From: Qu Wenruo wqu@suse.com

This version includes all needed on-disk format from kernel.

Only need to modify the include headers for U-Boot, everything else is untouched.

Also, since U-Boot btrfs is using a different endian convert timing (at tree block read time), it needs some forced type conversion before proper crossport.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/btrfs.c | 3 +- fs/btrfs/btrfs_tree.h | 766 --------------- fs/btrfs/ctree.h | 214 +---- fs/btrfs/inode.c | 5 +- fs/btrfs/kernel-shared/btrfs_tree.h | 1333 +++++++++++++++++++++++++++ fs/btrfs/root.c | 2 +- fs/btrfs/subvolume.c | 2 +- 7 files changed, 1343 insertions(+), 982 deletions(-) delete mode 100644 fs/btrfs/btrfs_tree.h create mode 100644 fs/btrfs/kernel-shared/btrfs_tree.h

diff --git a/fs/btrfs/btrfs.c b/fs/btrfs/btrfs.c index de16217d0d..9f2888bab3 100644 --- a/fs/btrfs/btrfs.c +++ b/fs/btrfs/btrfs.c @@ -32,7 +32,8 @@ static int readdir_callback(const struct btrfs_root *root, char filetime[32], *target = NULL; time_t mtime;

- if (btrfs_lookup_inode(root, &item->location, &inode, NULL)) { + if (btrfs_lookup_inode(root, (struct btrfs_key *)&item->location, + &inode, NULL)) { printf("%s: Cannot find inode item for directory entry %.*s!\n", __func__, item->name_len, name); return 0; diff --git a/fs/btrfs/btrfs_tree.h b/fs/btrfs/btrfs_tree.h deleted file mode 100644 index aa0f3d6c86..0000000000 --- a/fs/btrfs/btrfs_tree.h +++ /dev/null @@ -1,766 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * From linux/include/uapi/linux/btrfs_tree.h - */ - -#ifndef __BTRFS_BTRFS_TREE_H__ -#define __BTRFS_BTRFS_TREE_H__ - -#include <common.h> - -#define BTRFS_VOL_NAME_MAX 255 -#define BTRFS_NAME_MAX 255 -#define BTRFS_LABEL_SIZE 256 -#define BTRFS_FSID_SIZE 16 -#define BTRFS_UUID_SIZE 16 - -/* - * This header contains the structure definitions and constants used - * by file system objects that can be retrieved using - * the BTRFS_IOC_SEARCH_TREE ioctl. That means basically anything that - * is needed to describe a leaf node's key or item contents. - */ - -/* holds pointers to all of the tree roots */ -#define BTRFS_ROOT_TREE_OBJECTID 1ULL - -/* stores information about which extents are in use, and reference counts */ -#define BTRFS_EXTENT_TREE_OBJECTID 2ULL - -/* - * chunk tree stores translations from logical -> physical block numbering - * the super block points to the chunk tree - */ -#define BTRFS_CHUNK_TREE_OBJECTID 3ULL - -/* - * stores information about which areas of a given device are in use. - * one per device. The tree of tree roots points to the device tree - */ -#define BTRFS_DEV_TREE_OBJECTID 4ULL - -/* one per subvolume, storing files and directories */ -#define BTRFS_FS_TREE_OBJECTID 5ULL - -/* directory objectid inside the root tree */ -#define BTRFS_ROOT_TREE_DIR_OBJECTID 6ULL - -/* holds checksums of all the data extents */ -#define BTRFS_CSUM_TREE_OBJECTID 7ULL - -/* holds quota configuration and tracking */ -#define BTRFS_QUOTA_TREE_OBJECTID 8ULL - -/* for storing items that use the BTRFS_UUID_KEY* types */ -#define BTRFS_UUID_TREE_OBJECTID 9ULL - -/* tracks free space in block groups. */ -#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL - -/* device stats in the device tree */ -#define BTRFS_DEV_STATS_OBJECTID 0ULL - -/* for storing balance parameters in the root tree */ -#define BTRFS_BALANCE_OBJECTID -4ULL - -/* orhpan objectid for tracking unlinked/truncated files */ -#define BTRFS_ORPHAN_OBJECTID -5ULL - -/* does write ahead logging to speed up fsyncs */ -#define BTRFS_TREE_LOG_OBJECTID -6ULL -#define BTRFS_TREE_LOG_FIXUP_OBJECTID -7ULL - -/* for space balancing */ -#define BTRFS_TREE_RELOC_OBJECTID -8ULL -#define BTRFS_DATA_RELOC_TREE_OBJECTID -9ULL - -/* - * extent checksums all have this objectid - * this allows them to share the logging tree - * for fsyncs - */ -#define BTRFS_EXTENT_CSUM_OBJECTID -10ULL - -/* For storing free space cache */ -#define BTRFS_FREE_SPACE_OBJECTID -11ULL - -/* - * The inode number assigned to the special inode for storing - * free ino cache - */ -#define BTRFS_FREE_INO_OBJECTID -12ULL - -/* dummy objectid represents multiple objectids */ -#define BTRFS_MULTIPLE_OBJECTIDS -255ULL - -/* - * All files have objectids in this range. - */ -#define BTRFS_FIRST_FREE_OBJECTID 256ULL -#define BTRFS_LAST_FREE_OBJECTID -256ULL -#define BTRFS_FIRST_CHUNK_TREE_OBJECTID 256ULL - - -/* - * the device items go into the chunk tree. The key is in the form - * [ 1 BTRFS_DEV_ITEM_KEY device_id ] - */ -#define BTRFS_DEV_ITEMS_OBJECTID 1ULL - -#define BTRFS_BTREE_INODE_OBJECTID 1 - -#define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2 - -#define BTRFS_DEV_REPLACE_DEVID 0ULL - -/* - * inode items have the data typically returned from stat and store other - * info about object characteristics. There is one for every file and dir in - * the FS - */ -#define BTRFS_INODE_ITEM_KEY 1 -#define BTRFS_INODE_REF_KEY 12 -#define BTRFS_INODE_EXTREF_KEY 13 -#define BTRFS_XATTR_ITEM_KEY 24 -#define BTRFS_ORPHAN_ITEM_KEY 48 -/* reserve 2-15 close to the inode for later flexibility */ - -/* - * dir items are the name -> inode pointers in a directory. There is one - * for every name in a directory. - */ -#define BTRFS_DIR_LOG_ITEM_KEY 60 -#define BTRFS_DIR_LOG_INDEX_KEY 72 -#define BTRFS_DIR_ITEM_KEY 84 -#define BTRFS_DIR_INDEX_KEY 96 -/* - * extent data is for file data - */ -#define BTRFS_EXTENT_DATA_KEY 108 - -/* - * extent csums are stored in a separate tree and hold csums for - * an entire extent on disk. - */ -#define BTRFS_EXTENT_CSUM_KEY 128 - -/* - * root items point to tree roots. They are typically in the root - * tree used by the super block to find all the other trees - */ -#define BTRFS_ROOT_ITEM_KEY 132 - -/* - * root backrefs tie subvols and snapshots to the directory entries that - * reference them - */ -#define BTRFS_ROOT_BACKREF_KEY 144 - -/* - * root refs make a fast index for listing all of the snapshots and - * subvolumes referenced by a given root. They point directly to the - * directory item in the root that references the subvol - */ -#define BTRFS_ROOT_REF_KEY 156 - -/* - * extent items are in the extent map tree. These record which blocks - * are used, and how many references there are to each block - */ -#define BTRFS_EXTENT_ITEM_KEY 168 - -/* - * The same as the BTRFS_EXTENT_ITEM_KEY, except it's metadata we already know - * the length, so we save the level in key->offset instead of the length. - */ -#define BTRFS_METADATA_ITEM_KEY 169 - -#define BTRFS_TREE_BLOCK_REF_KEY 176 - -#define BTRFS_EXTENT_DATA_REF_KEY 178 - -#define BTRFS_EXTENT_REF_V0_KEY 180 - -#define BTRFS_SHARED_BLOCK_REF_KEY 182 - -#define BTRFS_SHARED_DATA_REF_KEY 184 - -/* - * block groups give us hints into the extent allocation trees. Which - * blocks are free etc etc - */ -#define BTRFS_BLOCK_GROUP_ITEM_KEY 192 - -/* - * Every block group is represented in the free space tree by a free space info - * item, which stores some accounting information. It is keyed on - * (block_group_start, FREE_SPACE_INFO, block_group_length). - */ -#define BTRFS_FREE_SPACE_INFO_KEY 198 - -/* - * A free space extent tracks an extent of space that is free in a block group. - * It is keyed on (start, FREE_SPACE_EXTENT, length). - */ -#define BTRFS_FREE_SPACE_EXTENT_KEY 199 - -/* - * When a block group becomes very fragmented, we convert it to use bitmaps - * instead of extents. A free space bitmap is keyed on - * (start, FREE_SPACE_BITMAP, length); the corresponding item is a bitmap with - * (length / sectorsize) bits. - */ -#define BTRFS_FREE_SPACE_BITMAP_KEY 200 - -#define BTRFS_DEV_EXTENT_KEY 204 -#define BTRFS_DEV_ITEM_KEY 216 -#define BTRFS_CHUNK_ITEM_KEY 228 - -/* - * Records the overall state of the qgroups. - * There's only one instance of this key present, - * (0, BTRFS_QGROUP_STATUS_KEY, 0) - */ -#define BTRFS_QGROUP_STATUS_KEY 240 -/* - * Records the currently used space of the qgroup. - * One key per qgroup, (0, BTRFS_QGROUP_INFO_KEY, qgroupid). - */ -#define BTRFS_QGROUP_INFO_KEY 242 -/* - * Contains the user configured limits for the qgroup. - * One key per qgroup, (0, BTRFS_QGROUP_LIMIT_KEY, qgroupid). - */ -#define BTRFS_QGROUP_LIMIT_KEY 244 -/* - * Records the child-parent relationship of qgroups. For - * each relation, 2 keys are present: - * (childid, BTRFS_QGROUP_RELATION_KEY, parentid) - * (parentid, BTRFS_QGROUP_RELATION_KEY, childid) - */ -#define BTRFS_QGROUP_RELATION_KEY 246 - -/* - * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY. - */ -#define BTRFS_BALANCE_ITEM_KEY 248 - -/* - * The key type for tree items that are stored persistently, but do not need to - * exist for extended period of time. The items can exist in any tree. - * - * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data] - * - * Existing items: - * - * - balance status item - * (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0) - */ -#define BTRFS_TEMPORARY_ITEM_KEY 248 - -/* - * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY - */ -#define BTRFS_DEV_STATS_KEY 249 - -/* - * The key type for tree items that are stored persistently and usually exist - * for a long period, eg. filesystem lifetime. The item kinds can be status - * information, stats or preference values. The item can exist in any tree. - * - * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data] - * - * Existing items: - * - * - device statistics, store IO stats in the device tree, one key for all - * stats - * (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0) - */ -#define BTRFS_PERSISTENT_ITEM_KEY 249 - -/* - * Persistantly stores the device replace state in the device tree. - * The key is built like this: (0, BTRFS_DEV_REPLACE_KEY, 0). - */ -#define BTRFS_DEV_REPLACE_KEY 250 - -/* - * Stores items that allow to quickly map UUIDs to something else. - * These items are part of the filesystem UUID tree. - * The key is built like this: - * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits). - */ -#if BTRFS_UUID_SIZE != 16 -#error "UUID items require BTRFS_UUID_SIZE == 16!" -#endif -#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */ -#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to - * received subvols */ - -/* - * string items are for debugging. They just store a short string of - * data in the FS - */ -#define BTRFS_STRING_ITEM_KEY 253 - - - -/* 32 bytes in various csum fields */ -#define BTRFS_CSUM_SIZE 32 - -/* csum types */ -#define BTRFS_CSUM_TYPE_CRC32 0 - -/* - * flags definitions for directory entry item type - * - * Used by: - * struct btrfs_dir_item.type - */ -#define BTRFS_FT_UNKNOWN 0 -#define BTRFS_FT_REG_FILE 1 -#define BTRFS_FT_DIR 2 -#define BTRFS_FT_CHRDEV 3 -#define BTRFS_FT_BLKDEV 4 -#define BTRFS_FT_FIFO 5 -#define BTRFS_FT_SOCK 6 -#define BTRFS_FT_SYMLINK 7 -#define BTRFS_FT_XATTR 8 -#define BTRFS_FT_MAX 9 - -/* - * The key defines the order in the tree, and so it also defines (optimal) - * block layout. - * - * objectid corresponds to the inode number. - * - * type tells us things about the object, and is a kind of stream selector. - * so for a given inode, keys with type of 1 might refer to the inode data, - * type of 2 may point to file data in the btree and type == 3 may point to - * extents. - * - * offset is the starting byte offset for this key in the stream. - */ - -struct btrfs_key { - __u64 objectid; - __u8 type; - __u64 offset; -} __attribute__ ((__packed__)); - -struct btrfs_dev_item { - /* the internal btrfs device id */ - __u64 devid; - - /* size of the device */ - __u64 total_bytes; - - /* bytes used */ - __u64 bytes_used; - - /* optimal io alignment for this device */ - __u32 io_align; - - /* optimal io width for this device */ - __u32 io_width; - - /* minimal io size for this device */ - __u32 sector_size; - - /* type and info about this device */ - __u64 type; - - /* expected generation for this device */ - __u64 generation; - - /* - * starting byte of this partition on the device, - * to allow for stripe alignment in the future - */ - __u64 start_offset; - - /* grouping information for allocation decisions */ - __u32 dev_group; - - /* seek speed 0-100 where 100 is fastest */ - __u8 seek_speed; - - /* bandwidth 0-100 where 100 is fastest */ - __u8 bandwidth; - - /* btrfs generated uuid for this device */ - __u8 uuid[BTRFS_UUID_SIZE]; - - /* uuid of FS who owns this device */ - __u8 fsid[BTRFS_UUID_SIZE]; -} __attribute__ ((__packed__)); - -struct btrfs_stripe { - __u64 devid; - __u64 offset; - __u8 dev_uuid[BTRFS_UUID_SIZE]; -} __attribute__ ((__packed__)); - -struct btrfs_chunk { - /* size of this chunk in bytes */ - __u64 length; - - /* objectid of the root referencing this chunk */ - __u64 owner; - - __u64 stripe_len; - __u64 type; - - /* optimal io alignment for this chunk */ - __u32 io_align; - - /* optimal io width for this chunk */ - __u32 io_width; - - /* minimal io size for this chunk */ - __u32 sector_size; - - /* 2^16 stripes is quite a lot, a second limit is the size of a single - * item in the btree - */ - __u16 num_stripes; - - /* sub stripes only matter for raid10 */ - __u16 sub_stripes; - struct btrfs_stripe stripe; - /* additional stripes go here */ -} __attribute__ ((__packed__)); - -#define BTRFS_FREE_SPACE_EXTENT 1 -#define BTRFS_FREE_SPACE_BITMAP 2 - -struct btrfs_free_space_entry { - __u64 offset; - __u64 bytes; - __u8 type; -} __attribute__ ((__packed__)); - -struct btrfs_free_space_header { - struct btrfs_key location; - __u64 generation; - __u64 num_entries; - __u64 num_bitmaps; -} __attribute__ ((__packed__)); - -#define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0) -#define BTRFS_HEADER_FLAG_RELOC (1ULL << 1) - -/* Super block flags */ -/* Errors detected */ -#define BTRFS_SUPER_FLAG_ERROR (1ULL << 2) - -#define BTRFS_SUPER_FLAG_SEEDING (1ULL << 32) -#define BTRFS_SUPER_FLAG_METADUMP (1ULL << 33) - - -/* - * items in the extent btree are used to record the objectid of the - * owner of the block and the number of references - */ - -struct btrfs_extent_item { - __u64 refs; - __u64 generation; - __u64 flags; -} __attribute__ ((__packed__)); - - -#define BTRFS_EXTENT_FLAG_DATA (1ULL << 0) -#define BTRFS_EXTENT_FLAG_TREE_BLOCK (1ULL << 1) - -/* following flags only apply to tree blocks */ - -/* use full backrefs for extent pointers in the block */ -#define BTRFS_BLOCK_FLAG_FULL_BACKREF (1ULL << 8) - -/* - * this flag is only used internally by scrub and may be changed at any time - * it is only declared here to avoid collisions - */ -#define BTRFS_EXTENT_FLAG_SUPER (1ULL << 48) - -struct btrfs_tree_block_info { - struct btrfs_key key; - __u8 level; -} __attribute__ ((__packed__)); - -struct btrfs_extent_data_ref { - __u64 root; - __u64 objectid; - __u64 offset; - __u32 count; -} __attribute__ ((__packed__)); - -struct btrfs_shared_data_ref { - __u32 count; -} __attribute__ ((__packed__)); - -struct btrfs_extent_inline_ref { - __u8 type; - __u64 offset; -} __attribute__ ((__packed__)); - -/* dev extents record free space on individual devices. The owner - * field points back to the chunk allocation mapping tree that allocated - * the extent. The chunk tree uuid field is a way to double check the owner - */ -struct btrfs_dev_extent { - __u64 chunk_tree; - __u64 chunk_objectid; - __u64 chunk_offset; - __u64 length; - __u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; -} __attribute__ ((__packed__)); - -struct btrfs_inode_ref { - __u64 index; - __u16 name_len; - /* name goes here */ -} __attribute__ ((__packed__)); - -struct btrfs_inode_extref { - __u64 parent_objectid; - __u64 index; - __u16 name_len; - __u8 name[0]; - /* name goes here */ -} __attribute__ ((__packed__)); - -struct btrfs_timespec { - __u64 sec; - __u32 nsec; -} __attribute__ ((__packed__)); - -struct btrfs_inode_item { - /* nfs style generation number */ - __u64 generation; - /* transid that last touched this inode */ - __u64 transid; - __u64 size; - __u64 nbytes; - __u64 block_group; - __u32 nlink; - __u32 uid; - __u32 gid; - __u32 mode; - __u64 rdev; - __u64 flags; - - /* modification sequence number for NFS */ - __u64 sequence; - - /* - * a little future expansion, for more than this we can - * just grow the inode item and version it - */ - __u64 reserved[4]; - struct btrfs_timespec atime; - struct btrfs_timespec ctime; - struct btrfs_timespec mtime; - struct btrfs_timespec otime; -} __attribute__ ((__packed__)); - -struct btrfs_dir_log_item { - __u64 end; -} __attribute__ ((__packed__)); - -struct btrfs_dir_item { - struct btrfs_key location; - __u64 transid; - __u16 data_len; - __u16 name_len; - __u8 type; -} __attribute__ ((__packed__)); - -#define BTRFS_ROOT_SUBVOL_RDONLY (1ULL << 0) - -/* - * Internal in-memory flag that a subvolume has been marked for deletion but - * still visible as a directory - */ -#define BTRFS_ROOT_SUBVOL_DEAD (1ULL << 48) - -struct btrfs_root_item { - struct btrfs_inode_item inode; - __u64 generation; - __u64 root_dirid; - __u64 bytenr; - __u64 byte_limit; - __u64 bytes_used; - __u64 last_snapshot; - __u64 flags; - __u32 refs; - struct btrfs_key drop_progress; - __u8 drop_level; - __u8 level; - - /* - * The following fields appear after subvol_uuids+subvol_times - * were introduced. - */ - - /* - * This generation number is used to test if the new fields are valid - * and up to date while reading the root item. Every time the root item - * is written out, the "generation" field is copied into this field. If - * anyone ever mounted the fs with an older kernel, we will have - * mismatching generation values here and thus must invalidate the - * new fields. See btrfs_update_root and btrfs_find_last_root for - * details. - * the offset of generation_v2 is also used as the start for the memset - * when invalidating the fields. - */ - __u64 generation_v2; - __u8 uuid[BTRFS_UUID_SIZE]; - __u8 parent_uuid[BTRFS_UUID_SIZE]; - __u8 received_uuid[BTRFS_UUID_SIZE]; - __u64 ctransid; /* updated when an inode changes */ - __u64 otransid; /* trans when created */ - __u64 stransid; /* trans when sent. non-zero for received subvol */ - __u64 rtransid; /* trans when received. non-zero for received subvol */ - struct btrfs_timespec ctime; - struct btrfs_timespec otime; - struct btrfs_timespec stime; - struct btrfs_timespec rtime; - __u64 reserved[8]; /* for future */ -} __attribute__ ((__packed__)); - -/* - * this is used for both forward and backward root refs - */ -struct btrfs_root_ref { - __u64 dirid; - __u64 sequence; - __u16 name_len; -} __attribute__ ((__packed__)); - -#define BTRFS_FILE_EXTENT_INLINE 0 -#define BTRFS_FILE_EXTENT_REG 1 -#define BTRFS_FILE_EXTENT_PREALLOC 2 - -enum btrfs_compression_type { - BTRFS_COMPRESS_NONE = 0, - BTRFS_COMPRESS_ZLIB = 1, - BTRFS_COMPRESS_LZO = 2, - BTRFS_COMPRESS_ZSTD = 3, - BTRFS_COMPRESS_TYPES = 3, - BTRFS_COMPRESS_LAST = 4, -}; - -struct btrfs_file_extent_item { - /* - * transaction id that created this extent - */ - __u64 generation; - /* - * max number of bytes to hold this extent in ram - * when we split a compressed extent we can't know how big - * each of the resulting pieces will be. So, this is - * an upper limit on the size of the extent in ram instead of - * an exact limit. - */ - __u64 ram_bytes; - - /* - * 32 bits for the various ways we might encode the data, - * including compression and encryption. If any of these - * are set to something a given disk format doesn't understand - * it is treated like an incompat flag for reading and writing, - * but not for stat. - */ - __u8 compression; - __u8 encryption; - __u16 other_encoding; /* spare for later use */ - - /* are we inline data or a real extent? */ - __u8 type; - - /* - * disk space consumed by the extent, checksum blocks are included - * in these numbers - * - * At this offset in the structure, the inline extent data start. - */ - __u64 disk_bytenr; - __u64 disk_num_bytes; - /* - * the logical offset in file blocks (no csums) - * this extent record is for. This allows a file extent to point - * into the middle of an existing extent on disk, sharing it - * between two snapshots (useful if some bytes in the middle of the - * extent have changed - */ - __u64 offset; - /* - * the logical number of file blocks (no csums included). This - * always reflects the size uncompressed and without encoding. - */ - __u64 num_bytes; - -} __attribute__ ((__packed__)); - -struct btrfs_csum_item { - __u8 csum; -} __attribute__ ((__packed__)); - -/* different types of block groups (and chunks) */ -#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0) -#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1) -#define BTRFS_BLOCK_GROUP_METADATA (1ULL << 2) -#define BTRFS_BLOCK_GROUP_RAID0 (1ULL << 3) -#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4) -#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5) -#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6) -#define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7) -#define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8) -#define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ - BTRFS_SPACE_INFO_GLOBAL_RSV) - -enum btrfs_raid_types { - BTRFS_RAID_RAID10, - BTRFS_RAID_RAID1, - BTRFS_RAID_DUP, - BTRFS_RAID_RAID0, - BTRFS_RAID_SINGLE, - BTRFS_RAID_RAID5, - BTRFS_RAID_RAID6, - BTRFS_NR_RAID_TYPES -}; - -#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ - BTRFS_BLOCK_GROUP_SYSTEM | \ - BTRFS_BLOCK_GROUP_METADATA) - -#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \ - BTRFS_BLOCK_GROUP_RAID1 | \ - BTRFS_BLOCK_GROUP_RAID5 | \ - BTRFS_BLOCK_GROUP_RAID6 | \ - BTRFS_BLOCK_GROUP_DUP | \ - BTRFS_BLOCK_GROUP_RAID10) -#define BTRFS_BLOCK_GROUP_RAID56_MASK (BTRFS_BLOCK_GROUP_RAID5 | \ - BTRFS_BLOCK_GROUP_RAID6) - -/* - * We need a bit for restriper to be able to tell when chunks of type - * SINGLE are available. This "extended" profile format is used in - * fs_info->avail_*_alloc_bits (in-memory) and balance item fields - * (on-disk). The corresponding on-disk bit in chunk.type is reserved - * to avoid remappings between two formats in future. - */ -#define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48) - -/* - * A fake block group type that is used to communicate global block reserve - * size to userspace via the SPACE_INFO ioctl. - */ -#define BTRFS_SPACE_INFO_GLOBAL_RSV (1ULL << 49) - -#define BTRFS_EXTENDED_PROFILE_MASK (BTRFS_BLOCK_GROUP_PROFILE_MASK | \ - BTRFS_AVAIL_ALLOC_BIT_SINGLE) - -#endif /* __BTRFS_BTRFS_TREE_H__ */ diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 65c152a52f..156ce69ed0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -11,28 +11,16 @@

#include <common.h> #include <compiler.h> -#include "btrfs_tree.h" - -#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */ +#include "kernel-shared/btrfs_tree.h"

#define BTRFS_MAX_MIRRORS 3

-#define BTRFS_MAX_LEVEL 8 - -#define BTRFS_COMPAT_EXTENT_TREE_V0 - /* * the max metadata block size. This limit is somewhat artificial, * but the memmove costs go through the roof for larger blocks. */ #define BTRFS_MAX_METADATA_BLOCKSIZE 65536

-/* - * we can actually store much bigger names, but lets not confuse the rest - * of linux - */ -#define BTRFS_NAME_LEN 255 - /* * Theoretical limit is larger, but we keep this down to a sane * value. That should limit greatly the possibility of collisions on @@ -40,8 +28,6 @@ */ #define BTRFS_LINK_MAX 65535U

-static const int btrfs_csum_sizes[] = { 4 }; - /* four bytes for CRC32 */ #define BTRFS_EMPTY_DIR_SIZE 0

@@ -61,207 +47,12 @@ static const int btrfs_csum_sizes[] = { 4 }; #define BTRFS_FS_STATE_DEV_REPLACING 3 #define BTRFS_FS_STATE_DUMMY_FS_INFO 4

-#define BTRFS_BACKREF_REV_MAX 256 -#define BTRFS_BACKREF_REV_SHIFT 56 -#define BTRFS_BACKREF_REV_MASK (((u64)BTRFS_BACKREF_REV_MAX - 1) << \ - BTRFS_BACKREF_REV_SHIFT) - -#define BTRFS_OLD_BACKREF_REV 0 -#define BTRFS_MIXED_BACKREF_REV 1 - -/* - * every tree block (leaf or node) starts with this header. - */ -struct btrfs_header { - /* these first four must match the super block */ - __u8 csum[BTRFS_CSUM_SIZE]; - __u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */ - __u64 bytenr; /* which block this node is supposed to live in */ - __u64 flags; - - /* allowed to be different from the super from here on down */ - __u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; - __u64 generation; - __u64 owner; - __u32 nritems; - __u8 level; -} __attribute__ ((__packed__)); - -/* - * this is a very generous portion of the super block, giving us - * room to translate 14 chunks with 3 stripes each. - */ -#define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048 - -/* - * just in case we somehow lose the roots and are not able to mount, - * we store an array of the roots from previous transactions - * in the super. - */ -#define BTRFS_NUM_BACKUP_ROOTS 4 -struct btrfs_root_backup { - __u64 tree_root; - __u64 tree_root_gen; - - __u64 chunk_root; - __u64 chunk_root_gen; - - __u64 extent_root; - __u64 extent_root_gen; - - __u64 fs_root; - __u64 fs_root_gen; - - __u64 dev_root; - __u64 dev_root_gen; - - __u64 csum_root; - __u64 csum_root_gen; - - __u64 total_bytes; - __u64 bytes_used; - __u64 num_devices; - /* future */ - __u64 unused_64[4]; - - __u8 tree_root_level; - __u8 chunk_root_level; - __u8 extent_root_level; - __u8 fs_root_level; - __u8 dev_root_level; - __u8 csum_root_level; - /* future and to align */ - __u8 unused_8[10]; -} __attribute__ ((__packed__)); - -/* - * the super block basically lists the main trees of the FS - * it currently lacks any block count etc etc - */ -struct btrfs_super_block { - __u8 csum[BTRFS_CSUM_SIZE]; - /* the first 4 fields must match struct btrfs_header */ - __u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */ - __u64 bytenr; /* this block number */ - __u64 flags; - - /* allowed to be different from the btrfs_header from here own down */ - __u64 magic; - __u64 generation; - __u64 root; - __u64 chunk_root; - __u64 log_root; - - /* this will help find the new super based on the log root */ - __u64 log_root_transid; - __u64 total_bytes; - __u64 bytes_used; - __u64 root_dir_objectid; - __u64 num_devices; - __u32 sectorsize; - __u32 nodesize; - __u32 __unused_leafsize; - __u32 stripesize; - __u32 sys_chunk_array_size; - __u64 chunk_root_generation; - __u64 compat_flags; - __u64 compat_ro_flags; - __u64 incompat_flags; - __u16 csum_type; - __u8 root_level; - __u8 chunk_root_level; - __u8 log_root_level; - struct btrfs_dev_item dev_item; - - char label[BTRFS_LABEL_SIZE]; - - __u64 cache_generation; - __u64 uuid_tree_generation; - - /* future expansion */ - __u64 reserved[30]; - __u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; - struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; -} __attribute__ ((__packed__)); - -/* - * Compat flags that we support. If any incompat flags are set other than the - * ones specified below then we will fail to mount - */ -#define BTRFS_FEATURE_COMPAT_SUPP 0ULL -#define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL -#define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL - -#define BTRFS_FEATURE_COMPAT_RO_SUPP \ - (BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE | \ - BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID) - -#define BTRFS_FEATURE_COMPAT_RO_SAFE_SET 0ULL -#define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR 0ULL - -#define BTRFS_FEATURE_INCOMPAT_SUPP \ - (BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF | \ - BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL | \ - BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS | \ - BTRFS_FEATURE_INCOMPAT_BIG_METADATA | \ - BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \ - BTRFS_FEATURE_INCOMPAT_RAID56 | \ - BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \ - BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ - BTRFS_FEATURE_INCOMPAT_NO_HOLES) - -#define BTRFS_FEATURE_INCOMPAT_SAFE_SET \ - (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) -#define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL - -/* - * A leaf is full of items. offset and size tell us where to find - * the item in the leaf (relative to the start of the data area) - */ -struct btrfs_item { - struct btrfs_key key; - __u32 offset; - __u32 size; -} __attribute__ ((__packed__)); - -/* - * leaves have an item area and a data area: - * [item0, item1....itemN] [free space] [dataN...data1, data0] - * - * The data is separate from the items to get the keys closer together - * during searches. - */ -struct btrfs_leaf { - struct btrfs_header header; - struct btrfs_item items[]; -} __attribute__ ((__packed__)); - -/* - * all non-leaf blocks are nodes, they hold only keys and pointers to - * other blocks - */ -struct btrfs_key_ptr { - struct btrfs_key key; - __u64 blockptr; - __u64 generation; -} __attribute__ ((__packed__)); - -struct btrfs_node { - struct btrfs_header header; - struct btrfs_key_ptr ptrs[]; -} __attribute__ ((__packed__)); - union btrfs_tree_node { struct btrfs_header header; struct btrfs_leaf leaf; struct btrfs_node node; };

