--- zzzz-none-000/linux-3.10.107/drivers/md/dm-thin-metadata.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/drivers/md/dm-thin-metadata.c	2021-02-04 17:41:59.000000000 +0000
@@ -76,7 +76,7 @@
 
 #define THIN_SUPERBLOCK_MAGIC 27022010
 #define THIN_SUPERBLOCK_LOCATION 0
-#define THIN_VERSION 1
+#define THIN_VERSION 2
 #define THIN_METADATA_CACHE_SIZE 64
 #define SECTOR_TO_BLOCK_SHIFT 3
 
@@ -184,7 +184,6 @@
 	uint64_t trans_id;
 	unsigned long flags;
 	sector_t data_block_size;
-	bool read_only:1;
 
 	/*
 	 * Set if a transaction has to be aborted but the attempt to roll back
@@ -192,6 +191,13 @@
 	 * operation possible in this state is the closing of the device.
 	 */
 	bool fail_io:1;
+
+	/*
+	 * Reading the space map roots can fail, so we read it into these
+	 * buffers before the superblock is locked and updated.
+	 */
+	__u8 data_space_map_root[SPACE_MAP_ROOT_SIZE];
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 struct dm_thin_device {
@@ -390,7 +396,9 @@
 		}
 	}
 
-	return dm_bm_unlock(b);
+	dm_bm_unlock(b);
+
+	return 0;
 }
 
 static void __setup_btree_details(struct dm_pool_metadata *pmd)
@@ -431,26 +439,53 @@
 	pmd->details_info.value_type.equal = NULL;
 }
 
+static int save_sm_roots(struct dm_pool_metadata *pmd)
+{
+	int r;
+	size_t len;
+
+	r = dm_sm_root_size(pmd->metadata_sm, &len);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_copy_root(pmd->metadata_sm, &pmd->metadata_space_map_root, len);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_root_size(pmd->data_sm, &len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(pmd->data_sm, &pmd->data_space_map_root, len);
+}
+
+static void copy_sm_roots(struct dm_pool_metadata *pmd,
+			  struct thin_disk_superblock *disk)
+{
+	memcpy(&disk->metadata_space_map_root,
+	       &pmd->metadata_space_map_root,
+	       sizeof(pmd->metadata_space_map_root));
+
+	memcpy(&disk->data_space_map_root,
+	       &pmd->data_space_map_root,
+	       sizeof(pmd->data_space_map_root));
+}
+
 static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 {
 	int r;
 	struct dm_block *sblock;
-	size_t metadata_len, data_len;
 	struct thin_disk_superblock *disk_super;
 	sector_t bdev_size = i_size_read(pmd->bdev->bd_inode) >> SECTOR_SHIFT;
 
 	if (bdev_size > THIN_METADATA_MAX_SECTORS)
 		bdev_size = THIN_METADATA_MAX_SECTORS;
 
-	r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
-	if (r < 0)
-		return r;
-
-	r = dm_sm_root_size(pmd->data_sm, &data_len);
+	r = dm_sm_commit(pmd->data_sm);
 	if (r < 0)
 		return r;
 
-	r = dm_sm_commit(pmd->data_sm);
+	r = save_sm_roots(pmd);
 	if (r < 0)
 		return r;
 
@@ -471,27 +506,15 @@
 	disk_super->trans_id = 0;
 	disk_super->held_root = 0;
 
-	r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		goto bad_locked;
-
-	r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
-			    data_len);
-	if (r < 0)
-		goto bad_locked;
+	copy_sm_roots(pmd, disk_super);
 
 	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);
 
 	return dm_tm_commit(pmd->tm, sblock);
-
-bad_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 static int __format_metadata(struct dm_pool_metadata *pmd)
@@ -629,7 +652,9 @@
 	}
 
 	__setup_btree_details(pmd);
-	return dm_bm_unlock(sblock);
+	dm_bm_unlock(sblock);
+
+	return 0;
 
 bad_cleanup_data_sm:
 	dm_sm_destroy(pmd->data_sm);
@@ -660,7 +685,7 @@
 {
 	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)) {
@@ -778,6 +803,10 @@
 	if (r < 0)
 		return r;
 
+	r = save_sm_roots(pmd);
+	if (r < 0)
+		return r;
+
 	r = superblock_lock(pmd, &sblock);
 	if (r)
 		return r;
@@ -789,21 +818,9 @@
 	disk_super->trans_id = cpu_to_le64(pmd->trans_id);
 	disk_super->flags = cpu_to_le32(pmd->flags);
 
