1 files changed, 82 insertions, 132 deletions

diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index c33f61a4cc28..6578b7bc1fbb 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/sort.h>
 #include <linux/rbtree.h>
 
@@ -268,7 +269,7 @@ struct pool {
 	process_mapping_fn process_prepared_mapping;
 	process_mapping_fn process_prepared_discard;
 
-	struct dm_bio_prison_cell *cell_sort_array[CELL_SORT_ARRAY_SIZE];
+	struct dm_bio_prison_cell **cell_sort_array;
 };
 
 static enum pool_mode get_pool_mode(struct pool *pool);
@@ -331,9 +332,6 @@ struct thin_c {
  *
  * Description:
  *    Asynchronously issue a discard request for the sectors in question.
- *    NOTE: this variant of blk-core's blkdev_issue_discard() is a stop-gap
- *    that is being kept local to DM thinp until the block changes to allow
- *    late bio splitting land upstream.
  */
 static int __blkdev_issue_discard_async(struct block_device *bdev, sector_t sector,
 					sector_t nr_sects, gfp_t gfp_mask, unsigned long flags,
@@ -341,91 +339,36 @@ static int __blkdev_issue_discard_async(struct block_device *bdev, sector_t sect
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	int type = REQ_WRITE | REQ_DISCARD;
-	unsigned int max_discard_sectors, granularity;
-	int alignment;
 	struct bio *bio;
-	int ret = 0;
-	struct blk_plug plug;
 
-	if (!q)
+	if (!q || !nr_sects)
 		return -ENXIO;
 
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
 
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
-	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
-	/*
-	 * Ensure that max_discard_sectors is of the proper
-	 * granularity, so that requests stay aligned after a split.
-	 */
-	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
-	max_discard_sectors -= max_discard_sectors % granularity;
-	if (unlikely(!max_discard_sectors)) {
-		/* Avoid infinite loop below. Being cautious never hurts. */
-		return -EOPNOTSUPP;
-	}
-
 	if (flags & BLKDEV_DISCARD_SECURE) {
 		if (!blk_queue_secdiscard(q))
 			return -EOPNOTSUPP;
 		type |= REQ_SECURE;
 	}
 
-	blk_start_plug(&plug);
-	while (nr_sects) {
-		unsigned int req_sects;
-		sector_t end_sect, tmp;
-
-		/*
-		 * Required bio_put occurs in bio_endio thanks to bio_chain below
-		 */
-		bio = bio_alloc(gfp_mask, 1);
-		if (!bio) {
-			ret = -ENOMEM;
-			break;
-		}
-
-		req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
-
-		/*
-		 * If splitting a request, and the next starting sector would be
-		 * misaligned, stop the discard at the previous aligned sector.
-		 */
-		end_sect = sector + req_sects;
-		tmp = end_sect;
-		if (req_sects < nr_sects &&
-		    sector_div(tmp, granularity) != alignment) {
-			end_sect = end_sect - alignment;
-			sector_div(end_sect, granularity);
-			end_sect = end_sect * granularity + alignment;
-			req_sects = end_sect - sector;
-		}
-
-		bio_chain(bio, parent_bio);
-
-		bio->bi_iter.bi_sector = sector;
-		bio->bi_bdev = bdev;
+	/*
+	 * Required bio_put occurs in bio_endio thanks to bio_chain below
+	 */
+	bio = bio_alloc(gfp_mask, 1);
+	if (!bio)
+		return -ENOMEM;
 
-		bio->bi_iter.bi_size = req_sects << 9;
-		nr_sects -= req_sects;
-		sector = end_sect;
+	bio_chain(bio, parent_bio);
 
-		submit_bio(type, bio);
+	bio->bi_iter.bi_sector = sector;
+	bio->bi_bdev = bdev;
+	bio->bi_iter.bi_size = nr_sects << 9;
 
