[RFC PATCH 05/10] btrfs: allow mounting filesystems with remap-tree incompat flag

[Mark Harmstone <maharmstone@fb.com>]

If we encounter a filesystem with the remap-tree incompat flag set,
valdiate its compatibility with the other flags, and load the remap tree
using the values that have been added to the superblock.

The remap-tree feature depends on the free space tere, but no-holes and
block-group-tree have been made dependencies to reduce the testing
matrix. Similarly I'm not aware of any reason why mixed-bg and zoned would be
incompatible with remap-tree, but this is blocked for the time being
until it can be fully tested.

Signed-off-by: Mark Harmstone <maharmstone@fb.com>
---
 fs/btrfs/Kconfig                |  2 ++
 fs/btrfs/accessors.h            |  6 ++++
 fs/btrfs/disk-io.c              | 60 +++++++++++++++++++++++++++++++++
 fs/btrfs/extent-tree.c          |  2 ++
 fs/btrfs/fs.h                   |  4 ++-
 fs/btrfs/transaction.c          |  7 ++++
 include/uapi/linux/btrfs_tree.h |  5 ++-
 7 files changed, 84 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index c352f3ae0385..f41446102b14 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -114,6 +114,8 @@ config BTRFS_EXPERIMENTAL
 
 	  - extent tree v2 - complex rework of extent tracking
 
+	  - remap-tree - logical address remapping tree
+
 	  If unsure, say N.
 
 config BTRFS_FS_REF_VERIFY
diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index 6e6dd664217b..1bb6c0439ba7 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -919,6 +919,12 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
 			 uuid_tree_generation, 64);
 BTRFS_SETGET_STACK_FUNCS(super_nr_global_roots, struct btrfs_super_block,
 			 nr_global_roots, 64);
+BTRFS_SETGET_STACK_FUNCS(super_remap_root, struct btrfs_super_block,
+			 remap_root, 64);
+BTRFS_SETGET_STACK_FUNCS(super_remap_root_generation, struct btrfs_super_block,
+			 remap_root_generation, 64);
+BTRFS_SETGET_STACK_FUNCS(super_remap_root_level, struct btrfs_super_block,
+			 remap_root_level, 8);
 
 /* struct btrfs_file_extent_item */
 BTRFS_SETGET_STACK_FUNCS(stack_file_extent_type, struct btrfs_file_extent_item,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 95058c9aa31b..68fc6fea221d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1181,6 +1181,8 @@ static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info,
 		return btrfs_grab_root(btrfs_global_root(fs_info, &key));
 	case BTRFS_RAID_STRIPE_TREE_OBJECTID:
 		return btrfs_grab_root(fs_info->stripe_root);
+	case BTRFS_REMAP_TREE_OBJECTID:
+		return btrfs_grab_root(fs_info->remap_root);
 	default:
 		return NULL;
 	}
@@ -1269,6 +1271,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 	btrfs_put_root(fs_info->data_reloc_root);
 	btrfs_put_root(fs_info->block_group_root);
 	btrfs_put_root(fs_info->stripe_root);
+	btrfs_put_root(fs_info->remap_root);
 	btrfs_check_leaked_roots(fs_info);
 	btrfs_extent_buffer_leak_debug_check(fs_info);
 	kfree(fs_info->super_copy);
@@ -1823,6 +1826,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 	free_root_extent_buffers(info->data_reloc_root);
 	free_root_extent_buffers(info->block_group_root);
 	free_root_extent_buffers(info->stripe_root);
+	free_root_extent_buffers(info->remap_root);
 	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 }
@@ -2258,6 +2262,17 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	if (ret)
 		goto out;
 
+	if (btrfs_fs_incompat(fs_info, REMAP_TREE)) {
+		/* remap_root already loaded in load_important_roots() */
+		root = fs_info->remap_root;
+
+		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+
+		root->root_key.objectid = BTRFS_REMAP_TREE_OBJECTID;
+		root->root_key.type = BTRFS_ROOT_ITEM_KEY;
+		root->root_key.offset = 0;
+	}
+
 	/*
 	 * This tree can share blocks with some other fs tree during relocation
 	 * and we need a proper setup by btrfs_get_fs_root
@@ -2525,6 +2540,28 @@ int btrfs_validate_super(const struct btrfs_fs_info *fs_info,
 		ret = -EINVAL;
 	}
 