-	r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		goto out_locked;
-
-	r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
-			    data_len);
-	if (r < 0)
-		goto out_locked;
+	copy_sm_roots(pmd, disk_super);
 
 	return dm_tm_commit(pmd->tm, sblock);
-
-out_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
@@ -822,7 +839,6 @@
 	init_rwsem(&pmd->root_lock);
 	pmd->time = 0;
 	INIT_LIST_HEAD(&pmd->thin_devices);
-	pmd->read_only = false;
 	pmd->fail_io = false;
 	pmd->bdev = bdev;
 	pmd->data_block_size = data_block_size;
@@ -866,7 +882,7 @@
 		return -EBUSY;
 	}
 
-	if (!pmd->read_only && !pmd->fail_io) {
+	if (!dm_bm_is_read_only(pmd->bm) && !pmd->fail_io) {
 		r = __commit_transaction(pmd);
 		if (r < 0)
 			DMWARN("%s: __commit_transaction() failed, error = %d",
@@ -1291,7 +1307,9 @@
 	dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
 	dm_sm_dec_block(pmd->metadata_sm, held_root);
 
-	return dm_tm_unlock(pmd->tm, copy);
+	dm_tm_unlock(pmd->tm, copy);
+
+	return 0;
 }
 
 int dm_pool_release_metadata_snap(struct dm_pool_metadata *pmd)
@@ -1321,7 +1339,9 @@
 	disk_super = dm_block_data(sblock);
 	*result = le64_to_cpu(disk_super->held_root);
 
-	return dm_bm_unlock(sblock);
+	dm_bm_unlock(sblock);
+
+	return 0;
 }
 
 int dm_pool_get_metadata_snap(struct dm_pool_metadata *pmd,
@@ -1376,45 +1396,99 @@
 }
 
 int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block,
-		       int can_block, struct dm_thin_lookup_result *result)
+		       int can_issue_io, struct dm_thin_lookup_result *result)
 {
-	int r = -EINVAL;
-	uint64_t block_time = 0;
+	int r;
 	__le64 value;
 	struct dm_pool_metadata *pmd = td->pmd;
 	dm_block_t keys[2] = { td->id, block };
 	struct dm_btree_info *info;
 
-	if (can_block) {
-		down_read(&pmd->root_lock);
+	down_read(&pmd->root_lock);
+	if (pmd->fail_io) {
+		up_read(&pmd->root_lock);
+		return -EINVAL;
+	}
+
+	if (can_issue_io) {
 		info = &pmd->info;
-	} else if (down_read_trylock(&pmd->root_lock))
+	} else
 		info = &pmd->nb_info;
-	else
-		return -EWOULDBLOCK;
-
-	if (pmd->fail_io)
-		goto out;
 
 	r = dm_btree_lookup(info, pmd->root, keys, &value);
-	if (!r)
-		block_time = le64_to_cpu(value);
-
-out:
-	up_read(&pmd->root_lock);
-
 	if (!r) {
+		uint64_t block_time = 0;
 		dm_block_t exception_block;
 		uint32_t exception_time;
+
+		block_time = le64_to_cpu(value);
 		unpack_block_time(block_time, &exception_block,
 				  &exception_time);
 		result->block = exception_block;
 		result->shared = __snapshotted_since(td, exception_time);
 	}
 
+	up_read(&pmd->root_lock);
 	return r;
 }
 
+/* FIXME: write a more efficient one in btree */
+int dm_thin_find_mapped_range(struct dm_thin_device *td,
+			      dm_block_t begin, dm_block_t end,
+			      dm_block_t *thin_begin, dm_block_t *thin_end,
+			      dm_block_t *pool_begin, bool *maybe_shared)
+{
+	int r;
+	dm_block_t pool_end;
+	struct dm_thin_lookup_result lookup;
+
+	if (end < begin)
+		return -ENODATA;
+
+	/*
+	 * Find first mapped block.
+	 */
+	while (begin < end) {
+		r = dm_thin_find_block(td, begin, true, &lookup);
+		if (r) {
+			if (r != -ENODATA)
+				return r;
+		} else
+			break;
+
+		begin++;
+	}
+
+	if (begin == end)
+		return -ENODATA;
+
+	*thin_begin = begin;
+	*pool_begin = lookup.block;
+	*maybe_shared = lookup.shared;
+
+	begin++;
+	pool_end = *pool_begin + 1;
+	while (begin != end) {
+		r = dm_thin_find_block(td, begin, true, &lookup);
+		if (r) {
+			if (r == -ENODATA)
+				break;
+			else
+				return r;
+		}
+
+		if ((lookup.block != pool_end) ||
+		    (lookup.shared != *maybe_shared))
+			break;
+
+		pool_end++;
+		begin++;
+	}
+
+	*thin_end = begin;
+	return 0;
+}
+
 static int __insert(struct dm_thin_device *td, dm_block_t block,
 		    dm_block_t data_block)
 {
@@ -1467,6 +1541,65 @@
 	return 0;
 }
 
