diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/export/export.c | 5 | ||||
| -rw-r--r-- | block/mirror.c | 13 | ||||
| -rw-r--r-- | block/replication.c | 111 | ||||
| -rw-r--r-- | block/vvfat.c | 43 |
4 files changed, 89 insertions, 83 deletions
diff --git a/block/export/export.c b/block/export/export.c index fec7d9f738..6d3b9964c8 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -111,6 +111,7 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) if (export->has_iothread) { IOThread *iothread; AioContext *new_ctx; + Error **set_context_errp; iothread = iothread_by_id(export->iothread); if (!iothread) { @@ -120,7 +121,9 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) new_ctx = iothread_get_aio_context(iothread); - ret = bdrv_try_set_aio_context(bs, new_ctx, errp); + /* Ignore errors with fixed-iothread=false */ + set_context_errp = fixed_iothread ? errp : NULL; + ret = bdrv_try_set_aio_context(bs, new_ctx, set_context_errp); if (ret == 0) { aio_context_release(ctx); aio_context_acquire(new_ctx); diff --git a/block/mirror.c b/block/mirror.c index 019f6deaa5..98fc66eabf 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -107,6 +107,7 @@ struct MirrorOp { bool is_in_flight; CoQueue waiting_requests; Coroutine *co; + MirrorOp *waiting_for_op; QTAILQ_ENTRY(MirrorOp) next; }; @@ -159,7 +160,18 @@ static void coroutine_fn mirror_wait_on_conflicts(MirrorOp *self, if (ranges_overlap(self_start_chunk, self_nb_chunks, op_start_chunk, op_nb_chunks)) { + /* + * If the operation is already (indirectly) waiting for us, or + * will wait for us as soon as it wakes up, then just go on + * (instead of producing a deadlock in the former case). + */ + if (op->waiting_for_op) { + continue; + } + + self->waiting_for_op = op; qemu_co_queue_wait(&op->waiting_requests, NULL); + self->waiting_for_op = NULL; break; } } @@ -1343,6 +1355,7 @@ static MirrorOp *coroutine_fn active_write_prepare(MirrorBlockJob *s, .bytes = bytes, .is_active_write = true, .is_in_flight = true, + .co = qemu_coroutine_self(), }; qemu_co_queue_init(&op->waiting_requests); QTAILQ_INSERT_TAIL(&s->ops_in_flight, op, next); diff --git a/block/replication.c b/block/replication.c index 774e15df16..32444b9a8f 100644 --- a/block/replication.c +++ b/block/replication.c @@ -35,7 +35,6 @@ typedef enum { typedef struct BDRVReplicationState { ReplicationMode mode; ReplicationStage stage; - BdrvChild *active_disk; BlockJob *commit_job; BdrvChild *hidden_disk; BdrvChild *secondary_disk; @@ -166,7 +165,12 @@ static void replication_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { - *nperm = BLK_PERM_CONSISTENT_READ; + if (role & BDRV_CHILD_PRIMARY) { + *nperm = BLK_PERM_CONSISTENT_READ; + } else { + *nperm = 0; + } + if ((bs->open_flags & (BDRV_O_INACTIVE | BDRV_O_RDWR)) == BDRV_O_RDWR) { *nperm |= BLK_PERM_WRITE; } @@ -307,8 +311,10 @@ out: return ret; } -static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp) +static void secondary_do_checkpoint(BlockDriverState *bs, Error **errp) { + BDRVReplicationState *s = bs->opaque; + BdrvChild *active_disk = bs->file; Error *local_err = NULL; int ret; @@ -323,13 +329,13 @@ static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp) return; } - if (!s->active_disk->bs->drv) { + if (!active_disk->bs->drv) { error_setg(errp, "Active disk %s is ejected", - s->active_disk->bs->node_name); + active_disk->bs->node_name); return; } - ret = bdrv_make_empty(s->active_disk, errp); + ret = bdrv_make_empty(active_disk, errp); if (ret < 0) { return; } @@ -340,17 +346,7 @@ static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp) return; } - BlockBackend *blk = blk_new(qemu_get_current_aio_context(), - BLK_PERM_WRITE, BLK_PERM_ALL); - blk_insert_bs(blk, s->hidden_disk->bs, &local_err); - if (local_err) { - error_propagate(errp, local_err); - blk_unref(blk); - return; - } - - ret = blk_make_empty(blk, errp); - blk_unref(blk); + ret = bdrv_make_empty(s->hidden_disk, errp); if (ret < 0) { return; } @@ -365,27 +361,35 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, Error **errp) { BDRVReplicationState *s = bs->opaque; + BdrvChild *hidden_disk, *secondary_disk; BlockReopenQueue *reopen_queue = NULL; + /* + * s->hidden_disk