-typedef __u8 u8; -typedef __u16 u16; -typedef __u32 u32; -typedef __u64 u64; - struct btrfs_path { union btrfs_tree_node *nodes[BTRFS_MAX_LEVEL]; u32 slots[BTRFS_MAX_LEVEL]; @@ -283,7 +74,8 @@ int btrfs_prev_slot(struct btrfs_path *); int btrfs_next_slot(struct btrfs_path *);

static inline struct btrfs_key *btrfs_path_leaf_key(struct btrfs_path *p) { - return &p->nodes[0]->leaf.items[p->slots[0]].key; + /* At tree read time we have converted the endian for btrfs_disk_key */ + return (struct btrfs_key *)&p->nodes[0]->leaf.items[p->slots[0]].key; }

static inline struct btrfs_key * diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 991c2f68c3..d88ae67217 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -29,7 +29,7 @@ u64 btrfs_lookup_inode_ref(struct btrfs_root *root, u64 inr, *refp = *ref;

if (name) { - if (ref->name_len > BTRFS_NAME_MAX) { + if (ref->name_len > BTRFS_NAME_LEN) { printf("%s: inode name too long: %u\n", __func__, ref->name_len); goto out; @@ -255,7 +255,8 @@ u64 btrfs_lookup_path(struct btrfs_root *root, u64 inr, const char *path,

type = item.type; have_inode = 1; - if (btrfs_lookup_inode(root, &item.location, &inode_item, root)) + if (btrfs_lookup_inode(root, (struct btrfs_key *)&item.location, + &inode_item, root)) return -1ULL;

if (item.type == BTRFS_FT_SYMLINK && symlink_limit >= 0) { diff --git a/fs/btrfs/kernel-shared/btrfs_tree.h b/fs/btrfs/kernel-shared/btrfs_tree.h new file mode 100644 index 0000000000..6a76d1e456 --- /dev/null +++ b/fs/btrfs/kernel-shared/btrfs_tree.h @@ -0,0 +1,1333 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copied from kernel/include/uapi/linux/btrfs_btree.h. + * + * Only modified the header. + */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __BTRFS_TREE_H__ +#define __BTRFS_TREE_H__ + +#include <linux/types.h> + +#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */ + +/* + * The max metadata block size (node size). + * + * This limit is somewhat artificial. The memmove and tree block locking cost + * go up with larger node size. + */ +#define BTRFS_MAX_METADATA_BLOCKSIZE 65536 + +/* + * We can actually store much bigger names, but lets not confuse the rest + * of linux. + * + * btrfs_dir_item::name_len follows this limitation. + */ +#define BTRFS_NAME_LEN 255 + +/* + * Objectids start from here. + * + * Check btrfs_disk_key for the meaning of objectids. + */ + +/* + * Root tree holds pointers to all of the tree roots. + * Without special mention, the root tree contains the root bytenr of all other + * trees, except the chunk tree and the log tree. + * + * The super block contains the root bytenr of this tree. + */ +#define BTRFS_ROOT_TREE_OBJECTID 1ULL + +/* + * Extent tree stores information about which extents are in use, and backrefs + * for each extent. + */ +#define BTRFS_EXTENT_TREE_OBJECTID 2ULL + +/* + * Chunk tree stores btrfs logical address -> physical address mapping. + * + * The super block contains part of chunk tree for bootstrap, and contains + * the root bytenr of this tree. + */ +#define BTRFS_CHUNK_TREE_OBJECTID 3ULL + +/* + * Device tree stores info about which areas of a given device are in use, + * and physical address -> btrfs logical address mapping. + */ +#define BTRFS_DEV_TREE_OBJECTID 4ULL + +/* The fs tree is the first subvolume tree, storing files and directories. */ +#define BTRFS_FS_TREE_OBJECTID 5ULL + +/* Shows the directory objectid inside the root tree. */ +#define BTRFS_ROOT_TREE_DIR_OBJECTID 6ULL + +/* Csum tree holds checksums of all the data extents. */ +#define BTRFS_CSUM_TREE_OBJECTID 7ULL + +/* Quota tree holds quota configuration and tracking. */ +#define BTRFS_QUOTA_TREE_OBJECTID 8ULL + +/* UUID tree stores items that use the BTRFS_UUID_KEY* types. */ +#define BTRFS_UUID_TREE_OBJECTID 9ULL + +/* Free space cache tree (v2 space cache) tracks free space in block groups. */ +#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL + +/* Indicates device stats in the device tree. */ +#define BTRFS_DEV_STATS_OBJECTID 0ULL + +/* For storing balance parameters in the root tree. */ +#define BTRFS_BALANCE_OBJECTID -4ULL + +/* Orhpan objectid for tracking unlinked/truncated files. */ +#define BTRFS_ORPHAN_OBJECTID -5ULL + +/* Does write ahead logging to speed up fsyncs. */ +#define BTRFS_TREE_LOG_OBJECTID -6ULL +#define BTRFS_TREE_LOG_FIXUP_OBJECTID -7ULL + +/* For space balancing. */ +#define BTRFS_TREE_RELOC_OBJECTID -8ULL +#define BTRFS_DATA_RELOC_TREE_OBJECTID -9ULL + +/* Extent checksums, shared between the csum tree and log trees. */ +#define BTRFS_EXTENT_CSUM_OBJECTID -10ULL + +/* For storing free space cache (v1 space cache). */ +#define BTRFS_FREE_SPACE_OBJECTID -11ULL + +/* The inode number assigned to the special inode for storing free ino cache. */ +#define BTRFS_FREE_INO_OBJECTID -12ULL + +/* Dummy objectid represents multiple objectids. */ +#define BTRFS_MULTIPLE_OBJECTIDS -255ULL + +/* All files have objectids in this range. */ +#define BTRFS_FIRST_FREE_OBJECTID 256ULL +#define BTRFS_LAST_FREE_OBJECTID -256ULL +#define BTRFS_FIRST_CHUNK_TREE_OBJECTID 256ULL + + +/* + * The device items go into the chunk tree. + * + * The key is in the form + * (BTRFS_DEV_ITEMS_OBJECTID, BTRFS_DEV_ITEM_KEY, <device_id>) + */ +#define BTRFS_DEV_ITEMS_OBJECTID 1ULL + +#define BTRFS_BTREE_INODE_OBJECTID 1 + +#define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2 + +#define BTRFS_DEV_REPLACE_DEVID 0ULL + +/* + * Types start from here. + * + * Check btrfs_disk_key for details about types. + */ + +/* + * Inode items have the data typically returned from stat and store other + * info about object characteristics. + * + * There is one for every file and dir in the FS. + */ +#define BTRFS_INODE_ITEM_KEY 1 +/* reserve 2-11 close to the inode for later flexibility */ +#define BTRFS_INODE_REF_KEY 12 +#define BTRFS_INODE_EXTREF_KEY 13 +#define BTRFS_XATTR_ITEM_KEY 24 +#define BTRFS_ORPHAN_ITEM_KEY 48 + +/* + * Dir items are the name -> inode pointers in a directory. + * + * There is one for every name in a directory. + */ +#define BTRFS_DIR_LOG_ITEM_KEY 60 +#define BTRFS_DIR_LOG_INDEX_KEY 72 +#define BTRFS_DIR_ITEM_KEY 84 +#define BTRFS_DIR_INDEX_KEY 96 + +/* Stores info (position, size ...) about a data extent of a file */ +#define BTRFS_EXTENT_DATA_KEY 108 + +/* + * Extent csums are stored in a separate tree and hold csums for + * an entire extent on disk. + */ +#define BTRFS_EXTENT_CSUM_KEY 128 + +/* + * Root items point to tree roots. + * + * They are typically in the root tree used by the super block to find all the + * other trees. + */ +#define BTRFS_ROOT_ITEM_KEY 132 + +/* + * Root backrefs tie subvols and snapshots to the directory entries that + * reference them. + */ +#define BTRFS_ROOT_BACKREF_KEY 144 + +/* + * Root refs make a fast index for listing all of the snapshots and + * subvolumes referenced by a given root. They point directly to the + * directory item in the root that references the subvol. + */ +#define BTRFS_ROOT_REF_KEY 156 + +/* + * Extent items are in the extent tree. + * + * These record which blocks are used, and how many references there are. + */ +#define BTRFS_EXTENT_ITEM_KEY 168 + +/* + * The same as the BTRFS_EXTENT_ITEM_KEY, except it's metadata we already know + * the length, so we save the level in key->offset instead of the length. + */ +#define BTRFS_METADATA_ITEM_KEY 169 + +#define BTRFS_TREE_BLOCK_REF_KEY 176 + +#define BTRFS_EXTENT_DATA_REF_KEY 178 + +#define BTRFS_EXTENT_REF_V0_KEY 180 + +#define BTRFS_SHARED_BLOCK_REF_KEY 182 + +#define BTRFS_SHARED_DATA_REF_KEY 184 + +/* + * Block groups give us hints into the extent allocation trees. + * + * Stores how many free space there is in a block group. + */ +#define BTRFS_BLOCK_GROUP_ITEM_KEY 192 + +/* + * Every block group is represented in the free space tree by a free space info + * item, which stores some accounting information. It is keyed on + * (block_group_start, FREE_SPACE_INFO, block_group_length). + */ +#define BTRFS_FREE_SPACE_INFO_KEY 198 + +/* + * A free space extent tracks an extent of space that is free in a block group. + * It is keyed on (start, FREE_SPACE_EXTENT, length). + */ +#define BTRFS_FREE_SPACE_EXTENT_KEY 199 + +/* + * When a block group becomes very fragmented, we convert it to use bitmaps + * instead of extents. + * + * A free space bitmap is keyed on (start, FREE_SPACE_BITMAP, length). + * The corresponding item is a bitmap with (length / sectorsize) bits. + */ +#define BTRFS_FREE_SPACE_BITMAP_KEY 200 + +#define BTRFS_DEV_EXTENT_KEY 204 +#define BTRFS_DEV_ITEM_KEY 216 +#define BTRFS_CHUNK_ITEM_KEY 228 + +/* + * Records the overall state of the qgroups. + * + * There's only one instance of this key present, + * (0, BTRFS_QGROUP_STATUS_KEY, 0) + */ +#define BTRFS_QGROUP_STATUS_KEY 240 +/* + * Records the currently used space of the qgroup. + * + * One key per qgroup, (0, BTRFS_QGROUP_INFO_KEY, qgroupid). + */ +#define BTRFS_QGROUP_INFO_KEY 242 + +/* + * Contains the user configured limits for the qgroup. + * + * One key per qgroup, (0, BTRFS_QGROUP_LIMIT_KEY, qgroupid). + */ +#define BTRFS_QGROUP_LIMIT_KEY 244 + +/* + * Records the child-parent relationship of qgroups. For + * each relation, 2 keys are present: + * (childid, BTRFS_QGROUP_RELATION_KEY, parentid) + * (parentid, BTRFS_QGROUP_RELATION_KEY, childid) + */ +#define BTRFS_QGROUP_RELATION_KEY 246 + +/* Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY. */ +#define BTRFS_BALANCE_ITEM_KEY 248 + +/* + * The key type for tree items that are stored persistently, but do not need to + * exist for extended period of time. The items can exist in any tree. + * + * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data] + * + * Existing items: + * + * - balance status item + * (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0) + */ +#define BTRFS_TEMPORARY_ITEM_KEY 248 + +/* Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY */ +#define BTRFS_DEV_STATS_KEY 249 + +/* + * The key type for tree items that are stored persistently and usually exist + * for a long period, eg. filesystem lifetime. The item kinds can be status + * information, stats or preference values. The item can exist in any tree. + * + * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data] + * + * Existing items: + * + * - device statistics, store IO stats in the device tree, one key for all + * stats + * (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0) + */ +#define BTRFS_PERSISTENT_ITEM_KEY 249 + +/* + * Persistently stores the device replace state in the device tree. + * + * The key is built like this: (0, BTRFS_DEV_REPLACE_KEY, 0). + */ +#define BTRFS_DEV_REPLACE_KEY 250 + +/* + * Stores items that allow to quickly map UUIDs to something else. + * + * These items are part of the filesystem UUID tree. + * The key is built like this: + * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits). + */ +#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */ +#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to + * received subvols */ + +/* + * String items are for debugging. + * + * They just store a short string of data in the FS. + */ +#define BTRFS_STRING_ITEM_KEY 253 + + + +/* 32 bytes in various csum fields */ +#define BTRFS_CSUM_SIZE 32 + +/* Csum types */ +enum btrfs_csum_type { + BTRFS_CSUM_TYPE_CRC32 = 0, + BTRFS_CSUM_TYPE_XXHASH = 1, + BTRFS_CSUM_TYPE_SHA256 = 2, + BTRFS_CSUM_TYPE_BLAKE2 = 3, +}; + +/* + * Flags definitions for directory entry item type. + * + * Used by: + * struct btrfs_dir_item.type + * + * Values 0..7 must match common file type values in fs_types.h. + */ +#define BTRFS_FT_UNKNOWN 0 +#define BTRFS_FT_REG_FILE 1 +#define BTRFS_FT_DIR 2 +#define BTRFS_FT_CHRDEV 3 +#define BTRFS_FT_BLKDEV 4 +#define BTRFS_FT_FIFO 5 +#define BTRFS_FT_SOCK 6 +#define BTRFS_FT_SYMLINK 7 +#define BTRFS_FT_XATTR 8 +#define BTRFS_FT_MAX 9 + +#define BTRFS_FSID_SIZE 16 +#define BTRFS_UUID_SIZE 16 + +/* + * The key defines the order in the tree, and so it also defines (optimal) + * block layout. + * + * Objectid and offset are interpreted based on type. + * While normally for objectid, it either represents a root number, or an + * inode number. + * + * Type tells us things about the object, and is a kind of stream selector. + * Check the following URL for full references about btrfs_disk_key/btrfs_key: + * https://btrfs.wiki.kernel.org/index.php/Btree_Items + * + * btrfs_disk_key is in disk byte order. struct btrfs_key is always + * in cpu native order. Otherwise they are identical and their sizes + * should be the same (ie both packed) + */ +struct btrfs_disk_key { + __le64 objectid; + __u8 type; + __le64 offset; +} __attribute__ ((__packed__)); + +struct btrfs_key { + __u64 objectid; + __u8 type; + __u64 offset; +} __attribute__ ((__packed__)); + +struct btrfs_dev_item { + /* The internal btrfs device id */ + __le64 devid; + + /* Size of the device */ + __le64 total_bytes; + + /* Bytes used */ + __le64 bytes_used; + + /* Optimal io alignment for this device */ + __le32 io_align; + + /* Optimal io width for this device */ + __le32 io_width; + + /* Minimal io size for this device */ + __le32 sector_size; + + /* Type and info about this device */ + __le64 type; + + /* Expected generation for this device */ + __le64 generation; + + /* + * Starting byte of this partition on the device, + * to allow for stripe alignment in the future. + */ + __le64 start_offset; + + /* Grouping information for allocation decisions */ + __le32 dev_group; + + /* Optimal seek speed 0-100 where 100 is fastest */ + __u8 seek_speed; + + /* Optimal bandwidth 0-100 where 100 is fastest */ + __u8 bandwidth; + + /* Btrfs generated uuid for this device */ + __u8 uuid[BTRFS_UUID_SIZE]; + + /* UUID of FS who owns this device */ + __u8 fsid[BTRFS_UUID_SIZE]; +} __attribute__ ((__packed__)); + +struct btrfs_stripe { + __le64 devid; + __le64 offset; + __u8 dev_uuid[BTRFS_UUID_SIZE]; +} __attribute__ ((__packed__)); + +struct btrfs_chunk { + /* Size of this chunk in bytes */ + __le64 length; + + /* Objectid of the root referencing this chunk */ + __le64 owner; + + __le64 stripe_len; + __le64 type; + + /* Optimal io alignment for this chunk */ + __le32 io_align; + + /* Optimal io width for this chunk */ + __le32 io_width; + + /* Minimal io size for this chunk */ + __le32 sector_size; + + /* + * 2^16 stripes is quite a lot, a second limit is the size of a single + * item in the btree. + */ + __le16 num_stripes; + + /* Sub stripes only matter for raid10 */ + __le16 sub_stripes; + struct btrfs_stripe stripe; + /* additional stripes go here */ +} __attribute__ ((__packed__)); + +#define BTRFS_FREE_SPACE_EXTENT 1 +#define BTRFS_FREE_SPACE_BITMAP 2 + +struct btrfs_free_space_entry { + __le64 offset; + __le64 bytes; + __u8 type; +} __attribute__ ((__packed__)); + +struct btrfs_free_space_header { + struct btrfs_disk_key location; + __le64 generation; + __le64 num_entries; + __le64 num_bitmaps; +} __attribute__ ((__packed__)); + +#define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0) +#define BTRFS_HEADER_FLAG_RELOC (1ULL << 1) + +/* Super block flags */ +/* Errors detected */ +#define BTRFS_SUPER_FLAG_ERROR (1ULL << 2) + +#define BTRFS_SUPER_FLAG_SEEDING (1ULL << 32) +#define BTRFS_SUPER_FLAG_METADUMP (1ULL << 33) +#define BTRFS_SUPER_FLAG_METADUMP_V2 (1ULL << 34) +#define BTRFS_SUPER_FLAG_CHANGING_FSID (1ULL << 35) +#define BTRFS_SUPER_FLAG_CHANGING_FSID_V2 (1ULL << 36) + + +/* + * Items in the extent tree are used to record the objectid of the + * owner of the block and the number of references. + */ +struct btrfs_extent_item { + __le64 refs; + __le64 generation; + __le64 flags; +} __attribute__ ((__packed__)); + +struct btrfs_extent_item_v0 { + __le32 refs; +} __attribute__ ((__packed__)); + + +#define BTRFS_EXTENT_FLAG_DATA (1ULL << 0) +#define BTRFS_EXTENT_FLAG_TREE_BLOCK (1ULL << 1) + +/* Use full backrefs for extent pointers in the block */ +#define BTRFS_BLOCK_FLAG_FULL_BACKREF (1ULL << 8) + +/* + * This flag is only used internally by scrub and may be changed at any time + * it is only declared here to avoid collisions. + */ +#define BTRFS_EXTENT_FLAG_SUPER (1ULL << 48) + +struct btrfs_tree_block_info { + struct btrfs_disk_key key; + __u8 level; +} __attribute__ ((__packed__)); + +struct btrfs_extent_data_ref { + __le64 root; + __le64 objectid; + __le64 offset; + __le32 count; +} __attribute__ ((__packed__)); + +struct btrfs_shared_data_ref { + __le32 count; +} __attribute__ ((__packed__)); + +struct btrfs_extent_inline_ref { + __u8 type; + __le64 offset; +} __attribute__ ((__packed__)); + +/* Old style backrefs item */ +struct btrfs_extent_ref_v0 { + __le64 root; + __le64 generation; + __le64 objectid; + __le32 count; +} __attribute__ ((__packed__)); + + +/* Dev extents record used space on individual devices. + * + * The owner field points back to the chunk allocation mapping tree that + * allocated the extent. + * The chunk tree uuid field is a way to double check the owner. + */ +struct btrfs_dev_extent { + __le64 chunk_tree; + __le64 chunk_objectid; + __le64 chunk_offset; + __le64 length; + __u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; +} __attribute__ ((__packed__)); + +struct btrfs_inode_ref { + __le64 index; + __le16 name_len; + /* Name goes here */ +} __attribute__ ((__packed__)); + +struct btrfs_inode_extref { + __le64 parent_objectid; + __le64 index; + __le16 name_len; + __u8 name[0]; + /* Name goes here */ +} __attribute__ ((__packed__)); + +struct btrfs_timespec { + __le64 sec; + __le32 nsec; +} __attribute__ ((__packed__)); + +/* Inode flags */ +#define BTRFS_INODE_NODATASUM (1 << 0) +#define BTRFS_INODE_NODATACOW (1 << 1) +#define BTRFS_INODE_READONLY (1 << 2) +#define BTRFS_INODE_NOCOMPRESS (1 << 3) +#define BTRFS_INODE_PREALLOC (1 << 4) +#define BTRFS_INODE_SYNC (1 << 5) +#define BTRFS_INODE_IMMUTABLE (1 << 6) +#define BTRFS_INODE_APPEND (1 << 7) +#define BTRFS_INODE_NODUMP (1 << 8) +#define BTRFS_INODE_NOATIME (1 << 9) +#define BTRFS_INODE_DIRSYNC (1 << 10) +#define BTRFS_INODE_COMPRESS (1 << 11) + +#define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31) + +#define BTRFS_INODE_FLAG_MASK \ + (BTRFS_INODE_NODATASUM | \ + BTRFS_INODE_NODATACOW | \ + BTRFS_INODE_READONLY | \ + BTRFS_INODE_NOCOMPRESS | \ + BTRFS_INODE_PREALLOC | \ + BTRFS_INODE_SYNC | \ + BTRFS_INODE_IMMUTABLE | \ + BTRFS_INODE_APPEND | \ + BTRFS_INODE_NODUMP | \ + BTRFS_INODE_NOATIME | \ + BTRFS_INODE_DIRSYNC | \ + BTRFS_INODE_COMPRESS | \ + BTRFS_INODE_ROOT_ITEM_INIT) + +struct btrfs_inode_item { + /* Nfs style generation number */ + __le64 generation; + /* Transid that last touched this inode */ + __le64 transid; + __le64 size; + __le64 nbytes; + __le64 block_group; + __le32 nlink; + __le32 uid; + __le32 gid; + __le32 mode; + __le64 rdev; + __le64 flags; + + /* Modification sequence number for NFS */ + __le64 sequence; + + /* + * A little future expansion, for more than this we can just grow the + * inode item and version it + */ + __le64 reserved[4]; + struct btrfs_timespec atime; + struct btrfs_timespec ctime; + struct btrfs_timespec mtime; + struct btrfs_timespec otime; +} __attribute__ ((__packed__)); + +struct btrfs_dir_log_item { + __le64 end; +} __attribute__ ((__packed__)); + +struct btrfs_dir_item { + struct btrfs_disk_key location; + __le64 transid; + __le16 data_len; + __le16 name_len; + __u8 type; +} __attribute__ ((__packed__)); + +#define BTRFS_ROOT_SUBVOL_RDONLY (1ULL << 0) + +/* + * Internal in-memory flag that a subvolume has been marked for deletion but + * still visible as a directory + */ +#define BTRFS_ROOT_SUBVOL_DEAD (1ULL << 48) + +struct btrfs_root_item { + struct btrfs_inode_item inode; + __le64 generation; + __le64 root_dirid; + __le64 bytenr; + __le64 byte_limit; + __le64 bytes_used; + __le64 last_snapshot; + __le64 flags; + __le32 refs; + struct btrfs_disk_key drop_progress; + __u8 drop_level; + __u8 level; + + /* + * The following fields appear after subvol_uuids+subvol_times + * were introduced. + */ + + /* + * This generation number is used to test if the new fields are valid + * and up to date while reading the root item. Every time the root item + * is written out, the "generation" field is copied into this field. If + * anyone ever mounted the fs with an older kernel, we will have + * mismatching generation values here and thus must invalidate the + * new fields. See btrfs_update_root and btrfs_find_last_root for + * details. + * The offset of generation_v2 is also used as the start for the memset + * when invalidating the fields. + */ + __le64 generation_v2; + __u8 uuid[BTRFS_UUID_SIZE]; + __u8 parent_uuid[BTRFS_UUID_SIZE]; + __u8 received_uuid[BTRFS_UUID_SIZE]; + __le64 ctransid; /* Updated when an inode changes */ + __le64 otransid; /* Trans when created */ + __le64 stransid; /* Trans when sent. Non-zero for received subvol. */ + __le64 rtransid; /* Trans when received. Non-zero for received subvol.*/ + struct btrfs_timespec ctime; + struct btrfs_timespec otime; + struct btrfs_timespec stime; + struct btrfs_timespec rtime; + __le64 reserved[8]; /* For future */ +} __attribute__ ((__packed__)); + +/* This is used for both forward and backward root refs */ +struct btrfs_root_ref { + __le64 dirid; + __le64 sequence; + __le16 name_len; +} __attribute__ ((__packed__)); + +struct btrfs_disk_balance_args { + /* + * Profiles to operate on. + * + * SINGLE is denoted by BTRFS_AVAIL_ALLOC_BIT_SINGLE. + */ + __le64 profiles; + + /* + * Usage filter + * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N' + * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max + */ + union { + __le64 usage; + struct { + __le32 usage_min; + __le32 usage_max; + }; + }; + + /* Devid filter */ + __le64 devid; + + /* Devid subset filter [pstart..pend) */ + __le64 pstart; + __le64 pend; + + /* Btrfs virtual address space subset filter [vstart..vend) */ + __le64 vstart; + __le64 vend; + + /* + * Profile to convert to. + * + * SINGLE is denoted by BTRFS_AVAIL_ALLOC_BIT_SINGLE. + */ + __le64 target; + + /* BTRFS_BALANCE_ARGS_* */ + __le64 flags; + + /* + * BTRFS_BALANCE_ARGS_LIMIT with value 'limit'. + * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum + * and maximum. + */ + union { + __le64 limit; + struct { + __le32 limit_min; + __le32 limit_max; + }; + }; + + /* + * Process chunks that cross stripes_min..stripes_max devices, + * BTRFS_BALANCE_ARGS_STRIPES_RANGE. + */ + __le32 stripes_min; + __le32 stripes_max; + + __le64 unused[6]; +} __attribute__ ((__packed__)); + +/* + * Stores balance parameters to disk so that balance can be properly + * resumed after crash or unmount. + */ +struct btrfs_balance_item { + /* BTRFS_BALANCE_* */ + __le64 flags; + + struct btrfs_disk_balance_args data; + struct btrfs_disk_balance_args meta; + struct btrfs_disk_balance_args sys; + + __le64 unused[4]; +} __attribute__ ((__packed__)); + +enum { + BTRFS_FILE_EXTENT_INLINE = 0, + BTRFS_FILE_EXTENT_REG = 1, + BTRFS_FILE_EXTENT_PREALLOC = 2, + BTRFS_NR_FILE_EXTENT_TYPES = 3, +}; + +enum btrfs_compression_type { + BTRFS_COMPRESS_NONE = 0, + BTRFS_COMPRESS_ZLIB = 1, + BTRFS_COMPRESS_LZO = 2, + BTRFS_COMPRESS_ZSTD = 3, + BTRFS_NR_COMPRESS_TYPES = 4, +}; + +struct btrfs_file_extent_item { + /* Transaction id that created this extent */ + __le64 generation; + /* + * Max number of bytes to hold this extent in ram. + * + * When we split a compressed extent we can't know how big each of the + * resulting pieces will be. So, this is an upper limit on the size of + * the extent in ram instead of an exact limit. + */ + __le64 ram_bytes; + + /* + * 32 bits for the various ways we might encode the data, + * including compression and encryption. If any of these + * are set to something a given disk format doesn't understand + * it is treated like an incompat flag for reading and writing, + * but not for stat. + */ + __u8 compression; + __u8 encryption; + __le16 other_encoding; /* Spare for later use */ + + /* Are we inline data or a real extent? */ + __u8 type; + + /* + * Disk space consumed by the extent, checksum blocks are not included + * in these numbers + * + * At this offset in the structure, the inline extent data start. + */ + __le64 disk_bytenr; + __le64 disk_num_bytes; + + /* + * The logical offset inside the file extent. + * + * This allows a file extent to point into the middle of an existing + * extent on disk, sharing it between two snapshots (useful if some + * bytes in the middle of the extent have changed). + */ + __le64 offset; + + /* + * The logical number of bytes this file extent is referencing (no + * csums included). + * + * This always reflects the size uncompressed and without encoding. + */ + __le64 num_bytes; + +} __attribute__ ((__packed__)); + +struct btrfs_csum_item { + __u8 csum; +} __attribute__ ((__packed__)); + +enum btrfs_dev_stat_values { + /* Disk I/O failure stats */ + BTRFS_DEV_STAT_WRITE_ERRS, /* EIO or EREMOTEIO from lower layers */ + BTRFS_DEV_STAT_READ_ERRS, /* EIO or EREMOTEIO from lower layers */ + BTRFS_DEV_STAT_FLUSH_ERRS, /* EIO or EREMOTEIO from lower layers */ + + /* Stats for indirect indications for I/O failures */ + BTRFS_DEV_STAT_CORRUPTION_ERRS, /* Checksum error, bytenr error or + * contents is illegal: this is an + * indication that the block was damaged + * during read or write, or written to + * wrong location or read from wrong + * location */ + BTRFS_DEV_STAT_GENERATION_ERRS, /* An indication that blocks have not + * been written */ + + BTRFS_DEV_STAT_VALUES_MAX +}; + +struct btrfs_dev_stats_item { + /* + * Grow this item struct at the end for future enhancements and keep + * the existing values unchanged. + */ + __le64 values[BTRFS_DEV_STAT_VALUES_MAX]; +} __attribute__ ((__packed__)); + +#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS 0 +#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_AVOID 1 + +struct btrfs_dev_replace_item { + /* + * Grow this item struct at the end for future enhancements and keep + * the existing values unchanged. + */ + __le64 src_devid; + __le64 cursor_left; + __le64 cursor_right; + __le64 cont_reading_from_srcdev_mode; + + __le64 replace_state; + __le64 time_started; + __le64 time_stopped; + __le64 num_write_errors; + __le64 num_uncorrectable_read_errors; +} __attribute__ ((__packed__)); + +/* Different types of block groups (and chunks) */ +#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0) +#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1) +#define BTRFS_BLOCK_GROUP_METADATA (1ULL << 2) +#define BTRFS_BLOCK_GROUP_RAID0 (1ULL << 3) +#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4) +#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5) +#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6) +#define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7) +#define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8) +#define BTRFS_BLOCK_GROUP_RAID1C3 (1ULL << 9) +#define BTRFS_BLOCK_GROUP_RAID1C4 (1ULL << 10) +#define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ + BTRFS_SPACE_INFO_GLOBAL_RSV) + +enum btrfs_raid_types { + BTRFS_RAID_RAID10, + BTRFS_RAID_RAID1, + BTRFS_RAID_DUP, + BTRFS_RAID_RAID0, + BTRFS_RAID_SINGLE, + BTRFS_RAID_RAID5, + BTRFS_RAID_RAID6, + BTRFS_RAID_RAID1C3, + BTRFS_RAID_RAID1C4, + BTRFS_NR_RAID_TYPES +}; + +#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ + BTRFS_BLOCK_GROUP_SYSTEM | \ + BTRFS_BLOCK_GROUP_METADATA) + +#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \ + BTRFS_BLOCK_GROUP_RAID1 | \ + BTRFS_BLOCK_GROUP_RAID1C3 | \ + BTRFS_BLOCK_GROUP_RAID1C4 | \ + BTRFS_BLOCK_GROUP_RAID5 | \ + BTRFS_BLOCK_GROUP_RAID6 | \ + BTRFS_BLOCK_GROUP_DUP | \ + BTRFS_BLOCK_GROUP_RAID10) +#define BTRFS_BLOCK_GROUP_RAID56_MASK (BTRFS_BLOCK_GROUP_RAID5 | \ + BTRFS_BLOCK_GROUP_RAID6) + +#define BTRFS_BLOCK_GROUP_RAID1_MASK (BTRFS_BLOCK_GROUP_RAID1 | \ + BTRFS_BLOCK_GROUP_RAID1C3 | \ + BTRFS_BLOCK_GROUP_RAID1C4) + +/* + * We need a bit for restriper to be able to tell when chunks of type + * SINGLE are available. This "extended" profile format is used in + * fs_info->avail_*_alloc_bits (in-memory) and balance item fields + * (on-disk). The corresponding on-disk bit in chunk.type is reserved + * to avoid remappings between two formats in future. + */ +#define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48) + +/* + * A fake block group type that is used to communicate global block reserve + * size to userspace via the SPACE_INFO ioctl. + */ +#define BTRFS_SPACE_INFO_GLOBAL_RSV (1ULL << 49) + +#define BTRFS_EXTENDED_PROFILE_MASK (BTRFS_BLOCK_GROUP_PROFILE_MASK | \ + BTRFS_AVAIL_ALLOC_BIT_SINGLE) + +static inline __u64 chunk_to_extended(__u64 flags) +{ + if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0) + flags |= BTRFS_AVAIL_ALLOC_BIT_SINGLE; + + return flags; +} +static inline __u64 extended_to_chunk(__u64 flags) +{ + return flags & ~BTRFS_AVAIL_ALLOC_BIT_SINGLE; +} + +struct btrfs_block_group_item { + __le64 used; + __le64 chunk_objectid; + __le64 flags; +} __attribute__ ((__packed__)); + +struct btrfs_free_space_info { + __le32 extent_count; + __le32 flags; +} __attribute__ ((__packed__)); + +#define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0) + +#define BTRFS_QGROUP_LEVEL_SHIFT 48 +static inline __u64 btrfs_qgroup_level(__u64 qgroupid) +{ + return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT; +} + +/* Is subvolume quota turned on? */ +#define BTRFS_QGROUP_STATUS_FLAG_ON (1ULL << 0) + +/* Is qgroup rescan running? */ +#define BTRFS_QGROUP_STATUS_FLAG_RESCAN (1ULL << 1) + +/* + * Some qgroup entries are known to be out of date, either because the + * configuration has changed in a way that makes a rescan necessary, or + * because the fs has been mounted with a non-qgroup-aware version. + */ +#define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1ULL << 2) + +#define BTRFS_QGROUP_STATUS_VERSION 1 + +struct btrfs_qgroup_status_item { + __le64 version; + /* + * The generation is updated during every commit. As older + * versions of btrfs are not aware of qgroups, it will be + * possible to detect inconsistencies by checking the + * generation on mount time. + */ + __le64 generation; + + /* Flag definitions see above */ + __le64 flags; + + /* + * Only used during scanning to record the progress of the scan. + * It contains a logical address. + */ + __le64 rescan; +} __attribute__ ((__packed__)); + +struct btrfs_qgroup_info_item { + __le64 generation; + __le64 rfer; + __le64 rfer_cmpr; + __le64 excl; + __le64 excl_cmpr; +} __attribute__ ((__packed__)); + +/* + * Flags definition for qgroup limits + * + * Used by: + * struct btrfs_qgroup_limit.flags + * struct btrfs_qgroup_limit_item.flags + */ +#define BTRFS_QGROUP_LIMIT_MAX_RFER (1ULL << 0) +#define BTRFS_QGROUP_LIMIT_MAX_EXCL (1ULL << 1) +#define BTRFS_QGROUP_LIMIT_RSV_RFER (1ULL << 2) +#define BTRFS_QGROUP_LIMIT_RSV_EXCL (1ULL << 3) +#define BTRFS_QGROUP_LIMIT_RFER_CMPR (1ULL << 4) +#define BTRFS_QGROUP_LIMIT_EXCL_CMPR (1ULL << 5) + +struct btrfs_qgroup_limit_item { + /* Only updated when any of the other values change. */ + __le64 flags; + __le64 max_rfer; + __le64 max_excl; + __le64 rsv_rfer; + __le64 rsv_excl; +} __attribute__ ((__packed__)); + +/* + * Just in case we somehow lose the roots and are not able to mount, + * we store an array of the roots from previous transactions in the super. + */ +#define BTRFS_NUM_BACKUP_ROOTS 4 +struct btrfs_root_backup { + __le64 tree_root; + __le64 tree_root_gen; + + __le64 chunk_root; + __le64 chunk_root_gen; + + __le64 extent_root; + __le64 extent_root_gen; + + __le64 fs_root; + __le64 fs_root_gen; + + __le64 dev_root; + __le64 dev_root_gen; + + __le64 csum_root; + __le64 csum_root_gen; + + __le64 total_bytes; + __le64 bytes_used; + __le64 num_devices; + /* future */ + __le64 unused_64[4]; + + u8 tree_root_level; + u8 chunk_root_level; + u8 extent_root_level; + u8 fs_root_level; + u8 dev_root_level; + u8 csum_root_level; + /* future and to align */ + u8 unused_8[10]; +} __attribute__ ((__packed__)); + +/* + * This is a very generous portion of the super block, giving us room to + * translate 14 chunks with 3 stripes each. + */ +#define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048 + +#define BTRFS_LABEL_SIZE 256 + +/* The super block basically lists the main trees of the FS. */ +struct btrfs_super_block { + /* The first 4 fields must match struct btrfs_header */ + u8 csum[BTRFS_CSUM_SIZE]; + /* FS specific UUID, visible to user */ + u8 fsid[BTRFS_FSID_SIZE]; + __le64 bytenr; /* this block number */ + __le64 flags; + + /* Allowed to be different from the btrfs_header from here own down. */ + __le64 magic; + __le64 generation; + __le64 root; + __le64 chunk_root; + __le64 log_root; + + /* This will help find the new super based on the log root. */ + __le64 log_root_transid; + __le64 total_bytes; + __le64 bytes_used; + __le64 root_dir_objectid; + __le64 num_devices; + __le32 sectorsize; + __le32 nodesize; + __le32 __unused_leafsize; + __le32 stripesize; + __le32 sys_chunk_array_size; + __le64 chunk_root_generation; + __le64 compat_flags; + __le64 compat_ro_flags; + __le64 incompat_flags; + __le16 csum_type; + u8 root_level; + u8 chunk_root_level; + u8 log_root_level; + struct btrfs_dev_item dev_item; + + char label[BTRFS_LABEL_SIZE]; + + __le64 cache_generation; + __le64 uuid_tree_generation; + + /* The UUID written into btree blocks */ + u8 metadata_uuid[BTRFS_FSID_SIZE]; + + /* Future expansion */ + __le64 reserved[28]; + u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; + struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; +} __attribute__ ((__packed__)); + +/* + * Feature flags + * + * Used by: + * struct btrfs_super_block::(compat|compat_ro|incompat)_flags + * struct btrfs_ioctl_feature_flags + */ +#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0) + +/* + * Older kernels (< 4.9) on big-endian systems produced broken free space tree + * bitmaps, and btrfs-progs also used to corrupt the free space tree (versions + * < 4.7.3). If this bit is clear, then the free space tree cannot be trusted. + * btrfs-progs can also intentionally clear this bit to ask the kernel to + * rebuild the free space tree, however this might not work on older kernels + * that do not know about this bit. If not sure, clear the cache manually on + * first mount when booting older kernel versions. + */ +#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID (1ULL << 1) + +#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0) +#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1) +#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2) +#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO (1ULL << 3) +#define BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD (1ULL << 4) + +/* + * Older kernels tried to do bigger metadata blocks, but the + * code was pretty buggy. Lets not let them try anymore. + */ +#define BTRFS_FEATURE_INCOMPAT_BIG_METADATA (1ULL << 5) + +#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF (1ULL << 6) +#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7) +#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8) +#define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9) +#define BTRFS_FEATURE_INCOMPAT_METADATA_UUID (1ULL << 10) +#define BTRFS_FEATURE_INCOMPAT_RAID1C34 (1ULL << 11) + +/* + * Compat flags that we support. + * + * If any incompat flags are set other than the ones specified below then we + * will fail to mount. + */ +#define BTRFS_FEATURE_COMPAT_SUPP 0ULL +#define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL +#define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL + +#define BTRFS_FEATURE_COMPAT_RO_SUPP \ + (BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE | \ + BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID) + +#define BTRFS_FEATURE_COMPAT_RO_SAFE_SET 0ULL +#define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR 0ULL + +#define BTRFS_FEATURE_INCOMPAT_SUPP \ + (BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF | \ + BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL | \ + BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS | \ + BTRFS_FEATURE_INCOMPAT_BIG_METADATA | \ + BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \ + BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD | \ + BTRFS_FEATURE_INCOMPAT_RAID56 | \ + BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \ + BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ + BTRFS_FEATURE_INCOMPAT_NO_HOLES | \ + BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \ + BTRFS_FEATURE_INCOMPAT_RAID1C34) + +#define BTRFS_FEATURE_INCOMPAT_SAFE_SET \ + (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) +#define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL + +#define BTRFS_BACKREF_REV_MAX 256 +#define BTRFS_BACKREF_REV_SHIFT 56 +#define BTRFS_BACKREF_REV_MASK (((u64)BTRFS_BACKREF_REV_MAX - 1) << \ + BTRFS_BACKREF_REV_SHIFT) + +#define BTRFS_OLD_BACKREF_REV 0 +#define BTRFS_MIXED_BACKREF_REV 1 + +#define BTRFS_MAX_LEVEL 8 + +/* Every tree block (leaf or node) starts with this header. */ +struct btrfs_header { + /* These first four must match the super block */ + u8 csum[BTRFS_CSUM_SIZE]; + u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */ + __le64 bytenr; /* Which block this node is supposed to live in */ + __le64 flags; + + /* Allowed to be different from the super from here on down. */ + u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; + __le64 generation; + __le64 owner; + __le32 nritems; + u8 level; +} __attribute__ ((__packed__)); + +/* + * A leaf is full of items. Offset and size tell us where to find + * the item in the leaf (relative to the start of the data area). + */ +struct btrfs_item { + struct btrfs_disk_key key; + __le32 offset; + __le32 size; +} __attribute__ ((__packed__)); + +/* + * leaves have an item area and a data area: + * [item0, item1....itemN] [free space] [dataN...data1, data0] + * + * The data is separate from the items to get the keys closer together + * during searches. + */ +struct btrfs_leaf { + struct btrfs_header header; + struct btrfs_item items[]; +} __attribute__ ((__packed__)); + +/* + * All non-leaf blocks are nodes, they hold only keys and pointers to children + * blocks. + */ +struct btrfs_key_ptr { + struct btrfs_disk_key key; + __le64 blockptr; + __le64 generation; +} __attribute__ ((__packed__)); + +struct btrfs_node { + struct btrfs_header header; + struct btrfs_key_ptr ptrs[]; +} __attribute__ ((__packed__)); + +#endif /* __BTRFS_TREE_H__ */ diff --git a/fs/btrfs/root.c b/fs/btrfs/root.c index 127b67fd1c..61155e8918 100644 --- a/fs/btrfs/root.c +++ b/fs/btrfs/root.c @@ -75,7 +75,7 @@ u64 btrfs_lookup_root_ref(u64 subvolid, struct btrfs_root_ref *refp, char *name) *refp = *ref;

if (name) { - if (ref->name_len > BTRFS_VOL_NAME_MAX) { + if (ref->name_len > BTRFS_NAME_LEN) { printf("%s: volume name too long: %u\n", __func__, ref->name_len); goto out; diff --git a/fs/btrfs/subvolume.c b/fs/btrfs/subvolume.c index 06e54f3310..dbe92d13cb 100644 --- a/fs/btrfs/subvolume.c +++ b/fs/btrfs/subvolume.c @@ -14,7 +14,7 @@ static int get_subvol_name(u64 subvolid, char *name, int max_len) struct btrfs_inode_ref iref; struct btrfs_root root; u64 dir; - char tmp[max(BTRFS_VOL_NAME_MAX, BTRFS_NAME_MAX)]; + char tmp[BTRFS_NAME_LEN]; char *ptr;

ptr = name + max_len - 1;

From: Qu Wenruo wqu@suse.com

This patch uses generic code from btrfs-progs to read one super block from block device.