-		/*
-		 * We can loop for a long time in here, if someone does
-		 * full device discards (like mkfs). Be nice and allow
-		 * us to schedule out to avoid softlocking if preempt
-		 * is disabled.
-		 */
-		cond_resched();
-	}
-	blk_finish_plug(&plug);
+	submit_bio(type, bio);
 
-	return ret;
+	return 0;
 }
 
 static bool block_size_is_power_of_two(struct pool *pool)
@@ -614,8 +557,10 @@ static void error_bio_list(struct bio_list *bios, int error)
 {
 	struct bio *bio;
 
-	while ((bio = bio_list_pop(bios)))
-		bio_endio(bio, error);
+	while ((bio = bio_list_pop(bios))) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	}
 }
 
 static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, int error)
@@ -665,16 +610,21 @@ static void requeue_io(struct thin_c *tc)
 	requeue_deferred_cells(tc);
 }
 
-static void error_retry_list(struct pool *pool)
+static void error_retry_list_with_code(struct pool *pool, int error)
 {
 	struct thin_c *tc;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tc, &pool->active_thins, list)
-		error_thin_bio_list(tc, &tc->retry_on_resume_list, -EIO);
+		error_thin_bio_list(tc, &tc->retry_on_resume_list, error);
 	rcu_read_unlock();
 }
 
+static void error_retry_list(struct pool *pool)
+{
+	return error_retry_list_with_code(pool, -EIO);
+}
+
 /*
  * This section of code contains the logic for processing a thin device's IO.
  * Much of the code depends on pool object resources (lists, workqueues, etc)
@@ -864,14 +814,14 @@ static void copy_complete(int read_err, unsigned long write_err, void *context)
 	complete_mapping_preparation(m);
 }
 
-static void overwrite_endio(struct bio *bio, int err)
+static void overwrite_endio(struct bio *bio)
 {
 	struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
 	struct dm_thin_new_mapping *m = h->overwrite_mapping;
 
 	bio->bi_end_io = m->saved_bi_end_io;
 
-	m->err = err;
+	m->err = bio->bi_error;
 	complete_mapping_preparation(m);
 }
 
@@ -996,7 +946,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 	 */
 	if (bio) {
 		inc_remap_and_issue_cell(tc, m->cell, m->data_block);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	} else {
 		inc_all_io_entry(tc->pool, m->cell->holder);
 		remap_and_issue(tc, m->cell->holder, m->data_block);
@@ -1026,7 +976,7 @@ static void process_prepared_discard_fail(struct dm_thin_new_mapping *m)
 
 static void process_prepared_discard_success(struct dm_thin_new_mapping *m)
 {
-	bio_endio(m->bio, 0);
+	bio_endio(m->bio);
 	free_discard_mapping(m);
 }
 
@@ -1040,7 +990,7 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m)
 		metadata_operation_failed(tc->pool, "dm_thin_remove_range", r);
 		bio_io_error(m->bio);
 	} else
-		bio_endio(m->bio, 0);
+		bio_endio(m->bio);
 
 	cell_defer_no_holder(tc, m->cell);
 	mempool_free(m, tc->pool->mapping_pool);
@@ -1111,7 +1061,8 @@ static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
 	 * Even if r is set, there could be sub discards in flight that we
 	 * need to wait for.
 	 */
-	bio_endio(m->bio, r);
+	m->bio->bi_error = r;
+	bio_endio(m->bio);
 	cell_defer_no_holder(tc, m->cell);
 	mempool_free(m, pool->mapping_pool);
 }
@@ -1487,9 +1438,10 @@ static void handle_unserviceable_bio(struct pool *pool, struct bio *bio)
 {
 	int error = should_error_unserviceable_bio(pool);
 
-	if (error)
-		bio_endio(bio, error);
-	else
+	if (error) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	} else
 		retry_on_resume(bio);
 }
 
@@ -1533,9 +1485,8 @@ static void process_discard_cell_no_passdown(struct thin_c *tc,
 }
 