+static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end)
+{
+	int r;
+	unsigned count, total_count = 0;
+	struct dm_pool_metadata *pmd = td->pmd;
+	dm_block_t keys[1] = { td->id };
+	__le64 value;
+	dm_block_t mapping_root;
+
+	/*
+	 * Find the mapping tree
+	 */
+	r = dm_btree_lookup(&pmd->tl_info, pmd->root, keys, &value);
+	if (r)
+		return r;
+
+	/*
+	 * Remove from the mapping tree, taking care to inc the
+	 * ref count so it doesn't get deleted.
+	 */
+	mapping_root = le64_to_cpu(value);
+	dm_tm_inc(pmd->tm, mapping_root);
+	r = dm_btree_remove(&pmd->tl_info, pmd->root, keys, &pmd->root);
+	if (r)
+		return r;
+
+	/*
+	 * Remove leaves stops at the first unmapped entry, so we have to
+	 * loop round finding mapped ranges.
+	 */
+	while (begin < end) {
+		r = dm_btree_lookup_next(&pmd->bl_info, mapping_root, &begin, &begin, &value);
+		if (r == -ENODATA)
+			break;
+
+		if (r)
+			return r;
+
+		if (begin >= end)
+			break;
+
+		r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count);
+		if (r)
+			return r;
+
+		total_count += count;
+	}
+
+	td->mapped_blocks -= total_count;
+	td->changed = 1;
+
+	/*
+	 * Reinsert the mapping tree.
+	 */
+	value = cpu_to_le64(mapping_root);
+	__dm_bless_for_disk(&value);
+	return dm_btree_insert(&pmd->tl_info, pmd->root, keys, &value, &pmd->root);
+}
+
 int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block)
 {
 	int r = -EINVAL;
@@ -1479,6 +1612,19 @@
 	return r;
 }
 
+int dm_thin_remove_range(struct dm_thin_device *td,
+			 dm_block_t begin, dm_block_t end)
+{
+	int r = -EINVAL;
+
+	down_write(&td->pmd->root_lock);
+	if (!td->pmd->fail_io)
+		r = __remove_range(td, begin, end);
+	up_write(&td->pmd->root_lock);
+
+	return r;
+}
+
 int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result)
 {
 	int r;
@@ -1631,15 +1777,6 @@
 	return r;
 }
 
-int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result)
-{
-	down_read(&pmd->root_lock);
-	*result = pmd->data_block_size;
-	up_read(&pmd->root_lock);
-
-	return 0;
-}
-
 int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result)
 {
 	int r = -EINVAL;
@@ -1744,11 +1881,17 @@
 void dm_pool_metadata_read_only(struct dm_pool_metadata *pmd)
 {
 	down_write(&pmd->root_lock);
-	pmd->read_only = true;
 	dm_bm_set_read_only(pmd->bm);
 	up_write(&pmd->root_lock);
 }
 
+void dm_pool_metadata_read_write(struct dm_pool_metadata *pmd)
+{
+	down_write(&pmd->root_lock);
+	dm_bm_set_read_write(pmd->bm);
+	up_write(&pmd->root_lock);
+}
+
 int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd,
 					dm_block_t threshold,
 					dm_sm_threshold_fn fn,
@@ -1762,3 +1905,46 @@
 
 	return r;
 }
+
+int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd)
+{
+	int r;
+	struct dm_block *sblock;
+	struct thin_disk_superblock *disk_super;
+
+	down_write(&pmd->root_lock);
+	pmd->flags |= THIN_METADATA_NEEDS_CHECK_FLAG;
+
+	r = superblock_lock(pmd, &sblock);
+	if (r) {
+		DMERR("couldn't read superblock");
+		goto out;
+	}
+
+	disk_super = dm_block_data(sblock);
+	disk_super->flags = cpu_to_le32(pmd->flags);
+
+	dm_bm_unlock(sblock);
+out:
+	up_write(&pmd->root_lock);
+	return r;
+}
+
+bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd)
+{
+	bool needs_check;
+
+	down_read(&pmd->root_lock);
+	needs_check = pmd->flags & THIN_METADATA_NEEDS_CHECK_FLAG;
+	up_read(&pmd->root_lock);
+
+	return needs_check;
+}
+
+void dm_pool_issue_prefetches(struct dm_pool_metadata *pmd)
+{
+	down_read(&pmd->root_lock);
+	if (!pmd->fail_io)
+		dm_tm_issue_prefetches(pmd->tm);
+	up_read(&pmd->root_lock);
+}