To support the btrfs-progs coding style, the following is also crossported: - BTRFS_SETGET_FUNC for btrfs_super_block - btrfs_check_super() function - Move btrfs_read_superblock() to disk-io.[ch] Since super.c only contains pretty small amount of code, and the extra check will be covered in later root read patches.

Differences between this implementation and btrfs-progs: - No sbflags/sb_bytenr support Since we only need to read the primary super block (like kernel), sbflags/sb_bytenr used by super block recovery is not needed.

This also changes the following behavior of U-Boot btrfs: - Only reads the primary super block The old implementation reads all 3 super blocks, and also one non-existing backup. This is not correct, especially if there is another filesystem created on the device but old superblocks are not rewritten.

Just like kernel, we only check the primary super block.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/Makefile | 2 +- fs/btrfs/btrfs.c | 1 + fs/btrfs/compat.h | 63 +++++++++++ fs/btrfs/ctree.c | 32 ++++++ fs/btrfs/ctree.h | 67 ++++++++++++ fs/btrfs/disk-io.c | 213 +++++++++++++++++++++++++++++++++++++ fs/btrfs/disk-io.h | 7 ++ fs/btrfs/super.c | 258 --------------------------------------------- 8 files changed, 384 insertions(+), 259 deletions(-) create mode 100644 fs/btrfs/compat.h delete mode 100644 fs/btrfs/super.c

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 84b3b5ec0e..bd4b848d1b 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -3,4 +3,4 @@ # 2017 Marek Behun, CZ.NIC, marek.behun@nic.cz

obj-y := btrfs.o chunk-map.o compression.o ctree.o dev.o dir-item.o \ - extent-io.o inode.o root.o subvolume.o super.o crypto/hash.o disk-io.o + extent-io.o inode.o root.o subvolume.o crypto/hash.o disk-io.o diff --git a/fs/btrfs/btrfs.c b/fs/btrfs/btrfs.c index d5a87c175c..78a32497b5 100644 --- a/fs/btrfs/btrfs.c +++ b/fs/btrfs/btrfs.c @@ -11,6 +11,7 @@ #include <linux/time.h> #include "btrfs.h" #include "crypto/hash.h" +#include "disk-io.h"

struct btrfs_info btrfs_info;

diff --git a/fs/btrfs/compat.h b/fs/btrfs/compat.h new file mode 100644 index 0000000000..e7d7dc9f6e --- /dev/null +++ b/fs/btrfs/compat.h @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#ifndef __BTRFS_COMPAT_H__ +#define __BTRFS_COMPAT_H__ + +#include <linux/errno.h> +#include <fs_internal.h> +#include <uuid.h> + +/* Provide a compatibility layer to make code syncing easier */ + +/* A simple wraper to for error() used in btrfs-progs */ +__attribute__((format (__printf__, 1, 2))) +static inline void error(const char *fmt, ...) +{ + printf("BTRFS: "); + printf(fmt, __builtin_va_arg_pack()); + printf("\n"); +} + +#define BTRFS_UUID_UNPARSED_SIZE 37 + +/* + * Macros to generate set/get funcs for the struct fields + * assume there is a lefoo_to_cpu for every type, so lets make a simple + * one for u8: + */ +#define le8_to_cpu(v) (v) +#define cpu_to_le8(v) (v) +#define __le8 u8 + +/* + * Read data from device specified by @desc and @part + * + * U-boot equivalent of pread(). + * + * Return the bytes of data read. + * Return <0 for error. + */ +static inline int __btrfs_devread(struct blk_desc *desc, + struct disk_partition *part, + void *buf, size_t size, u64 offset) +{ + lbaint_t sector; + int byte_offset; + int ret; + + sector = offset >> desc->log2blksz; + byte_offset = offset % desc->blksz; + + /* fs_devread() return 0 for error, >0 for success */ + ret = fs_devread(desc, part, sector, byte_offset, size, buf); + if (!ret) + return -EIO; + return size; +} + +static inline void uuid_unparse(const u8 *uuid, char *out) +{ + return uuid_bin_to_str((unsigned char *)uuid, out, 0); +} + +#endif diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 28f98d43ad..1d8f7e168f 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -10,6 +10,38 @@ #include <malloc.h> #include <memalign.h>

+static const struct btrfs_csum { + u16 size; + const char name[14]; +} btrfs_csums[] = { + [BTRFS_CSUM_TYPE_CRC32] = { 4, "crc32c" }, + [BTRFS_CSUM_TYPE_XXHASH] = { 8, "xxhash64" }, + [BTRFS_CSUM_TYPE_SHA256] = { 32, "sha256" }, + [BTRFS_CSUM_TYPE_BLAKE2] = { 32, "blake2" }, +}; + +u16 btrfs_super_csum_size(const struct btrfs_super_block *sb) +{ + const u16 csum_type = btrfs_super_csum_type(sb); + + return btrfs_csums[csum_type].size; +} + +const char *btrfs_super_csum_name(u16 csum_type) +{ + return btrfs_csums[csum_type].name; +} + +size_t btrfs_super_num_csums(void) +{ + return ARRAY_SIZE(btrfs_csums); +} + +u16 btrfs_csum_type_size(u16 csum_type) +{ + return btrfs_csums[csum_type].size; +} + int btrfs_comp_keys(struct btrfs_key *a, struct btrfs_key *b) { if (a->objectid > b->objectid) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 156ce69ed0..02125e5e10 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -12,6 +12,7 @@ #include <common.h> #include <compiler.h> #include "kernel-shared/btrfs_tree.h" +#include "compat.h"

#define BTRFS_MAX_MIRRORS 3

@@ -47,6 +48,16 @@ #define BTRFS_FS_STATE_DEV_REPLACING 3 #define BTRFS_FS_STATE_DUMMY_FS_INFO 4

+#define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \ +static inline u##bits btrfs_##name(const type *s) \ +{ \ + return le##bits##_to_cpu(s->member); \ +} \ +static inline void btrfs_set_##name(type *s, u##bits val) \ +{ \ + s->member = cpu_to_le##bits(val); \ +} + union btrfs_tree_node { struct btrfs_header header; struct btrfs_leaf leaf; @@ -122,4 +133,60 @@ static inline void *btrfs_path_leaf_data(struct btrfs_path *p) #define btrfs_path_item_ptr(p,t) \ ((t *) btrfs_path_leaf_data((p)))

+u16 btrfs_super_csum_size(const struct btrfs_super_block *s); +const char *btrfs_super_csum_name(u16 csum_type); +u16 btrfs_csum_type_size(u16 csum_type); +size_t btrfs_super_num_csums(void); + +/* struct btrfs_super_block */ + +BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64); +BTRFS_SETGET_STACK_FUNCS(super_flags, struct btrfs_super_block, flags, 64); +BTRFS_SETGET_STACK_FUNCS(super_generation, struct btrfs_super_block, + generation, 64); +BTRFS_SETGET_STACK_FUNCS(super_root, struct btrfs_super_block, root, 64); +BTRFS_SETGET_STACK_FUNCS(super_sys_array_size, + struct btrfs_super_block, sys_chunk_array_size, 32); +BTRFS_SETGET_STACK_FUNCS(super_chunk_root_generation, + struct btrfs_super_block, chunk_root_generation, 64); +BTRFS_SETGET_STACK_FUNCS(super_root_level, struct btrfs_super_block, + root_level, 8); +BTRFS_SETGET_STACK_FUNCS(super_chunk_root, struct btrfs_super_block, + chunk_root, 64); +BTRFS_SETGET_STACK_FUNCS(super_chunk_root_level, struct btrfs_super_block, + chunk_root_level, 8); +BTRFS_SETGET_STACK_FUNCS(super_log_root, struct btrfs_super_block, + log_root, 64); +BTRFS_SETGET_STACK_FUNCS(super_log_root_transid, struct btrfs_super_block, + log_root_transid, 64); +BTRFS_SETGET_STACK_FUNCS(super_log_root_level, struct btrfs_super_block, + log_root_level, 8); +BTRFS_SETGET_STACK_FUNCS(super_total_bytes, struct btrfs_super_block, + total_bytes, 64); +BTRFS_SETGET_STACK_FUNCS(super_bytes_used, struct btrfs_super_block, + bytes_used, 64); +BTRFS_SETGET_STACK_FUNCS(super_sectorsize, struct btrfs_super_block, + sectorsize, 32); +BTRFS_SETGET_STACK_FUNCS(super_nodesize, struct btrfs_super_block, + nodesize, 32); +BTRFS_SETGET_STACK_FUNCS(super_stripesize, struct btrfs_super_block, + stripesize, 32); +BTRFS_SETGET_STACK_FUNCS(super_root_dir, struct btrfs_super_block, + root_dir_objectid, 64); +BTRFS_SETGET_STACK_FUNCS(super_num_devices, struct btrfs_super_block, + num_devices, 64); +BTRFS_SETGET_STACK_FUNCS(super_compat_flags, struct btrfs_super_block, + compat_flags, 64); +BTRFS_SETGET_STACK_FUNCS(super_compat_ro_flags, struct btrfs_super_block, + compat_ro_flags, 64); +BTRFS_SETGET_STACK_FUNCS(super_incompat_flags, struct btrfs_super_block, + incompat_flags, 64); +BTRFS_SETGET_STACK_FUNCS(super_csum_type, struct btrfs_super_block, + csum_type, 16); +BTRFS_SETGET_STACK_FUNCS(super_cache_generation, struct btrfs_super_block, + cache_generation, 64); +BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block, + uuid_tree_generation, 64); +BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64); + #endif /* __BTRFS_CTREE_H__ */ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 58c32b548e..edebf741fd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1,7 +1,12 @@ // SPDX-License-Identifier: GPL-2.0+ #include <common.h> #include <fs_internal.h> +#include <uuid.h> +#include <memalign.h> +#include "kernel-shared/btrfs_tree.h" #include "disk-io.h" +#include "ctree.h" +#include "btrfs.h" #include "crypto/hash.h"

int btrfs_csum_data(u16 csum_type, const u8 *data, u8 *out, size_t len) @@ -20,3 +25,211 @@ int btrfs_csum_data(u16 csum_type, const u8 *data, u8 *out, size_t len) return -EINVAL; } } + +/* + * Check if the super is valid: + * - nodesize/sectorsize - minimum, maximum, alignment + * - tree block starts - alignment + * - number of devices - something sane + * - sys array size - maximum + */ +static int btrfs_check_super(struct btrfs_super_block *sb) +{ + u8 result[BTRFS_CSUM_SIZE]; + u16 csum_type; + int csum_size; + u8 *metadata_uuid; + + if (btrfs_super_magic(sb) != BTRFS_MAGIC) + return -EIO; + + csum_type = btrfs_super_csum_type(sb); + if (csum_type >= btrfs_super_num_csums()) { + error("unsupported checksum algorithm %u", csum_type); + return -EIO; + } + csum_size = btrfs_super_csum_size(sb); + + btrfs_csum_data(csum_type, (u8 *)sb + BTRFS_CSUM_SIZE, + result, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); + + if (memcmp(result, sb->csum, csum_size)) { + error("superblock checksum mismatch"); + return -EIO; + } + if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) { + error("tree_root level too big: %d >= %d", + btrfs_super_root_level(sb), BTRFS_MAX_LEVEL); + goto error_out; + } + if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) { + error("chunk_root level too big: %d >= %d", + btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL); + goto error_out; + } + if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) { + error("log_root level too big: %d >= %d", + btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL); + goto error_out; + } + + if (!IS_ALIGNED(btrfs_super_root(sb), 4096)) { + error("tree_root block unaligned: %llu", btrfs_super_root(sb)); + goto error_out; + } + if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096)) { + error("chunk_root block unaligned: %llu", + btrfs_super_chunk_root(sb)); + goto error_out; + } + if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096)) { + error("log_root block unaligned: %llu", + btrfs_super_log_root(sb)); + goto error_out; + } + if (btrfs_super_nodesize(sb) < 4096) { + error("nodesize too small: %u < 4096", + btrfs_super_nodesize(sb)); + goto error_out; + } + if (!IS_ALIGNED(btrfs_super_nodesize(sb), 4096)) { + error("nodesize unaligned: %u", btrfs_super_nodesize(sb)); + goto error_out; + } + if (btrfs_super_sectorsize(sb) < 4096) { + error("sectorsize too small: %u < 4096", + btrfs_super_sectorsize(sb)); + goto error_out; + } + if (!IS_ALIGNED(btrfs_super_sectorsize(sb), 4096)) { + error("sectorsize unaligned: %u", btrfs_super_sectorsize(sb)); + goto error_out; + } + if (btrfs_super_total_bytes(sb) == 0) { + error("invalid total_bytes 0"); + goto error_out; + } + if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) { + error("invalid bytes_used %llu", btrfs_super_bytes_used(sb)); + goto error_out; + } + if ((btrfs_super_stripesize(sb) != 4096) + && (btrfs_super_stripesize(sb) != btrfs_super_sectorsize(sb))) { + error("invalid stripesize %u", btrfs_super_stripesize(sb)); + goto error_out; + } + + if (btrfs_super_incompat_flags(sb) & BTRFS_FEATURE_INCOMPAT_METADATA_UUID) + metadata_uuid = sb->metadata_uuid; + else + metadata_uuid = sb->fsid; + + if (memcmp(metadata_uuid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) { + char fsid[BTRFS_UUID_UNPARSED_SIZE]; + char dev_fsid[BTRFS_UUID_UNPARSED_SIZE]; + + uuid_unparse(sb->metadata_uuid, fsid); + uuid_unparse(sb->dev_item.fsid, dev_fsid); + error("dev_item UUID does not match fsid: %s != %s", + dev_fsid, fsid); + goto error_out; + } + + /* + * Hint to catch really bogus numbers, bitflips or so + */ + if (btrfs_super_num_devices(sb) > (1UL << 31)) { + error("suspicious number of devices: %llu", + btrfs_super_num_devices(sb)); + } + + if (btrfs_super_num_devices(sb) == 0) { + error("number of devices is 0"); + goto error_out; + } + + /* + * Obvious sys_chunk_array corruptions, it must hold at least one key + * and one chunk + */ + if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { + error("system chunk array too big %u > %u", + btrfs_super_sys_array_size(sb), + BTRFS_SYSTEM_CHUNK_ARRAY_SIZE); + goto error_out; + } + if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key) + + sizeof(struct btrfs_chunk)) { + error("system chunk array too small %u < %zu", + btrfs_super_sys_array_size(sb), + sizeof(struct btrfs_disk_key) + + sizeof(struct btrfs_chunk)); + goto error_out; + } + + return 0; + +error_out: + error("superblock checksum matches but it has invalid members"); + return -EIO; +} + +/* + * btrfs_read_dev_super - read a valid primary superblock from a block device + * @desc,@part: file descriptor of the device + * @sb: buffer where the superblock is going to be read in + * + * Unlike the btrfs-progs/kernel version, here we ony care about the first + * super block, thus it's much simpler. + */ +int btrfs_read_dev_super(struct blk_desc *desc, struct disk_partition *part, + struct btrfs_super_block *sb) +{ + char tmp[BTRFS_SUPER_INFO_SIZE]; + struct btrfs_super_block *buf = (struct btrfs_super_block *)tmp; + int ret; + + ret = __btrfs_devread(desc, part, tmp, BTRFS_SUPER_INFO_SIZE, + BTRFS_SUPER_INFO_OFFSET); + if (ret < BTRFS_SUPER_INFO_SIZE) + return -EIO; + + if (btrfs_super_bytenr(buf) != BTRFS_SUPER_INFO_OFFSET) + return -EIO; + + if (btrfs_check_super(buf)) + return -EIO; + + memcpy(sb, buf, BTRFS_SUPER_INFO_SIZE); + return 0; +} + +int btrfs_read_superblock(void) +{ + ALLOC_CACHE_ALIGN_BUFFER(char, raw_sb, BTRFS_SUPER_INFO_SIZE); + struct btrfs_super_block *sb = (struct btrfs_super_block *) raw_sb; + int ret; + + + btrfs_info.sb.generation = 0; + + ret = btrfs_read_dev_super(btrfs_blk_desc, btrfs_part_info, sb); + if (ret < 0) { + pr_debug("%s: No valid BTRFS superblock found!\n", __func__); + return ret; + } + btrfs_super_block_to_cpu(sb); + memcpy(&btrfs_info.sb, sb, sizeof(*sb)); + + if (btrfs_info.sb.num_devices != 1) { + printf("%s: Unsupported number of devices (%lli). This driver " + "only supports filesystem on one device.\n", __func__, + btrfs_info.sb.num_devices); + return -1; + } + + pr_debug("Chosen superblock with generation = %llu\n", + btrfs_info.sb.generation); + + return 0; +} diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index efb715828c..fe4093cbd8 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -2,10 +2,14 @@ #ifndef __BTRFS_DISK_IO_H__ #define __BTRFS_DISK_IO_H__

+#include <linux/sizes.h> +#include <fs_internal.h> #include "crypto/hash.h" #include "ctree.h" #include "disk-io.h"

+#define BTRFS_SUPER_INFO_OFFSET SZ_64K +#define BTRFS_SUPER_INFO_SIZE SZ_4K static inline u64 btrfs_name_hash(const char *name, int len) { u32 crc; @@ -17,4 +21,7 @@ static inline u64 btrfs_name_hash(const char *name, int len)

int btrfs_csum_data(u16 csum_type, const u8 *data, u8 *out, size_t len);

+int btrfs_read_dev_super(struct blk_desc *desc, struct disk_partition *part, + struct btrfs_super_block *sb); +int btrfs_read_superblock(void); #endif diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c deleted file mode 100644 index d67d5a2447..0000000000 --- a/fs/btrfs/super.c +++ /dev/null @@ -1,258 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * BTRFS filesystem implementation for U-Boot - * - * 2017 Marek Behun, CZ.NIC, marek.behun@nic.cz - */ - -#include <common.h> -#include <log.h> -#include <memalign.h> -#include <part.h> -#include <linux/compat.h> -#include "btrfs.h" -#include "disk-io.h" - -#define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN \ - | BTRFS_HEADER_FLAG_RELOC \ - | BTRFS_SUPER_FLAG_ERROR \ - | BTRFS_SUPER_FLAG_SEEDING \ - | BTRFS_SUPER_FLAG_METADUMP) - -#define BTRFS_SUPER_INFO_SIZE 4096 - -/* - * checks if a valid root backup is present. - * considers the case when all root backups empty valid. - * returns -1 in case of invalid root backup and 0 for valid. - */ -static int btrfs_check_super_roots(struct btrfs_super_block *sb) -{ - struct btrfs_root_backup *root_backup; - int i, newest = -1; - int num_empty = 0; - - for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; ++i) { - root_backup = sb->super_roots + i; - - if (root_backup->tree_root == 0 && root_backup->tree_root_gen == 0) - num_empty++; - - if (root_backup->tree_root_gen == sb->generation) - newest = i; - } - - if (num_empty == BTRFS_NUM_BACKUP_ROOTS) { - return 0; - } else if (newest >= 0) { - return 0; - } - - return -1; -} - -static inline int is_power_of_2(u64 x) -{ - return !(x & (x - 1)); -} - -static int btrfs_check_super_csum(char *raw_disk_sb) -{ - struct btrfs_super_block *disk_sb = - (struct btrfs_super_block *) raw_disk_sb; - u16 csum_type = le16_to_cpu(disk_sb->csum_type); - - if (csum_type == BTRFS_CSUM_TYPE_CRC32 || - csum_type == BTRFS_CSUM_TYPE_SHA256 || - csum_type == BTRFS_CSUM_TYPE_XXHASH) { - u8 result[BTRFS_CSUM_SIZE]; - - btrfs_csum_data(csum_type, (u8 *)raw_disk_sb + BTRFS_CSUM_SIZE, - result, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); - - if (memcmp(raw_disk_sb, result, BTRFS_CSUM_SIZE)) - return -EIO; - } else if (csum_type == BTRFS_CSUM_TYPE_BLAKE2) { - printf("Blake2 csum type is not supported yet\n"); - return -ENOTSUPP; - } - - return 0; -} - -static int btrfs_check_super(struct btrfs_super_block *sb) -{ - int ret = 0; - - if (sb->flags & ~BTRFS_SUPER_FLAG_SUPP) { - printf("%s: Unsupported flags: %llu\n", __func__, - sb->flags & ~BTRFS_SUPER_FLAG_SUPP); - } - - if (sb->root_level > BTRFS_MAX_LEVEL) { - printf("%s: tree_root level too big: %d >= %d\n", __func__, - sb->root_level, BTRFS_MAX_LEVEL); - ret = -1; - } - - if (sb->chunk_root_level > BTRFS_MAX_LEVEL) { - printf("%s: chunk_root level too big: %d >= %d\n", __func__, - sb->chunk_root_level, BTRFS_MAX_LEVEL); - ret = -1; - } - - if (sb->log_root_level > BTRFS_MAX_LEVEL) { - printf("%s: log_root level too big: %d >= %d\n", __func__, - sb->log_root_level, BTRFS_MAX_LEVEL); - ret = -1; - } - - if (!is_power_of_2(sb->sectorsize) || sb->sectorsize < 4096 || - sb->sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) { - printf("%s: invalid sectorsize %u\n", __func__, - sb->sectorsize); - ret = -1; - } - - if (!is_power_of_2(sb->nodesize) || sb->nodesize < sb->sectorsize || - sb->nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) { - printf("%s: invalid nodesize %u\n", __func__, sb->nodesize); - ret = -1; - } - - if (sb->nodesize != sb->__unused_leafsize) { - printf("%s: invalid leafsize %u, should be %u\n", __func__, - sb->__unused_leafsize, sb->nodesize); - ret = -1; - } - - if (!IS_ALIGNED(sb->root, sb->sectorsize)) { - printf("%s: tree_root block unaligned: %llu\n", __func__, - sb->root); - ret = -1; - } - - if (!IS_ALIGNED(sb->chunk_root, sb->sectorsize)) { - printf("%s: chunk_root block unaligned: %llu\n", __func__, - sb->chunk_root); - ret = -1; - } - - if (!IS_ALIGNED(sb->log_root, sb->sectorsize)) { - printf("%s: log_root block unaligned: %llu\n", __func__, - sb->log_root); - ret = -1; - } - - if (memcmp(sb->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) { - printf("%s: dev_item UUID does not match fsid\n", __func__); - ret = -1; - } - - if (sb->bytes_used < 6*sb->nodesize) { - printf("%s: bytes_used is too small %llu\n", __func__, - sb->bytes_used); - ret = -1; - } - - if (!is_power_of_2(sb->stripesize)) { - printf("%s: invalid stripesize %u\n", __func__, sb->stripesize); - ret = -1; - } - - if (sb->sys_chunk_array_size > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { - printf("%s: system chunk array too big %u > %u\n", __func__, - sb->sys_chunk_array_size, BTRFS_SYSTEM_CHUNK_ARRAY_SIZE); - ret = -1; - } - - if (sb->sys_chunk_array_size < sizeof(struct btrfs_key) + - sizeof(struct btrfs_chunk)) { - printf("%s: system chunk array too small %u < %zu\n", __func__, - sb->sys_chunk_array_size, sizeof(struct btrfs_key) - + sizeof(struct btrfs_chunk)); - ret = -1; - } - - return ret; -} - -int btrfs_read_superblock(void) -{ - const u64 superblock_offsets[4] = { - 0x10000ull, - 0x4000000ull, - 0x4000000000ull, - 0x4000000000000ull - }; - ALLOC_CACHE_ALIGN_BUFFER(char, raw_sb, BTRFS_SUPER_INFO_SIZE); - struct btrfs_super_block *sb = (struct btrfs_super_block *) raw_sb; - u64 dev_total_bytes; - int i; - - dev_total_bytes = (u64) btrfs_part_info->size * btrfs_part_info->blksz; - - btrfs_info.sb.generation = 0; - - for (i = 0; i < 4; ++i) { - if (superblock_offsets[i] + sizeof(sb) > dev_total_bytes) - break; - - if (!btrfs_devread(superblock_offsets[i], BTRFS_SUPER_INFO_SIZE, - raw_sb)) - break; - - if (btrfs_check_super_csum(raw_sb)) { - debug("%s: invalid checksum at superblock mirror %i\n", - __func__, i); - continue; - } - - btrfs_super_block_to_cpu(sb); - - if (sb->magic != BTRFS_MAGIC) { - debug("%s: invalid BTRFS magic 0x%016llX at " - "superblock mirror %i\n", __func__, sb->magic, i); - } else if (sb->bytenr != superblock_offsets[i]) { - printf("%s: invalid bytenr 0x%016llX (expected " - "0x%016llX) at superblock mirror %i\n", - __func__, sb->bytenr, superblock_offsets[i], i); - } else if (btrfs_check_super(sb)) { - printf("%s: Checking superblock mirror %i failed\n", - __func__, i); - } else if (sb->generation > btrfs_info.sb.generation) { - memcpy(&btrfs_info.sb, sb, sizeof(*sb)); - } else { - /* Nothing */ - } - } - - if (!btrfs_info.sb.generation) { - debug("%s: No valid BTRFS superblock found!\n", __func__); - return -1; - } - - if (btrfs_check_super_roots(&btrfs_info.sb)) { - printf("%s: No valid root_backup found!\n", __func__); - return -1; - } - - if (sb->sectorsize != PAGE_SIZE) { - printf( - "%s: Unsupported sector size (%u), only supports %u as sector size\n", - __func__, sb->sectorsize, PAGE_SIZE); - return -1; - } - - if (btrfs_info.sb.num_devices != 1) { - printf("%s: Unsupported number of devices (%lli). This driver " - "only supports filesystem on one device.\n", __func__, - btrfs_info.sb.num_devices); - return -1; - } - - debug("Chosen superblock with generation = %llu\n", - btrfs_info.sb.generation); - - return 0; -}

From: Qu Wenruo wqu@suse.com

This patch implements an infrastructure to insert/search/merge an extent range (with variable length).

This provides the basis for later extent buffer cache used in btrfs.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/extent-cache.c | 318 ++++++++++++++++++++++++++++++++++++++++ fs/btrfs/extent-cache.h | 104 +++++++++++++ 2 files changed, 422 insertions(+) create mode 100644 fs/btrfs/extent-cache.c create mode 100644 fs/btrfs/extent-cache.h

diff --git a/fs/btrfs/extent-cache.c b/fs/btrfs/extent-cache.c new file mode 100644 index 0000000000..bc8cf3a522 --- /dev/null +++ b/fs/btrfs/extent-cache.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Crossported from the same named file of btrfs-progs. + * + * Minor modification to include headers. + */ +#include <linux/kernel.h> +#include <linux/rbtree.h> +#include <linux/errno.h> +#include <linux/bug.h> +#include <stdlib.h> +#include "extent-cache.h" +#include "common/rbtree-utils.h" + +struct cache_extent_search_range { + u64 objectid; + u64 start; + u64 size; +}; + +static int cache_tree_comp_range(struct rb_node *node, void *data) +{ + struct cache_extent *entry; + struct cache_extent_search_range *range; + + range = (struct cache_extent_search_range *)data; + entry = rb_entry(node, struct cache_extent, rb_node); + + if (entry->start + entry->size <= range->start) + return 1; + else if (range->start + range->size <= entry->start) + return -1; + else + return 0; +} + +static int cache_tree_comp_nodes(struct rb_node *node1, struct rb_node *node2) +{ + struct cache_extent *entry; + struct cache_extent_search_range range; + + entry = rb_entry(node2, struct cache_extent, rb_node); + range.start = entry->start; + range.size = entry->size; + + return cache_tree_comp_range(node1, (void *)&range); +} + +static int cache_tree_comp_range2(struct rb_node *node, void *data) +{ + struct cache_extent *entry; + struct cache_extent_search_range *range; + + range = (struct cache_extent_search_range *)data; + entry = rb_entry(node, struct cache_extent, rb_node); + + if (entry->objectid < range->objectid) + return 1; + else if (entry->objectid > range->objectid) + return -1; + else if (entry->start + entry->size <= range->start) + return 1; + else if (range->start + range->size <= entry->start) + return -1; + else + return 0; +} + +static int cache_tree_comp_nodes2(struct rb_node *node1, struct rb_node *node2) +{ + struct cache_extent *entry; + struct cache_extent_search_range range; + + entry = rb_entry(node2, struct cache_extent, rb_node); + range.objectid = entry->objectid; + range.start = entry->start; + range.size = entry->size; + + return cache_tree_comp_range2(node1, (void *)&range); +} + +void cache_tree_init(struct cache_tree *tree) +{ + tree->root = RB_ROOT; +} + +static struct cache_extent *alloc_cache_extent(u64 start, u64 size) +{ + struct cache_extent *pe = malloc(sizeof(*pe)); + + if (!pe) + return pe; + + pe->objectid = 0; + pe->start = start; + pe->size = size; + return pe; +} + +int add_cache_extent(struct cache_tree *tree, u64 start, u64 size) +{ + struct cache_extent *pe = alloc_cache_extent(start, size); + int ret; + + if (!pe) + return -ENOMEM; + + ret = insert_cache_extent(tree, pe); + if (ret) + free(pe); + + return ret; +} + +int insert_cache_extent(struct cache_tree *tree, struct cache_extent *pe) +{ + return rb_insert(&tree->root, &pe->rb_node, cache_tree_comp_nodes); +} + +int insert_cache_extent2(struct cache_tree *tree, struct cache_extent *pe) +{ + return rb_insert(&tree->root, &pe->rb_node, cache_tree_comp_nodes2); +} + +struct cache_extent *lookup_cache_extent(struct cache_tree *tree, + u64 start, u64 size) +{ + struct rb_node *node; + struct cache_extent *entry; + struct cache_extent_search_range range; + + range.start = start; + range.size = size; + node = rb_search(&tree->root, &range, cache_tree_comp_range, NULL); + if (!node) + return NULL; + + entry = rb_entry(node, struct cache_extent, rb_node); + return entry; +} + +struct cache_extent *lookup_cache_extent2(struct cache_tree *tree, + u64 objectid, u64 start, u64 size) +{ + struct rb_node *node; + struct cache_extent *entry; + struct cache_extent_search_range range; + + range.objectid = objectid; + range.start = start; + range.size = size; + node = rb_search(&tree->root, &range, cache_tree_comp_range2, NULL); + if (!node) + return NULL; + + entry = rb_entry(node, struct cache_extent, rb_node); + return entry; +} + +struct cache_extent *search_cache_extent(struct cache_tree *tree, u64 start) +{ + struct rb_node *next; + struct rb_node *node; + struct cache_extent *entry; + struct cache_extent_search_range range; + + range.start = start; + range.size = 1; + node = rb_search(&tree->root, &range, cache_tree_comp_range, &next); + if (!node) + node = next; + if (!node) + return NULL; + + entry = rb_entry(node, struct cache_extent, rb_node); + return entry; +} + +struct cache_extent *search_cache_extent2(struct cache_tree *tree, + u64 objectid, u64 start) +{ + struct rb_node *next; + struct rb_node *node; + struct cache_extent *entry; + struct cache_extent_search_range range; + + range.objectid = objectid; + range.start = start; + range.size = 1; + node = rb_search(&tree->root, &range, cache_tree_comp_range2, &next); + if (!node) + node = next; + if (!node) + return NULL; + + entry = rb_entry(node, struct cache_extent, rb_node); + return entry; +} + +struct cache_extent *first_cache_extent(struct cache_tree *tree) +{ + struct rb_node *node = rb_first(&tree->root); + + if (!node) + return NULL; + return rb_entry(node, struct cache_extent, rb_node); +} + +struct cache_extent *last_cache_extent(struct cache_tree *tree) +{ + struct rb_node *node = rb_last(&tree->root); + + if (!node) + return NULL; + return rb_entry(node, struct cache_extent, rb_node); +} + +struct cache_extent *prev_cache_extent(struct cache_extent *pe) +{ + struct rb_node *node = rb_prev(&pe->rb_node); + + if (!node) + return NULL; + return rb_entry(node, struct cache_extent, rb_node); +} + +struct cache_extent *next_cache_extent(struct cache_extent *pe) +{ + struct rb_node *node = rb_next(&pe->rb_node); + + if (!node) + return NULL; + return rb_entry(node, struct cache_extent, rb_node); +} + +void remove_cache_extent(struct cache_tree *tree, struct cache_extent *pe) +{ + rb_erase(&pe->rb_node, &tree->root); +} + +void cache_tree_free_extents(struct cache_tree *tree, + free_cache_extent free_func) +{ + struct cache_extent *ce; + + while ((ce = first_cache_extent(tree))) { + remove_cache_extent(tree, ce); + free_func(ce); + } +} + +static void free_extent_cache(struct cache_extent *pe) +{ + free(pe); +} + +void free_extent_cache_tree(struct cache_tree *tree) +{ + cache_tree_free_extents(tree, free_extent_cache); +} + +int add_merge_cache_extent(struct cache_tree *tree, u64 start, u64 size) +{ + struct cache_extent *cache; + struct cache_extent *next = NULL; + struct cache_extent *prev = NULL; + int next_merged = 0; + int prev_merged = 0; + int ret = 0; + + if (cache_tree_empty(tree)) + goto insert; + + cache = search_cache_extent(tree, start); + if (!cache) { + /* + * Either the tree is completely empty, or the no range after + * start. + * Either way, the last cache_extent should be prev. + */ + prev = last_cache_extent(tree); + } else if (start <= cache->start) { + next = cache; + prev = prev_cache_extent(cache); + } else { + prev = cache; + next = next_cache_extent(cache); + } + + /* + * Ensure the range to be inserted won't cover with existings + * Or we will need extra loop to do merge + */ + BUG_ON(next && start + size > next->start); + BUG_ON(prev && prev->start + prev->size > start); + + if (next && start + size == next->start) { + next_merged = 1; + next->size = next->start + next->size - start; + next->start = start; + } + if (prev && prev->start + prev->size == start) { + prev_merged = 1; + if (next_merged) { + next->size = next->start + next->size - prev->start; + next->start = prev->start; + remove_cache_extent(tree, prev); + free(prev); + } else { + prev->size = start + size - prev->start; + } + } +insert: + if (!prev_merged && !next_merged) + ret = add_cache_extent(tree, start, size); + return ret; +} diff --git a/fs/btrfs/extent-cache.h b/fs/btrfs/extent-cache.h new file mode 100644 index 0000000000..2fee81a66e --- /dev/null +++ b/fs/btrfs/extent-cache.h @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Crossported from the same named file of btrfs-progs. + * + * Minor modification to include headers. + */ +#ifndef __BTRFS_EXTENT_CACHE_H__ +#define __BTRFS_EXTENT_CACHE_H__ + +#include <linux/rbtree.h> +#include <linux/types.h> + +struct cache_tree { + struct rb_root root; +}; + +struct cache_extent { + struct rb_node rb_node; + u64 objectid; + u64 start; + u64 size; +}; + +void cache_tree_init(struct cache_tree *tree); + +struct cache_extent *first_cache_extent(struct cache_tree *tree); +struct cache_extent *last_cache_extent(struct cache_tree *tree); +struct cache_extent *prev_cache_extent(struct cache_extent *pe); +struct cache_extent *next_cache_extent(struct cache_extent *pe); + +/* + * Find a cache_extent which covers start. + * + * If not found, return next cache_extent if possible. + */ +struct cache_extent *search_cache_extent(struct cache_tree *tree, u64 start); + +/* + * Find a cache_extent which restrictly covers start. + * + * If not found, return NULL. + */ +struct cache_extent *lookup_cache_extent(struct cache_tree *tree, + u64 start, u64 size); + +/* + * Add an non-overlap extent into cache tree + * + * If [start, start+size) overlap with existing one, it will return -EEXIST. + */ +int add_cache_extent(struct cache_tree *tree, u64 start, u64 size); + +/* + * Same with add_cache_extent, but with cache_extent strcut. + */ +int insert_cache_extent(struct cache_tree *tree, struct cache_extent *pe); +void remove_cache_extent(struct cache_tree *tree, struct cache_extent *pe); + +static inline int cache_tree_empty(struct cache_tree *tree) +{ + return RB_EMPTY_ROOT(&tree->root); +} + +typedef void (*free_cache_extent)(struct cache_extent *pe); + +void cache_tree_free_extents(struct cache_tree *tree, + free_cache_extent free_func); + +#define FREE_EXTENT_CACHE_BASED_TREE(name, free_func) \ +static void free_##name##_tree(struct cache_tree *tree) \ +{ \ + cache_tree_free_extents(tree, free_func); \ +} + +void free_extent_cache_tree(struct cache_tree *tree); + +/* + * Search a cache_extent with same objectid, and covers start. + * + * If not found, return next if possible. + */ +struct cache_extent *search_cache_extent2(struct cache_tree *tree, + u64 objectid, u64 start); +/* + * Search a cache_extent with same objectid, and covers the range + * [start, start + size) + * + * If not found, return next cache_extent if possible. + */ +struct cache_extent *lookup_cache_extent2(struct cache_tree *tree, + u64 objectid, u64 start, u64 size); +int insert_cache_extent2(struct cache_tree *tree, struct cache_extent *pe); + +/* + * Insert a cache_extent range [start, start + size). + * + * This function may merge with existing cache_extent. + * NOTE: caller must ensure the inserted range won't cover with any existing + * range. + */ +int add_merge_cache_extent(struct cache_tree *tree, u64 start, u64 size); + +#endif

