1 files changed, 53 insertions, 84 deletions

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5edc3079e7c1..ce543b761be7 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -18,54 +18,17 @@
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/lcm.h>
 #include <linux/blk-mq.h>
 #include <linux/mount.h>
 #include <linux/dax.h>
 
 #define DM_MSG_PREFIX "table"
 
-#define MAX_DEPTH 16
 #define NODE_SIZE L1_CACHE_BYTES
 #define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
 #define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)
 
-struct dm_table {
-	struct mapped_device *md;
-	enum dm_queue_mode type;
-
-	/* btree table */
-	unsigned int depth;
-	unsigned int counts[MAX_DEPTH];	/* in nodes */
-	sector_t *index[MAX_DEPTH];
-
-	unsigned int num_targets;
-	unsigned int num_allocated;
-	sector_t *highs;
-	struct dm_target *targets;
-
-	struct target_type *immutable_target_type;
-
-	bool integrity_supported:1;
-	bool singleton:1;
-	unsigned integrity_added:1;
-
-	/*
-	 * Indicates the rw permissions for the new logical
-	 * device.  This should be a combination of FMODE_READ
-	 * and FMODE_WRITE.
-	 */
-	fmode_t mode;
-
-	/* a list of devices used by this table */
-	struct list_head devices;
-
-	/* events get handed up using this callback */
-	void (*event_fn)(void *);
-	void *event_context;
-
-	struct dm_md_mempools *mempools;
-};
-
 /*
  * Similar to ceiling(log_size(n))
  */
@@ -841,8 +804,7 @@ EXPORT_SYMBOL(dm_consume_args);
 static bool __table_type_bio_based(enum dm_queue_mode table_type)
 {
 	return (table_type == DM_TYPE_BIO_BASED ||
-		table_type == DM_TYPE_DAX_BIO_BASED ||
-		table_type == DM_TYPE_NVME_BIO_BASED);
+		table_type == DM_TYPE_DAX_BIO_BASED);
 }
 
 static bool __table_type_request_based(enum dm_queue_mode table_type)
@@ -860,10 +822,14 @@ EXPORT_SYMBOL_GPL(dm_table_set_type);
 int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
 			sector_t start, sector_t len, void *data)
 {
-	int blocksize = *(int *) data;
+	int blocksize = *(int *) data, id;
+	bool rc;
 
-	return generic_fsdax_supported(dev->dax_dev, dev->bdev, blocksize,
-				       start, len);
+	id = dax_read_lock();
+	rc = dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
+	dax_read_unlock(id);
+
+	return rc;
 }
 
 /* Check devices support synchronous DAX */
@@ -894,8 +860,6 @@ bool dm_table_supports_dax(struct dm_table *t,
 	return true;
 }
 
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t);
-
 static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
@@ -903,7 +867,7 @@ static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
 	struct request_queue *q = bdev_get_queue(bdev);
 
 	/* request-based cannot stack on partitions! */
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return false;
 
 	return queue_is_mq(q);
@@ -925,7 +889,6 @@ static int dm_table_determine_type(struct dm_table *t)
 			goto verify_bio_based;
 		}
 		BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
-		BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED);
 		goto verify_rq_based;
 	}
 
@@ -964,15 +927,6 @@ verify_bio_based:
 		if (dm_table_supports_dax(t, device_supports_dax, &page_size) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
-		} else {
-			/* Check if upgrading to NVMe bio-based is valid or required */
-			tgt = dm_table_get_immutable_target(t);
-			if (tgt && !tgt->max_io_len && dm_table_does_not_support_partial_completion(t)) {
-				t->type = DM_TYPE_NVME_BIO_BASED;
-				goto verify_rq_based; /* must be stacked directly on NVMe (blk-mq) */
-			} else if (list_empty(devices) && live_md_type == DM_TYPE_NVME_BIO_BASED) {
-				t->type = DM_TYPE_NVME_BIO_BASED;
-			}
 		}
 		return 0;
 	}
@@ -989,8 +943,7 @@ verify_rq_based:
 	 * (e.g. request completion process for partial completion.)
 	 */
 	if (t->num_targets > 1) {
-		DMERR("%s DM doesn't support multiple targets",
-		      t->type == DM_TYPE_NVME_BIO_BASED ? "nvme bio-based" : "request-based");
+		DMERR("request-based DM doesn't support multiple targets");
 		return -EINVAL;
 	}
 
@@ -1502,6 +1455,10 @@ int dm_calculate_queue_limits(struct dm_table *table,
 			zone_sectors = ti_limits.chunk_sectors;
 		}
 
+		/* Stack chunk_sectors if target-specific splitting is required */
+		if (ti->max_io_len)
+			ti_limits.chunk_sectors = lcm_not_zero(ti->max_io_len,
+							       ti_limits.chunk_sectors);
 		/* Set I/O hints portion of queue limits */
 		if (ti->type->io_hints)
 			ti->type->io_hints(ti, &ti_limits);
@@ -1680,20 +1637,6 @@ static bool dm_table_all_devices_attribute(struct dm_table *t,
 	return true;
 }
 
-static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev,
-					sector_t start, sector_t len, void *data)
-{
-	char b[BDEVNAME_SIZE];
-
-	/* For now, NVMe devices are the only devices of this class */
-	return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0);
-}
-
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t)
-{
-	return dm_table_all_devices_attribute(t, device_no_partial_completion);
-}
-
 static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
 					 sector_t start, sector_t len, void *data)
 {
@@ -1748,6 +1691,33 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t)
 	return true;
 }
 
+static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
+				     sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && !blk_queue_nowait(q);
+}
+
+static bool dm_table_supports_nowait(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!dm_target_supports_nowait(ti->type))
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    ti->type->iterate_devices(ti, device_not_nowait_capable, NULL))
+			return false;
+	}
+
+	return true;
+}
+
 static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev,
 				      sector_t start, sector_t len, void *data)
 {
@@ -1815,7 +1785,7 @@ static int device_requires_stable_pages(struct dm_target *ti,
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
 
-	return q && bdi_cap_stable_pages_required(q->backing_dev_info);
+	return q && blk_queue_stable_writes(q);
 }
 
 /*
@@ -1850,6 +1820,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 */
 	q->limits = *limits;
 
+	if (dm_table_supports_nowait(t))
+		blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
+
 	if (!dm_table_supports_discards(t)) {
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 		/* Must also clear discard limits... */
@@ -1900,9 +1875,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 * because they do their own checksumming.
 	 */
 	if (dm_table_requires_stable_pages(t))
-		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 	else
-		q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
 
 	/*
 	 * Determine whether or not this queue's I/O timings contribute
@@ -1925,8 +1900,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 #endif
 
-	/* Allow reads to exceed readahead limits */
-	q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9);
+	blk_queue_update_readahead(q);
 }
 
 unsigned int dm_table_get_num_targets(struct dm_table *t)
@@ -2045,16 +2019,11 @@ EXPORT_SYMBOL_GPL(dm_table_device_name);
 
 void dm_table_run_md_queue_async(struct dm_table *t)
 {
-	struct mapped_device *md;
-	struct request_queue *queue;
-
 	if (!dm_table_request_based(t))
 		return;
 
-	md = dm_table_get_md(t);
-	queue = dm_get_md_queue(md);
-	if (queue)
-		blk_mq_run_hw_queues(queue, true);
+	if (t->md->queue)
+		blk_mq_run_hw_queues(t->md->queue, true);
 }
 EXPORT_SYMBOL(dm_table_run_md_queue_async);