block: fix blk_stack_limits() regression due to lcm() change

Linux 3.19 commit 69c953c8 ("lib/lcm.c: lcm(n,0)=lcm(0,n) is 0, not n")
caused blk_stack_limits() to not properly stack queue_limits for stacked
devices (e.g. DM).

Fix this regression by establishing lcm_not_zero() and switching
blk_stack_limits() over to using it.

DM uses blk_set_stacking_limits() to establish the initial top-level
queue_limits that are then built up based on underlying devices' limits
using blk_stack_limits().  In the case of optimal_io_size (io_opt)
blk_set_stacking_limits() establishes a default value of 0.  With commit
69c953c8, lcm(0, n) is no longer n, which compromises proper stacking of
the underlying devices' io_opt.

Test:
$ modprobe scsi_debug dev_size_mb=10 num_tgts=1 opt_blks=1536
$ cat /sys/block/sde/queue/optimal_io_size
786432
$ dmsetup create node --table "0 100 linear /dev/sde 0"

Before this fix:
$ cat /sys/block/dm-5/queue/optimal_io_size
0

After this fix:
$ cat /sys/block/dm-5/queue/optimal_io_size
786432
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.19+
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block/blk-settings.c

@@ -585,7 +585,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 				     b->physical_block_size);
 
 	t->io_min = max(t->io_min, b->io_min);
-	t->io_opt = lcm(t->io_opt, b->io_opt);
+	t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
 
 	t->cluster &= b->cluster;
 	t->discard_zeroes_data &= b->discard_zeroes_data;
@@ -616,7 +616,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		    b->raid_partial_stripes_expensive);
 
 	/* Find lowest common alignment_offset */
-	t->alignment_offset = lcm(t->alignment_offset, alignment)
+	t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment)
 		% max(t->physical_block_size, t->io_min);
 
 	/* Verify that new alignment_offset is on a logical block boundary */
@@ -643,7 +643,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 						      b->max_discard_sectors);
 		t->discard_granularity = max(t->discard_granularity,
 					     b->discard_granularity);
-		t->discard_alignment = lcm(t->discard_alignment, alignment) %
+		t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
 			t->discard_granularity;
 	}
 

include/linux/lcm.h

@@ -4,5 +4,6 @@
 #include <linux/compiler.h>
 
 unsigned long lcm(unsigned long a, unsigned long b) __attribute_const__;
+unsigned long lcm_not_zero(unsigned long a, unsigned long b) __attribute_const__;
 
 #endif /* _LCM_H */

lib/lcm.c

@@ -12,3 +12,14 @@ unsigned long lcm(unsigned long a, unsigned long b)
 		return 0;
 }
 EXPORT_SYMBOL_GPL(lcm);
+
+unsigned long lcm_not_zero(unsigned long a, unsigned long b)
+{
+	unsigned long l = lcm(a, b);
+
+	if (l)
+		return l;
+
+	return (b ? : a);
+}
+EXPORT_SYMBOL_GPL(lcm_not_zero);