From: Qu Wenruo wqu@suse.com

This brings all structure accessors from btrfs-progs/ctree.h, as in kernel's ctree.h.

All these accessors handle the endian convert at runtime, and since all of them are defined as static inline functions, those which aren't used won't take space in resulting binary.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/compat.h | 14 + fs/btrfs/ctree.h | 1136 ++++++++++++++++++++++++++++++++++++++++---- fs/btrfs/disk-io.h | 9 - 3 files changed, 1064 insertions(+), 95 deletions(-)

diff --git a/fs/btrfs/compat.h b/fs/btrfs/compat.h index e7d7dc9f6e..2bbe97779e 100644 --- a/fs/btrfs/compat.h +++ b/fs/btrfs/compat.h @@ -29,6 +29,20 @@ static inline void error(const char *fmt, ...) #define cpu_to_le8(v) (v) #define __le8 u8

+/* + * Macros to generate set/get funcs for the struct fields + * assume there is a lefoo_to_cpu for every type, so lets make a simple + * one for u8: + */ +#define le8_to_cpu(v) (v) +#define cpu_to_le8(v) (v) +#define __le8 u8 + +#define get_unaligned_le8(p) (*((u8 *)(p))) +#define get_unaligned_8(p) (*((u8 *)(p))) +#define put_unaligned_le8(val,p) ((*((u8 *)(p))) = (val)) +#define put_unaligned_8(val,p) ((*((u8 *)(p))) = (val)) + /* * Read data from device specified by @desc and @part * diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index c7528d1ac3..a09587233e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -12,7 +12,10 @@ #include <common.h> #include <compiler.h> #include <linux/rbtree.h> +#include <linux/unaligned/le_byteshift.h> +#include <u-boot/crc.h> #include "kernel-shared/btrfs_tree.h" +#include "crypto/hash.h" #include "compat.h" #include "extent-io.h"

@@ -34,6 +37,20 @@ /* four bytes for CRC32 */ #define BTRFS_EMPTY_DIR_SIZE 0

+struct btrfs_mapping_tree { + struct cache_tree cache_tree; +}; + +static inline unsigned long btrfs_chunk_item_size(int num_stripes) +{ + BUG_ON(num_stripes == 0); + return sizeof(struct btrfs_chunk) + + sizeof(struct btrfs_stripe) * (num_stripes - 1); +} + +#define __BTRFS_LEAF_DATA_SIZE(bs) ((bs) - sizeof(struct btrfs_header)) +#define BTRFS_LEAF_DATA_SIZE(fs_info) \ + (__BTRFS_LEAF_DATA_SIZE(fs_info->nodesize)) /* ioprio of readahead is set to idle */ #define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))

@@ -41,6 +58,35 @@

#define BTRFS_MAX_EXTENT_SIZE SZ_128M

+struct btrfs_device; +struct btrfs_fs_devices; +struct btrfs_fs_info { + u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; + u8 *new_chunk_tree_uuid; + struct btrfs_root *fs_root; + struct btrfs_root *tree_root; + struct btrfs_root *chunk_root; + struct btrfs_root *csum_root; + + struct rb_root fs_root_tree; + + struct extent_io_tree extent_cache; + + /* logical->physical extent mapping */ + struct btrfs_mapping_tree mapping_tree; + + u64 last_trans_committed; + + struct btrfs_super_block *super_copy; + + struct btrfs_fs_devices *fs_devices; + + /* Cached block sizes */ + u32 nodesize; + u32 sectorsize; + u32 stripesize; +}; + /* * File system states */ @@ -62,6 +108,35 @@ offsetof(type, member), \ sizeof(((type *)0)->member)))

+#define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \ +static inline u##bits btrfs_##name(const struct extent_buffer *eb) \ +{ \ + const struct btrfs_header *h = (struct btrfs_header *)eb->data; \ + return le##bits##_to_cpu(h->member); \ +} \ +static inline void btrfs_set_##name(struct extent_buffer *eb, \ + u##bits val) \ +{ \ + struct btrfs_header *h = (struct btrfs_header *)eb->data; \ + h->member = cpu_to_le##bits(val); \ +} + +#define BTRFS_SETGET_FUNCS(name, type, member, bits) \ +static inline u##bits btrfs_##name(const struct extent_buffer *eb, \ + const type *s) \ +{ \ + unsigned long offset = (unsigned long)s; \ + const type *p = (type *) (eb->data + offset); \ + return get_unaligned_le##bits(&p->member); \ +} \ +static inline void btrfs_set_##name(struct extent_buffer *eb, \ + type *s, u##bits val) \ +{ \ + unsigned long offset = (unsigned long)s; \ + type *p = (type *) (eb->data + offset); \ + put_unaligned_le##bits(val, &p->member); \ +} + #define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \ static inline u##bits btrfs_##name(const type *s) \ { \ @@ -72,126 +147,721 @@ static inline void btrfs_set_##name(type *s, u##bits val) \ s->member = cpu_to_le##bits(val); \ }

-union btrfs_tree_node { - struct btrfs_header header; - struct btrfs_leaf leaf; - struct btrfs_node node; -}; +BTRFS_SETGET_FUNCS(device_type, struct btrfs_dev_item, type, 64); +BTRFS_SETGET_FUNCS(device_total_bytes, struct btrfs_dev_item, total_bytes, 64); +BTRFS_SETGET_FUNCS(device_bytes_used, struct btrfs_dev_item, bytes_used, 64); +BTRFS_SETGET_FUNCS(device_io_align, struct btrfs_dev_item, io_align, 32); +BTRFS_SETGET_FUNCS(device_io_width, struct btrfs_dev_item, io_width, 32); +BTRFS_SETGET_FUNCS(device_start_offset, struct btrfs_dev_item, + start_offset, 64); +BTRFS_SETGET_FUNCS(device_sector_size, struct btrfs_dev_item, sector_size, 32); +BTRFS_SETGET_FUNCS(device_id, struct btrfs_dev_item, devid, 64); +BTRFS_SETGET_FUNCS(device_group, struct btrfs_dev_item, dev_group, 32); +BTRFS_SETGET_FUNCS(device_seek_speed, struct btrfs_dev_item, seek_speed, 8); +BTRFS_SETGET_FUNCS(device_bandwidth, struct btrfs_dev_item, bandwidth, 8); +BTRFS_SETGET_FUNCS(device_generation, struct btrfs_dev_item, generation, 64);

-struct btrfs_path { - union btrfs_tree_node *nodes[BTRFS_MAX_LEVEL]; - u32 slots[BTRFS_MAX_LEVEL]; -}; +BTRFS_SETGET_STACK_FUNCS(stack_device_type, struct btrfs_dev_item, type, 64); +BTRFS_SETGET_STACK_FUNCS(stack_device_total_bytes, struct btrfs_dev_item, + total_bytes, 64); +BTRFS_SETGET_STACK_FUNCS(stack_device_bytes_used, struct btrfs_dev_item, + bytes_used, 64); +BTRFS_SETGET_STACK_FUNCS(stack_device_io_align, struct btrfs_dev_item, + io_align, 32); +BTRFS_SETGET_STACK_FUNCS(stack_device_io_width, struct btrfs_dev_item, + io_width, 32); +BTRFS_SETGET_STACK_FUNCS(stack_device_sector_size, struct btrfs_dev_item, + sector_size, 32); +BTRFS_SETGET_STACK_FUNCS(stack_device_id, struct btrfs_dev_item, devid, 64); +BTRFS_SETGET_STACK_FUNCS(stack_device_group, struct btrfs_dev_item, + dev_group, 32); +BTRFS_SETGET_STACK_FUNCS(stack_device_seek_speed, struct btrfs_dev_item, + seek_speed, 8); +BTRFS_SETGET_STACK_FUNCS(stack_device_bandwidth, struct btrfs_dev_item, + bandwidth, 8); +BTRFS_SETGET_STACK_FUNCS(stack_device_generation, struct btrfs_dev_item, + generation, 64);

-struct btrfs_root { - u64 objectid; - u64 bytenr; - u64 root_dirid; -}; +static inline char *btrfs_device_uuid(struct btrfs_dev_item *d) +{ + return (char *)d + offsetof(struct btrfs_dev_item, uuid); +}

-struct btrfs_mapping_tree { - struct cache_tree cache_tree; -}; +static inline char *btrfs_device_fsid(struct btrfs_dev_item *d) +{ + return (char *)d + offsetof(struct btrfs_dev_item, fsid); +}

-struct btrfs_device; -struct btrfs_fs_info { - u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; - u8 *new_chunk_tree_uuid; - struct btrfs_root *fs_root; - struct btrfs_root *tree_root; - struct btrfs_root *chunk_root; - struct btrfs_root *csum_root; +BTRFS_SETGET_FUNCS(chunk_length, struct btrfs_chunk, length, 64); +BTRFS_SETGET_FUNCS(chunk_owner, struct btrfs_chunk, owner, 64); +BTRFS_SETGET_FUNCS(chunk_stripe_len, struct btrfs_chunk, stripe_len, 64); +BTRFS_SETGET_FUNCS(chunk_io_align, struct btrfs_chunk, io_align, 32); +BTRFS_SETGET_FUNCS(chunk_io_width, struct btrfs_chunk, io_width, 32); +BTRFS_SETGET_FUNCS(chunk_sector_size, struct btrfs_chunk, sector_size, 32); +BTRFS_SETGET_FUNCS(chunk_type, struct btrfs_chunk, type, 64); +BTRFS_SETGET_FUNCS(chunk_num_stripes, struct btrfs_chunk, num_stripes, 16); +BTRFS_SETGET_FUNCS(chunk_sub_stripes, struct btrfs_chunk, sub_stripes, 16); +BTRFS_SETGET_FUNCS(stripe_devid, struct btrfs_stripe, devid, 64); +BTRFS_SETGET_FUNCS(stripe_offset, struct btrfs_stripe, offset, 64);

- struct rb_root fs_root_tree; +static inline char *btrfs_stripe_dev_uuid(struct btrfs_stripe *s) +{ + return (char *)s + offsetof(struct btrfs_stripe, dev_uuid); +}

- struct extent_io_tree extent_cache; - struct extent_io_tree free_space_cache; - struct extent_io_tree pinned_extents; - struct extent_io_tree extent_ins; - struct extent_io_tree *excluded_extents; +BTRFS_SETGET_STACK_FUNCS(stack_chunk_length, struct btrfs_chunk, length, 64); +BTRFS_SETGET_STACK_FUNCS(stack_chunk_owner, struct btrfs_chunk, owner, 64); +BTRFS_SETGET_STACK_FUNCS(stack_chunk_stripe_len, struct btrfs_chunk, + stripe_len, 64); +BTRFS_SETGET_STACK_FUNCS(stack_chunk_io_align, struct btrfs_chunk, + io_align, 32); +BTRFS_SETGET_STACK_FUNCS(stack_chunk_io_width, struct btrfs_chunk, + io_width, 32); +BTRFS_SETGET_STACK_FUNCS(stack_chunk_sector_size, struct btrfs_chunk, + sector_size, 32); +BTRFS_SETGET_STACK_FUNCS(stack_chunk_type, struct btrfs_chunk, type, 64); +BTRFS_SETGET_STACK_FUNCS(stack_chunk_num_stripes, struct btrfs_chunk, + num_stripes, 16); +BTRFS_SETGET_STACK_FUNCS(stack_chunk_sub_stripes, struct btrfs_chunk, + sub_stripes, 16); +BTRFS_SETGET_STACK_FUNCS(stack_stripe_devid, struct btrfs_stripe, devid, 64); +BTRFS_SETGET_STACK_FUNCS(stack_stripe_offset, struct btrfs_stripe, offset, 64);

- struct rb_root block_group_cache_tree; - /* logical->physical extent mapping */ - struct btrfs_mapping_tree mapping_tree; +static inline struct btrfs_stripe *btrfs_stripe_nr(struct btrfs_chunk *c, + int nr) +{ + unsigned long offset = (unsigned long)c; + offset += offsetof(struct btrfs_chunk, stripe); + offset += nr * sizeof(struct btrfs_stripe); + return (struct btrfs_stripe *)offset; +}

- u64 generation; - u64 last_trans_committed; +static inline char *btrfs_stripe_dev_uuid_nr(struct btrfs_chunk *c, int nr) +{ + return btrfs_stripe_dev_uuid(btrfs_stripe_nr(c, nr)); +}

- struct btrfs_super_block *super_copy; +static inline u64 btrfs_stripe_offset_nr(struct extent_buffer *eb, + struct btrfs_chunk *c, int nr) +{ + return btrfs_stripe_offset(eb, btrfs_stripe_nr(c, nr)); +}

- u64 super_bytenr; +static inline void btrfs_set_stripe_offset_nr(struct extent_buffer *eb, + struct btrfs_chunk *c, int nr, + u64 val) +{ + btrfs_set_stripe_offset(eb, btrfs_stripe_nr(c, nr), val); +}

- /* Only support one device yet */ - struct btrfs_devvice *dev; +static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb, + struct btrfs_chunk *c, int nr) +{ + return btrfs_stripe_devid(eb, btrfs_stripe_nr(c, nr)); +}

- /* Cached block sizes */ - u32 nodesize; - u32 sectorsize; - u32 stripesize; -}; +static inline void btrfs_set_stripe_devid_nr(struct extent_buffer *eb, + struct btrfs_chunk *c, int nr, + u64 val) +{ + btrfs_set_stripe_devid(eb, btrfs_stripe_nr(c, nr), val); +}

-int btrfs_comp_keys(struct btrfs_key *, struct btrfs_key *); -int btrfs_comp_keys_type(struct btrfs_key *, struct btrfs_key *); -int btrfs_bin_search(union btrfs_tree_node *, struct btrfs_key *, int *); -void btrfs_free_path(struct btrfs_path *); -int btrfs_search_tree(const struct btrfs_root *, struct btrfs_key *, - struct btrfs_path *); -int btrfs_prev_slot(struct btrfs_path *); -int btrfs_next_slot(struct btrfs_path *); +/* struct btrfs_block_group_item */ +BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item, + used, 64); +BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item, + used, 64); +BTRFS_SETGET_STACK_FUNCS(block_group_chunk_objectid, + struct btrfs_block_group_item, chunk_objectid, 64);

-static inline struct btrfs_key *btrfs_path_leaf_key(struct btrfs_path *p) { - /* At tree read time we have converted the endian for btrfs_disk_key */ - return (struct btrfs_key *)&p->nodes[0]->leaf.items[p->slots[0]].key; +BTRFS_SETGET_FUNCS(disk_block_group_chunk_objectid, + struct btrfs_block_group_item, chunk_objectid, 64); +BTRFS_SETGET_FUNCS(disk_block_group_flags, + struct btrfs_block_group_item, flags, 64); +BTRFS_SETGET_STACK_FUNCS(block_group_flags, + struct btrfs_block_group_item, flags, 64); + +/* struct btrfs_free_space_info */ +BTRFS_SETGET_FUNCS(free_space_extent_count, struct btrfs_free_space_info, + extent_count, 32); +BTRFS_SETGET_FUNCS(free_space_flags, struct btrfs_free_space_info, flags, 32); + +/* struct btrfs_inode_ref */ +BTRFS_SETGET_FUNCS(inode_ref_name_len, struct btrfs_inode_ref, name_len, 16); +BTRFS_SETGET_STACK_FUNCS(stack_inode_ref_name_len, struct btrfs_inode_ref, name_len, 16); +BTRFS_SETGET_FUNCS(inode_ref_index, struct btrfs_inode_ref, index, 64); + +/* struct btrfs_inode_extref */ +BTRFS_SETGET_FUNCS(inode_extref_parent, struct btrfs_inode_extref, + parent_objectid, 64); +BTRFS_SETGET_FUNCS(inode_extref_name_len, struct btrfs_inode_extref, + name_len, 16); +BTRFS_SETGET_FUNCS(inode_extref_index, struct btrfs_inode_extref, index, 64); + +/* struct btrfs_inode_item */ +BTRFS_SETGET_FUNCS(inode_generation, struct btrfs_inode_item, generation, 64); +BTRFS_SETGET_FUNCS(inode_sequence, struct btrfs_inode_item, sequence, 64); +BTRFS_SETGET_FUNCS(inode_transid, struct btrfs_inode_item, transid, 64); +BTRFS_SETGET_FUNCS(inode_size, struct btrfs_inode_item, size, 64); +BTRFS_SETGET_FUNCS(inode_nbytes, struct btrfs_inode_item, nbytes, 64); +BTRFS_SETGET_FUNCS(inode_block_group, struct btrfs_inode_item, block_group, 64); +BTRFS_SETGET_FUNCS(inode_nlink, struct btrfs_inode_item, nlink, 32); +BTRFS_SETGET_FUNCS(inode_uid, struct btrfs_inode_item, uid, 32); +BTRFS_SETGET_FUNCS(inode_gid, struct btrfs_inode_item, gid, 32); +BTRFS_SETGET_FUNCS(inode_mode, struct btrfs_inode_item, mode, 32); +BTRFS_SETGET_FUNCS(inode_rdev, struct btrfs_inode_item, rdev, 64); +BTRFS_SETGET_FUNCS(inode_flags, struct btrfs_inode_item, flags, 64); + +BTRFS_SETGET_STACK_FUNCS(stack_inode_generation, + struct btrfs_inode_item, generation, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_sequence, + struct btrfs_inode_item, sequence, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_transid, + struct btrfs_inode_item, transid, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_size, + struct btrfs_inode_item, size, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_nbytes, + struct btrfs_inode_item, nbytes, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_block_group, + struct btrfs_inode_item, block_group, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_nlink, + struct btrfs_inode_item, nlink, 32); +BTRFS_SETGET_STACK_FUNCS(stack_inode_uid, + struct btrfs_inode_item, uid, 32); +BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, + struct btrfs_inode_item, gid, 32); +BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, + struct btrfs_inode_item, mode, 32); +BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, + struct btrfs_inode_item, rdev, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, + struct btrfs_inode_item, flags, 64); + +static inline struct btrfs_timespec * +btrfs_inode_atime(struct btrfs_inode_item *inode_item) +{ + unsigned long ptr = (unsigned long)inode_item; + ptr += offsetof(struct btrfs_inode_item, atime); + return (struct btrfs_timespec *)ptr; }

-static inline struct btrfs_key * -btrfs_search_tree_key_type(const struct btrfs_root *root, u64 objectid, - u8 type, struct btrfs_path *path) +static inline struct btrfs_timespec * +btrfs_inode_mtime(struct btrfs_inode_item *inode_item) { - struct btrfs_key key, *res; + unsigned long ptr = (unsigned long)inode_item; + ptr += offsetof(struct btrfs_inode_item, mtime); + return (struct btrfs_timespec *)ptr; +}

- key.objectid = objectid; - key.type = type; - key.offset = 0; +static inline struct btrfs_timespec * +btrfs_inode_ctime(struct btrfs_inode_item *inode_item) +{ + unsigned long ptr = (unsigned long)inode_item; + ptr += offsetof(struct btrfs_inode_item, ctime); + return (struct btrfs_timespec *)ptr; +}

- if (btrfs_search_tree(root, &key, path)) - return NULL; +static inline struct btrfs_timespec * +btrfs_inode_otime(struct btrfs_inode_item *inode_item) +{ + unsigned long ptr = (unsigned long)inode_item; + ptr += offsetof(struct btrfs_inode_item, otime); + return (struct btrfs_timespec *)ptr; +}

- res = btrfs_path_leaf_key(path); - if (btrfs_comp_keys_type(&key, res)) { - btrfs_free_path(path); - return NULL; - } +BTRFS_SETGET_FUNCS(timespec_sec, struct btrfs_timespec, sec, 64); +BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32); +BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, + sec, 64); +BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, + nsec, 32);

- return res; +/* struct btrfs_dev_extent */ +BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent, + chunk_tree, 64); +BTRFS_SETGET_FUNCS(dev_extent_chunk_objectid, struct btrfs_dev_extent, + chunk_objectid, 64); +BTRFS_SETGET_FUNCS(dev_extent_chunk_offset, struct btrfs_dev_extent, + chunk_offset, 64); +BTRFS_SETGET_FUNCS(dev_extent_length, struct btrfs_dev_extent, length, 64); + +BTRFS_SETGET_STACK_FUNCS(stack_dev_extent_length, struct btrfs_dev_extent, + length, 64); + +static inline u8 *btrfs_dev_extent_chunk_tree_uuid(struct btrfs_dev_extent *dev) +{ + unsigned long ptr = offsetof(struct btrfs_dev_extent, chunk_tree_uuid); + return (u8 *)((unsigned long)dev + ptr); }

-static inline u32 btrfs_path_item_size(struct btrfs_path *p) + +/* struct btrfs_extent_item */ +BTRFS_SETGET_FUNCS(extent_refs, struct btrfs_extent_item, refs, 64); +BTRFS_SETGET_STACK_FUNCS(stack_extent_refs, struct btrfs_extent_item, refs, 64); +BTRFS_SETGET_FUNCS(extent_generation, struct btrfs_extent_item, + generation, 64); +BTRFS_SETGET_FUNCS(extent_flags, struct btrfs_extent_item, flags, 64); +BTRFS_SETGET_STACK_FUNCS(stack_extent_flags, struct btrfs_extent_item, flags, 64); + +BTRFS_SETGET_FUNCS(extent_refs_v0, struct btrfs_extent_item_v0, refs, 32); + +BTRFS_SETGET_FUNCS(tree_block_level, struct btrfs_tree_block_info, level, 8); + +static inline void btrfs_tree_block_key(struct extent_buffer *eb, + struct btrfs_tree_block_info *item, + struct btrfs_disk_key *key) { - return p->nodes[0]->leaf.items[p->slots[0]].size; + read_eb_member(eb, item, struct btrfs_tree_block_info, key, key); }

-static inline void *btrfs_leaf_data(struct btrfs_leaf *leaf, u32 slot) +static inline void btrfs_set_tree_block_key(struct extent_buffer *eb, + struct btrfs_tree_block_info *item, + struct btrfs_disk_key *key) { - return ((u8 *) leaf) + sizeof(struct btrfs_header) - + leaf->items[slot].offset; + write_eb_member(eb, item, struct btrfs_tree_block_info, key, key); }

-static inline void *btrfs_path_leaf_data(struct btrfs_path *p) +BTRFS_SETGET_FUNCS(extent_data_ref_root, struct btrfs_extent_data_ref, + root, 64); +BTRFS_SETGET_FUNCS(extent_data_ref_objectid, struct btrfs_extent_data_ref, + objectid, 64); +BTRFS_SETGET_FUNCS(extent_data_ref_offset, struct btrfs_extent_data_ref, + offset, 64); +BTRFS_SETGET_FUNCS(extent_data_ref_count, struct btrfs_extent_data_ref, + count, 32); + +BTRFS_SETGET_FUNCS(shared_data_ref_count, struct btrfs_shared_data_ref, + count, 32); + +BTRFS_SETGET_FUNCS(extent_inline_ref_type, struct btrfs_extent_inline_ref, + type, 8); +BTRFS_SETGET_FUNCS(extent_inline_ref_offset, struct btrfs_extent_inline_ref, + offset, 64); +BTRFS_SETGET_STACK_FUNCS(stack_extent_inline_ref_type, + struct btrfs_extent_inline_ref, type, 8); +BTRFS_SETGET_STACK_FUNCS(stack_extent_inline_ref_offset, + struct btrfs_extent_inline_ref, offset, 64); + +static inline u32 btrfs_extent_inline_ref_size(int type) { - return btrfs_leaf_data(&p->nodes[0]->leaf, p->slots[0]); + if (type == BTRFS_TREE_BLOCK_REF_KEY || + type == BTRFS_SHARED_BLOCK_REF_KEY) + return sizeof(struct btrfs_extent_inline_ref); + if (type == BTRFS_SHARED_DATA_REF_KEY) + return sizeof(struct btrfs_shared_data_ref) + + sizeof(struct btrfs_extent_inline_ref); + if (type == BTRFS_EXTENT_DATA_REF_KEY) + return sizeof(struct btrfs_extent_data_ref) + + offsetof(struct btrfs_extent_inline_ref, offset); + BUG(); + return 0; }

-#define btrfs_item_ptr(l,s,t) \ - ((t *) btrfs_leaf_data((l),(s))) +BTRFS_SETGET_FUNCS(ref_root_v0, struct btrfs_extent_ref_v0, root, 64); +BTRFS_SETGET_FUNCS(ref_generation_v0, struct btrfs_extent_ref_v0, + generation, 64); +BTRFS_SETGET_FUNCS(ref_objectid_v0, struct btrfs_extent_ref_v0, objectid, 64); +BTRFS_SETGET_FUNCS(ref_count_v0, struct btrfs_extent_ref_v0, count, 32);

-#define btrfs_path_item_ptr(p,t) \ - ((t *) btrfs_path_leaf_data((p))) +/* struct btrfs_node */ +BTRFS_SETGET_FUNCS(key_blockptr, struct btrfs_key_ptr, blockptr, 64); +BTRFS_SETGET_FUNCS(key_generation, struct btrfs_key_ptr, generation, 64);

