dm thin: support discard with non power of two block size

Support discards when the pool's block size is not a power of 2.
The block layer assumes discard_granularity is a power of 2 (in
blkdev_issue_discard), so we set this to the largest power of 2 that is
a divides into the number of sectors in each block, but never less than
DATA_DEV_BLOCK_SIZE_MIN_SECTORS.

This patch eliminates the "Discard support must be disabled when the
block size is not a power of 2" constraint that was imposed in commit
55f2b8b ("dm thin: support for non power of 2 pool blocksize").  That
commit was incomplete: using a block size that is not a power of 2
shouldn't mean disabling discard support on the device completely.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Joe Thornber <ejt@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 c29410af1e2211cbba6029a16128e2fabbf97976..df20a115136f7b6fce7fc142bdb250d22f474908 100644 (file)
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2272,15 +2272,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
                goto out_flags_changed;
        }
 
-       /*
-        * The block layer requires discard_granularity to be a power of 2.
-        */
-       if (pf.discard_enabled && !is_power_of_2(block_size)) {
-               ti->error = "Discard support must be disabled when the block size is not a power of 2";
-               r = -EINVAL;
-               goto out_flags_changed;
-       }
-
        pt->pool = pool;
        pt->ti = ti;
        pt->metadata_dev = metadata_dev;
@@ -2762,6 +2753,11 @@ static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
        return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
 }
 
+static bool block_size_is_power_of_two(struct pool *pool)
+{
+       return pool->sectors_per_block_shift >= 0;
+}
+
 static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits)
 {
        struct pool *pool = pt->pool;
@@ -2775,8 +2771,15 @@ static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits)
        if (pt->adjusted_pf.discard_passdown) {
                data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits;
                limits->discard_granularity = data_limits->discard_granularity;
-       } else
+       } else if (block_size_is_power_of_two(pool))
                limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
+       else
+               /*
+                * Use largest power of 2 that is a factor of sectors_per_block
+                * but at least DATA_DEV_BLOCK_SIZE_MIN_SECTORS.
+                */
+               limits->discard_granularity = max(1 << (ffs(pool->sectors_per_block) - 1),
+                                                 DATA_DEV_BLOCK_SIZE_MIN_SECTORS) << SECTOR_SHIFT;
 }
 
 static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)