+	/* Ditto for remap_tree */
+	if (btrfs_fs_incompat(fs_info, REMAP_TREE) &&
+	    (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID) ||
+	     !btrfs_fs_incompat(fs_info, NO_HOLES) ||
+	     !btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE))) {
+		btrfs_err(fs_info,
+"remap-tree feature requires free-space-tree, no-holes, and block-group-tree");
+		ret = -EINVAL;
+	}
+
+	if (btrfs_fs_incompat(fs_info, REMAP_TREE) &&
+	    btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
+		btrfs_err(fs_info, "remap-tree not supported with mixed-bg");
+		ret = -EINVAL;
+	}
+
+	if (btrfs_fs_incompat(fs_info, REMAP_TREE) &&
+	    btrfs_fs_incompat(fs_info, ZONED)) {
+		btrfs_err(fs_info, "remap-tree not supported with zoned devices");
+		ret = -EINVAL;
+	}
+
 	/*
 	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
 	 * done later
@@ -2683,6 +2720,18 @@ static int load_important_roots(struct btrfs_fs_info *fs_info)
 		btrfs_warn(fs_info, "couldn't read tree root");
 		return ret;
 	}
+
+	if (btrfs_fs_incompat(fs_info, REMAP_TREE)) {
+		bytenr = btrfs_super_remap_root(sb);
+		gen = btrfs_super_remap_root_generation(sb);
+		level = btrfs_super_remap_root_level(sb);
+		ret = load_super_root(fs_info->remap_root, bytenr, gen, level);
+		if (ret) {
+			btrfs_warn(fs_info, "couldn't read remap root");
+			return ret;
+		}
+	}
+
 	return 0;
 }
 
@@ -3291,6 +3340,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_root *tree_root;
 	struct btrfs_root *chunk_root;
+	struct btrfs_root *remap_root;
 	int ret;
 	int level;
 
@@ -3325,6 +3375,16 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_alloc;
 	}
 
+	if (btrfs_super_incompat_flags(disk_super) & BTRFS_FEATURE_INCOMPAT_REMAP_TREE) {
+		remap_root = btrfs_alloc_root(fs_info, BTRFS_REMAP_TREE_OBJECTID,
+					      GFP_KERNEL);
+		fs_info->remap_root = remap_root;
+		if (!remap_root) {
+			ret = -ENOMEM;
+			goto fail_alloc;
+		}
+	}
+
 	btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid);
 	/*
 	 * Verify the type first, if that or the checksum value are
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index cb6128778a83..065bd48fcebe 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2562,6 +2562,8 @@ static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
 		flags = BTRFS_BLOCK_GROUP_DATA;
 	else if (root == fs_info->chunk_root)
 		flags = BTRFS_BLOCK_GROUP_SYSTEM;
+	else if (root == fs_info->remap_root)
+		flags = BTRFS_BLOCK_GROUP_REMAP;
 	else
 		flags = BTRFS_BLOCK_GROUP_METADATA;
 
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index 2dfdbfda5901..5072a2031631 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -286,7 +286,8 @@ enum {
 #define BTRFS_FEATURE_INCOMPAT_SUPP		\
 	(BTRFS_FEATURE_INCOMPAT_SUPP_STABLE |	\
 	 BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE | \
-	 BTRFS_FEATURE_INCOMPAT_EXTENT_TREE_V2)
+	 BTRFS_FEATURE_INCOMPAT_EXTENT_TREE_V2 | \
+	 BTRFS_FEATURE_INCOMPAT_REMAP_TREE)
 
 #else
 
@@ -434,6 +435,7 @@ struct btrfs_fs_info {
 	struct btrfs_root *data_reloc_root;
 	struct btrfs_root *block_group_root;
 	struct btrfs_root *stripe_root;
+	struct btrfs_root *remap_root;
 
 	/* The log root tree is a directory of all the other log roots */
 	struct btrfs_root *log_root_tree;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index b96195d6480f..68525e833753 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1951,6 +1951,13 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
 		super->cache_generation = 0;
 	if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
 		super->uuid_tree_generation = root_item->generation;
+
+	if (btrfs_fs_incompat(fs_info, REMAP_TREE)) {
+		root_item = &fs_info->remap_root->root_item;
+		super->remap_root = root_item->bytenr;
+		super->remap_root_generation = root_item->generation;
+		super->remap_root_level = root_item->level;
+	}
 }
 
 int btrfs_transaction_blocked(struct btrfs_fs_info *info)
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index 500e3a7df90b..89bcb80081a6 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -721,9 +721,12 @@ struct btrfs_super_block {
 	__u8 metadata_uuid[BTRFS_FSID_SIZE];
 
 	__u64 nr_global_roots;
+	__le64 remap_root;
+	__le64 remap_root_generation;
+	__u8 remap_root_level;
 
 	/* Future expansion */
-	__le64 reserved[27];
+	__u8 reserved[199];
 	__u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE];
 	struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS];
 
-- 
2.49.0