diff options
Diffstat (limited to 'drivers/md')
| -rw-r--r-- | drivers/md/dm-thin-metadata.c | 30 | ||||
| -rw-r--r-- | drivers/md/dm-thin-metadata.h | 3 | ||||
| -rw-r--r-- | drivers/md/dm-thin.c | 102 |
3 files changed, 124 insertions, 11 deletions
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 43824d73366d..a15091a0d40c 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1677,6 +1677,36 @@ int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *resu return r; } +int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e) +{ + int r = 0; + + down_write(&pmd->root_lock); + for (; b != e; b++) { + r = dm_sm_inc_block(pmd->data_sm, b); + if (r) + break; + } + up_write(&pmd->root_lock); + + return r; +} + +int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e) +{ + int r = 0; + + down_write(&pmd->root_lock); + for (; b != e; b++) { + r = dm_sm_dec_block(pmd->data_sm, b); + if (r) + break; + } + up_write(&pmd->root_lock); + + return r; +} + bool dm_thin_changed_this_transaction(struct dm_thin_device *td) { int r; diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h index a938babe4258..35e954ea20a9 100644 --- a/drivers/md/dm-thin-metadata.h +++ b/drivers/md/dm-thin-metadata.h @@ -197,6 +197,9 @@ int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result); int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result); +int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e); +int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e); + /* * Returns -ENOSPC if the new size is too small and already allocated * blocks would be lost. diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 5f9e3d799d66..197ea2003400 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -253,6 +253,7 @@ struct pool { struct bio_list deferred_flush_bios; struct list_head prepared_mappings; struct list_head prepared_discards; + struct list_head prepared_discards_pt2; struct list_head active_thins; struct dm_deferred_set *shared_read_ds; @@ -269,6 +270,7 @@ struct pool { process_mapping_fn process_prepared_mapping; process_mapping_fn process_prepared_discard; + process_mapping_fn process_prepared_discard_pt2; struct dm_bio_prison_cell **cell_sort_array; }; @@ -1001,7 +1003,8 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m) /*----------------------------------------------------------------*/ -static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m) +static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m, + struct bio *discard_parent) { /* * We've already unmapped this range of blocks, but before we @@ -1014,7 +1017,7 @@ static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m dm_block_t b = m->data_block, e, end = m->data_block + m->virt_end - m->virt_begin; struct discard_op op; - begin_discard(&op, tc, m->bio); + begin_discard(&op, tc, discard_parent); while (b != end) { /* find start of unmapped run */ for (; b < end; b++) { @@ -1049,28 +1052,101 @@ out: end_discard(&op, r); } -static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m) +static void queue_passdown_pt2(struct dm_thin_new_mapping *m) +{ + unsigned long flags; + struct pool *pool = m->tc->pool; + + spin_lock_irqsave(&pool->lock, flags); + list_add_tail(&m->list, &pool->prepared_discards_pt2); + spin_unlock_irqrestore(&pool->lock, flags); + wake_worker(pool); +} + +static void passdown_endio(struct bio *bio) +{ + /* + * It doesn't matter if the passdown discard failed, we still want + * to unmap (we ignore err). + */ + queue_passdown_pt2(bio->bi_private); +} + +static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m) { int r; struct thin_c *tc = m->tc; struct pool *pool = tc->pool; + struct bio *discard_parent; + dm_block_t data_end = m->data_block + (m->virt_end - m->virt_begin); + /* + * Only this thread allocates blocks, so we can be sure that the + * newly unmapped blocks will not be allocated before the end of + * the function. + */ r = dm_thin_remove_range(tc->td, m->virt_begin, m->virt_end); if (r) { metadata_operation_failed(pool, "dm_thin_remove_range", r); bio_io_error(m->bio); + cell_defer_no_holder(tc, m->cell); + mempool_free(m, pool->mapping_pool); + return; + } - } else if (m->maybe_shared) { - passdown_double_checking_shared_status(m); + discard_parent = bio_alloc(GFP_NOIO, 1); + if (!discard_parent) { + DMWARN("%s: unable to allocate top level discard bio for passdown. Skipping passdown.", + dm_device_name(tc->pool->pool_md)); + queue_passdown_pt2(m); } else { - struct discard_op op; - begin_discard(&op, tc, m->bio); - r = issue_discard(&op, m->data_block, - m->data_block + (m->virt_end - m->virt_begin)); - end_discard(&op, r); + discard_parent->bi_end_io = passdown_endio; + discard_parent->bi_private = m; + + if (m->maybe_shared) + passdown_double_checking_shared_status(m, discard_parent); + else { + struct discard_op op; + + begin_discard(&op, tc, discard_parent); + r = issue_discard(&op, m->data_block, data_end); + end_discard(&op, r); + } } + /* + * Increment the unmapped blocks. This prevents a race between the + * passdown io and reallocation of freed blocks. + */ + r = dm_pool_inc_data_range(pool->pmd, m->data_block, data_end); + if (r) { + metadata_operation_failed(pool, "dm_pool_inc_data_range", r); + bio_io_error(m->bio); + cell_defer_no_holder(tc, m->cell); + mempool_free(m, pool->mapping_pool); + return; + } +} + +static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m) +{ + int r; + struct thin_c *tc = m->tc; + struct pool *pool = tc->pool; + + /* + * The passdown has completed, so now we can decrement all those + * unmapped blocks. + */ + r = dm_pool_dec_data_range(pool->pmd, m->data_block, + m->data_block + (m->virt_end - m->virt_begin)); + if (r) { + metadata_operation_failed(pool, "dm_pool_dec_data_range", r); + bio_io_error(m->bio); + } else + bio_endio(m->bio); + cell_defer_no_holder(tc, m->cell); mempool_free(m, pool->mapping_pool); } @@ -2215,6 +2291,8 @@ static void do_worker(struct work_struct *ws) throttle_work_update(&pool->throttle); process_prepared(pool, &pool->prepared_discards, &pool->process_prepared_discard); throttle_work_update(&pool->throttle); + process_prepared(pool, &pool->prepared_discards_pt2, &pool->process_prepared_discard_pt2); + throttle_work_update(&pool->throttle); process_deferred_bios(pool); throttle_work_complete(&pool->throttle); } @@ -2343,7 +2421,8 @@ static void set_discard_callbacks(struct pool *pool) if (passdown_enabled(pt)) { pool->process_discard_cell = process_discard_cell_passdown; - pool->process_prepared_discard = process_prepared_discard_passdown; + pool->process_prepared_discard = process_prepared_discard_passdown_pt1; + pool->process_prepared_discard_pt2 = process_prepared_discard_passdown_pt2; } else { pool->process_discard_cell = process_discard_cell_no_passdown; pool->process_prepared_discard = process_prepared_discard_no_passdown; @@ -2830,6 +2909,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, bio_list_init(&pool->deferred_flush_bios); INIT_LIST_HEAD(&pool->prepared_mappings); INIT_LIST_HEAD(&pool->prepared_discards); + INIT_LIST_HEAD(&pool->prepared_discards_pt2); INIT_LIST_HEAD(&pool->active_thins); pool->low_water_triggered = false; pool->suspended = true; |