-u16 btrfs_super_csum_size(const struct btrfs_super_block *s); -const char *btrfs_super_csum_name(u16 csum_type); -u16 btrfs_csum_type_size(u16 csum_type); -size_t btrfs_super_num_csums(void); +static inline u64 btrfs_node_blockptr(struct extent_buffer *eb, int nr) +{ + unsigned long ptr; + ptr = offsetof(struct btrfs_node, ptrs) + + sizeof(struct btrfs_key_ptr) * nr; + return btrfs_key_blockptr(eb, (struct btrfs_key_ptr *)ptr); +} + +static inline void btrfs_set_node_blockptr(struct extent_buffer *eb, + int nr, u64 val) +{ + unsigned long ptr; + ptr = offsetof(struct btrfs_node, ptrs) + + sizeof(struct btrfs_key_ptr) * nr; + btrfs_set_key_blockptr(eb, (struct btrfs_key_ptr *)ptr, val); +} + +static inline u64 btrfs_node_ptr_generation(struct extent_buffer *eb, int nr) +{ + unsigned long ptr; + ptr = offsetof(struct btrfs_node, ptrs) + + sizeof(struct btrfs_key_ptr) * nr; + return btrfs_key_generation(eb, (struct btrfs_key_ptr *)ptr); +} + +static inline void btrfs_set_node_ptr_generation(struct extent_buffer *eb, + int nr, u64 val) +{ + unsigned long ptr; + ptr = offsetof(struct btrfs_node, ptrs) + + sizeof(struct btrfs_key_ptr) * nr; + btrfs_set_key_generation(eb, (struct btrfs_key_ptr *)ptr, val); +} + +static inline unsigned long btrfs_node_key_ptr_offset(int nr) +{ + return offsetof(struct btrfs_node, ptrs) + + sizeof(struct btrfs_key_ptr) * nr; +} + +static inline void btrfs_node_key(struct extent_buffer *eb, + struct btrfs_disk_key *disk_key, int nr) +{ + unsigned long ptr; + ptr = btrfs_node_key_ptr_offset(nr); + read_eb_member(eb, (struct btrfs_key_ptr *)ptr, + struct btrfs_key_ptr, key, disk_key); +} + +static inline void btrfs_set_node_key(struct extent_buffer *eb, + struct btrfs_disk_key *disk_key, int nr) +{ + unsigned long ptr; + ptr = btrfs_node_key_ptr_offset(nr); + write_eb_member(eb, (struct btrfs_key_ptr *)ptr, + struct btrfs_key_ptr, key, disk_key); +} + +/* struct btrfs_item */ +BTRFS_SETGET_FUNCS(item_offset, struct btrfs_item, offset, 32); +BTRFS_SETGET_FUNCS(item_size, struct btrfs_item, size, 32); + +static inline unsigned long btrfs_item_nr_offset(int nr) +{ + return offsetof(struct btrfs_leaf, items) + + sizeof(struct btrfs_item) * nr; +} + +static inline struct btrfs_item *btrfs_item_nr(int nr) +{ + return (struct btrfs_item *)btrfs_item_nr_offset(nr); +} + +static inline u32 btrfs_item_end(struct extent_buffer *eb, + struct btrfs_item *item) +{ + return btrfs_item_offset(eb, item) + btrfs_item_size(eb, item); +} + +static inline u32 btrfs_item_end_nr(struct extent_buffer *eb, int nr) +{ + return btrfs_item_end(eb, btrfs_item_nr(nr)); +} + +static inline u32 btrfs_item_offset_nr(const struct extent_buffer *eb, int nr) +{ + return btrfs_item_offset(eb, btrfs_item_nr(nr)); +} + +static inline u32 btrfs_item_size_nr(struct extent_buffer *eb, int nr) +{ + return btrfs_item_size(eb, btrfs_item_nr(nr)); +} + +static inline void btrfs_item_key(struct extent_buffer *eb, + struct btrfs_disk_key *disk_key, int nr) +{ + struct btrfs_item *item = btrfs_item_nr(nr); + read_eb_member(eb, item, struct btrfs_item, key, disk_key); +} + +static inline void btrfs_set_item_key(struct extent_buffer *eb, + struct btrfs_disk_key *disk_key, int nr) +{ + struct btrfs_item *item = btrfs_item_nr(nr); + write_eb_member(eb, item, struct btrfs_item, key, disk_key); +} + +BTRFS_SETGET_FUNCS(dir_log_end, struct btrfs_dir_log_item, end, 64); + +/* + * struct btrfs_root_ref + */ +BTRFS_SETGET_FUNCS(root_ref_dirid, struct btrfs_root_ref, dirid, 64); +BTRFS_SETGET_FUNCS(root_ref_sequence, struct btrfs_root_ref, sequence, 64); +BTRFS_SETGET_FUNCS(root_ref_name_len, struct btrfs_root_ref, name_len, 16); + +BTRFS_SETGET_STACK_FUNCS(stack_root_ref_dirid, struct btrfs_root_ref, dirid, 64); +BTRFS_SETGET_STACK_FUNCS(stack_root_ref_sequence, struct btrfs_root_ref, sequence, 64); +BTRFS_SETGET_STACK_FUNCS(stack_root_ref_name_len, struct btrfs_root_ref, name_len, 16); + +/* struct btrfs_dir_item */ +BTRFS_SETGET_FUNCS(dir_data_len, struct btrfs_dir_item, data_len, 16); +BTRFS_SETGET_FUNCS(dir_type, struct btrfs_dir_item, type, 8); +BTRFS_SETGET_FUNCS(dir_name_len, struct btrfs_dir_item, name_len, 16); +BTRFS_SETGET_FUNCS(dir_transid, struct btrfs_dir_item, transid, 64); + +BTRFS_SETGET_STACK_FUNCS(stack_dir_data_len, struct btrfs_dir_item, data_len, 16); +BTRFS_SETGET_STACK_FUNCS(stack_dir_type, struct btrfs_dir_item, type, 8); +BTRFS_SETGET_STACK_FUNCS(stack_dir_name_len, struct btrfs_dir_item, name_len, 16); +BTRFS_SETGET_STACK_FUNCS(stack_dir_transid, struct btrfs_dir_item, transid, 64); + +static inline void btrfs_dir_item_key(struct extent_buffer *eb, + struct btrfs_dir_item *item, + struct btrfs_disk_key *key) +{ + read_eb_member(eb, item, struct btrfs_dir_item, location, key); +} + +static inline void btrfs_set_dir_item_key(struct extent_buffer *eb, + struct btrfs_dir_item *item, + struct btrfs_disk_key *key) +{ + write_eb_member(eb, item, struct btrfs_dir_item, location, key); +} + +/* struct btrfs_free_space_header */ +BTRFS_SETGET_FUNCS(free_space_entries, struct btrfs_free_space_header, + num_entries, 64); +BTRFS_SETGET_FUNCS(free_space_bitmaps, struct btrfs_free_space_header, + num_bitmaps, 64); +BTRFS_SETGET_FUNCS(free_space_generation, struct btrfs_free_space_header, + generation, 64); + +static inline void btrfs_free_space_key(struct extent_buffer *eb, + struct btrfs_free_space_header *h, + struct btrfs_disk_key *key) +{ + read_eb_member(eb, h, struct btrfs_free_space_header, location, key); +} + +static inline void btrfs_set_free_space_key(struct extent_buffer *eb, + struct btrfs_free_space_header *h, + struct btrfs_disk_key *key) +{ + write_eb_member(eb, h, struct btrfs_free_space_header, location, key); +} + +/* struct btrfs_disk_key */ +BTRFS_SETGET_STACK_FUNCS(disk_key_objectid, struct btrfs_disk_key, + objectid, 64); +BTRFS_SETGET_STACK_FUNCS(disk_key_offset, struct btrfs_disk_key, offset, 64); +BTRFS_SETGET_STACK_FUNCS(disk_key_type, struct btrfs_disk_key, type, 8); + +static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu, + struct btrfs_disk_key *disk) +{ + cpu->offset = le64_to_cpu(disk->offset); + cpu->type = disk->type; + cpu->objectid = le64_to_cpu(disk->objectid); +} + +static inline void btrfs_cpu_key_to_disk(struct btrfs_disk_key *disk, + const struct btrfs_key *cpu) +{ + disk->offset = cpu_to_le64(cpu->offset); + disk->type = cpu->type; + disk->objectid = cpu_to_le64(cpu->objectid); +} + +static inline void btrfs_node_key_to_cpu(struct extent_buffer *eb, + struct btrfs_key *key, int nr) +{ + struct btrfs_disk_key disk_key; + btrfs_node_key(eb, &disk_key, nr); + btrfs_disk_key_to_cpu(key, &disk_key); +} + +static inline void btrfs_item_key_to_cpu(struct extent_buffer *eb, + struct btrfs_key *key, int nr) +{ + struct btrfs_disk_key disk_key; + btrfs_item_key(eb, &disk_key, nr); + btrfs_disk_key_to_cpu(key, &disk_key); +} + +static inline void btrfs_dir_item_key_to_cpu(struct extent_buffer *eb, + struct btrfs_dir_item *item, + struct btrfs_key *key) +{ + struct btrfs_disk_key disk_key; + btrfs_dir_item_key(eb, item, &disk_key); + btrfs_disk_key_to_cpu(key, &disk_key); +} + +/* struct btrfs_header */ +BTRFS_SETGET_HEADER_FUNCS(header_bytenr, struct btrfs_header, bytenr, 64); +BTRFS_SETGET_HEADER_FUNCS(header_generation, struct btrfs_header, + generation, 64); +BTRFS_SETGET_HEADER_FUNCS(header_owner, struct btrfs_header, owner, 64); +BTRFS_SETGET_HEADER_FUNCS(header_nritems, struct btrfs_header, nritems, 32); +BTRFS_SETGET_HEADER_FUNCS(header_flags, struct btrfs_header, flags, 64); +BTRFS_SETGET_HEADER_FUNCS(header_level, struct btrfs_header, level, 8); +BTRFS_SETGET_STACK_FUNCS(stack_header_bytenr, struct btrfs_header, bytenr, 64); +BTRFS_SETGET_STACK_FUNCS(stack_header_nritems, struct btrfs_header, nritems, + 32); +BTRFS_SETGET_STACK_FUNCS(stack_header_owner, struct btrfs_header, owner, 64); +BTRFS_SETGET_STACK_FUNCS(stack_header_generation, struct btrfs_header, + generation, 64); + +static inline int btrfs_header_flag(struct extent_buffer *eb, u64 flag) +{ + return (btrfs_header_flags(eb) & flag) == flag; +} + +static inline int btrfs_set_header_flag(struct extent_buffer *eb, u64 flag) +{ + u64 flags = btrfs_header_flags(eb); + btrfs_set_header_flags(eb, flags | flag); + return (flags & flag) == flag; +} + +static inline int btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag) +{ + u64 flags = btrfs_header_flags(eb); + btrfs_set_header_flags(eb, flags & ~flag); + return (flags & flag) == flag; +} + +static inline int btrfs_header_backref_rev(struct extent_buffer *eb) +{ + u64 flags = btrfs_header_flags(eb); + return flags >> BTRFS_BACKREF_REV_SHIFT; +} + +static inline void btrfs_set_header_backref_rev(struct extent_buffer *eb, + int rev) +{ + u64 flags = btrfs_header_flags(eb); + flags &= ~BTRFS_BACKREF_REV_MASK; + flags |= (u64)rev << BTRFS_BACKREF_REV_SHIFT; + btrfs_set_header_flags(eb, flags); +} + +static inline unsigned long btrfs_header_fsid(void) +{ + return offsetof(struct btrfs_header, fsid); +} + +static inline unsigned long btrfs_header_chunk_tree_uuid(struct extent_buffer *eb) +{ + return offsetof(struct btrfs_header, chunk_tree_uuid); +} + +static inline u8 *btrfs_header_csum(struct extent_buffer *eb) +{ + unsigned long ptr = offsetof(struct btrfs_header, csum); + return (u8 *)ptr; +} + +static inline int btrfs_is_leaf(struct extent_buffer *eb) +{ + return (btrfs_header_level(eb) == 0); +} + +/* struct btrfs_root_item */ +BTRFS_SETGET_FUNCS(disk_root_generation, struct btrfs_root_item, + generation, 64); +BTRFS_SETGET_FUNCS(disk_root_refs, struct btrfs_root_item, refs, 32); +BTRFS_SETGET_FUNCS(disk_root_bytenr, struct btrfs_root_item, bytenr, 64); +BTRFS_SETGET_FUNCS(disk_root_level, struct btrfs_root_item, level, 8); + +BTRFS_SETGET_STACK_FUNCS(root_generation, struct btrfs_root_item, + generation, 64); +BTRFS_SETGET_STACK_FUNCS(root_bytenr, struct btrfs_root_item, bytenr, 64); +BTRFS_SETGET_STACK_FUNCS(root_level, struct btrfs_root_item, level, 8); +BTRFS_SETGET_STACK_FUNCS(root_dirid, struct btrfs_root_item, root_dirid, 64); +BTRFS_SETGET_STACK_FUNCS(root_refs, struct btrfs_root_item, refs, 32); +BTRFS_SETGET_STACK_FUNCS(root_flags, struct btrfs_root_item, flags, 64); +BTRFS_SETGET_STACK_FUNCS(root_used, struct btrfs_root_item, bytes_used, 64); +BTRFS_SETGET_STACK_FUNCS(root_limit, struct btrfs_root_item, byte_limit, 64); +BTRFS_SETGET_STACK_FUNCS(root_last_snapshot, struct btrfs_root_item, + last_snapshot, 64); +BTRFS_SETGET_STACK_FUNCS(root_generation_v2, struct btrfs_root_item, + generation_v2, 64); +BTRFS_SETGET_STACK_FUNCS(root_ctransid, struct btrfs_root_item, + ctransid, 64); +BTRFS_SETGET_STACK_FUNCS(root_otransid, struct btrfs_root_item, + otransid, 64); +BTRFS_SETGET_STACK_FUNCS(root_stransid, struct btrfs_root_item, + stransid, 64); +BTRFS_SETGET_STACK_FUNCS(root_rtransid, struct btrfs_root_item, + rtransid, 64); + +static inline struct btrfs_timespec* btrfs_root_ctime( + struct btrfs_root_item *root_item) +{ + unsigned long ptr = (unsigned long)root_item; + ptr += offsetof(struct btrfs_root_item, ctime); + return (struct btrfs_timespec *)ptr; +} + +static inline struct btrfs_timespec* btrfs_root_otime( + struct btrfs_root_item *root_item) +{ + unsigned long ptr = (unsigned long)root_item; + ptr += offsetof(struct btrfs_root_item, otime); + return (struct btrfs_timespec *)ptr; +} + +static inline struct btrfs_timespec* btrfs_root_stime( + struct btrfs_root_item *root_item) +{ + unsigned long ptr = (unsigned long)root_item; + ptr += offsetof(struct btrfs_root_item, stime); + return (struct btrfs_timespec *)ptr; +} + +static inline struct btrfs_timespec* btrfs_root_rtime( + struct btrfs_root_item *root_item) +{ + unsigned long ptr = (unsigned long)root_item; + ptr += offsetof(struct btrfs_root_item, rtime); + return (struct btrfs_timespec *)ptr; +} + +/* struct btrfs_root_backup */ +BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup, + tree_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_tree_root_gen, struct btrfs_root_backup, + tree_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_tree_root_level, struct btrfs_root_backup, + tree_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root, struct btrfs_root_backup, + chunk_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_gen, struct btrfs_root_backup, + chunk_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_level, struct btrfs_root_backup, + chunk_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_extent_root, struct btrfs_root_backup, + extent_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_extent_root_gen, struct btrfs_root_backup, + extent_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_extent_root_level, struct btrfs_root_backup, + extent_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_fs_root, struct btrfs_root_backup, + fs_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_fs_root_gen, struct btrfs_root_backup, + fs_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_fs_root_level, struct btrfs_root_backup, + fs_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_dev_root, struct btrfs_root_backup, + dev_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_dev_root_gen, struct btrfs_root_backup, + dev_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_dev_root_level, struct btrfs_root_backup, + dev_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_csum_root, struct btrfs_root_backup, + csum_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_csum_root_gen, struct btrfs_root_backup, + csum_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_csum_root_level, struct btrfs_root_backup, + csum_root_level, 8); +BTRFS_SETGET_STACK_FUNCS(backup_total_bytes, struct btrfs_root_backup, + total_bytes, 64); +BTRFS_SETGET_STACK_FUNCS(backup_bytes_used, struct btrfs_root_backup, + bytes_used, 64); +BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup, + num_devices, 64);

/* struct btrfs_super_block */

@@ -244,4 +914,298 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block, uuid_tree_generation, 64); BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64);

+static inline unsigned long btrfs_leaf_data(struct extent_buffer *l) +{ + return offsetof(struct btrfs_leaf, items); +} + +/* struct btrfs_file_extent_item */ +BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_type, struct btrfs_file_extent_item, type, 8); + +static inline unsigned long btrfs_file_extent_inline_start(struct + btrfs_file_extent_item *e) +{ + unsigned long offset = (unsigned long)e; + offset += offsetof(struct btrfs_file_extent_item, disk_bytenr); + return offset; +} + +static inline u32 btrfs_file_extent_calc_inline_size(u32 datasize) +{ + return offsetof(struct btrfs_file_extent_item, disk_bytenr) + datasize; +} + +BTRFS_SETGET_FUNCS(file_extent_disk_bytenr, struct btrfs_file_extent_item, + disk_bytenr, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_bytenr, struct btrfs_file_extent_item, + disk_bytenr, 64); +BTRFS_SETGET_FUNCS(file_extent_generation, struct btrfs_file_extent_item, + generation, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_generation, struct btrfs_file_extent_item, + generation, 64); +BTRFS_SETGET_FUNCS(file_extent_disk_num_bytes, struct btrfs_file_extent_item, + disk_num_bytes, 64); +BTRFS_SETGET_FUNCS(file_extent_offset, struct btrfs_file_extent_item, + offset, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_offset, struct btrfs_file_extent_item, + offset, 64); +BTRFS_SETGET_FUNCS(file_extent_num_bytes, struct btrfs_file_extent_item, + num_bytes, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_num_bytes, struct btrfs_file_extent_item, + num_bytes, 64); +BTRFS_SETGET_FUNCS(file_extent_ram_bytes, struct btrfs_file_extent_item, + ram_bytes, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_ram_bytes, struct btrfs_file_extent_item, + ram_bytes, 64); +BTRFS_SETGET_FUNCS(file_extent_compression, struct btrfs_file_extent_item, + compression, 8); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_compression, struct btrfs_file_extent_item, + compression, 8); +BTRFS_SETGET_FUNCS(file_extent_encryption, struct btrfs_file_extent_item, + encryption, 8); +BTRFS_SETGET_FUNCS(file_extent_other_encoding, struct btrfs_file_extent_item, + other_encoding, 16); + +/* btrfs_qgroup_status_item */ +BTRFS_SETGET_FUNCS(qgroup_status_version, struct btrfs_qgroup_status_item, + version, 64); +BTRFS_SETGET_FUNCS(qgroup_status_generation, struct btrfs_qgroup_status_item, + generation, 64); +BTRFS_SETGET_FUNCS(qgroup_status_flags, struct btrfs_qgroup_status_item, + flags, 64); +BTRFS_SETGET_FUNCS(qgroup_status_rescan, struct btrfs_qgroup_status_item, + rescan, 64); + +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_status_version, + struct btrfs_qgroup_status_item, version, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_status_generation, + struct btrfs_qgroup_status_item, generation, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_status_flags, + struct btrfs_qgroup_status_item, flags, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_status_rescan, + struct btrfs_qgroup_status_item, rescan, 64); + +/* btrfs_qgroup_info_item */ +BTRFS_SETGET_FUNCS(qgroup_info_generation, struct btrfs_qgroup_info_item, + generation, 64); +BTRFS_SETGET_FUNCS(qgroup_info_referenced, struct btrfs_qgroup_info_item, + rfer, 64); +BTRFS_SETGET_FUNCS(qgroup_info_referenced_compressed, + struct btrfs_qgroup_info_item, rfer_cmpr, 64); +BTRFS_SETGET_FUNCS(qgroup_info_exclusive, struct btrfs_qgroup_info_item, + excl, 64); +BTRFS_SETGET_FUNCS(qgroup_info_exclusive_compressed, + struct btrfs_qgroup_info_item, excl_cmpr, 64); + +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_generation, + struct btrfs_qgroup_info_item, generation, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_referenced, + struct btrfs_qgroup_info_item, rfer, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_referenced_compressed, + struct btrfs_qgroup_info_item, rfer_cmpr, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_exclusive, + struct btrfs_qgroup_info_item, excl, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_exclusive_compressed, + struct btrfs_qgroup_info_item, excl_cmpr, 64); + +/* btrfs_qgroup_limit_item */ +BTRFS_SETGET_FUNCS(qgroup_limit_flags, struct btrfs_qgroup_limit_item, + flags, 64); +BTRFS_SETGET_FUNCS(qgroup_limit_max_referenced, struct btrfs_qgroup_limit_item, + max_rfer, 64); +BTRFS_SETGET_FUNCS(qgroup_limit_max_exclusive, struct btrfs_qgroup_limit_item, + max_excl, 64); +BTRFS_SETGET_FUNCS(qgroup_limit_rsv_referenced, struct btrfs_qgroup_limit_item, + rsv_rfer, 64); +BTRFS_SETGET_FUNCS(qgroup_limit_rsv_exclusive, struct btrfs_qgroup_limit_item, + rsv_excl, 64); + +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_limit_flags, + struct btrfs_qgroup_limit_item, flags, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_limit_max_referenced, + struct btrfs_qgroup_limit_item, max_rfer, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_limit_max_exclusive, + struct btrfs_qgroup_limit_item, max_excl, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_limit_rsv_referenced, + struct btrfs_qgroup_limit_item, rsv_rfer, 64); +BTRFS_SETGET_STACK_FUNCS(stack_qgroup_limit_rsv_exclusive, + struct btrfs_qgroup_limit_item, rsv_excl, 64); + +/* btrfs_balance_item */ +BTRFS_SETGET_FUNCS(balance_item_flags, struct btrfs_balance_item, flags, 64); + +static inline struct btrfs_disk_balance_args* btrfs_balance_item_data( + struct extent_buffer *eb, struct btrfs_balance_item *bi) +{ + unsigned long offset = (unsigned long)bi; + struct btrfs_balance_item *p; + p = (struct btrfs_balance_item *)(eb->data + offset); + return &p->data; +} + +static inline struct btrfs_disk_balance_args* btrfs_balance_item_meta( + struct extent_buffer *eb, struct btrfs_balance_item *bi) +{ + unsigned long offset = (unsigned long)bi; + struct btrfs_balance_item *p; + p = (struct btrfs_balance_item *)(eb->data + offset); + return &p->meta; +} + +static inline struct btrfs_disk_balance_args* btrfs_balance_item_sys( + struct extent_buffer *eb, struct btrfs_balance_item *bi) +{ + unsigned long offset = (unsigned long)bi; + struct btrfs_balance_item *p; + p = (struct btrfs_balance_item *)(eb->data + offset); + return &p->sys; +} + +static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb, + const struct btrfs_dev_stats_item *ptr, + int index) +{ + u64 val; + + read_extent_buffer(eb, &val, + offsetof(struct btrfs_dev_stats_item, values) + + ((unsigned long)ptr) + (index * sizeof(u64)), + sizeof(val)); + return val; +} + +/* + * this returns the number of bytes used by the item on disk, minus the + * size of any extent headers. If a file is compressed on disk, this is + * the compressed size + */ +static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb, + struct btrfs_item *e) +{ + unsigned long offset; + offset = offsetof(struct btrfs_file_extent_item, disk_bytenr); + return btrfs_item_size(eb, e) - offset; +} + +#define btrfs_fs_incompat(fs_info, opt) \ + __btrfs_fs_incompat((fs_info), BTRFS_FEATURE_INCOMPAT_##opt) + +static inline bool __btrfs_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag) +{ + struct btrfs_super_block *disk_super; + disk_super = fs_info->super_copy; + return !!(btrfs_super_incompat_flags(disk_super) & flag); +} + +#define btrfs_fs_compat_ro(fs_info, opt) \ + __btrfs_fs_compat_ro((fs_info), BTRFS_FEATURE_COMPAT_RO_##opt) + +static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag) +{ + struct btrfs_super_block *disk_super; + disk_super = fs_info->super_copy; + return !!(btrfs_super_compat_ro_flags(disk_super) & flag); +} + +/* helper function to cast into the data area of the leaf. */ +#define btrfs_item_ptr(leaf, slot, type) \ + ((type *)(btrfs_leaf_data(leaf) + \ + btrfs_item_offset_nr(leaf, slot))) + +#define btrfs_item_ptr_offset(leaf, slot) \ + ((unsigned long)(btrfs_leaf_data(leaf) + \ + btrfs_item_offset_nr(leaf, slot))) + +static inline u64 btrfs_name_hash(const char *name, int len) +{ + return (u64)crc32c((u32)~1, (u8 *)name, len); +} + +/* + * Figure the key offset of an extended inode ref + */ +static inline u64 btrfs_extref_hash(u64 parent_objectid, const char *name, + int len) +{ + return crc32(parent_objectid, (u8 *)name, len); +} + +union btrfs_tree_node { + struct btrfs_header header; + struct btrfs_leaf leaf; + struct btrfs_node node; +}; + +struct btrfs_path { + union btrfs_tree_node *nodes[BTRFS_MAX_LEVEL]; + u32 slots[BTRFS_MAX_LEVEL]; +}; + +struct btrfs_root { + u64 objectid; + u64 bytenr; + u64 root_dirid; +}; + +int btrfs_comp_keys(struct btrfs_key *, struct btrfs_key *); +int btrfs_comp_keys_type(struct btrfs_key *, struct btrfs_key *); +int btrfs_bin_search(union btrfs_tree_node *, struct btrfs_key *, int *); +void btrfs_free_path(struct btrfs_path *); +int btrfs_search_tree(const struct btrfs_root *, struct btrfs_key *, + struct btrfs_path *); +int btrfs_prev_slot(struct btrfs_path *); +int btrfs_next_slot(struct btrfs_path *); + +static inline struct btrfs_key *btrfs_path_leaf_key(struct btrfs_path *p) { + /* At tree read time we have converted the endian for btrfs_disk_key */ + return (struct btrfs_key *)&p->nodes[0]->leaf.items[p->slots[0]].key; +} + +static inline struct btrfs_key * +btrfs_search_tree_key_type(const struct btrfs_root *root, u64 objectid, + u8 type, struct btrfs_path *path) +{ + struct btrfs_key key, *res; + + key.objectid = objectid; + key.type = type; + key.offset = 0; + + if (btrfs_search_tree(root, &key, path)) + return NULL; + + res = btrfs_path_leaf_key(path); + if (btrfs_comp_keys_type(&key, res)) { + btrfs_free_path(path); + return NULL; + } + + return res; +} + +static inline u32 btrfs_path_item_size(struct btrfs_path *p) +{ + return p->nodes[0]->leaf.items[p->slots[0]].size; +} + +static inline void *__btrfs_leaf_data(struct btrfs_leaf *leaf, u32 slot) +{ + return ((u8 *) leaf) + sizeof(struct btrfs_header) + + leaf->items[slot].offset; +} + +static inline void *btrfs_path_leaf_data(struct btrfs_path *p) +{ + return __btrfs_leaf_data(&p->nodes[0]->leaf, p->slots[0]); +} + +#define btrfs_path_item_ptr(p,t) \ + ((t *) btrfs_path_leaf_data((p))) + +u16 btrfs_super_csum_size(const struct btrfs_super_block *s); +const char *btrfs_super_csum_name(u16 csum_type); +u16 btrfs_csum_type_size(u16 csum_type); +size_t btrfs_super_num_csums(void); + #endif /* __BTRFS_CTREE_H__ */ diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index fe4093cbd8..35b9293946 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -4,20 +4,11 @@

#include <linux/sizes.h> #include <fs_internal.h> -#include "crypto/hash.h" #include "ctree.h" #include "disk-io.h"

#define BTRFS_SUPER_INFO_OFFSET SZ_64K #define BTRFS_SUPER_INFO_SIZE SZ_4K -static inline u64 btrfs_name_hash(const char *name, int len) -{ - u32 crc; - - crc = crc32c((u32)~1, (unsigned char *)name, len); - - return (u64)crc; -}

int btrfs_csum_data(u16 csum_type, const u8 *data, u8 *out, size_t len);

From: Qu Wenruo wqu@suse.com

This is the one of the basic stone function for btrfs, which: - Resolves the chunk mappings - Reads data from disk - Does various sanity check

With read_tree_block(), we can finally crossport needed btrfs btree operations to U-Boot.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/ctree.c | 188 +++++++++++++++++++++++- fs/btrfs/ctree.h | 50 ++++++- fs/btrfs/disk-io.c | 348 +++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/disk-io.h | 18 ++- fs/btrfs/inode.c | 6 +- 5 files changed, 602 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 1d8f7e168f..d97e195e5e 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -42,7 +42,7 @@ u16 btrfs_csum_type_size(u16 csum_type) return btrfs_csums[csum_type].size; }

-int btrfs_comp_keys(struct btrfs_key *a, struct btrfs_key *b) +int __btrfs_comp_keys(struct btrfs_key *a, struct btrfs_key *b) { if (a->objectid > b->objectid) return 1; @@ -82,7 +82,7 @@ static int generic_bin_search(void *addr, int item_size, struct btrfs_key *key, mid = (low + high) / 2;

tmp = (struct btrfs_key *) ((u8 *) addr + mid*item_size); - ret = btrfs_comp_keys(tmp, key); + ret = __btrfs_comp_keys(tmp, key);

if (ret < 0) { low = mid + 1; @@ -321,3 +321,187 @@ int btrfs_next_slot(struct btrfs_path *p) p->slots[0]++; return 0; } + +int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2) +{ + if (k1->objectid > k2->objectid) + return 1; + if (k1->objectid < k2->objectid) + return -1; + if (k1->type > k2->type) + return 1; + if (k1->type < k2->type) + return -1; + if (k1->offset > k2->offset) + return 1; + if (k1->offset < k2->offset) + return -1; + return 0; +} + +static int btrfs_comp_keys(struct btrfs_disk_key *disk, + const struct btrfs_key *k2) +{ + struct btrfs_key k1; + + btrfs_disk_key_to_cpu(&k1, disk); + return btrfs_comp_cpu_keys(&k1, k2); +} + +enum btrfs_tree_block_status +btrfs_check_node(struct btrfs_fs_info *fs_info, + struct btrfs_disk_key *parent_key, struct extent_buffer *buf) +{ + int i; + struct btrfs_key cpukey; + struct btrfs_disk_key key; + u32 nritems = btrfs_header_nritems(buf); + enum btrfs_tree_block_status ret = BTRFS_TREE_BLOCK_INVALID_NRITEMS; + + if (nritems == 0 || nritems > BTRFS_NODEPTRS_PER_BLOCK(fs_info)) + goto fail; + + ret = BTRFS_TREE_BLOCK_INVALID_PARENT_KEY; + if (parent_key && parent_key->type) { + btrfs_node_key(buf, &key, 0); + if (memcmp(parent_key, &key, sizeof(key))) + goto fail; + } + ret = BTRFS_TREE_BLOCK_BAD_KEY_ORDER; + for (i = 0; nritems > 1 && i < nritems - 2; i++) { + btrfs_node_key(buf, &key, i); + btrfs_node_key_to_cpu(buf, &cpukey, i + 1); + if (btrfs_comp_keys(&key, &cpukey) >= 0) + goto fail; + } + return BTRFS_TREE_BLOCK_CLEAN; +fail: + return ret; +} + +enum btrfs_tree_block_status +btrfs_check_leaf(struct btrfs_fs_info *fs_info, + struct btrfs_disk_key *parent_key, struct extent_buffer *buf) +{ + int i; + struct btrfs_key cpukey; + struct btrfs_disk_key key; + u32 nritems = btrfs_header_nritems(buf); + enum btrfs_tree_block_status ret = BTRFS_TREE_BLOCK_INVALID_NRITEMS; + + if (nritems * sizeof(struct btrfs_item) > buf->len) { + fprintf(stderr, "invalid number of items %llu\n", + (unsigned long long)buf->start); + goto fail; + } + + if (btrfs_header_level(buf) != 0) { + ret = BTRFS_TREE_BLOCK_INVALID_LEVEL; + fprintf(stderr, "leaf is not a leaf %llu\n", + (unsigned long long)btrfs_header_bytenr(buf)); + goto fail; + } + if (btrfs_leaf_free_space(buf) < 0) { + ret = BTRFS_TREE_BLOCK_INVALID_FREE_SPACE; + fprintf(stderr, "leaf free space incorrect %llu %d\n", + (unsigned long long)btrfs_header_bytenr(buf), + btrfs_leaf_free_space(buf)); + goto fail; + } + + if (nritems == 0) + return BTRFS_TREE_BLOCK_CLEAN; + + btrfs_item_key(buf, &key, 0); + if (parent_key && parent_key->type && + memcmp(parent_key, &key, sizeof(key))) { + ret = BTRFS_TREE_BLOCK_INVALID_PARENT_KEY; + fprintf(stderr, "leaf parent key incorrect %llu\n", + (unsigned long long)btrfs_header_bytenr(buf)); + goto fail; + } + for (i = 0; nritems > 1 && i < nritems - 1; i++) { + btrfs_item_key(buf, &key, i); + btrfs_item_key_to_cpu(buf, &cpukey, i + 1); + if (btrfs_comp_keys(&key, &cpukey) >= 0) { + ret = BTRFS_TREE_BLOCK_BAD_KEY_ORDER; + fprintf(stderr, "bad key ordering %d %d\n", i, i+1); + goto fail; + } + if (btrfs_item_offset_nr(buf, i) != + btrfs_item_end_nr(buf, i + 1)) { + ret = BTRFS_TREE_BLOCK_INVALID_OFFSETS; + fprintf(stderr, "incorrect offsets %u %u\n", + btrfs_item_offset_nr(buf, i), + btrfs_item_end_nr(buf, i + 1)); + goto fail; + } + if (i == 0 && btrfs_item_end_nr(buf, i) != + BTRFS_LEAF_DATA_SIZE(fs_info)) { + ret = BTRFS_TREE_BLOCK_INVALID_OFFSETS; + fprintf(stderr, "bad item end %u wanted %u\n", + btrfs_item_end_nr(buf, i), + (unsigned)BTRFS_LEAF_DATA_SIZE(fs_info)); + goto fail; + } + } + + for (i = 0; i < nritems; i++) { + if (btrfs_item_end_nr(buf, i) > + BTRFS_LEAF_DATA_SIZE(fs_info)) { + btrfs_item_key(buf, &key, 0); + ret = BTRFS_TREE_BLOCK_INVALID_OFFSETS; + fprintf(stderr, "slot end outside of leaf %llu > %llu\n", + (unsigned long long)btrfs_item_end_nr(buf, i), + (unsigned long long)BTRFS_LEAF_DATA_SIZE( + fs_info)); + goto fail; + } + } + + return BTRFS_TREE_BLOCK_CLEAN; +fail: + return ret; +} + +/* + * how many bytes are required to store the items in a leaf. start + * and nr indicate which items in the leaf to check. This totals up the + * space used both by the item structs and the item data + */ +static int leaf_space_used(struct extent_buffer *l, int start, int nr) +{ + int data_len; + int nritems = btrfs_header_nritems(l); + int end = min(nritems, start + nr) - 1; + + if (!nr) + return 0; + data_len = btrfs_item_end_nr(l, start); + data_len = data_len - btrfs_item_offset_nr(l, end); + data_len += sizeof(struct btrfs_item) * nr; + WARN_ON(data_len < 0); + return data_len; +} + +/* + * The space between the end of the leaf items and + * the start of the leaf data. IOW, how much room + * the leaf has left for both items and data + */ +int btrfs_leaf_free_space(struct extent_buffer *leaf) +{ + int nritems = btrfs_header_nritems(leaf); + u32 leaf_data_size; + int ret; + + BUG_ON(leaf->fs_info && leaf->fs_info->nodesize != leaf->len); + leaf_data_size = __BTRFS_LEAF_DATA_SIZE(leaf->len); + ret = leaf_data_size - leaf_space_used(leaf, 0 ,nritems); + if (ret < 0) { + printk("leaf free space ret %d, leaf data size %u, used %d nritems %d\n", + ret, leaf_data_size, leaf_space_used(leaf, 0, nritems), + nritems); + } + return ret; +} diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index c746d3fd45..7f024c0145 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -59,6 +59,16 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)

#define BTRFS_MAX_EXTENT_SIZE SZ_128M

+enum btrfs_tree_block_status { + BTRFS_TREE_BLOCK_CLEAN, + BTRFS_TREE_BLOCK_INVALID_NRITEMS, + BTRFS_TREE_BLOCK_INVALID_PARENT_KEY, + BTRFS_TREE_BLOCK_BAD_KEY_ORDER, + BTRFS_TREE_BLOCK_INVALID_LEVEL, + BTRFS_TREE_BLOCK_INVALID_FREE_SPACE, + BTRFS_TREE_BLOCK_INVALID_OFFSETS, +}; + struct btrfs_device; struct btrfs_fs_devices; struct btrfs_fs_info { @@ -88,6 +98,35 @@ struct btrfs_fs_info { u32 stripesize; };

+static inline u32 BTRFS_MAX_ITEM_SIZE(const struct btrfs_fs_info *info) +{ + return BTRFS_LEAF_DATA_SIZE(info) - sizeof(struct btrfs_item); +} + +static inline u32 BTRFS_NODEPTRS_PER_BLOCK(const struct btrfs_fs_info *info) +{ + return BTRFS_LEAF_DATA_SIZE(info) / sizeof(struct btrfs_key_ptr); +} + +static inline u32 BTRFS_NODEPTRS_PER_EXTENT_BUFFER(const struct extent_buffer *eb) +{ + BUG_ON(eb->fs_info && eb->fs_info->nodesize != eb->len); + return __BTRFS_LEAF_DATA_SIZE(eb->len) / sizeof(struct btrfs_key_ptr); +} + +#define BTRFS_FILE_EXTENT_INLINE_DATA_START \ + (offsetof(struct btrfs_file_extent_item, disk_bytenr)) +static inline u32 BTRFS_MAX_INLINE_DATA_SIZE(const struct btrfs_fs_info *info) +{ + return BTRFS_MAX_ITEM_SIZE(info) - + BTRFS_FILE_EXTENT_INLINE_DATA_START; +} + +static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info) +{ + return BTRFS_MAX_ITEM_SIZE(info) - sizeof(struct btrfs_dir_item); +} + /* * File system states */ @@ -1149,7 +1188,7 @@ struct btrfs_root { u64 root_dirid; };

-int btrfs_comp_keys(struct btrfs_key *, struct btrfs_key *); +int __btrfs_comp_keys(struct btrfs_key *, struct btrfs_key *); int btrfs_comp_keys_type(struct btrfs_key *, struct btrfs_key *); int btrfs_bin_search(union btrfs_tree_node *, struct btrfs_key *, int *); void btrfs_free_path(struct btrfs_path *); @@ -1209,4 +1248,13 @@ const char *btrfs_super_csum_name(u16 csum_type); u16 btrfs_csum_type_size(u16 csum_type); size_t btrfs_super_num_csums(void);

+/* ctree.c */ +int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2); +enum btrfs_tree_block_status +btrfs_check_node(struct btrfs_fs_info *fs_info, + struct btrfs_disk_key *parent_key, struct extent_buffer *buf); +enum btrfs_tree_block_status +btrfs_check_leaf(struct btrfs_fs_info *fs_info, + struct btrfs_disk_key *parent_key, struct extent_buffer *buf); +int btrfs_leaf_free_space(struct extent_buffer *leaf); #endif /* __BTRFS_CTREE_H__ */ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index edebf741fd..65b4020ebe 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -7,8 +7,113 @@ #include "disk-io.h" #include "ctree.h" #include "btrfs.h" +#include "volumes.h" +#include "extent-io.h" #include "crypto/hash.h"

