get_remaining_dirty() + - block_mig_state.submitted * BLOCK_SIZE + - block_mig_state.read_done * BLOCK_SIZE; + pending += block_mig_state.submitted * BLOCK_SIZE + + block_mig_state.read_done * BLOCK_SIZE; + blk_mig_unlock(); /* Report at least one block pending during bulk phase */ if (pending <= max_size && !block_mig_state.bulk_completed) { pending = max_size + BLOCK_SIZE; } - blk_mig_unlock(); - qemu_mutex_unlock_iothread(); DPRINTF("Enter save live pending %" PRIu64 "\n", pending); /* We don't do postcopy */ |