dm cache: prevent corruption caused by discard_block_size > cache_block_size

If the discard block size is larger than the cache block size we will
not properly quiesce IO to a region that is about to be discarded. This
results in a race between a cache migration where no copy is needed, and
a write to an adjacent cache block that's within the same large discard
block.

Workaround this by limiting the discard_block_size to cache_block_size.
Also limit the max_discard_sectors to cache_block_size.

A more comprehensive fix that introduces range locking support in the
bio_prison and proper quiescing of a discard range that spans multiple
cache blocks is already in development.

Reported-by: Morgan Mears <[e-mail]>
Signed-off-by: Mike Snitzer <[e-mail]>
Acked-by: Joe Thornber <[e-mail]>
Acked-by: Heinz Mauelshagen <[e-mail]>
Cc: [e-mail]

drivers/md/dm-cache-target.c

···
 	 */
 	dm_dblock_t discard_nr_blocks;
 	unsigned long *discard_bitset;
-	uint32_t discard_block_size; /* a power of 2 times sectors per block */
+	uint32_t discard_block_size;
 
 	/*
 	 * Rather than reconstructing the table line for the status we just
···
 	return 0;
 }
 
-/*
- * We want the discard block size to be a power of two, at least the size
- * of the cache block size, and have no more than 2^14 discard blocks
- * across the origin.
- */
-#define MAX_DISCARD_BLOCKS (1 << 14)
-
-static bool too_many_discard_blocks(sector_t discard_block_size,
-				    sector_t origin_size)
-{
-	(void) sector_div(origin_size, discard_block_size);
-
-	return origin_size > MAX_DISCARD_BLOCKS;
-}
-
-static sector_t calculate_discard_block_size(sector_t cache_block_size,
-					     sector_t origin_size)
-{
-	sector_t discard_block_size;
-
-	discard_block_size = roundup_pow_of_two(cache_block_size);
-
-	if (origin_size)
-		while (too_many_discard_blocks(discard_block_size, origin_size))
-			discard_block_size *= 2;
-
-	return discard_block_size;
-}
-
 #define DEFAULT_MIGRATION_THRESHOLD 2048
 
 static int cache_create(struct cache_args *ca, struct cache **result)
···
 	}
 	clear_bitset(cache->dirty_bitset, from_cblock(cache->cache_size));
 
-	cache->discard_block_size =
-		calculate_discard_block_size(cache->sectors_per_block,
-					     cache->origin_sectors);
+	cache->discard_block_size = cache->sectors_per_block;
 	cache->discard_nr_blocks = oblock_to_dblock(cache, cache->origin_blocks);
 	cache->discard_bitset = alloc_bitset(from_dblock(cache->discard_nr_blocks));
 	if (!cache->discard_bitset) {
···
 	/*
 	 * FIXME: these limits may be incompatible with the cache device
 	 */
-	limits->max_discard_sectors = cache->discard_block_size * 1024;
+	limits->max_discard_sectors = cache->discard_block_size;
 	limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT;
 }