+/* specified errno for check_tree_block */ +#define BTRFS_BAD_BYTENR (-1) +#define BTRFS_BAD_FSID (-2) +#define BTRFS_BAD_LEVEL (-3) +#define BTRFS_BAD_NRITEMS (-4) + +/* Calculate max possible nritems for a leaf/node */ +static u32 max_nritems(u8 level, u32 nodesize) +{ + + if (level == 0) + return ((nodesize - sizeof(struct btrfs_header)) / + sizeof(struct btrfs_item)); + return ((nodesize - sizeof(struct btrfs_header)) / + sizeof(struct btrfs_key_ptr)); +} + +static int check_tree_block(struct btrfs_fs_info *fs_info, + struct extent_buffer *buf) +{ + + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + u32 nodesize = fs_info->nodesize; + bool fsid_match = false; + int ret = BTRFS_BAD_FSID; + + if (buf->start != btrfs_header_bytenr(buf)) + return BTRFS_BAD_BYTENR; + if (btrfs_header_level(buf) >= BTRFS_MAX_LEVEL) + return BTRFS_BAD_LEVEL; + if (btrfs_header_nritems(buf) > max_nritems(btrfs_header_level(buf), + nodesize)) + return BTRFS_BAD_NRITEMS; + + /* Only leaf can be empty */ + if (btrfs_header_nritems(buf) == 0 && + btrfs_header_level(buf) != 0) + return BTRFS_BAD_NRITEMS; + + while (fs_devices) { + /* + * Checking the incompat flag is only valid for the current + * fs. For seed devices it's forbidden to have their uuid + * changed so reading ->fsid in this case is fine + */ + if (fs_devices == fs_info->fs_devices && + btrfs_fs_incompat(fs_info, METADATA_UUID)) + fsid_match = !memcmp_extent_buffer(buf, + fs_devices->metadata_uuid, + btrfs_header_fsid(), + BTRFS_FSID_SIZE); + else + fsid_match = !memcmp_extent_buffer(buf, + fs_devices->fsid, + btrfs_header_fsid(), + BTRFS_FSID_SIZE); + + + if (fsid_match) { + ret = 0; + break; + } + fs_devices = fs_devices->seed; + } + return ret; +} + +static void print_tree_block_error(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + int err) +{ + char fs_uuid[BTRFS_UUID_UNPARSED_SIZE] = {'\0'}; + char found_uuid[BTRFS_UUID_UNPARSED_SIZE] = {'\0'}; + u8 buf[BTRFS_UUID_SIZE]; + + if (!err) + return; + + fprintf(stderr, "bad tree block %llu, ", eb->start); + switch (err) { + case BTRFS_BAD_FSID: + read_extent_buffer(eb, buf, btrfs_header_fsid(), + BTRFS_UUID_SIZE); + uuid_unparse(buf, found_uuid); + uuid_unparse(fs_info->fs_devices->metadata_uuid, fs_uuid); + fprintf(stderr, "fsid mismatch, want=%s, have=%s\n", + fs_uuid, found_uuid); + break; + case BTRFS_BAD_BYTENR: + fprintf(stderr, "bytenr mismatch, want=%llu, have=%llu\n", + eb->start, btrfs_header_bytenr(eb)); + break; + case BTRFS_BAD_LEVEL: + fprintf(stderr, "bad level, %u > %d\n", + btrfs_header_level(eb), BTRFS_MAX_LEVEL); + break; + case BTRFS_BAD_NRITEMS: + fprintf(stderr, "invalid nr_items: %u\n", + btrfs_header_nritems(eb)); + break; + } +} + int btrfs_csum_data(u16 csum_type, const u8 *data, u8 *out, size_t len) { memset(out, 0, BTRFS_CSUM_SIZE); @@ -233,3 +338,246 @@ int btrfs_read_superblock(void)

return 0; } + +static int __csum_tree_block_size(struct extent_buffer *buf, u16 csum_size, + int verify, int silent, u16 csum_type) +{ + u8 result[BTRFS_CSUM_SIZE]; + u32 len; + + len = buf->len - BTRFS_CSUM_SIZE; + btrfs_csum_data(csum_type, (u8 *)buf->data + BTRFS_CSUM_SIZE, + result, len); + + if (verify) { + if (memcmp_extent_buffer(buf, result, 0, csum_size)) { + /* FIXME: format */ + if (!silent) + printk("checksum verify failed on %llu found %08X wanted %08X\n", + (unsigned long long)buf->start, + result[0], + buf->data[0]); + return 1; + } + } else { + write_extent_buffer(buf, result, 0, csum_size); + } + return 0; +} + +int csum_tree_block_size(struct extent_buffer *buf, u16 csum_size, int verify, + u16 csum_type) +{ + return __csum_tree_block_size(buf, csum_size, verify, 0, csum_type); +} + +static int csum_tree_block(struct btrfs_fs_info *fs_info, + struct extent_buffer *buf, int verify) +{ + u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + u16 csum_type = btrfs_super_csum_type(fs_info->super_copy); + + return csum_tree_block_size(buf, csum_size, verify, csum_type); +} + +struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, + u64 bytenr, u32 blocksize) +{ + return find_extent_buffer(&fs_info->extent_cache, + bytenr, blocksize); +} + +struct extent_buffer* btrfs_find_create_tree_block( + struct btrfs_fs_info *fs_info, u64 bytenr) +{ + return alloc_extent_buffer(fs_info, bytenr, fs_info->nodesize); +} + +static int verify_parent_transid(struct extent_io_tree *io_tree, + struct extent_buffer *eb, u64 parent_transid, + int ignore) +{ + int ret; + + if (!parent_transid || btrfs_header_generation(eb) == parent_transid) + return 0; + + if (extent_buffer_uptodate(eb) && + btrfs_header_generation(eb) == parent_transid) { + ret = 0; + goto out; + } + printk("parent transid verify failed on %llu wanted %llu found %llu\n", + (unsigned long long)eb->start, + (unsigned long long)parent_transid, + (unsigned long long)btrfs_header_generation(eb)); + if (ignore) { + eb->flags |= EXTENT_BAD_TRANSID; + printk("Ignoring transid failure\n"); + return 0; + } + + ret = 1; +out: + clear_extent_buffer_uptodate(eb); + return ret; + +} + +int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) +{ + int ret; + + ret = extent_buffer_uptodate(buf); + if (!ret) + return ret; + + ret = verify_parent_transid(&buf->fs_info->extent_cache, buf, + parent_transid, 1); + return !ret; +} + +int btrfs_set_buffer_uptodate(struct extent_buffer *eb) +{ + return set_extent_buffer_uptodate(eb); +} + +int read_whole_eb(struct btrfs_fs_info *info, struct extent_buffer *eb, int mirror) +{ + unsigned long offset = 0; + struct btrfs_multi_bio *multi = NULL; + struct btrfs_device *device; + int ret = 0; + u64 read_len; + unsigned long bytes_left = eb->len; + + while (bytes_left) { + read_len = bytes_left; + device = NULL; + + ret = btrfs_map_block(info, READ, eb->start + offset, + &read_len, &multi, mirror, NULL); + if (ret) { + printk("Couldn't map the block %Lu\n", eb->start + offset); + kfree(multi); + return -EIO; + } + device = multi->stripes[0].dev; + + if (!device->desc || !device->part) { + kfree(multi); + return -EIO; + } + + if (read_len > bytes_left) + read_len = bytes_left; + + ret = read_extent_from_disk(device->desc, device->part, + multi->stripes[0].physical, eb, + offset, read_len); + kfree(multi); + multi = NULL; + + if (ret) + return -EIO; + offset += read_len; + bytes_left -= read_len; + } + return 0; +} + +struct extent_buffer* read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, + u64 parent_transid) +{ + int ret; + struct extent_buffer *eb; + u64 best_transid = 0; + u32 sectorsize = fs_info->sectorsize; + int mirror_num = 1; + int good_mirror = 0; + int candidate_mirror = 0; + int num_copies; + int ignore = 0; + + /* + * Don't even try to create tree block for unaligned tree block + * bytenr. + * Such unaligned tree block will free overlapping extent buffer, + * causing use-after-free bugs for fuzzed images. + */ + if (bytenr < sectorsize || !IS_ALIGNED(bytenr, sectorsize)) { + error("tree block bytenr %llu is not aligned to sectorsize %u", + bytenr, sectorsize); + return ERR_PTR(-EIO); + } + + eb = btrfs_find_create_tree_block(fs_info, bytenr); + if (!eb) + return ERR_PTR(-ENOMEM); + + if (btrfs_buffer_uptodate(eb, parent_transid)) + return eb; + + num_copies = btrfs_num_copies(fs_info, eb->start, eb->len); + while (1) { + ret = read_whole_eb(fs_info, eb, mirror_num); + if (ret == 0 && csum_tree_block(fs_info, eb, 1) == 0 && + check_tree_block(fs_info, eb) == 0 && + verify_parent_transid(&fs_info->extent_cache, eb, + parent_transid, ignore) == 0) { + /* + * check_tree_block() is less strict to allow btrfs + * check to get raw eb with bad key order and fix it. + * But we still need to try to get a good copy if + * possible, or bad key order can go into tools like + * btrfs ins dump-tree. + */ + if (btrfs_header_level(eb)) + ret = btrfs_check_node(fs_info, NULL, eb); + else + ret = btrfs_check_leaf(fs_info, NULL, eb); + if (!ret || candidate_mirror == mirror_num) { + btrfs_set_buffer_uptodate(eb); + return eb; + } + if (candidate_mirror <= 0) + candidate_mirror = mirror_num; + } + if (ignore) { + if (candidate_mirror > 0) { + mirror_num = candidate_mirror; + continue; + } + if (check_tree_block(fs_info, eb)) + print_tree_block_error(fs_info, eb, + check_tree_block(fs_info, eb)); + else + fprintf(stderr, "Csum didn't match\n"); + ret = -EIO; + break; + } + if (num_copies == 1) { + ignore = 1; + continue; + } + if (btrfs_header_generation(eb) > best_transid) { + best_transid = btrfs_header_generation(eb); + good_mirror = mirror_num; + } + mirror_num++; + if (mirror_num > num_copies) { + if (candidate_mirror > 0) + mirror_num = candidate_mirror; + else + mirror_num = good_mirror; + ignore = 1; + continue; + } + } + /* + * We failed to read this tree block, it be should deleted right now + * to avoid stale cache populate the cache. + */ + free_extent_buffer(eb); + return ERR_PTR(ret); +} diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 35b9293946..ca731a5245 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -10,9 +10,23 @@ #define BTRFS_SUPER_INFO_OFFSET SZ_64K #define BTRFS_SUPER_INFO_SIZE SZ_4K

-int btrfs_csum_data(u16 csum_type, const u8 *data, u8 *out, size_t len); +/* U-boot specific */ +int btrfs_read_superblock(void); + +/* From btrfs-progs */ +int read_whole_eb(struct btrfs_fs_info *info, struct extent_buffer *eb, int mirror); +struct extent_buffer* read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, + u64 parent_transid);

+struct extent_buffer* btrfs_find_create_tree_block( + struct btrfs_fs_info *fs_info, u64 bytenr); +struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, + u64 bytenr, u32 blocksize); int btrfs_read_dev_super(struct blk_desc *desc, struct disk_partition *part, struct btrfs_super_block *sb); -int btrfs_read_superblock(void); +int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid); +int btrfs_set_buffer_uptodate(struct extent_buffer *buf); +int btrfs_csum_data(u16 csum_type, const u8 *data, u8 *out, size_t len); +int csum_tree_block_size(struct extent_buffer *buf, u16 csum_sectorsize, + int verify, u16 csum_type); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d88ae67217..55f431a289 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -65,7 +65,7 @@ int btrfs_lookup_inode(const struct btrfs_root *root, if (btrfs_search_tree(&tmp_root, location, &path)) return res;

- if (btrfs_comp_keys(location, btrfs_path_leaf_key(&path))) + if (__btrfs_comp_keys(location, btrfs_path_leaf_key(&path))) goto out;

if (item) { @@ -98,7 +98,7 @@ int btrfs_readlink(const struct btrfs_root *root, u64 inr, char *target) if (btrfs_search_tree(root, &key, &path)) return -1;

- if (btrfs_comp_keys(&key, btrfs_path_leaf_key(&path))) + if (__btrfs_comp_keys(&key, btrfs_path_leaf_key(&path))) goto out;

extent = btrfs_path_item_ptr(&path, struct btrfs_file_extent_item); @@ -333,7 +333,7 @@ u64 btrfs_file_read(const struct btrfs_root *root, u64 inr, u64 offset, if (btrfs_search_tree(root, &key, &path)) return -1ULL;

- if (btrfs_comp_keys(&key, btrfs_path_leaf_key(&path)) < 0) { + if (__btrfs_comp_keys(&key, btrfs_path_leaf_key(&path)) < 0) { if (btrfs_prev_slot(&path)) goto out;

From: Qu Wenruo wqu@suse.com

This is to avoid naming conflicts between extent buffer based btrfs_root.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/btrfs.c | 10 +++++----- fs/btrfs/btrfs.h | 26 +++++++++++++------------- fs/btrfs/ctree.c | 2 +- fs/btrfs/ctree.h | 6 +++--- fs/btrfs/dir-item.c | 4 ++-- fs/btrfs/inode.c | 16 ++++++++-------- fs/btrfs/root.c | 2 +- fs/btrfs/subvolume.c | 2 +- 8 files changed, 34 insertions(+), 34 deletions(-)

diff --git a/fs/btrfs/btrfs.c b/fs/btrfs/btrfs.c index 78a32497b5..b4535c9551 100644 --- a/fs/btrfs/btrfs.c +++ b/fs/btrfs/btrfs.c @@ -15,7 +15,7 @@

struct btrfs_info btrfs_info;

-static int readdir_callback(const struct btrfs_root *root, +static int readdir_callback(const struct __btrfs_root *root, struct btrfs_dir_item *item) { static const char typestr[BTRFS_FT_MAX][4] = { @@ -116,7 +116,7 @@ int btrfs_probe(struct blk_desc *fs_dev_desc,

int btrfs_ls(const char *path) { - struct btrfs_root root = btrfs_info.fs_root; + struct __btrfs_root root = btrfs_info.fs_root; u64 inr; u8 type;

@@ -142,7 +142,7 @@ int btrfs_ls(const char *path)

int btrfs_exists(const char *file) { - struct btrfs_root root = btrfs_info.fs_root; + struct __btrfs_root root = btrfs_info.fs_root; u64 inr; u8 type;

@@ -153,7 +153,7 @@ int btrfs_exists(const char *file)

int btrfs_size(const char *file, loff_t *size) { - struct btrfs_root root = btrfs_info.fs_root; + struct __btrfs_root root = btrfs_info.fs_root; struct btrfs_inode_item inode; u64 inr; u8 type; @@ -178,7 +178,7 @@ int btrfs_size(const char *file, loff_t *size) int btrfs_read(const char *file, void *buf, loff_t offset, loff_t len, loff_t *actread) { - struct btrfs_root root = btrfs_info.fs_root; + struct __btrfs_root root = btrfs_info.fs_root; struct btrfs_inode_item inode; u64 inr, rd; u8 type; diff --git a/fs/btrfs/btrfs.h b/fs/btrfs/btrfs.h index a52fd34489..ae29226e9a 100644 --- a/fs/btrfs/btrfs.h +++ b/fs/btrfs/btrfs.h @@ -14,9 +14,9 @@ struct btrfs_info { struct btrfs_super_block sb;

- struct btrfs_root tree_root; - struct btrfs_root fs_root; - struct btrfs_root chunk_root; + struct __btrfs_root tree_root; + struct __btrfs_root fs_root; + struct __btrfs_root chunk_root;

struct rb_root chunks_root; }; @@ -42,26 +42,26 @@ u32 btrfs_decompress(u8 type, const char *, u32, char *, u32); int btrfs_read_superblock(void);

/* dir-item.c */ -typedef int (*btrfs_readdir_callback_t)(const struct btrfs_root *, +typedef int (*btrfs_readdir_callback_t)(const struct __btrfs_root *, struct btrfs_dir_item *);

-int btrfs_lookup_dir_item(const struct btrfs_root *, u64, const char *, int, +int btrfs_lookup_dir_item(const struct __btrfs_root *, u64, const char *, int, struct btrfs_dir_item *); -int btrfs_readdir(const struct btrfs_root *, u64, btrfs_readdir_callback_t); +int btrfs_readdir(const struct __btrfs_root *, u64, btrfs_readdir_callback_t);

/* root.c */ -int btrfs_find_root(u64, struct btrfs_root *, struct btrfs_root_item *); +int btrfs_find_root(u64, struct __btrfs_root *, struct btrfs_root_item *); u64 btrfs_lookup_root_ref(u64, struct btrfs_root_ref *, char *);

/* inode.c */ -u64 btrfs_lookup_inode_ref(struct btrfs_root *, u64, struct btrfs_inode_ref *, +u64 btrfs_lookup_inode_ref(struct __btrfs_root *, u64, struct btrfs_inode_ref *, char *); -int btrfs_lookup_inode(const struct btrfs_root *, struct btrfs_key *, - struct btrfs_inode_item *, struct btrfs_root *); -int btrfs_readlink(const struct btrfs_root *, u64, char *); -u64 btrfs_lookup_path(struct btrfs_root *, u64, const char *, u8 *, +int btrfs_lookup_inode(const struct __btrfs_root *, struct btrfs_key *, + struct btrfs_inode_item *, struct __btrfs_root *); +int btrfs_readlink(const struct __btrfs_root *, u64, char *); +u64 btrfs_lookup_path(struct __btrfs_root *, u64, const char *, u8 *, struct btrfs_inode_item *, int); -u64 btrfs_file_read(const struct btrfs_root *, u64, u64, u64, char *); +u64 btrfs_file_read(const struct __btrfs_root *, u64, u64, u64, char *);

/* subvolume.c */ u64 btrfs_get_default_subvol_objectid(void); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 7bd12c2a1b..2956fe2cea 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -181,7 +181,7 @@ static int read_tree_node(u64 physical, union btrfs_tree_node **buf) return 0; }

-int btrfs_search_tree(const struct btrfs_root *root, struct btrfs_key *key, +int btrfs_search_tree(const struct __btrfs_root *root, struct btrfs_key *key, struct __btrfs_path *p) { u8 lvl, prev_lvl; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4562be9381..0aa6b49a65 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1182,7 +1182,7 @@ struct __btrfs_path { u32 slots[BTRFS_MAX_LEVEL]; };

-struct btrfs_root { +struct __btrfs_root { u64 objectid; u64 bytenr; u64 root_dirid; @@ -1192,7 +1192,7 @@ int __btrfs_comp_keys(struct btrfs_key *, struct btrfs_key *); int btrfs_comp_keys_type(struct btrfs_key *, struct btrfs_key *); int btrfs_bin_search(union btrfs_tree_node *, struct btrfs_key *, int *); void __btrfs_free_path(struct __btrfs_path *); -int btrfs_search_tree(const struct btrfs_root *, struct btrfs_key *, +int btrfs_search_tree(const struct __btrfs_root *, struct btrfs_key *, struct __btrfs_path *); int btrfs_prev_slot(struct __btrfs_path *); int btrfs_next_slot(struct __btrfs_path *); @@ -1203,7 +1203,7 @@ static inline struct btrfs_key *btrfs_path_leaf_key(struct __btrfs_path *p) { }

static inline struct btrfs_key * -btrfs_search_tree_key_type(const struct btrfs_root *root, u64 objectid, +btrfs_search_tree_key_type(const struct __btrfs_root *root, u64 objectid, u8 type, struct __btrfs_path *path) { struct btrfs_key key, *res; diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 5595542dab..756918df2e 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -61,7 +61,7 @@ btrfs_match_dir_item_name(struct __btrfs_path *path, const char *name, return NULL; }

-int btrfs_lookup_dir_item(const struct btrfs_root *root, u64 dir, +int btrfs_lookup_dir_item(const struct __btrfs_root *root, u64 dir, const char *name, int name_len, struct btrfs_dir_item *item) { @@ -87,7 +87,7 @@ out: return res ? 0 : -1; }

-int btrfs_readdir(const struct btrfs_root *root, u64 dir, +int btrfs_readdir(const struct __btrfs_root *root, u64 dir, btrfs_readdir_callback_t callback) { struct __btrfs_path path; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c0778726a0..be385d8a3f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8,7 +8,7 @@ #include "btrfs.h" #include <malloc.h>

-u64 btrfs_lookup_inode_ref(struct btrfs_root *root, u64 inr, +u64 btrfs_lookup_inode_ref(struct __btrfs_root *root, u64 inr, struct btrfs_inode_ref *refp, char *name) { struct __btrfs_path path; @@ -44,12 +44,12 @@ out: return res; }

-int btrfs_lookup_inode(const struct btrfs_root *root, +int btrfs_lookup_inode(const struct __btrfs_root *root, struct btrfs_key *location, struct btrfs_inode_item *item, - struct btrfs_root *new_root) + struct __btrfs_root *new_root) { - struct btrfs_root tmp_root = *root; + struct __btrfs_root tmp_root = *root; struct __btrfs_path path; int res = -1;

@@ -83,7 +83,7 @@ out: return res; }

-int btrfs_readlink(const struct btrfs_root *root, u64 inr, char *target) +int btrfs_readlink(const struct __btrfs_root *root, u64 inr, char *target) { struct __btrfs_path path; struct btrfs_key key; @@ -137,7 +137,7 @@ out:

/* inr must be a directory (for regular files with multiple hard links this function returns only one of the parents of the file) */ -static u64 get_parent_inode(struct btrfs_root *root, u64 inr, +static u64 get_parent_inode(struct __btrfs_root *root, u64 inr, struct btrfs_inode_item *inode_item) { struct btrfs_key key; @@ -209,7 +209,7 @@ static inline const char *skip_current_directories(const char *cur) return cur; }

-u64 btrfs_lookup_path(struct btrfs_root *root, u64 inr, const char *path, +u64 btrfs_lookup_path(struct __btrfs_root *root, u64 inr, const char *path, u8 *type_p, struct btrfs_inode_item *inode_item_p, int symlink_limit) { @@ -317,7 +317,7 @@ u64 btrfs_lookup_path(struct btrfs_root *root, u64 inr, const char *path, return inr; }

-u64 btrfs_file_read(const struct btrfs_root *root, u64 inr, u64 offset, +u64 btrfs_file_read(const struct __btrfs_root *root, u64 inr, u64 offset, u64 size, char *buf) { struct __btrfs_path path; diff --git a/fs/btrfs/root.c b/fs/btrfs/root.c index 9b5f645015..a424966df6 100644 --- a/fs/btrfs/root.c +++ b/fs/btrfs/root.c @@ -31,7 +31,7 @@ static void read_root_item(struct __btrfs_path *p, struct btrfs_root_item *item) } }

-int btrfs_find_root(u64 objectid, struct btrfs_root *root, +int btrfs_find_root(u64 objectid, struct __btrfs_root *root, struct btrfs_root_item *root_item) { struct __btrfs_path path; diff --git a/fs/btrfs/subvolume.c b/fs/btrfs/subvolume.c index fa5ef1e0ac..72b847b940 100644 --- a/fs/btrfs/subvolume.c +++ b/fs/btrfs/subvolume.c @@ -12,7 +12,7 @@ static int get_subvol_name(u64 subvolid, char *name, int max_len) { struct btrfs_root_ref rref; struct btrfs_inode_ref iref; - struct btrfs_root root; + struct __btrfs_root root; u64 dir; char tmp[BTRFS_NAME_LEN]; char *ptr;

From: Qu Wenruo wqu@suse.com

This patch copies the core function, btrfs_search_slot(), from btrfs-progs.

This version has the following functionality removed: - The ability to COW tree block Related code is commented out, and can be enabled in the future.

- The readahead functionality This is abused in kernel. Remove it completely.

With the core function in place, btrfs developers should feel at home now.

This also crossports supporting code like btrfs_previous_item() to ctree.[ch].

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/ctree.c | 537 ++++++++++++++++++++++++++++++++++++++++++++++- fs/btrfs/ctree.h | 61 +++++- 2 files changed, 591 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 2956fe2cea..98c08d353a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -5,10 +5,12 @@ * 2017 Marek Behun, CZ.NIC, marek.behun@nic.cz */

-#include "btrfs.h" +#include <linux/kernel.h> #include <log.h> #include <malloc.h> #include <memalign.h> +#include "btrfs.h" +#include "disk-io.h"

static const struct btrfs_csum { u16 size; @@ -42,6 +44,32 @@ u16 btrfs_csum_type_size(u16 csum_type) return btrfs_csums[csum_type].size; }

+struct btrfs_path *btrfs_alloc_path(void) +{ + struct btrfs_path *path; + path = kzalloc(sizeof(struct btrfs_path), GFP_NOFS); + return path; +} + +void btrfs_free_path(struct btrfs_path *p) +{ + if (!p) + return; + btrfs_release_path(p); + kfree(p); +} + +void btrfs_release_path(struct btrfs_path *p) +{ + int i; + for (i = 0; i < BTRFS_MAX_LEVEL; i++) { + if (!p->nodes[i]) + continue; + free_extent_buffer(p->nodes[i]); + } + memset(p, 0, sizeof(*p)); +} + int __btrfs_comp_keys(struct btrfs_key *a, struct btrfs_key *b) { if (a->objectid > b->objectid) @@ -72,7 +100,17 @@ int btrfs_comp_keys_type(struct btrfs_key *a, struct btrfs_key *b) return 0; }

-static int generic_bin_search(void *addr, int item_size, struct btrfs_key *key, +/* + * search for key in the extent_buffer. The items start at offset p, + * and they are item_size apart. There are 'max' items in p. + * + * the slot in the array is returned via slot, and it points to + * the place where you would insert key if it is not found in + * the array. + * + * slot may point to max if the key is bigger than all of the keys + */ +static int __generic_bin_search(void *addr, int item_size, struct btrfs_key *key, int max, int *slot) { int low = 0, high = max, mid, ret; @@ -98,8 +136,8 @@ static int generic_bin_search(void *addr, int item_size, struct btrfs_key *key, return 1; }

-int btrfs_bin_search(union btrfs_tree_node *p, struct btrfs_key *key, - int *slot) +int __btrfs_bin_search(union btrfs_tree_node *p, struct btrfs_key *key, + int *slot) { void *addr; unsigned long size; @@ -112,7 +150,7 @@ int btrfs_bin_search(union btrfs_tree_node *p, struct btrfs_key *key, size = sizeof(struct btrfs_item); }

- return generic_bin_search(addr, size, key, p->header.nritems, slot); + return __generic_bin_search(addr, size, key, p->header.nritems, slot); }

static void clear_path(struct __btrfs_path *p) @@ -209,7 +247,7 @@ int btrfs_search_tree(const struct __btrfs_root *root, struct btrfs_key *key, } prev_lvl = lvl;

- ret = btrfs_bin_search(buf, key, &slot); + ret = __btrfs_bin_search(buf, key, &slot); if (ret < 0) goto err; if (ret && slot > 0 && lvl) @@ -464,6 +502,349 @@ fail: return ret; }

+static int noinline check_block(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, int level) +{ + struct btrfs_disk_key key; + struct btrfs_disk_key *key_ptr = NULL; + struct extent_buffer *parent; + enum btrfs_tree_block_status ret; + + if (path->nodes[level + 1]) { + parent = path->nodes[level + 1]; + btrfs_node_key(parent, &key, path->slots[level + 1]); + key_ptr = &key; + } + if (level == 0) + ret = btrfs_check_leaf(fs_info, key_ptr, path->nodes[0]); + else + ret = btrfs_check_node(fs_info, key_ptr, path->nodes[level]); + if (ret == BTRFS_TREE_BLOCK_CLEAN) + return 0; + return -EIO; +} + +/* + * search for key in the extent_buffer. The items start at offset p, + * and they are item_size apart. There are 'max' items in p. + * + * the slot in the array is returned via slot, and it points to + * the place where you would insert key if it is not found in + * the array. + * + * slot may point to max if the key is bigger than all of the keys + */ +static int generic_bin_search(struct extent_buffer *eb, unsigned long p, + int item_size, const struct btrfs_key *key, + int max, int *slot) +{ + int low = 0; + int high = max; + int mid; + int ret; + unsigned long offset; + struct btrfs_disk_key *tmp; + + while(low < high) { + mid = (low + high) / 2; + offset = p + mid * item_size; + + tmp = (struct btrfs_disk_key *)(eb->data + offset); + ret = btrfs_comp_keys(tmp, key); + + if (ret < 0) + low = mid + 1; + else if (ret > 0) + high = mid; + else { + *slot = mid; + return 0; + } + } + *slot = low; + return 1; +} + +/* + * simple bin_search frontend that does the right thing for + * leaves vs nodes + */ +int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key, + int *slot) +{ + if (btrfs_header_level(eb) == 0) + return generic_bin_search(eb, + offsetof(struct btrfs_leaf, items), + sizeof(struct btrfs_item), + key, btrfs_header_nritems(eb), + slot); + else + return generic_bin_search(eb, + offsetof(struct btrfs_node, ptrs), + sizeof(struct btrfs_key_ptr), + key, btrfs_header_nritems(eb), + slot); +} + +struct extent_buffer *read_node_slot(struct btrfs_fs_info *fs_info, + struct extent_buffer *parent, int slot) +{ + struct extent_buffer *ret; + int level = btrfs_header_level(parent); + + if (slot < 0) + return NULL; + if (slot >= btrfs_header_nritems(parent)) + return NULL; + + if (level == 0) + return NULL; + + ret = read_tree_block(fs_info, btrfs_node_blockptr(parent, slot), + btrfs_node_ptr_generation(parent, slot)); + if (!extent_buffer_uptodate(ret)) + return ERR_PTR(-EIO); + + if (btrfs_header_level(ret) != level - 1) { + error("child eb corrupted: parent bytenr=%llu item=%d parent level=%d child level=%d", + btrfs_header_bytenr(parent), slot, + btrfs_header_level(parent), btrfs_header_level(ret)); + free_extent_buffer(ret); + return ERR_PTR(-EIO); + } + return ret; +} + +int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path, + u64 iobjectid, u64 ioff, u8 key_type, + struct btrfs_key *found_key) +{ + int ret; + struct btrfs_key key; + struct extent_buffer *eb; + struct btrfs_path *path; + + key.type = key_type; + key.objectid = iobjectid; + key.offset = ioff; + + if (found_path == NULL) { + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + } else + path = found_path; + + ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0); + if ((ret < 0) || (found_key == NULL)) + goto out; + + eb = path->nodes[0]; + if (ret && path->slots[0] >= btrfs_header_nritems(eb)) { + ret = btrfs_next_leaf(fs_root, path); + if (ret) + goto out; + eb = path->nodes[0]; + } + + btrfs_item_key_to_cpu(eb, found_key, path->slots[0]); + if (found_key->type != key.type || + found_key->objectid != key.objectid) { + ret = 1; + goto out; + } + +out: + if (path != found_path) + btrfs_free_path(path); + return ret; +} + +/* + * look for key in the tree. path is filled in with nodes along the way + * if key is found, we return zero and you can find the item in the leaf + * level of the path (level 0) + * + * If the key isn't found, the path points to the slot where it should + * be inserted, and 1 is returned. If there are other errors during the + * search a negative error number is returned. + * + * if ins_len > 0, nodes and leaves will be split as we walk down the + * tree. if ins_len < 0, nodes will be merged as we walk down the tree (if + * possible) + * + * NOTE: This version has no COW ability, thus we expect trans == NULL, + * ins_len == 0 and cow == 0. + */ +int btrfs_search_slot(struct btrfs_trans_handle *trans, + struct btrfs_root *root, const struct btrfs_key *key, + struct btrfs_path *p, int ins_len, int cow) +{ + struct extent_buffer *b; + int slot; + int ret; + int level; + struct btrfs_fs_info *fs_info = root->fs_info; + u8 lowest_level = 0; + + assert(trans == NULL && ins_len == 0 && cow == 0); + lowest_level = p->lowest_level; + WARN_ON(lowest_level && ins_len > 0); + WARN_ON(p->nodes[0] != NULL); + + b = root->node; + extent_buffer_get(b); + while (b) { + level = btrfs_header_level(b); + /* + if (cow) { + int wret; + wret = btrfs_cow_block(trans, root, b, + p->nodes[level + 1], + p->slots[level + 1], + &b); + if (wret) { + free_extent_buffer(b); + return wret; + } + } + */ + BUG_ON(!cow && ins_len); + if (level != btrfs_header_level(b)) + WARN_ON(1); + level = btrfs_header_level(b); + p->nodes[level] = b; + ret = check_block(fs_info, p, level); + if (ret) + return -1; + ret = btrfs_bin_search(b, key, &slot); + if (level != 0) { + if (ret && slot > 0) + slot -= 1; + p->slots[level] = slot; + /* + if ((p->search_for_split || ins_len > 0) && + btrfs_header_nritems(b) >= + BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3) { + int sret = split_node(trans, root, p, level); + BUG_ON(sret > 0); + if (sret) + return sret; + b = p->nodes[level]; + slot = p->slots[level]; + } else if (ins_len < 0) { + int sret = balance_level(trans, root, p, + level); + if (sret) + return sret; + b = p->nodes[level]; + if (!b) { + btrfs_release_path(p); + goto again; + } + slot = p->slots[level]; + BUG_ON(btrfs_header_nritems(b) == 1); + } + */ + /* this is only true while dropping a snapshot */ + if (level == lowest_level) + break; + + b = read_node_slot(fs_info, b, slot); + if (!extent_buffer_uptodate(b)) + return -EIO; + } else { + p->slots[level] = slot; + /* + if (ins_len > 0 && + ins_len > btrfs_leaf_free_space(b)) { + int sret = split_leaf(trans, root, key, + p, ins_len, ret == 0); + BUG_ON(sret > 0); + if (sret) + return sret; + } + */ + return ret; + } + } + return 1; +} + +/* + * Helper to use instead of search slot if no exact match is needed but + * instead the next or previous item should be returned. + * When find_higher is true, the next higher item is returned, the next lower + * otherwise. + * When return_any and find_higher are both true, and no higher item is found, + * return the next lower instead. + * When return_any is true and find_higher is false, and no lower item is found, + * return the next higher instead. + * It returns 0 if any item is found, 1 if none is found (tree empty), and + * < 0 on error + */ +int btrfs_search_slot_for_read(struct btrfs_root *root, + const struct btrfs_key *key, + struct btrfs_path *p, int find_higher, + int return_any) +{ + int ret; + struct extent_buffer *leaf; + +again: + ret = btrfs_search_slot(NULL, root, key, p, 0, 0); + if (ret <= 0) + return ret; + /* + * A return value of 1 means the path is at the position where the item + * should be inserted. Normally this is the next bigger item, but in + * case the previous item is the last in a leaf, path points to the + * first free slot in the previous leaf, i.e. at an invalid item. + */ + leaf = p->nodes[0]; + + if (find_higher) { + if (p->slots[0] >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(root, p); + if (ret <= 0) + return ret; + if (!return_any) + return 1; + /* + * No higher item found, return the next lower instead + */ + return_any = 0; + find_higher = 0; + btrfs_release_path(p); + goto again; + } + } else { + if (p->slots[0] == 0) { + ret = btrfs_prev_leaf(root, p); + if (ret < 0) + return ret; + if (!ret) { + leaf = p->nodes[0]; + if (p->slots[0] == btrfs_header_nritems(leaf)) + p->slots[0]--; + return 0; + } + if (!return_any) + return 1; + /* + * No lower item found, return the next higher instead + */ + return_any = 0; + find_higher = 1; + btrfs_release_path(p); + goto again; + } else { + --p->slots[0]; + } + } + return 0; +} + /* * how many bytes are required to store the items in a leaf. start * and nr indicate which items in the leaf to check. This totals up the @@ -505,3 +886,147 @@ int btrfs_leaf_free_space(struct extent_buffer *leaf) } return ret; } + +/* + * walk up the tree as far as required to find the previous leaf. + * returns 0 if it found something or 1 if there are no lesser leaves. + * returns < 0 on io errors. + */ +int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) +{ + int slot; + int level = 1; + struct extent_buffer *c; + struct extent_buffer *next = NULL; + struct btrfs_fs_info *fs_info = root->fs_info; + + while(level < BTRFS_MAX_LEVEL) { + if (!path->nodes[level]) + return 1; + + slot = path->slots[level]; + c = path->nodes[level]; + if (slot == 0) { + level++; + if (level == BTRFS_MAX_LEVEL) + return 1; + continue; + } + slot--; + + next = read_node_slot(fs_info, c, slot); + if (!extent_buffer_uptodate(next)) { + if (IS_ERR(next)) + return PTR_ERR(next); + return -EIO; + } + break; + } + path->slots[level] = slot; + while(1) { + level--; + c = path->nodes[level]; + free_extent_buffer(c); + slot = btrfs_header_nritems(next); + if (slot != 0) + slot--; + path->nodes[level] = next; + path->slots[level] = slot; + if (!level) + break; + next = read_node_slot(fs_info, next, slot); + if (!extent_buffer_uptodate(next)) { + if (IS_ERR(next)) + return PTR_ERR(next); + return -EIO; + } + } + return 0; +} + +/* + * Walk up the tree as far as necessary to find the next sibling tree block. + * More generic version of btrfs_next_leaf(), as it could find sibling nodes + * if @path->lowest_level is not 0. + * + * returns 0 if it found something or 1 if there are no greater leaves. + * returns < 0 on io errors. + */ +int btrfs_next_sibling_tree_block(struct btrfs_fs_info *fs_info, + struct btrfs_path *path) +{ + int slot; + int level = path->lowest_level + 1; + struct extent_buffer *c; + struct extent_buffer *next = NULL; + + BUG_ON(path->lowest_level + 1 >= BTRFS_MAX_LEVEL); + do { + if (!path->nodes[level]) + return 1; + + slot = path->slots[level] + 1; + c = path->nodes[level]; + if (slot >= btrfs_header_nritems(c)) { + level++; + if (level == BTRFS_MAX_LEVEL) + return 1; + continue; + } + + next = read_node_slot(fs_info, c, slot); + if (!extent_buffer_uptodate(next)) + return -EIO; + break; + } while (level < BTRFS_MAX_LEVEL); + path->slots[level] = slot; + while(1) { + level--; + c = path->nodes[level]; + free_extent_buffer(c); + path->nodes[level] = next; + path->slots[level] = 0; + if (level == path->lowest_level) + break; + next = read_node_slot(fs_info, next, 0); + if (!extent_buffer_uptodate(next)) + return -EIO; + } + return 0; +} + +int btrfs_previous_item(struct btrfs_root *root, + struct btrfs_path *path, u64 min_objectid, + int type) +{ + struct btrfs_key found_key; + struct extent_buffer *leaf; + u32 nritems; + int ret; + + while(1) { + if (path->slots[0] == 0) { + ret = btrfs_prev_leaf(root, path); + if (ret != 0) + return ret; + } else { + path->slots[0]--; + } + leaf = path->nodes[0]; + nritems = btrfs_header_nritems(leaf); + if (nritems == 0) + return 1; + if (path->slots[0] == nritems) + path->slots[0]--; + + btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); + if (found_key.objectid < min_objectid) + break; + if (found_key.type == type) + return 0; + if (found_key.objectid == min_objectid && + found_key.type < type) + break; + } + return 1; +} diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index e658c88aee..7c814fd2a9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -52,6 +52,15 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes) #define __BTRFS_LEAF_DATA_SIZE(bs) ((bs) - sizeof(struct btrfs_header)) #define BTRFS_LEAF_DATA_SIZE(fs_info) \ (__BTRFS_LEAF_DATA_SIZE(fs_info->nodesize)) + +struct btrfs_path { + struct extent_buffer *nodes[BTRFS_MAX_LEVEL]; + int slots[BTRFS_MAX_LEVEL]; + + /* keep some upper locks as we walk down */ + u8 lowest_level; +}; + /* ioprio of readahead is set to idle */ #define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))

