dm thin: optimize power of two block size

dm-thin will be most likely used with a block size that is a power of
two. So it should be optimized for this case.

This patch changes division and modulo operations to shifts and bit
masks if block size is a power of two.

A test that bi_sector is divisible by a block size is removed from
io_overlaps_block. Device mapper never sends bios that span a block
boundary. Consequently, if we tested that bi_size is equivalent to block
size, bi_sector must already be on a block boundary.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 8286492..93e3e54 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -512,6 +512,7 @@
 
 	dm_block_t low_water_blocks;
 	uint32_t sectors_per_block;
+	int sectors_per_block_shift;
 
 	struct pool_features pf;
 	unsigned low_water_triggered:1;	/* A dm event has been sent */
@@ -679,7 +680,10 @@
 {
 	sector_t block_nr = bio->bi_sector;
 
-	(void) sector_div(block_nr, tc->pool->sectors_per_block);
+	if (tc->pool->sectors_per_block_shift < 0)
+		(void) sector_div(block_nr, tc->pool->sectors_per_block);
+	else
+		block_nr >>= tc->pool->sectors_per_block_shift;
 
 	return block_nr;
 }
@@ -690,8 +694,12 @@
 	sector_t bi_sector = bio->bi_sector;
 
 	bio->bi_bdev = tc->pool_dev->bdev;
-	bio->bi_sector = (block * pool->sectors_per_block) +
-			 sector_div(bi_sector, pool->sectors_per_block);
+	if (tc->pool->sectors_per_block_shift < 0)
+		bio->bi_sector = (block * pool->sectors_per_block) +
+				 sector_div(bi_sector, pool->sectors_per_block);
+	else
+		bio->bi_sector = (block << pool->sectors_per_block_shift) |
+				(bi_sector & (pool->sectors_per_block - 1));
 }
 
 static void remap_to_origin(struct thin_c *tc, struct bio *bio)
@@ -936,10 +944,7 @@
  */
 static int io_overlaps_block(struct pool *pool, struct bio *bio)
 {
-	sector_t bi_sector = bio->bi_sector;
-
-	return !sector_div(bi_sector, pool->sectors_per_block) &&
-		(bio->bi_size == (pool->sectors_per_block << SECTOR_SHIFT));
+	return bio->bi_size == (pool->sectors_per_block << SECTOR_SHIFT);
 }
 
 static int io_overwrites_block(struct pool *pool, struct bio *bio)
@@ -1721,6 +1726,10 @@
 
 	pool->pmd = pmd;
 	pool->sectors_per_block = block_size;
+	if (block_size & (block_size - 1))
+		pool->sectors_per_block_shift = -1;
+	else
+		pool->sectors_per_block_shift = __ffs(block_size);
 	pool->low_water_blocks = 0;
 	pool_features_init(&pool->pf);
 	pool->prison = prison_create(PRISON_CELLS);