dm: fix IO splitting

Commit 882ec4e ("dm table: stack 'chunk_sectors' limit to account
for target-specific splitting") caused a couple regressions:
1) Using lcm_not_zero() when stacking chunk_sectors was a bug because
   chunk_sectors must reflect the most limited of all devices in the
   IO stack.
2) DM targets that set max_io_len but that do _not_ provide an
   .iterate_devices method no longer had there IO split properly.

And commit 5091cde ("dm: change max_io_len() to use
blk_max_size_offset()") also caused a regression where DM no longer
supported varied (per target) IO splitting. The implication being the
potential for severely reduced performance for IO stacks that use a DM
target like dm-cache to hide performance limitations of a slower
device (e.g. one that requires 4K IO splitting).

Coming full circle: Fix all these issues by discontinuing stacking
chunk_sectors up using ti->max_io_len in dm_calculate_queue_limits(),
add optional chunk_sectors override argument to blk_max_size_offset()
and update DM's max_io_len() to pass ti->max_io_len to its
blk_max_size_offset() call.

Passing in an optional chunk_sectors override to blk_max_size_offset()
allows for code reuse of block's centralized calculation for max IO
size based on provided offset and split boundary.

Fixes: 882ec4e ("dm table: stack 'chunk_sectors' limit to account for target-specific splitting")
Fixes: 5091cde ("dm: change max_io_len() to use blk_max_size_offset()")
Cc: [email protected]
Reported-by: John Dorminy <[email protected]>
Reported-by: Bruce Johnston <[email protected]>
Reported-by: Kirill Tkhai <[email protected]>
Reviewed-by: John Dorminy <[email protected]>
Signed-off-by: Mike Snitzer <[email protected]>
Reviewed-by: Jens Axboe <[email protected]>

block/blk-merge.c

@@ -144,7 +144,7 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q,
 static inline unsigned get_max_io_size(struct request_queue *q,
 				       struct bio *bio)
 {
-	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
+	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0);
 	unsigned max_sectors = sectors;
 	unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT;
 	unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT;

drivers/md/dm-table.c

@@ -18,7 +18,6 @@
 #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>
@@ -1449,10 +1448,6 @@ 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);

drivers/md/dm.c

@@ -1039,15 +1039,18 @@ static sector_t max_io_len(struct dm_target *ti, sector_t sector)
 	sector_t max_len;
 
 	/*
-	 * Does the target need to split even further?
-	 * - q->limits.chunk_sectors reflects ti->max_io_len so
-	 *   blk_max_size_offset() provides required splitting.
-	 * - blk_max_size_offset() also respects q->limits.max_sectors
+	 * Does the target need to split IO even further?
+	 * - varied (per target) IO splitting is a tenet of DM; this
+	 *   explains why stacked chunk_sectors based splitting via
+	 *   blk_max_size_offset() isn't possible here. So pass in
+	 *   ti->max_io_len to override stacked chunk_sectors.
 	 */
-	max_len = blk_max_size_offset(ti->table->md->queue,
-				      target_offset);
-	if (len > max_len)
-		len = max_len;
+	if (ti->max_io_len) {
+		max_len = blk_max_size_offset(ti->table->md->queue,
+					      target_offset, ti->max_io_len);
+		if (len > max_len)
+			len = max_len;
+	}
 
 	return len;
 }

include/linux/blkdev.h

@@ -1073,11 +1073,12 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
  * file system requests.
  */
 static inline unsigned int blk_max_size_offset(struct request_queue *q,
-					       sector_t offset)
+					       sector_t offset,
+					       unsigned int chunk_sectors)
 {
-	unsigned int chunk_sectors = q->limits.chunk_sectors;
-
-	if (!chunk_sectors)
+	if (!chunk_sectors && q->limits.chunk_sectors)
+		chunk_sectors = q->limits.chunk_sectors;
+	else
 		return q->limits.max_sectors;
 
 	if (likely(is_power_of_2(chunk_sectors)))
@@ -1101,7 +1102,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
 	    req_op(rq) == REQ_OP_SECURE_ERASE)
 		return blk_queue_get_max_sectors(q, req_op(rq));
 
-	return min(blk_max_size_offset(q, offset),
+	return min(blk_max_size_offset(q, offset, 0),
 			blk_queue_get_max_sectors(q, req_op(rq)));
 }