@@ -86,6 +95,7 @@ struct btrfs_root { struct rb_node rb_node; };

+struct btrfs_trans_handle; struct btrfs_device; struct btrfs_fs_devices; struct btrfs_fs_info { @@ -1207,7 +1217,7 @@ struct __btrfs_root {

int __btrfs_comp_keys(struct btrfs_key *, struct btrfs_key *); int btrfs_comp_keys_type(struct btrfs_key *, struct btrfs_key *); -int btrfs_bin_search(union btrfs_tree_node *, struct btrfs_key *, int *); +int __btrfs_bin_search(union btrfs_tree_node *, struct btrfs_key *, int *); void __btrfs_free_path(struct __btrfs_path *); int btrfs_search_tree(const struct __btrfs_root *, struct btrfs_key *, struct __btrfs_path *); @@ -1273,5 +1283,54 @@ btrfs_check_node(struct btrfs_fs_info *fs_info, enum btrfs_tree_block_status btrfs_check_leaf(struct btrfs_fs_info *fs_info, struct btrfs_disk_key *parent_key, struct extent_buffer *buf); +struct extent_buffer *read_node_slot(struct btrfs_fs_info *fs_info, + struct extent_buffer *parent, int slot); +int btrfs_previous_item(struct btrfs_root *root, + struct btrfs_path *path, u64 min_objectid, + int type); +int btrfs_next_sibling_tree_block(struct btrfs_fs_info *fs_info, + struct btrfs_path *path); +/* + * Walk up the tree as far as necessary to find the next leaf. + * + * returns 0 if it found something or 1 if there are no greater leaves. + * returns < 0 on io errors. + */ +static inline int btrfs_next_leaf(struct btrfs_root *root, + struct btrfs_path *path) +{ + path->lowest_level = 0; + return btrfs_next_sibling_tree_block(root->fs_info, path); +} + +static inline int btrfs_next_item(struct btrfs_root *root, + struct btrfs_path *p) +{ + ++p->slots[0]; + if (p->slots[0] >= btrfs_header_nritems(p->nodes[0])) + return btrfs_next_leaf(root, p); + return 0; +} + +int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct extent_buffer *leaf); +int btrfs_search_slot(struct btrfs_trans_handle *trans, + struct btrfs_root *root, const struct btrfs_key *key, + struct btrfs_path *p, int ins_len, int cow); +int btrfs_search_slot_for_read(struct btrfs_root *root, + const struct btrfs_key *key, + struct btrfs_path *p, int find_higher, + int return_any); +void btrfs_release_path(struct btrfs_path *p); +struct btrfs_path *btrfs_alloc_path(void); +void btrfs_free_path(struct btrfs_path *p); +static inline void btrfs_init_path(struct btrfs_path *p) +{ + memset(p, 0, sizeof(*p)); +} +int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key, + int *slot); +int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path, + u64 iobjectid, u64 ioff, u8 key_type, + struct btrfs_key *found_key); #endif /* __BTRFS_CTREE_H__ */

From: Qu Wenruo wqu@suse.com

open_ctree_fs_info() is the main entry point to open btrfs.

This version is a simplfied version of __open_ctree_fd() of btrfs-progs, the main differences are: - Parameters on how to specify a block device Instead of @fd and @path, U-Boot uses blk_desc and disk_partition_t.

- Remove open_ctree flags There won't be multiple open ctree modes in U-Boot.

Otherwise functions structures are all kept the same.

With open_ctree_fs_info() implemented, also introduce the global current_fs_info pointer to show the current opened btrfs.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/Makefile | 2 +- fs/btrfs/btrfs.c | 15 +- fs/btrfs/btrfs.h | 1 + fs/btrfs/compat.h | 2 + fs/btrfs/ctree.h | 4 + fs/btrfs/disk-io.c | 509 +++++++++++++++++++++++++++++++++++++++++-- fs/btrfs/disk-io.h | 19 ++ fs/btrfs/root-tree.c | 47 ++++ 8 files changed, 579 insertions(+), 20 deletions(-) create mode 100644 fs/btrfs/root-tree.c

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index ec30aae765..8d76422ce2 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -4,4 +4,4 @@

obj-y := btrfs.o chunk-map.o compression.o ctree.o dev.o dir-item.o \ extent-io.o inode.o root.o subvolume.o crypto/hash.o disk-io.o \ - common/rbtree-utils.o extent-cache.o volumes.o + common/rbtree-utils.o extent-cache.o volumes.o root-tree.o diff --git a/fs/btrfs/btrfs.c b/fs/btrfs/btrfs.c index f5266f1b91..2bd2ec9ed9 100644 --- a/fs/btrfs/btrfs.c +++ b/fs/btrfs/btrfs.c @@ -14,6 +14,7 @@ #include "disk-io.h"

struct btrfs_info btrfs_info; +struct btrfs_fs_info *current_fs_info;

static int readdir_callback(const struct __btrfs_root *root, struct btrfs_dir_item *item) @@ -81,6 +82,9 @@ static int readdir_callback(const struct __btrfs_root *root, int btrfs_probe(struct blk_desc *fs_dev_desc, struct disk_partition *fs_partition) { + struct btrfs_fs_info *fs_info; + int ret = -1; + btrfs_blk_desc = fs_dev_desc; btrfs_part_info = fs_partition;

@@ -111,7 +115,12 @@ int btrfs_probe(struct blk_desc *fs_dev_desc, return -1; }

- return 0; + fs_info = open_ctree_fs_info(fs_dev_desc, fs_partition); + if (fs_info) { + current_fs_info = fs_info; + ret = 0; + } + return ret; }

int btrfs_ls(const char *path) @@ -215,6 +224,10 @@ int btrfs_read(const char *file, void *buf, loff_t offset, loff_t len, void btrfs_close(void) { btrfs_chunk_map_exit(); + if (current_fs_info) { + close_ctree_fs_info(current_fs_info); + current_fs_info = NULL; + } }

int btrfs_uuid(char *uuid_str) diff --git a/fs/btrfs/btrfs.h b/fs/btrfs/btrfs.h index 7dfdaf77ba..a52ff942f2 100644 --- a/fs/btrfs/btrfs.h +++ b/fs/btrfs/btrfs.h @@ -22,6 +22,7 @@ struct btrfs_info { };

extern struct btrfs_info btrfs_info; +extern struct btrfs_fs_info *current_fs_info;

/* dev.c */ extern struct blk_desc *btrfs_blk_desc; diff --git a/fs/btrfs/compat.h b/fs/btrfs/compat.h index b6b75deb3e..4da88fc311 100644 --- a/fs/btrfs/compat.h +++ b/fs/btrfs/compat.h @@ -18,6 +18,8 @@ static inline void error(const char *fmt, ...) printf("\n"); }

+#define ASSERT(c) assert(c) + #define BTRFS_UUID_UNPARSED_SIZE 37

/* diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7c814fd2a9..b050b5844d 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1275,6 +1275,10 @@ const char *btrfs_super_csum_name(u16 csum_type); u16 btrfs_csum_type_size(u16 csum_type); size_t btrfs_super_num_csums(void);

+/* root-tree.c */ +int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, + struct btrfs_root_item *item, struct btrfs_key *key); + /* ctree.c */ int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2); enum btrfs_tree_block_status diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 65b4020ebe..4d08b0204a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4,6 +4,7 @@ #include <uuid.h> #include <memalign.h> #include "kernel-shared/btrfs_tree.h" +#include "common/rbtree-utils.h" #include "disk-io.h" #include "ctree.h" #include "btrfs.h" @@ -424,24 +425,6 @@ out:

}

-int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) -{ - int ret; - - ret = extent_buffer_uptodate(buf); - if (!ret) - return ret; - - ret = verify_parent_transid(&buf->fs_info->extent_cache, buf, - parent_transid, 1); - return !ret; -} - -int btrfs_set_buffer_uptodate(struct extent_buffer *eb) -{ - return set_extent_buffer_uptodate(eb); -} - int read_whole_eb(struct btrfs_fs_info *info, struct extent_buffer *eb, int mirror) { unsigned long offset = 0; @@ -581,3 +564,493 @@ struct extent_buffer* read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, free_extent_buffer(eb); return ERR_PTR(ret); } + +void btrfs_setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, + u64 objectid) +{ + root->node = NULL; + root->track_dirty = 0; + + root->fs_info = fs_info; + root->objectid = objectid; + root->last_trans = 0; + root->last_inode_alloc = 0; + + memset(&root->root_key, 0, sizeof(root->root_key)); + memset(&root->root_item, 0, sizeof(root->root_item)); + root->root_key.objectid = objectid; +} + +static int find_and_setup_root(struct btrfs_root *tree_root, + struct btrfs_fs_info *fs_info, + u64 objectid, struct btrfs_root *root) +{ + int ret; + u64 generation; + + btrfs_setup_root(root, fs_info, objectid); + ret = btrfs_find_last_root(tree_root, objectid, + &root->root_item, &root->root_key); + if (ret) + return ret; + + generation = btrfs_root_generation(&root->root_item); + root->node = read_tree_block(fs_info, + btrfs_root_bytenr(&root->root_item), generation); + if (!extent_buffer_uptodate(root->node)) + return -EIO; + + return 0; +} + +int btrfs_free_fs_root(struct btrfs_root *root) +{ + if (root->node) + free_extent_buffer(root->node); + kfree(root); + return 0; +} + +static void __free_fs_root(struct rb_node *node) +{ + struct btrfs_root *root; + + root = container_of(node, struct btrfs_root, rb_node); + btrfs_free_fs_root(root); +} + +FREE_RB_BASED_TREE(fs_roots, __free_fs_root); + +struct btrfs_root *btrfs_read_fs_root_no_cache(struct btrfs_fs_info *fs_info, + struct btrfs_key *location) +{ + struct btrfs_root *root; + struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_path *path; + struct extent_buffer *l; + u64 generation; + int ret = 0; + + root = calloc(1, sizeof(*root)); + if (!root) + return ERR_PTR(-ENOMEM); + if (location->offset == (u64)-1) { + ret = find_and_setup_root(tree_root, fs_info, + location->objectid, root); + if (ret) { + free(root); + return ERR_PTR(ret); + } + goto insert; + } + + btrfs_setup_root(root, fs_info, + location->objectid); + + path = btrfs_alloc_path(); + if (!path) { + free(root); + return ERR_PTR(-ENOMEM); + } + + ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0); + if (ret != 0) { + if (ret > 0) + ret = -ENOENT; + goto out; + } + l = path->nodes[0]; + read_extent_buffer(l, &root->root_item, + btrfs_item_ptr_offset(l, path->slots[0]), + sizeof(root->root_item)); + memcpy(&root->root_key, location, sizeof(*location)); + + /* If this root is already an orphan, no need to read */ + if (btrfs_root_refs(&root->root_item) == 0) { + ret = -ENOENT; + goto out; + } + ret = 0; +out: + btrfs_free_path(path); + if (ret) { + free(root); + return ERR_PTR(ret); + } + generation = btrfs_root_generation(&root->root_item); + root->node = read_tree_block(fs_info, + btrfs_root_bytenr(&root->root_item), generation); + if (!extent_buffer_uptodate(root->node)) { + free(root); + return ERR_PTR(-EIO); + } +insert: + root->ref_cows = 1; + return root; +} + +static int btrfs_fs_roots_compare_objectids(struct rb_node *node, + void *data) +{ + u64 objectid = *((u64 *)data); + struct btrfs_root *root; + + root = rb_entry(node, struct btrfs_root, rb_node); + if (objectid > root->objectid) + return 1; + else if (objectid < root->objectid) + return -1; + else + return 0; +} + +int btrfs_fs_roots_compare_roots(struct rb_node *node1, struct rb_node *node2) +{ + struct btrfs_root *root; + + root = rb_entry(node2, struct btrfs_root, rb_node); + return btrfs_fs_roots_compare_objectids(node1, (void *)&root->objectid); +} + +struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info, + struct btrfs_key *location) +{ + struct btrfs_root *root; + struct rb_node *node; + int ret; + u64 objectid = location->objectid; + + if (location->objectid == BTRFS_ROOT_TREE_OBJECTID) + return fs_info->tree_root; + if (location->objectid == BTRFS_CHUNK_TREE_OBJECTID) + return fs_info->chunk_root; + if (location->objectid == BTRFS_CSUM_TREE_OBJECTID) + return fs_info->csum_root; + BUG_ON(location->objectid == BTRFS_TREE_RELOC_OBJECTID || + location->offset != (u64)-1); + + node = rb_search(&fs_info->fs_root_tree, (void *)&objectid, + btrfs_fs_roots_compare_objectids, NULL); + if (node) + return container_of(node, struct btrfs_root, rb_node); + + root = btrfs_read_fs_root_no_cache(fs_info, location); + if (IS_ERR(root)) + return root; + + ret = rb_insert(&fs_info->fs_root_tree, &root->rb_node, + btrfs_fs_roots_compare_roots); + BUG_ON(ret); + return root; +} + +void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) +{ + free(fs_info->tree_root); + free(fs_info->chunk_root); + free(fs_info->csum_root); + free(fs_info->super_copy); + free(fs_info); +} + +struct btrfs_fs_info *btrfs_new_fs_info(void) +{ + struct btrfs_fs_info *fs_info; + + fs_info = calloc(1, sizeof(struct btrfs_fs_info)); + if (!fs_info) + return NULL; + + fs_info->tree_root = calloc(1, sizeof(struct btrfs_root)); + fs_info->chunk_root = calloc(1, sizeof(struct btrfs_root)); + fs_info->csum_root = calloc(1, sizeof(struct btrfs_root)); + fs_info->super_copy = calloc(1, BTRFS_SUPER_INFO_SIZE); + + if (!fs_info->tree_root || !fs_info->chunk_root || + !fs_info->csum_root || !fs_info->super_copy) + goto free_all; + + extent_io_tree_init(&fs_info->extent_cache); + + fs_info->fs_root_tree = RB_ROOT; + cache_tree_init(&fs_info->mapping_tree.cache_tree); + + mutex_init(&fs_info->fs_mutex); + + return fs_info; +free_all: + btrfs_free_fs_info(fs_info); + return NULL; +} + +static int setup_root_or_create_block(struct btrfs_fs_info *fs_info, + struct btrfs_root *info_root, + u64 objectid, char *str) +{ + struct btrfs_root *root = fs_info->tree_root; + int ret; + + ret = find_and_setup_root(root, fs_info, objectid, info_root); + if (ret) { + error("could not setup %s tree", str); + return -EIO; + } + + return 0; +} + +int btrfs_setup_all_roots(struct btrfs_fs_info *fs_info) +{ + struct btrfs_super_block *sb = fs_info->super_copy; + struct btrfs_root *root; + struct btrfs_key key; + u64 root_tree_bytenr; + u64 generation; + int ret; + + root = fs_info->tree_root; + btrfs_setup_root(root, fs_info, BTRFS_ROOT_TREE_OBJECTID); + generation = btrfs_super_generation(sb); + + root_tree_bytenr = btrfs_super_root(sb); + + root->node = read_tree_block(fs_info, root_tree_bytenr, generation); + if (!extent_buffer_uptodate(root->node)) { + fprintf(stderr, "Couldn't read tree root\n"); + return -EIO; + } + + ret = setup_root_or_create_block(fs_info, fs_info->csum_root, + BTRFS_CSUM_TREE_OBJECTID, "csum"); + if (ret) + return ret; + fs_info->csum_root->track_dirty = 1; + + fs_info->last_trans_committed = generation; + + key.objectid = BTRFS_FS_TREE_OBJECTID; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + fs_info->fs_root = btrfs_read_fs_root(fs_info, &key); + + if (IS_ERR(fs_info->fs_root)) + return -EIO; + return 0; +} + +void btrfs_release_all_roots(struct btrfs_fs_info *fs_info) +{ + if (fs_info->csum_root) + free_extent_buffer(fs_info->csum_root->node); + if (fs_info->tree_root) + free_extent_buffer(fs_info->tree_root->node); + if (fs_info->chunk_root) + free_extent_buffer(fs_info->chunk_root->node); +} + +static void free_map_lookup(struct cache_extent *ce) +{ + struct map_lookup *map; + + map = container_of(ce, struct map_lookup, ce); + kfree(map); +} + +FREE_EXTENT_CACHE_BASED_TREE(mapping_cache, free_map_lookup); + +void btrfs_cleanup_all_caches(struct btrfs_fs_info *fs_info) +{ + free_mapping_cache_tree(&fs_info->mapping_tree.cache_tree); + extent_io_tree_cleanup(&fs_info->extent_cache); +} + +static int btrfs_scan_fs_devices(struct blk_desc *desc, + struct disk_partition *part, + struct btrfs_fs_devices **fs_devices) +{ + u64 total_devs; + int ret; + + if (round_up(BTRFS_SUPER_INFO_SIZE + BTRFS_SUPER_INFO_OFFSET, + desc->blksz) > (part->size << desc->log2blksz)) { + error("superblock end %u is larger than device size " LBAFU, + BTRFS_SUPER_INFO_SIZE + BTRFS_SUPER_INFO_OFFSET, + part->size << desc->log2blksz); + return -EINVAL; + } + + ret = btrfs_scan_one_device(desc, part, fs_devices, &total_devs); + if (ret) { + fprintf(stderr, "No valid Btrfs found\n"); + return ret; + } + return 0; +} + +int btrfs_check_fs_compatibility(struct btrfs_super_block *sb) +{ + u64 features; + + features = btrfs_super_incompat_flags(sb) & + ~BTRFS_FEATURE_INCOMPAT_SUPP; + if (features) { + printk("couldn't open because of unsupported " + "option features (%llx).\n", + (unsigned long long)features); + return -ENOTSUPP; + } + + features = btrfs_super_incompat_flags(sb); + if (!(features & BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF)) { + features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; + btrfs_set_super_incompat_flags(sb, features); + } + + return 0; +} + +static int btrfs_setup_chunk_tree_and_device_map(struct btrfs_fs_info *fs_info) +{ + struct btrfs_super_block *sb = fs_info->super_copy; + u64 chunk_root_bytenr; + u64 generation; + int ret; + + btrfs_setup_root(fs_info->chunk_root, fs_info, + BTRFS_CHUNK_TREE_OBJECTID); + + ret = btrfs_read_sys_array(fs_info); + if (ret) + return ret; + + generation = btrfs_super_chunk_root_generation(sb); + chunk_root_bytenr = btrfs_super_chunk_root(sb); + + fs_info->chunk_root->node = read_tree_block(fs_info, + chunk_root_bytenr, + generation); + if (!extent_buffer_uptodate(fs_info->chunk_root->node)) { + error("cannot read chunk root"); + return -EIO; + } + + ret = btrfs_read_chunk_tree(fs_info); + if (ret) { + fprintf(stderr, "Couldn't read chunk tree\n"); + return ret; + } + return 0; +} + +struct btrfs_fs_info *open_ctree_fs_info(struct blk_desc *desc, + struct disk_partition *part) +{ + struct btrfs_fs_info *fs_info; + struct btrfs_super_block *disk_super; + struct btrfs_fs_devices *fs_devices = NULL; + struct extent_buffer *eb; + int ret; + + fs_info = btrfs_new_fs_info(); + if (!fs_info) { + fprintf(stderr, "Failed to allocate memory for fs_info\n"); + return NULL; + } + + ret = btrfs_scan_fs_devices(desc, part, &fs_devices); + if (ret) + goto out; + + fs_info->fs_devices = fs_devices; + + ret = btrfs_open_devices(fs_devices); + if (ret) + goto out; + + disk_super = fs_info->super_copy; + ret = btrfs_read_dev_super(desc, part, disk_super); + if (ret) { + printk("No valid btrfs found\n"); + goto out_devices; + } + + if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_CHANGING_FSID) { + fprintf(stderr, "ERROR: Filesystem UUID change in progress\n"); + goto out_devices; + } + + ASSERT(!memcmp(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE)); + if (btrfs_fs_incompat(fs_info, METADATA_UUID)) + ASSERT(!memcmp(disk_super->metadata_uuid, + fs_devices->metadata_uuid, BTRFS_FSID_SIZE)); + + fs_info->sectorsize = btrfs_super_sectorsize(disk_super); + fs_info->nodesize = btrfs_super_nodesize(disk_super); + fs_info->stripesize = btrfs_super_stripesize(disk_super); + + ret = btrfs_check_fs_compatibility(fs_info->super_copy); + if (ret) + goto out_devices; + + ret = btrfs_setup_chunk_tree_and_device_map(fs_info); + if (ret) + goto out_chunk; + + /* Chunk tree root is unable to read, return directly */ + if (!fs_info->chunk_root) + return fs_info; + + eb = fs_info->chunk_root->node; + read_extent_buffer(eb, fs_info->chunk_tree_uuid, + btrfs_header_chunk_tree_uuid(eb), + BTRFS_UUID_SIZE); + + ret = btrfs_setup_all_roots(fs_info); + if (ret) + goto out_chunk; + + return fs_info; + +out_chunk: + btrfs_release_all_roots(fs_info); + btrfs_cleanup_all_caches(fs_info); +out_devices: + btrfs_close_devices(fs_devices); +out: + btrfs_free_fs_info(fs_info); + return NULL; +} + +int close_ctree_fs_info(struct btrfs_fs_info *fs_info) +{ + int ret; + int err = 0; + + free_fs_roots_tree(&fs_info->fs_root_tree); + + btrfs_release_all_roots(fs_info); + ret = btrfs_close_devices(fs_info->fs_devices); + btrfs_cleanup_all_caches(fs_info); + btrfs_free_fs_info(fs_info); + if (!err) + err = ret; + return err; +} + +int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) +{ + int ret; + + ret = extent_buffer_uptodate(buf); + if (!ret) + return ret; + + ret = verify_parent_transid(&buf->fs_info->extent_cache, buf, + parent_transid, 1); + return !ret; +} + +int btrfs_set_buffer_uptodate(struct extent_buffer *eb) +{ + return set_extent_buffer_uptodate(eb); +} diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index ca731a5245..9daf959c57 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -22,6 +22,25 @@ struct extent_buffer* btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, u64 bytenr); struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, u32 blocksize); +struct btrfs_root *btrfs_read_fs_root_no_cache(struct btrfs_fs_info *fs_info, + struct btrfs_key *location); +struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info, + struct btrfs_key *location); + +void btrfs_setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, + u64 objectid); + +void btrfs_free_fs_info(struct btrfs_fs_info *fs_info); +struct btrfs_fs_info *btrfs_new_fs_info(void); +int btrfs_check_fs_compatibility(struct btrfs_super_block *sb); +int btrfs_setup_all_roots(struct btrfs_fs_info *fs_info); +void btrfs_release_all_roots(struct btrfs_fs_info *fs_info); +void btrfs_cleanup_all_caches(struct btrfs_fs_info *fs_info); + +struct btrfs_fs_info *open_ctree_fs_info(struct blk_desc *desc, + struct disk_partition *part); +int close_ctree_fs_info(struct btrfs_fs_info *fs_info); + int btrfs_read_dev_super(struct blk_desc *desc, struct disk_partition *part, struct btrfs_super_block *sb); int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c new file mode 100644 index 0000000000..a39ad72067 --- /dev/null +++ b/fs/btrfs/root-tree.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include "ctree.h" + +int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, + struct btrfs_root_item *item, struct btrfs_key *key) +{ + struct btrfs_path *path; + struct btrfs_key search_key; + struct btrfs_key found_key; + struct extent_buffer *l; + int ret; + int slot; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + search_key.objectid = objectid; + search_key.type = BTRFS_ROOT_ITEM_KEY; + search_key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); + if (ret < 0) + goto out; + if (path->slots[0] == 0) { + ret = -ENOENT; + goto out; + } + + BUG_ON(ret == 0); + l = path->nodes[0]; + slot = path->slots[0] - 1; + btrfs_item_key_to_cpu(l, &found_key, slot); + if (found_key.type != BTRFS_ROOT_ITEM_KEY || + found_key.objectid != objectid) { + ret = -ENOENT; + goto out; + } + read_extent_buffer(l, item, btrfs_item_ptr_offset(l, slot), + sizeof(*item)); + memcpy(key, &found_key, sizeof(found_key)); + ret = 0; +out: + btrfs_free_path(path); + return ret; +}

From: Qu Wenruo wqu@suse.com

The existing __btrfs_readlink() can be easily re-implemented using the extent buffer based btrfs_readlink().

This is the first step to re-implement U-Boot's btrfs code.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/btrfs.h | 1 + fs/btrfs/inode.c | 101 ++++++++++++++++++++++++++++++----------------- 2 files changed, 65 insertions(+), 37 deletions(-)

diff --git a/fs/btrfs/btrfs.h b/fs/btrfs/btrfs.h index e8197391a2..53d53f310b 100644 --- a/fs/btrfs/btrfs.h +++ b/fs/btrfs/btrfs.h @@ -60,6 +60,7 @@ u64 __btrfs_lookup_inode_ref(struct __btrfs_root *, u64, struct btrfs_inode_ref int __btrfs_lookup_inode(const struct __btrfs_root *, struct btrfs_key *, struct btrfs_inode_item *, struct __btrfs_root *); int __btrfs_readlink(const struct __btrfs_root *, u64, char *); +int btrfs_readlink(struct btrfs_root *root, u64 ino, char *target); u64 __btrfs_lookup_path(struct __btrfs_root *, u64, const char *, u8 *, struct btrfs_inode_item *, int); u64 btrfs_file_read(const struct __btrfs_root *, u64, u64, u64, char *); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index eb34f546b5..007cf32c16 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5,8 +5,9 @@ * 2017 Marek Behun, CZ.NIC, marek.behun@nic.cz */

-#include "btrfs.h" #include <malloc.h> +#include "btrfs.h" +#include "disk-io.h"

u64 __btrfs_lookup_inode_ref(struct __btrfs_root *root, u64 inr, struct btrfs_inode_ref *refp, char *name) @@ -83,56 +84,82 @@ out: return res; }

-int __btrfs_readlink(const struct __btrfs_root *root, u64 inr, char *target) +/* + * Read the content of symlink inode @ino of @root, into @target. + * NOTE: @target will not be \0 termiated, caller should handle it properly. + * + * Return the number of read data. + * Return <0 for error. + */ +int btrfs_readlink(struct btrfs_root *root, u64 ino, char *target) { - struct __btrfs_path path; + struct btrfs_path path; struct btrfs_key key; - struct btrfs_file_extent_item *extent; - const char *data_ptr; - int res = -1; + struct btrfs_file_extent_item *fi; + int ret;

- key.objectid = inr; + key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = 0; + btrfs_init_path(&path);

- if (btrfs_search_tree(root, &key, &path)) - return -1; - - if (__btrfs_comp_keys(&key, btrfs_path_leaf_key(&path))) - goto out; - - extent = btrfs_path_item_ptr(&path, struct btrfs_file_extent_item); - if (extent->type != BTRFS_FILE_EXTENT_INLINE) { - printf("%s: Extent for symlink %llu not of INLINE type\n", - __func__, inr); + ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0); + if (ret < 0) + return ret; + if (ret > 0) { + ret = -ENOENT; goto out; } - - btrfs_file_extent_item_to_cpu_inl(extent); - - if (extent->compression != BTRFS_COMPRESS_NONE) { - printf("%s: Symlink %llu extent data compressed!\n", __func__, - inr); + fi = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_file_extent_item); + if (btrfs_file_extent_type(path.nodes[0], fi) != + BTRFS_FILE_EXTENT_INLINE) { + ret = -EUCLEAN; + error("Extent for symlink %llu must be INLINE type!", ino); goto out; - } else if (extent->encryption != 0) { - printf("%s: Symlink %llu extent data encrypted!\n", __func__, - inr); + } + if (btrfs_file_extent_compression(path.nodes[0], fi) != + BTRFS_COMPRESS_NONE) { + ret = -EUCLEAN; + error("Extent for symlink %llu must not be compressed!", ino); goto out; - } else if (extent->ram_bytes >= btrfs_info.sb.sectorsize) { - printf("%s: Symlink %llu extent data too long (%llu)!\n", - __func__, inr, extent->ram_bytes); + } + if (btrfs_file_extent_ram_bytes(path.nodes[0], fi) >= + root->fs_info->sectorsize) { + ret = -EUCLEAN; + error("Symlink %llu extent data too large (%llu)!\n", + ino, btrfs_file_extent_ram_bytes(path.nodes[0], fi)); goto out; } + read_extent_buffer(path.nodes[0], target, + btrfs_file_extent_inline_start(fi), + btrfs_file_extent_ram_bytes(path.nodes[0], fi)); + ret = btrfs_file_extent_ram_bytes(path.nodes[0], fi); +out: + btrfs_release_path(&path); + return ret; +}

- data_ptr = (const char *) extent - + offsetof(struct btrfs_file_extent_item, disk_bytenr); +int __btrfs_readlink(const struct __btrfs_root *root, u64 inr, char *target) +{ + struct btrfs_root *subvolume; + struct btrfs_fs_info *fs_info = current_fs_info; + struct btrfs_key key; + int ret; + + ASSERT(fs_info); + key.objectid = root->objectid; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + subvolume = btrfs_read_fs_root(fs_info, &key); + if (IS_ERR(subvolume)) + return -1;

- memcpy(target, data_ptr, extent->ram_bytes); - target[extent->ram_bytes] = '\0'; - res = 0; -out: - __btrfs_free_path(&path); - return res; + ret = btrfs_readlink(subvolume, inr, target); + if (ret < 0) + return -1; + target[ret] = '\0'; + return 0; }

/* inr must be a directory (for regular files with multiple hard links this

From: Qu Wenruo wqu@suse.com

This is the extent buffer based path lookup routine.

To implement this, btrfs_lookup_dir_item() is crossported from btrfs-progs, and implements btrfs_lookup_path() from scratch.

