dm thin: allow metadata space larger than supported to go unused

It was always intended that a user could provide a thin metadata device
that is larger than the max supported by the on-disk format.  The extra
space would just go unused.

Unfortunately that never worked.  If the user attempted to use a larger
metadata device on creation they would get an error like the following:

 device-mapper: space map common: space map too large
 device-mapper: transaction manager: couldn't create metadata space map
 device-mapper: thin metadata: tm_create_with_sm failed
 device-mapper: table: 252:17: thin-pool: Error creating metadata object
 device-mapper: ioctl: error adding target to table

Fix this by allowing the initial metadata space map creation to cap its
size at the max number of blocks supported (DM_SM_METADATA_MAX_BLOCKS).
get_metadata_dev_size() must also impose DM_SM_METADATA_MAX_BLOCKS (via
THIN_METADATA_MAX_SECTORS), otherwise extending metadata would cap at
THIN_METADATA_MAX_SECTORS_WARNING (which is larger than supported).

Also, the calculation for THIN_METADATA_MAX_SECTORS didn't account for
the sizeof the disk_bitmap_header.  So the supported maximum metadata
size is a bit smaller (reduced from 33423360 to 33292800 sectors).

Lastly, remove the "excess space will not be used" warning message from
get_metadata_dev_size(); it resulted in printing the warning multiple
times.  Factor out warn_if_metadata_device_too_big(), call it from
pool_ctr() and maybe_resize_metadata_dev().
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>

drivers/md/dm-thin-metadata.c

@@ -483,7 +483,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 
 	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
 	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
-	disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+	disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE);
 	disk_super->metadata_nr_blocks = cpu_to_le64(bdev_size >> SECTOR_TO_BLOCK_SHIFT);
 	disk_super->data_block_size = cpu_to_le32(pmd->data_block_size);
 
@@ -651,7 +651,7 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f
 {
 	int r;
 
-	pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE,
+	pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
 					  THIN_METADATA_CACHE_SIZE,
 					  THIN_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(pmd->bm)) {

drivers/md/dm-thin-metadata.h

@@ -9,16 +9,14 @@
 
 #include "persistent-data/dm-block-manager.h"
 #include "persistent-data/dm-space-map.h"
+#include "persistent-data/dm-space-map-metadata.h"
 
-#define THIN_METADATA_BLOCK_SIZE 4096
+#define THIN_METADATA_BLOCK_SIZE DM_SM_METADATA_BLOCK_SIZE
 
 /*
  * The metadata device is currently limited in size.
- *
- * We have one block of index, which can hold 255 index entries.  Each
- * index entry contains allocation info about 16k metadata blocks.
  */
-#define THIN_METADATA_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
+#define THIN_METADATA_MAX_SECTORS DM_SM_METADATA_MAX_SECTORS
 
 /*
  * A metadata device larger than 16GB triggers a warning.

drivers/md/dm-thin.c

@@ -2000,16 +2000,27 @@ static void metadata_low_callback(void *context)
 	dm_table_event(pool->ti->table);
 }
 
-static sector_t get_metadata_dev_size(struct block_device *bdev)
+static sector_t get_dev_size(struct block_device *bdev)
+{
+	return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+}
+
+static void warn_if_metadata_device_too_big(struct block_device *bdev)
 {
-	sector_t metadata_dev_size = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+	sector_t metadata_dev_size = get_dev_size(bdev);
 	char buffer[BDEVNAME_SIZE];
 
-	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING) {
+	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING)
 		DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.",
 		       bdevname(bdev, buffer), THIN_METADATA_MAX_SECTORS);
-		metadata_dev_size = THIN_METADATA_MAX_SECTORS_WARNING;
-	}
+}
+
+static sector_t get_metadata_dev_size(struct block_device *bdev)
+{
+	sector_t metadata_dev_size = get_dev_size(bdev);
+
+	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS)
+		metadata_dev_size = THIN_METADATA_MAX_SECTORS;
 
 	return metadata_dev_size;
 }
@@ -2018,7 +2029,7 @@ static dm_block_t get_metadata_dev_size_in_blocks(struct block_device *bdev)
 {
 	sector_t metadata_dev_size = get_metadata_dev_size(bdev);
 
-	sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+	sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE);
 
 	return metadata_dev_size;
 }
@@ -2096,12 +2107,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		ti->error = "Error opening metadata block device";
 		goto out_unlock;
 	}
-
-	/*
-	 * Run for the side-effect of possibly issuing a warning if the
-	 * device is too big.
-	 */
-	(void) get_metadata_dev_size(metadata_dev->bdev);
+	warn_if_metadata_device_too_big(metadata_dev->bdev);
 
 	r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev);
 	if (r) {
@@ -2288,6 +2294,7 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit)
 		return -EINVAL;
 
 	} else if (metadata_dev_size > sb_metadata_dev_size) {
+		warn_if_metadata_device_too_big(pool->md_dev);
 		DMINFO("%s: growing the metadata device from %llu to %llu blocks",
 		       dm_device_name(pool->pool_md),
 		       sb_metadata_dev_size, metadata_dev_size);

drivers/md/persistent-data/dm-space-map-metadata.c

@@ -680,6 +680,8 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
 	if (r)
 		return r;
 
+	if (nr_blocks > DM_SM_METADATA_MAX_BLOCKS)
+		nr_blocks = DM_SM_METADATA_MAX_BLOCKS;
 	r = sm_ll_extend(&smm->ll, nr_blocks);
 	if (r)
 		return r;

drivers/md/persistent-data/dm-space-map-metadata.h

@@ -9,6 +9,17 @@
 
 #include "dm-transaction-manager.h"
 
+#define DM_SM_METADATA_BLOCK_SIZE (4096 >> SECTOR_SHIFT)
+
+/*
+ * The metadata device is currently limited in size.
+ *
+ * We have one block of index, which can hold 255 index entries.  Each
+ * index entry contains allocation info about ~16k metadata blocks.
+ */
+#define DM_SM_METADATA_MAX_BLOCKS (255 * ((1 << 14) - 64))
+#define DM_SM_METADATA_MAX_SECTORS (DM_SM_METADATA_MAX_BLOCKS * DM_SM_METADATA_BLOCK_SIZE)
+
 /*
  * Unfortunately we have to use two-phase construction due to the cycle
  * between the tm and sm.