and s->secondary_disk may not be set yet, as they will + * only be set after the children are writable. + */ + hidden_disk = bs->file->bs->backing; + secondary_disk = hidden_disk->bs->backing; + if (writable) { - s->orig_hidden_read_only = bdrv_is_read_only(s->hidden_disk->bs); - s->orig_secondary_read_only = bdrv_is_read_only(s->secondary_disk->bs); + s->orig_hidden_read_only = bdrv_is_read_only(hidden_disk->bs); + s->orig_secondary_read_only = bdrv_is_read_only(secondary_disk->bs); } - bdrv_subtree_drained_begin(s->hidden_disk->bs); - bdrv_subtree_drained_begin(s->secondary_disk->bs); + bdrv_subtree_drained_begin(hidden_disk->bs); + bdrv_subtree_drained_begin(secondary_disk->bs); if (s->orig_hidden_read_only) { QDict *opts = qdict_new(); qdict_put_bool(opts, BDRV_OPT_READ_ONLY, !writable); - reopen_queue = bdrv_reopen_queue(reopen_queue, s->hidden_disk->bs, + reopen_queue = bdrv_reopen_queue(reopen_queue, hidden_disk->bs, opts, true); } if (s->orig_secondary_read_only) { QDict *opts = qdict_new(); qdict_put_bool(opts, BDRV_OPT_READ_ONLY, !writable); - reopen_queue = bdrv_reopen_queue(reopen_queue, s->secondary_disk->bs, + reopen_queue = bdrv_reopen_queue(reopen_queue, secondary_disk->bs, opts, true); } @@ -400,8 +404,8 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, } } - bdrv_subtree_drained_end(s->hidden_disk->bs); - bdrv_subtree_drained_end(s->secondary_disk->bs); + bdrv_subtree_drained_end(hidden_disk->bs); + bdrv_subtree_drained_end(secondary_disk->bs); } static void backup_job_cleanup(BlockDriverState *bs) @@ -458,6 +462,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, BlockDriverState *bs = rs->opaque; BDRVReplicationState *s; BlockDriverState *top_bs; + BdrvChild *active_disk, *hidden_disk, *secondary_disk; int64_t active_length, hidden_length, disk_length; AioContext *aio_context; Error *local_err = NULL; @@ -495,32 +500,31 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, case REPLICATION_MODE_PRIMARY: break; case REPLICATION_MODE_SECONDARY: - s->active_disk = bs->file; - if (!s->active_disk || !s->active_disk->bs || - !s->active_disk->bs->backing) { + active_disk = bs->file; + if (!active_disk || !active_disk->bs || !active_disk->bs->backing) { error_setg(errp, "Active disk doesn't have backing file"); aio_context_release(aio_context); return; } - s->hidden_disk = s->active_disk->bs->backing; - if (!s->hidden_disk->bs || !s->hidden_disk->bs->backing) { + hidden_disk = active_disk->bs->backing; + if (!hidden_disk->bs || !hidden_disk->bs->backing) { error_setg(errp, "Hidden disk doesn't have backing file"); aio_context_release(aio_context); return; } - s->secondary_disk = s->hidden_disk->bs->backing; - if (!s->secondary_disk->bs || !bdrv_has_blk(s->secondary_disk->bs)) { + secondary_disk = hidden_disk->bs->backing; + if (!secondary_disk->bs || !bdrv_has_blk(secondary_disk->bs)) { error_setg(errp, "The secondary disk doesn't have block backend"); aio_context_release(aio_context); return; } /* verify the length */ - active_length = bdrv_getlength(s->active_disk->bs); - hidden_length = bdrv_getlength(s->hidden_disk->bs); - disk_length = bdrv_getlength(s->secondary_disk->bs); + active_length = bdrv_getlength(active_disk->bs); + hidden_length = bdrv_getlength(hidden_disk->bs); + disk_length = bdrv_getlength(secondary_disk->bs); if (active_length < 0 || hidden_length < 0 || disk_length < 0 || active_length != hidden_length || hidden_length != disk_length) { error_setg(errp, "Active disk, hidden disk, secondary disk's length" @@ -530,10 +534,10 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, } /* Must be true, or the bdrv_getlength() calls would have failed */ - assert(s->active_disk->bs->drv && s->hidden_disk->bs->drv); + assert(active_disk->bs->drv && hidden_disk->bs->drv); - if (!s->active_disk->bs->drv->bdrv_make_empty || - !s->hidden_disk->bs->drv->bdrv_make_empty) { + if (!active_disk->bs->drv->bdrv_make_empty || + !hidden_disk->bs->drv->bdrv_make_empty) { error_setg(errp, "Active disk or hidden disk doesn't support make_empty"); aio_context_release(aio_context); @@ -548,6 +552,26 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, return; } + bdrv_ref(hidden_disk->bs); + s->hidden_disk = bdrv_attach_child(bs, hidden_disk->bs, "hidden disk", + &child_of_bds, BDRV_CHILD_DATA, + &local_err); + if (local_err) { + error_propagate(errp, local_err); + aio_context_release(aio_context); + return; + } + + bdrv_ref(secondary_disk->bs); + s->secondary_disk = bdrv_attach_child(bs, secondary_disk->bs, + "secondary disk", &child_of_bds, + BDRV_CHILD_DATA, &local_err); + if (local_err) { + error_propagate(errp, local_err); + aio_context_release(aio_context); + return; + } + /* start backup job now */ error_setg(&s->blocker, "Block device is in use by internal backup job"); @@ -586,7 +610,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, s->stage = BLOCK_REPLICATION_RUNNING; if (s->mode == REPLICATION_MODE_SECONDARY) { - secondary_do_checkpoint(s, errp); + secondary_do_checkpoint(bs, errp); } s->error = 0; @@ -615,7 +639,7 @@ static void replication_do_checkpoint(ReplicationState *rs, Error **errp) } if (s->mode == REPLICATION_MODE_SECONDARY) { - secondary_do_checkpoint(s, errp); + secondary_do_checkpoint(bs, errp); } aio_context_release(aio_context); } @@ -652,8 +676,9 @@ static void replication_done(void *opaque, int ret) if (ret == 0) { s->stage = BLOCK_REPLICATION_DONE; - s->active_disk = NULL; + bdrv_unref_child(bs, s->secondary_disk); s->secondary_disk = NULL; + bdrv_unref_child(bs, s->hidden_disk); s->hidden_disk = NULL; s->error = 0; } else { @@ -705,7 +730,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp) } if (!failover) { - secondary_do_checkpoint(s, errp); + secondary_do_checkpoint(bs, errp); s->stage = BLOCK_REPLICATION_DONE; aio_context_release(aio_context); return; @@ -713,7 +738,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp) s->stage = BLOCK_REPLICATION_FAILOVER; s->commit_job = commit_active_start( - NULL, s->active_disk->bs, s->secondary_disk->bs, + NULL, bs->file->bs, s->secondary_disk->bs, JOB_INTERNAL, 0, BLOCKDEV_ON_ERROR_REPORT, NULL, replication_done, bs, true, errp); break; diff --git a/block/vvfat.c b/block/vvfat.c index ae9d387da7..34bf1e3a86 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -3098,26 +3098,6 @@ static int coroutine_fn vvfat_co_block_status(BlockDriverState *bs, return BDRV_BLOCK_DATA; } -static int coroutine_fn -write_target_commit(BlockDriverState *bs, uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags) -{ - int ret; - - BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque); - qemu_co_mutex_lock(&s->lock); - ret = try_commit(s); - qemu_co_mutex_unlock(&s->lock); - - return ret; -} - -static BlockDriver vvfat_write_target = { - .format_name = "vvfat_write_target", - .instance_size = sizeof(void*), - .bdrv_co_pwritev = write_target_commit, -}; - static void vvfat_qcow_options(BdrvChildRole role, bool parent_is_format, int *child_flags, QDict *child_options, int parent_flags, QDict *parent_options) @@ -3133,7 +3113,6 @@ static int enable_write_target(BlockDriverState *bs, Error **errp) { BDRVVVFATState *s = bs->opaque; BlockDriver *bdrv_qcow = NULL; - BlockDriverState *backing; QemuOpts *opts = NULL; int ret; int size = sector2cluster(s, s->sector_count); @@ -3184,13 +3163,6 @@ static int enable_write_target(BlockDriverState *bs, Error **errp) unlink(s->qcow_filename); #endif - backing = bdrv_new_open_driver(&vvfat_write_target, NULL, BDRV_O_ALLOW_RDWR, - &error_abort); - *(void**) backing->opaque = s; - - bdrv_set_backing_hd(s->bs, backing, &error_abort); - bdrv_unref(backing); - return 0; err: @@ -3205,17 +3177,10 @@ static void vvfat_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { - if (role & BDRV_CHILD_DATA) { - /* This is a private node, nobody should try to attach to it */ - *nperm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE; - *nshared = BLK_PERM_WRITE_UNCHANGED; - } else { - assert(role & BDRV_CHILD_COW); - /* The backing file is there so 'commit' can use it. vvfat doesn't - * access it in any way. */ - *nperm = 0; - *nshared = BLK_PERM_ALL; - } + assert(role & BDRV_CHILD_DATA); + /* This is a private node, nobody should try to attach to it */ + *nperm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE; + *nshared = BLK_PERM_WRITE_UNCHANGED; } static void vvfat_close(BlockDriverState *bs) |