 /*
- * FIXME: DM local hack to defer parent bios's end_io until we
- * _know_ all chained sub range discard bios have completed.
- * Will go away once late bio splitting lands upstream!
+ * __bio_inc_remaining() is used to defer parent bios's end_io until
+ * we _know_ all chained sub range discard bios have completed.
  */
 static inline void __bio_inc_remaining(struct bio *bio)
 {
@@ -1625,7 +1576,7 @@ static void process_discard_cell_passdown(struct thin_c *tc, struct dm_bio_priso
 	 * will prevent completion until the sub range discards have
 	 * completed.
 	 */
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static void process_discard_bio(struct thin_c *tc, struct bio *bio)
@@ -1639,7 +1590,7 @@ static void process_discard_bio(struct thin_c *tc, struct bio *bio)
 		/*
 		 * The discard covers less than a block.
 		 */
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -1784,7 +1735,7 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block
 	if (bio_data_dir(bio) == READ) {
 		zero_fill_bio(bio);
 		cell_defer_no_holder(tc, cell);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -1849,7 +1800,7 @@ static void process_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell)
 
 			} else {
 				zero_fill_bio(bio);
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			}
 		} else
 			provision_block(tc, bio, block, cell);
@@ -1920,7 +1871,7 @@ static void __process_bio_read_only(struct thin_c *tc, struct bio *bio,
 		}
 
 		zero_fill_bio(bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		break;
 
 	default:
@@ -1945,7 +1896,7 @@ static void process_cell_read_only(struct thin_c *tc, struct dm_bio_prison_cell
 
 static void process_bio_success(struct thin_c *tc, struct bio *bio)
 {
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static void process_bio_fail(struct thin_c *tc, struct bio *bio)
@@ -2281,18 +2232,23 @@ static void do_waker(struct work_struct *ws)
 	queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
 }
 
+static void notify_of_pool_mode_change_to_oods(struct pool *pool);
+
 /*
  * We're holding onto IO to allow userland time to react.  After the
  * timeout either the pool will have been resized (and thus back in
- * PM_WRITE mode), or we degrade to PM_READ_ONLY and start erroring IO.
+ * PM_WRITE mode), or we degrade to PM_OUT_OF_DATA_SPACE w/ error_if_no_space.
  */
 static void do_no_space_timeout(struct work_struct *ws)
 {
 	struct pool *pool = container_of(to_delayed_work(ws), struct pool,
 					 no_space_timeout);
 
-	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space)
-		set_pool_mode(pool, PM_READ_ONLY);
+	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
+		pool->pf.error_if_no_space = true;
+		notify_of_pool_mode_change_to_oods(pool);
+		error_retry_list_with_code(pool, -ENOSPC);
+	}
 }
 
 /*----------------------------------------------------------------*/
@@ -2370,6 +2326,14 @@ static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode)
 	       dm_device_name(pool->pool_md), new_mode);
 }
 
+static void notify_of_pool_mode_change_to_oods(struct pool *pool)
+{
+	if (!pool->pf.error_if_no_space)
+		notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)");
+	else
+		notify_of_pool_mode_change(pool, "out-of-data-space (error IO)");
+}
+
 static bool passdown_enabled(struct pool_c *pt)
 {
 	return pt->adjusted_pf.discard_passdown;
@@ -2454,7 +2418,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		 * frequently seeing this mode.
 		 */
 		if (old_mode != new_mode)
-			notify_of_pool_mode_change(pool, "out-of-data-space");
+			notify_of_pool_mode_change_to_oods(pool);
 		pool->process_bio = process_bio_read_only;
 		pool->process_discard = process_discard_bio;
 		pool->process_cell = process_cell_read_only;
@@ -2581,7 +2545,8 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 	thin_hook_bio(tc, bio);
 
 	if (tc->requeue_mode) {
-		bio_endio(bio, DM_ENDIO_REQUEUE);
+		bio->bi_error = DM_ENDIO_REQUEUE;
+		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
 	}
 
@@ -2777,6 +2742,7 @@ static void __pool_destroy(struct pool *pool)
 {
 	__pool_table_remove(pool);
 
+	vfree(pool->cell_sort_array);
 	if (dm_pool_metadata_close(pool->pmd) < 0)
 		DMWARN("%s: dm_pool_metadata_close() failed.", __func__);
 
@@ -2889,6 +2855,13 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 		goto bad_mapping_pool;
 	}
 
+	pool->cell_sort_array = vmalloc(sizeof(*pool->cell_sort_array) * CELL_SORT_ARRAY_SIZE);
+	if (!pool->cell_sort_array) {
+		*error = "Error allocating cell sort array";
+		err_p = ERR_PTR(-ENOMEM);
+		goto bad_sort_array;
+	}
+
 	pool->ref_count = 1;
 	pool->last_commit_jiffies = jiffies;
 	pool->pool_md = pool_md;
@@ -2897,6 +2870,8 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 
 	return pool;
 
+bad_sort_array:
+	mempool_destroy(pool->mapping_pool);
 bad_mapping_pool:
 	dm_deferred_set_destroy(pool->all_io_ds);
 bad_all_io_ds:
@@ -3714,6 +3689,7 @@ static void emit_flags(struct pool_features *pf, char *result,
  * Status line is:
  *    <transaction id> <used metadata sectors>/<total metadata sectors>
  *    <used data sectors>/<total data sectors> <held metadata root>
+ *    <pool mode> <discard config> <no space config> <needs_check>
  */
 static void pool_status(struct dm_target *ti, status_type_t type,
 			unsigned status_flags, char *result, unsigned maxlen)
@@ -3815,6 +3791,11 @@ static void pool_status(struct dm_target *ti, status_type_t type,
 		else
 			DMEMIT("queue_if_no_space ");
 
+		if (dm_pool_metadata_needs_check(pool->pmd))
+			DMEMIT("needs_check ");
+		else
+			DMEMIT("- ");
+
 		break;
 
 	case STATUSTYPE_TABLE:
@@ -3840,20 +3821,6 @@ static int pool_iterate_devices(struct dm_target *ti,
 	return fn(ti, pt->data_dev, 0, ti->len, data);
 }
 
-static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		      struct bio_vec *biovec, int max_size)
-{
-	struct pool_c *pt = ti->private;
-	struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = pt->data_dev->bdev;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct pool_c *pt = ti->private;
@@ -3918,7 +3885,7 @@ static struct target_type pool_target = {
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 15, 0},
+	.version = {1, 16, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -3930,7 +3897,6 @@ static struct target_type pool_target = {
 	.resume = pool_resume,
 	.message = pool_message,
 	.status = pool_status,
-	.merge = pool_merge,
 	.iterate_devices = pool_iterate_devices,
 	.io_hints = pool_io_hints,
 };
@@ -4257,21 +4223,6 @@ err:
 	DMEMIT("Error");
 }
 
-static int thin_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		      struct bio_vec *biovec, int max_size)
-{
-	struct thin_c *tc = ti->private;
-	struct request_queue *q = bdev_get_queue(tc->pool_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = tc->pool_dev->bdev;
-	bvm->bi_sector = dm_target_offset(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int thin_iterate_devices(struct dm_target *ti,
 				iterate_devices_callout_fn fn, void *data)
 {
@@ -4305,7 +4256,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 15, 0},
+	.version = {1, 16, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
@@ -4315,7 +4266,6 @@ static struct target_type thin_target = {
 	.presuspend = thin_presuspend,
 	.postsuspend = thin_postsuspend,
 	.status = thin_status,
-	.merge = thin_merge,
 	.iterate_devices = thin_iterate_devices,
 	.io_hints = thin_io_hints,
 };