Unlike the existing __btrfs_lookup_path(), since btrfs_read_fs_root() will check whether a root is a orphan at read time, there is no need to check root backref, this makes the code a little easier to read.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/ctree.h | 4 + fs/btrfs/dir-item.c | 106 +++++++++++++++++++ fs/btrfs/inode.c | 250 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 360 insertions(+)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index d635b0814e..111a5a6a29 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1285,6 +1285,10 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_path *path, u64 dir, const char *name, int name_len, int mod); +/* inode.c */ +int btrfs_lookup_path(struct btrfs_root *root, u64 ino, const char *filename, + struct btrfs_root **root_ret, u64 *ino_ret, + u8 *type_ret, int symlink_limit);

/* ctree.c */ int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index aea621c72b..b49aaacbd8 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -8,6 +8,112 @@ #include "btrfs.h" #include "disk-io.h"

+static int verify_dir_item(struct btrfs_root *root, + struct extent_buffer *leaf, + struct btrfs_dir_item *dir_item) +{ + u16 namelen = BTRFS_NAME_LEN; + u8 type = btrfs_dir_type(leaf, dir_item); + + if (type == BTRFS_FT_XATTR) + namelen = XATTR_NAME_MAX; + + if (btrfs_dir_name_len(leaf, dir_item) > namelen) { + fprintf(stderr, "invalid dir item name len: %u\n", + (unsigned)btrfs_dir_data_len(leaf, dir_item)); + return 1; + } + + /* BTRFS_MAX_XATTR_SIZE is the same for all dir items */ + if ((btrfs_dir_data_len(leaf, dir_item) + + btrfs_dir_name_len(leaf, dir_item)) > + BTRFS_MAX_XATTR_SIZE(root->fs_info)) { + fprintf(stderr, "invalid dir item name + data len: %u + %u\n", + (unsigned)btrfs_dir_name_len(leaf, dir_item), + (unsigned)btrfs_dir_data_len(leaf, dir_item)); + return 1; + } + + return 0; +} + +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, int name_len) +{ + struct btrfs_dir_item *dir_item; + unsigned long name_ptr; + u32 total_len; + u32 cur = 0; + u32 this_len; + struct extent_buffer *leaf; + + leaf = path->nodes[0]; + dir_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); + total_len = btrfs_item_size_nr(leaf, path->slots[0]); + if (verify_dir_item(root, leaf, dir_item)) + return NULL; + + while(cur < total_len) { + this_len = sizeof(*dir_item) + + btrfs_dir_name_len(leaf, dir_item) + + btrfs_dir_data_len(leaf, dir_item); + if (this_len > (total_len - cur)) { + fprintf(stderr, "invalid dir item size\n"); + return NULL; + } + + name_ptr = (unsigned long)(dir_item + 1); + + if (btrfs_dir_name_len(leaf, dir_item) == name_len && + memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0) + return dir_item; + + cur += this_len; + dir_item = (struct btrfs_dir_item *)((char *)dir_item + + this_len); + } + return NULL; +} + +struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_path *path, u64 dir, + const char *name, int name_len, + int mod) +{ + int ret; + struct btrfs_key key; + int ins_len = mod < 0 ? -1 : 0; + int cow = mod != 0; + struct btrfs_key found_key; + struct extent_buffer *leaf; + + key.objectid = dir; + key.type = BTRFS_DIR_ITEM_KEY; + + key.offset = btrfs_name_hash(name, name_len); + + ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); + if (ret < 0) + return ERR_PTR(ret); + if (ret > 0) { + if (path->slots[0] == 0) + return NULL; + path->slots[0]--; + } + + leaf = path->nodes[0]; + btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); + + if (found_key.objectid != dir || + found_key.type != BTRFS_DIR_ITEM_KEY || + found_key.offset != key.offset) + return NULL; + + return btrfs_match_dir_item_name(root, path, name, name_len); +} + static int __verify_dir_item(struct btrfs_dir_item *item, u32 start, u32 total) { u16 max_len = BTRFS_NAME_LEN; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index da2a5e90a1..2e3fcad5a8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -162,6 +162,115 @@ int __btrfs_readlink(const struct __btrfs_root *root, u64 inr, char *target) return 0; }

+static int lookup_root_ref(struct btrfs_fs_info *fs_info, + u64 rootid, u64 *root_ret, u64 *dir_ret) +{ + struct btrfs_root *root = fs_info->tree_root; + struct btrfs_root_ref *root_ref; + struct btrfs_path path; + struct btrfs_key key; + int ret; + + btrfs_init_path(&path); + key.objectid = rootid; + key.type = BTRFS_ROOT_BACKREF_KEY; + key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0); + if (ret < 0) + return ret; + /* Should not happen */ + if (ret == 0) { + ret = -EUCLEAN; + goto out; + } + ret = btrfs_previous_item(root, &path, rootid, BTRFS_ROOT_BACKREF_KEY); + if (ret < 0) + goto out; + if (ret > 0) { + ret = -ENOENT; + goto out; + } + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + root_ref = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_root_ref); + *root_ret = key.offset; + *dir_ret = btrfs_root_ref_dirid(path.nodes[0], root_ref); +out: + btrfs_release_path(&path); + return ret; +} + +/* + * To get the parent inode of @ino of @root. + * + * @root_ret and @ino_ret will be filled. + * + * NOTE: This function is not reliable. It can only get one parent inode. + * The get the proper parent inode, we need a full VFS inodes stack to + * resolve properly. + */ +static int get_parent_inode(struct btrfs_root *root, u64 ino, + struct btrfs_root **root_ret, u64 *ino_ret) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_path path; + struct btrfs_key key; + int ret; + + if (ino == BTRFS_FIRST_FREE_OBJECTID) { + u64 parent_root = -1; + + /* It's top level already, no more parent */ + if (root->root_key.objectid == BTRFS_FS_TREE_OBJECTID) { + *root_ret = fs_info->fs_root; + *ino_ret = BTRFS_FIRST_FREE_OBJECTID; + return 0; + } + + ret = lookup_root_ref(fs_info, root->root_key.objectid, + &parent_root, ino_ret); + if (ret < 0) + return ret; + + key.objectid = parent_root; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + *root_ret = btrfs_read_fs_root(fs_info, &key); + if (IS_ERR(*root_ret)) + return PTR_ERR(*root_ret); + + return 0; + } + + btrfs_init_path(&path); + key.objectid = ino; + key.type = BTRFS_INODE_REF_KEY; + key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0); + if (ret < 0) + return ret; + /* Should not happen */ + if (ret == 0) { + ret = -EUCLEAN; + goto out; + } + ret = btrfs_previous_item(root, &path, ino, BTRFS_INODE_REF_KEY); + if (ret < 0) + goto out; + if (ret > 0) { + ret = -ENOENT; + goto out; + } + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + *root_ret = root; + *ino_ret = key.offset; +out: + btrfs_release_path(&path); + return ret; +} + /* inr must be a directory (for regular files with multiple hard links this function returns only one of the parents of the file) */ static u64 __get_parent_inode(struct __btrfs_root *root, u64 inr, @@ -240,6 +349,147 @@ static inline const char *skip_current_directories(const char *cur) return cur; }

+/* + * Resolve one filename of @ino of @root. + * + * key_ret: The child key (either INODE_ITEM or ROOT_ITEM type) + * type_ret: BTRFS_FT_* of the child inode. + * + * Return 0 with above members filled. + * Return <0 for error. + */ +static int resolve_one_filename(struct btrfs_root *root, u64 ino, + const char *name, int namelen, + struct btrfs_key *key_ret, u8 *type_ret) +{ + struct btrfs_dir_item *dir_item; + struct btrfs_path path; + int ret = 0; + + btrfs_init_path(&path); + + dir_item = btrfs_lookup_dir_item(NULL, root, &path, ino, name, + namelen, 0); + if (IS_ERR(dir_item)) { + ret = PTR_ERR(dir_item); + goto out; + } + + btrfs_dir_item_key_to_cpu(path.nodes[0], dir_item, key_ret); + *type_ret = btrfs_dir_type(path.nodes[0], dir_item); +out: + btrfs_release_path(&path); + return ret; +} + +/* + * Resolve a full path @filename. The start point is @ino of @root. + * + * The result will be filled into @root_ret, @ino_ret and @type_ret. + */ +int btrfs_lookup_path(struct btrfs_root *root, u64 ino, const char *filename, + struct btrfs_root **root_ret, u64 *ino_ret, + u8 *type_ret, int symlink_limit) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_root *next_root; + struct btrfs_key key; + const char *cur = filename; + u64 next_ino; + u8 next_type; + u8 type; + int len; + int ret = 0; + + /* If the path is absolute path, also search from fs root */ + if (*cur == '/') { + root = fs_info->fs_root; + ino = btrfs_root_dirid(&root->root_item); + type = BTRFS_FT_DIR; + } + + while (*cur != '\0') { + cur = skip_current_directories(cur); + + len = next_length(cur); + if (len > BTRFS_NAME_LEN) { + error("%s: Name too long at "%.*s"", __func__, + BTRFS_NAME_LEN, cur); + return -ENAMETOOLONG; + } + + if (len == 1 && cur[0] == '.') + break; + + if (len == 2 && cur[0] == '.' && cur[1] == '.') { + /* Go one level up */ + ret = get_parent_inode(root, ino, &next_root, &next_ino); + if (ret < 0) + return ret; + root = next_root; + ino = next_ino; + goto next; + } + + if (!*cur) + break; + + ret = resolve_one_filename(root, ino, cur, len, &key, &type); + if (ret < 0) + return ret; + + if (key.type == BTRFS_ROOT_ITEM_KEY) { + /* Child inode is a subvolume */ + + next_root = btrfs_read_fs_root(fs_info, &key); + if (IS_ERR(next_root)) + return PTR_ERR(next_root); + root = next_root; + ino = btrfs_root_dirid(&root->root_item); + } else if (type == BTRFS_FT_SYMLINK && symlink_limit >= 0) { + /* Child inode is a symlink */ + + char *target; + + if (symlink_limit == 0) { + error("%s: Too much symlinks!", __func__); + return -EMLINK; + } + target = malloc(fs_info->sectorsize); + if (!target) + return -ENOMEM; + ret = btrfs_readlink(root, key.objectid, target); + if (ret < 0) { + free(target); + return ret; + } + target[ret] = '\0'; + + ret = btrfs_lookup_path(root, ino, target, &next_root, + &next_ino, &next_type, + symlink_limit); + if (ret < 0) + return ret; + root = next_root; + ino = next_ino; + type = next_type; + } else { + /* Child inode is an inode */ + ino = key.objectid; + } +next: + cur += len; + } + + if (!ret) { + *root_ret = root; + *ino_ret = ino; + *type_ret = type; + } + + return ret; +} + u64 __btrfs_lookup_path(struct __btrfs_root *root, u64 inr, const char *path, u8 *type_p, struct btrfs_inode_item *inode_item_p, int symlink_limit)

From: Qu Wenruo wqu@suse.com

After this the only remaining function that still utilizes __btrfs_lookup_path() is btrfs_read().

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/btrfs.c | 65 +++++++++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/btrfs.c b/fs/btrfs/btrfs.c index 2278b52e4d..aec91a57ec 100644 --- a/fs/btrfs/btrfs.c +++ b/fs/btrfs/btrfs.c @@ -188,37 +188,66 @@ int btrfs_ls(const char *path)

int btrfs_exists(const char *file) { - struct __btrfs_root root = btrfs_info.fs_root; - u64 inr; + struct btrfs_fs_info *fs_info = current_fs_info; + struct btrfs_root *root; + u64 ino; u8 type; + int ret; + + ASSERT(fs_info);

- inr = __btrfs_lookup_path(&root, root.root_dirid, file, &type, NULL, 40); + ret = btrfs_lookup_path(fs_info->fs_root, BTRFS_FIRST_FREE_OBJECTID, + file, &root, &ino, &type, 40); + if (ret < 0) + return 0;

- return (inr != -1ULL && type == BTRFS_FT_REG_FILE); + if (type == BTRFS_FT_REG_FILE) + return 1; + return 0; }

int btrfs_size(const char *file, loff_t *size) { - struct __btrfs_root root = btrfs_info.fs_root; - struct btrfs_inode_item inode; - u64 inr; + struct btrfs_fs_info *fs_info = current_fs_info; + struct btrfs_inode_item *ii; + struct btrfs_root *root; + struct btrfs_path path; + struct btrfs_key key; + u64 ino; u8 type; + int ret;

- inr = __btrfs_lookup_path(&root, root.root_dirid, file, &type, &inode, - 40); - - if (inr == -1ULL) { + ret = btrfs_lookup_path(fs_info->fs_root, BTRFS_FIRST_FREE_OBJECTID, + file, &root, &ino, &type, 40); + if (ret < 0) { printf("Cannot lookup file %s\n", file); - return -1; + return ret; } - if (type != BTRFS_FT_REG_FILE) { printf("Not a regular file: %s\n", file); - return -1; + return -ENOENT; } + btrfs_init_path(&path); + key.objectid = ino; + key.type = BTRFS_INODE_ITEM_KEY; + key.offset = 0;

- *size = inode.size; - return 0; + ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0); + if (ret < 0) { + printf("Cannot lookup ino %llu\n", ino); + return ret; + } + if (ret > 0) { + printf("Ino %llu does not exist\n", ino); + ret = -ENOENT; + goto out; + } + ii = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_inode_item); + *size = btrfs_inode_size(path.nodes[0], ii); +out: + btrfs_release_path(&path); + return ret; }

int btrfs_read(const char *file, void *buf, loff_t offset, loff_t len, @@ -270,7 +299,9 @@ void btrfs_close(void) int btrfs_uuid(char *uuid_str) { #ifdef CONFIG_LIB_UUID - uuid_bin_to_str(btrfs_info.sb.fsid, uuid_str, UUID_STR_FORMAT_STD); + if (current_fs_info) + uuid_bin_to_str(current_fs_info->super_copy->fsid, uuid_str, + UUID_STR_FORMAT_STD); return 0; #endif return -ENOSYS;

From: Qu Wenruo wqu@suse.com

These two functions are used to do sector aligned read, which will be later used to implement btrfs_file_read().

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/ctree.h | 5 ++ fs/btrfs/disk-io.c | 36 ++++++++++ fs/btrfs/disk-io.h | 2 + fs/btrfs/inode.c | 162 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 205 insertions(+)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0cf5e63451..c4b25189dc 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1294,6 +1294,11 @@ int btrfs_iter_dir(struct btrfs_root *root, u64 ino, int btrfs_lookup_path(struct btrfs_root *root, u64 ino, const char *filename, struct btrfs_root **root_ret, u64 *ino_ret, u8 *type_ret, int symlink_limit); +int btrfs_read_extent_inline(struct btrfs_path *path, + struct btrfs_file_extent_item *fi, char *dest); +int btrfs_read_extent_reg(struct btrfs_path *path, + struct btrfs_file_extent_item *fi, u64 offset, + int len, char *dest);

/* ctree.c */ int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4d08b0204a..4da1b80038 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -565,6 +565,42 @@ struct extent_buffer* read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, return ERR_PTR(ret); }

+int read_extent_data(struct btrfs_fs_info *fs_info, char *data, u64 logical, + u64 *len, int mirror) +{ + u64 offset = 0; + struct btrfs_multi_bio *multi = NULL; + struct btrfs_device *device; + int ret = 0; + u64 max_len = *len; + + ret = btrfs_map_block(fs_info, READ, logical, len, &multi, mirror, + NULL); + if (ret) { + fprintf(stderr, "Couldn't map the block %llu\n", + logical + offset); + goto err; + } + device = multi->stripes[0].dev; + + if (*len > max_len) + *len = max_len; + if (!device->desc || !device->part) { + ret = -EIO; + goto err; + } + + ret = __btrfs_devread(device->desc, device->part, data, *len, + multi->stripes[0].physical); + if (ret != *len) + ret = -EIO; + else + ret = 0; +err: + kfree(multi); + return ret; +} + void btrfs_setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, u64 objectid) { diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 9daf959c57..424bb01dcd 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -18,6 +18,8 @@ int read_whole_eb(struct btrfs_fs_info *info, struct extent_buffer *eb, int mirr struct extent_buffer* read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, u64 parent_transid);

+int read_extent_data(struct btrfs_fs_info *fs_info, char *data, u64 logical, + u64 *len, int mirror); struct extent_buffer* btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, u64 bytenr); struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 83d21467d9..ab45db87a6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5,9 +5,12 @@ * 2017 Marek Behun, CZ.NIC, marek.behun@nic.cz */

+#include <linux/kernel.h> #include <malloc.h> +#include <memalign.h> #include "btrfs.h" #include "disk-io.h" +#include "volumes.h"

u64 __btrfs_lookup_inode_ref(struct __btrfs_root *root, u64 inr, struct btrfs_inode_ref *refp, char *name) @@ -663,3 +666,162 @@ out: __btrfs_free_path(&path); return rd_all; } + +/* + * Read out inline extent. + * + * Since inline extent should only exist for offset 0, no need for extra + * parameters. + * Truncating should be handled by the caller. + * + * Return the number of bytes read. + * Return <0 for error. + */ +int btrfs_read_extent_inline(struct btrfs_path *path, + struct btrfs_file_extent_item *fi, char *dest) +{ + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + char *cbuf = NULL; + char *dbuf = NULL; + u32 csize; + u32 dsize; + int ret; + + csize = btrfs_file_extent_inline_item_len(leaf, btrfs_item_nr(slot)); + if (btrfs_file_extent_compression(leaf, fi) == BTRFS_COMPRESS_NONE) { + /* Uncompressed, just read it out */ + read_extent_buffer(leaf, dest, + btrfs_file_extent_inline_start(fi), + csize); + return csize; + } + + /* Compressed extent, prepare the compressed and data buffer */ + dsize = btrfs_file_extent_ram_bytes(leaf, fi); + cbuf = malloc(csize); + dbuf = malloc(dsize); + if (!cbuf || !dbuf) { + ret = -ENOMEM; + goto out; + } + read_extent_buffer(leaf, cbuf, btrfs_file_extent_inline_start(fi), + csize); + ret = btrfs_decompress(btrfs_file_extent_compression(leaf, fi), + cbuf, csize, dbuf, dsize); + if (ret < 0 || ret != dsize) { + ret = -EIO; + goto out; + } + memcpy(dest, dbuf, dsize); + ret = dsize; +out: + free(cbuf); + free(dbuf); + return ret; +} + +/* + * Read out regular extent. + * + * Truncating should be handled by the caller. + * + * @offset and @len should not cross the extent boundary. + * Return the number of bytes read. + * Return <0 for error. + */ +int btrfs_read_extent_reg(struct btrfs_path *path, + struct btrfs_file_extent_item *fi, u64 offset, + int len, char *dest) +{ + struct extent_buffer *leaf = path->nodes[0]; + struct btrfs_fs_info *fs_info = leaf->fs_info; + struct btrfs_key key; + u64 extent_num_bytes; + u64 disk_bytenr; + u64 read; + char *cbuf = NULL; + char *dbuf = NULL; + u32 csize; + u32 dsize; + bool finished = false; + int num_copies; + int i; + int slot = path->slots[0]; + int ret; + + btrfs_item_key_to_cpu(leaf, &key, slot); + extent_num_bytes = btrfs_file_extent_num_bytes(leaf, fi); + ASSERT(IS_ALIGNED(offset, fs_info->sectorsize) && + IS_ALIGNED(len, fs_info->sectorsize)); + ASSERT(offset >= key.offset && + offset + len <= key.offset + extent_num_bytes); + + /* Preallocated or hole , fill @dest with zero */ + if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_PREALLOC || + btrfs_file_extent_disk_bytenr(leaf, fi) == 0) { + memset(dest, 0, len); + return len; + } + + if (btrfs_file_extent_compression(leaf, fi) == BTRFS_COMPRESS_NONE) { + u64 logical; + + logical = btrfs_file_extent_disk_bytenr(leaf, fi) + + btrfs_file_extent_offset(leaf, fi) + + offset - key.offset; + read = len; + + num_copies = btrfs_num_copies(fs_info, logical, len); + for (i = 1; i <= num_copies; i++) { + ret = read_extent_data(fs_info, dest, logical, &read, i); + if (ret < 0 || read != len) + continue; + finished = true; + break; + } + if (!finished) + return -EIO; + return len; + } + + csize = btrfs_file_extent_disk_num_bytes(leaf, fi); + dsize = btrfs_file_extent_ram_bytes(leaf, fi); + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); + num_copies = btrfs_num_copies(fs_info, disk_bytenr, csize); + + cbuf = malloc_cache_aligned(csize); + dbuf = malloc_cache_aligned(dsize); + if (!cbuf || !dbuf) { + ret = -ENOMEM; + goto out; + } + /* For compressed extent, we must read the whole on-disk extent */ + for (i = 1; i <= num_copies; i++) { + read = csize; + ret = read_extent_data(fs_info, cbuf, disk_bytenr, + &read, i); + if (ret < 0 || read != csize) + continue; + finished = true; + break; + } + if (!finished) { + ret = -EIO; + goto out; + } + + ret = btrfs_decompress(btrfs_file_extent_compression(leaf, fi), cbuf, + csize, dbuf, dsize); + if (ret != dsize) { + ret = -EIO; + goto out; + } + /* Then copy the needed part */ + memcpy(dest, dbuf + btrfs_file_extent_offset(leaf, fi), len); + ret = len; +out: + free(cbuf); + free(dbuf); + return ret; +}

From: Qu Wenruo wqu@suse.com

This version of btrfs_file_read() has the following new features: - Tries all mirrors - More handling on unaligned size - Better compressed extent handling The old implementation doesn't handle compressed extent with offset properly: we need to read out the whole compressed extent, then decompress the whole extent, and only then copy the requested part.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/btrfs.c | 48 +++++++++------- fs/btrfs/btrfs.h | 2 + fs/btrfs/inode.c | 146 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 176 insertions(+), 20 deletions(-)

diff --git a/fs/btrfs/btrfs.c b/fs/btrfs/btrfs.c index 7eb01c4ff9..ffd96427cc 100644 --- a/fs/btrfs/btrfs.c +++ b/fs/btrfs/btrfs.c @@ -253,37 +253,45 @@ out: int btrfs_read(const char *file, void *buf, loff_t offset, loff_t len, loff_t *actread) { - struct __btrfs_root root = btrfs_info.fs_root; - struct btrfs_inode_item inode; - u64 inr, rd; + struct btrfs_fs_info *fs_info = current_fs_info; + struct btrfs_root *root; + loff_t real_size; + u64 ino; u8 type; + int ret;

- inr = __btrfs_lookup_path(&root, root.root_dirid, file, &type, &inode, - 40); - - if (inr == -1ULL) { - printf("Cannot lookup file %s\n", file); - return -1; + ASSERT(fs_info); + ret = btrfs_lookup_path(fs_info->fs_root, BTRFS_FIRST_FREE_OBJECTID, + file, &root, &ino, &type, 40); + if (ret < 0) { + error("Cannot lookup file %s", file); + return ret; }

if (type != BTRFS_FT_REG_FILE) { - printf("Not a regular file: %s\n", file); - return -1; + error("Not a regular file: %s", file); + return -EINVAL; }

- if (!len) - len = inode.size; + if (!len) { + ret = btrfs_size(file, &real_size); + if (ret < 0) { + error("Failed to get inode size: %s", file); + return ret; + } + len = real_size; + }

- if (len > inode.size - offset) - len = inode.size - offset; + if (len > real_size - offset) + len = real_size - offset;

- rd = __btrfs_file_read(&root, inr, offset, len, buf); - if (rd == -1ULL) { - printf("An error occured while reading file %s\n", file); - return -1; + ret = btrfs_file_read(root, ino, offset, len, buf); + if (ret < 0) { + error("An error occured while reading file %s", file); + return ret; }

- *actread = rd; + *actread = len; return 0; }

diff --git a/fs/btrfs/btrfs.h b/fs/btrfs/btrfs.h index 32ea2fc53a..268ca077d9 100644 --- a/fs/btrfs/btrfs.h +++ b/fs/btrfs/btrfs.h @@ -59,6 +59,8 @@ int btrfs_readlink(struct btrfs_root *root, u64 ino, char *target); u64 __btrfs_lookup_path(struct __btrfs_root *, u64, const char *, u8 *, struct btrfs_inode_item *, int); u64 __btrfs_file_read(const struct __btrfs_root *, u64, u64, u64, char *); +int btrfs_file_read(struct btrfs_root *root, u64 ino, u64 file_offset, u64 len, + char *dest);

/* subvolume.c */ u64 btrfs_get_default_subvol_objectid(void); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 11eb30c27a..0c2b2b5705 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -926,3 +926,149 @@ check_next: *next_offset = key.offset; return 1; } + +static int read_and_truncate_page(struct btrfs_path *path, + struct btrfs_file_extent_item *fi, + int start, int len, char *dest) +{ + struct extent_buffer *leaf = path->nodes[0]; + struct btrfs_fs_info *fs_info = leaf->fs_info; + u64 aligned_start = round_down(start, fs_info->sectorsize); + u8 extent_type; + char *buf; + int page_off = start - aligned_start; + int page_len = fs_info->sectorsize - page_off; + int ret; + + ASSERT(start + len <= aligned_start + fs_info->sectorsize); + buf = malloc_cache_aligned(fs_info->sectorsize); + if (!buf) + return -ENOMEM; + + extent_type = btrfs_file_extent_type(leaf, fi); + if (extent_type == BTRFS_FILE_EXTENT_INLINE) { + ret = btrfs_read_extent_inline(path, fi, buf); + memcpy(dest, buf + page_off, min(page_len, ret)); + free(buf); + return len; + } + + ret = btrfs_read_extent_reg(path, fi, + round_down(start, fs_info->sectorsize), + fs_info->sectorsize, buf); + if (ret < 0) { + free(buf); + return ret; + } + memcpy(dest, buf + page_off, page_len); + free(buf); + return len; +} + +int btrfs_file_read(struct btrfs_root *root, u64 ino, u64 file_offset, u64 len, + char *dest) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_file_extent_item *fi; + struct btrfs_path path; + struct btrfs_key key; + u64 aligned_start = round_down(file_offset, fs_info->sectorsize); + u64 aligned_end = round_down(file_offset + len, fs_info->sectorsize); + u64 next_offset; + u64 cur = aligned_start; + int ret = 0; + + btrfs_init_path(&path); + + /* Set the whole dest all zero, so we won't need to bother holes */ + memset(dest, 0, len); + + /* Read out the leading unaligned part */ + if (aligned_start != file_offset) { + ret = lookup_data_extent(root, &path, ino, aligned_start, + &next_offset); + if (ret < 0) + goto out; + if (ret == 0) { + /* Read the unaligned part out*/ + fi = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_file_extent_item); + ret = read_and_truncate_page(&path, fi, file_offset, + round_up(file_offset, fs_info->sectorsize) - + file_offset, dest); + if (ret < 0) + goto out; + cur += fs_info->sectorsize; + } else { + /* The whole file is a hole */ + if (!next_offset) { + memset(dest, 0, len); + return len; + } + cur = next_offset; + } + } + + /* Read the aligned part */ + while (cur < aligned_end) { + u64 extent_num_bytes; + u8 type; + + btrfs_release_path(&path); + ret = lookup_data_extent(root, &path, ino, cur, &next_offset); + if (ret < 0) + goto out; + if (ret > 0) { + /* No next, direct exit */ + if (!next_offset) { + ret = 0; + goto out; + } + } + fi = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_file_extent_item); + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + type = btrfs_file_extent_type(path.nodes[0], fi); + if (type == BTRFS_FILE_EXTENT_INLINE) { + ret = btrfs_read_extent_inline(&path, fi, dest); + goto out; + } + /* Skip holes, as we have zeroed the dest */ + if (type == BTRFS_FILE_EXTENT_PREALLOC || + btrfs_file_extent_disk_bytenr(path.nodes[0], fi) == 0) { + cur = key.offset + btrfs_file_extent_num_bytes( + path.nodes[0], fi); + continue; + } + + /* Read the remaining part of the extent */ + extent_num_bytes = btrfs_file_extent_num_bytes(path.nodes[0], + fi); + ret = btrfs_read_extent_reg(&path, fi, cur, + min(extent_num_bytes, aligned_end - cur), + dest + cur - file_offset); + if (ret < 0) + goto out; + cur += min(extent_num_bytes, aligned_end - cur); + } + + /* Read the tailing unaligned part*/ + if (file_offset + len != aligned_end) { + btrfs_release_path(&path); + ret = lookup_data_extent(root, &path, ino, aligned_end, + &next_offset); + /* <0 is error, >0 means no extent */ + if (ret) + goto out; + fi = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_file_extent_item); + ret = read_and_truncate_page(&path, fi, aligned_end, + file_offset + len - aligned_end, + dest + aligned_end - file_offset); + } +out: + btrfs_release_path(&path); + if (ret < 0) + return ret; + return len; +}

From: Qu Wenruo wqu@suse.com

This patch introduces a new function, list_one_subvol(), which will resolve the path to FS_TREE of one subvolume.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/subvolume.c | 81 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+)

diff --git a/fs/btrfs/subvolume.c b/fs/btrfs/subvolume.c index b446e729cd..258c3dafef 100644 --- a/fs/btrfs/subvolume.c +++ b/fs/btrfs/subvolume.c @@ -8,6 +8,7 @@ #include <malloc.h> #include "ctree.h" #include "btrfs.h" +#include "disk-io.h"

/* * Resolve the path of ino inside subvolume @root into @path_ret. @@ -74,6 +75,86 @@ out: return ret; }

+static int list_one_subvol(struct btrfs_root *root, char *path_ret) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_path path; + struct btrfs_key key; + char *tmp; + u64 cur = root->root_key.objectid; + int ret = 0; + + tmp = malloc(PATH_MAX); + if (!tmp) + return -ENOMEM; + tmp[0] = '\0'; + path_ret[0] = '\0'; + btrfs_init_path(&path); + while (cur != BTRFS_FS_TREE_OBJECTID) { + struct btrfs_root_ref *rr; + struct btrfs_key location; + int name_len; + u64 ino; + + key.objectid = cur; + key.type = BTRFS_ROOT_BACKREF_KEY; + key.offset = (u64)-1; + btrfs_release_path(&path); + + ret = btrfs_search_slot(NULL, tree_root, &key, &path, 0, 0); + if (ret == 0) + ret = -EUCLEAN; + if (ret < 0) + goto out; + ret = btrfs_previous_item(tree_root, &path, cur, + BTRFS_ROOT_BACKREF_KEY); + if (ret > 0) + ret = -ENOENT; + if (ret < 0) + goto out; + + /* Get the subvolume name */ + rr = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_root_ref); + strncpy(tmp, path_ret, PATH_MAX); + name_len = btrfs_root_ref_name_len(path.nodes[0], rr); + if (name_len > BTRFS_NAME_LEN) { + ret = -ENAMETOOLONG; + goto out; + } + ino = btrfs_root_ref_dirid(path.nodes[0], rr); + read_extent_buffer(path.nodes[0], path_ret, + (unsigned long)(rr + 1), name_len); + path_ret[name_len] = '/'; + path_ret[name_len + 1] = '\0'; + strncat(path_ret, tmp, PATH_MAX); + + /* Get the path inside the parent subvolume */ + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + location.objectid = key.offset; + location.type = BTRFS_ROOT_ITEM_KEY; + location.offset = (u64)-1; + root = btrfs_read_fs_root(fs_info, &location); + if (IS_ERR(root)) { + ret = PTR_ERR(root); + goto out; + } + ret = get_path_in_subvol(root, ino, path_ret); + if (ret < 0) + goto out; + cur = key.offset; + } + /* Add the leading '/' */ + strncpy(tmp, path_ret, PATH_MAX); + strncpy(path_ret, "/", PATH_MAX); + strncat(path_ret, tmp, PATH_MAX); +out: + btrfs_release_path(&path); + free(tmp); + return ret; +} + static int get_subvol_name(u64 subvolid, char *name, int max_len) { struct btrfs_root_ref rref;

From: Qu Wenruo wqu@suse.com

This cleans up the now unneeded code from the old btrfs implementation.

Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: Marek Behún marek.behun@nic.cz --- fs/btrfs/Makefile | 4 +- fs/btrfs/btrfs.c | 31 ---- fs/btrfs/btrfs.h | 47 ------ fs/btrfs/chunk-map.c | 178 ----------------------- fs/btrfs/compression.c | 2 +- fs/btrfs/ctree.c | 290 ------------------------------------ fs/btrfs/ctree.h | 63 -------- fs/btrfs/dir-item.c | 79 ---------- fs/btrfs/disk-io.c | 30 ---- fs/btrfs/disk-io.h | 3 - fs/btrfs/extent-io.c | 116 --------------- fs/btrfs/inode.c | 323 ----------------------------------------- fs/btrfs/root.c | 92 ------------ fs/btrfs/subvolume.c | 111 -------------- 14 files changed, 3 insertions(+), 1366 deletions(-) delete mode 100644 fs/btrfs/chunk-map.c delete mode 100644 fs/btrfs/root.c

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 8d76422ce2..fc074c84d2 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -2,6 +2,6 @@ # # 2017 Marek Behun, CZ.NIC, marek.behun@nic.cz

-obj-y := btrfs.o chunk-map.o compression.o ctree.o dev.o dir-item.o \ - extent-io.o inode.o root.o subvolume.o crypto/hash.o disk-io.o \ +obj-y := btrfs.o compression.o ctree.o dev.o dir-item.o \ + extent-io.o inode.o subvolume.o crypto/hash.o disk-io.o \ common/rbtree-utils.o extent-cache.o volumes.o root-tree.o diff --git a/fs/btrfs/btrfs.c b/fs/btrfs/btrfs.c index ffd96427cc..786bb4733f 100644 --- a/fs/btrfs/btrfs.c +++ b/fs/btrfs/btrfs.c @@ -13,7 +13,6 @@ #include "crypto/hash.h" #include "disk-io.h"

-struct btrfs_info btrfs_info; struct btrfs_fs_info *current_fs_info;

static int show_dir(struct btrfs_root *root, struct extent_buffer *eb, @@ -120,36 +119,7 @@ int btrfs_probe(struct blk_desc *fs_dev_desc, struct btrfs_fs_info *fs_info; int ret = -1;

- btrfs_blk_desc = fs_dev_desc; - btrfs_part_info = fs_partition; - - memset(&btrfs_info, 0, sizeof(btrfs_info)); - btrfs_hash_init(); - if (btrfs_read_superblock()) - return -1; - - if (btrfs_chunk_map_init()) { - printf("%s: failed to init chunk map\n", __func__); - return -1; - } - - btrfs_info.tree_root.objectid = 0; - btrfs_info.tree_root.bytenr = btrfs_info.sb.root; - btrfs_info.chunk_root.objectid = 0; - btrfs_info.chunk_root.bytenr = btrfs_info.sb.chunk_root; - - if (__btrfs_read_chunk_tree()) { - printf("%s: failed to read chunk tree\n", __func__); - return -1; - } - - if (btrfs_find_root(btrfs_get_default_subvol_objectid(), - &btrfs_info.fs_root, NULL)) { - printf("%s: failed to find default subvolume\n", __func__); - return -1; - } - fs_info = open_ctree_fs_info(fs_dev_desc, fs_partition); if (fs_info) { current_fs_info = fs_info; @@ -297,7 +267,6 @@ int btrfs_read(const char *file, void *buf, loff_t offset, loff_t len,

void btrfs_close(void) { - btrfs_chunk_map_exit(); if (current_fs_info) { close_ctree_fs_info(current_fs_info); current_fs_info = NULL; diff --git a/fs/btrfs/btrfs.h b/fs/btrfs/btrfs.h index 268ca077d9..7d8b395b26 100644 --- a/fs/btrfs/btrfs.h +++ b/fs/btrfs/btrfs.h @@ -11,65 +11,18 @@ #include <linux/rbtree.h> #include "conv-funcs.h"

-struct btrfs_info { - struct btrfs_super_block sb; - - struct __btrfs_root tree_root; - struct __btrfs_root fs_root; - struct __btrfs_root chunk_root; - - struct rb_root chunks_root; -}; - extern struct btrfs_info btrfs_info; extern struct btrfs_fs_info *current_fs_info;

-/* dev.c */ -extern struct blk_desc *btrfs_blk_desc; -extern struct disk_partition *btrfs_part_info; - -int btrfs_devread(u64, int, void *); - -/* chunk-map.c */ -u64 btrfs_map_logical_to_physical(u64); -int btrfs_chunk_map_init(void); -void btrfs_chunk_map_exit(void); -int __btrfs_read_chunk_tree(void); - /* compression.c */ u32 btrfs_decompress(u8 type, const char *, u32, char *, u32);

-/* super.c */ -int btrfs_read_superblock(void); - -/* dir-item.c */ -int __btrfs_lookup_dir_item(const struct __btrfs_root *, u64, const char *, int, - struct btrfs_dir_item *); -/* root.c */ -int btrfs_find_root(u64, struct __btrfs_root *, struct btrfs_root_item *); -u64 btrfs_lookup_root_ref(u64, struct btrfs_root_ref *, char *); - /* inode.c */ -u64 __btrfs_lookup_inode_ref(struct __btrfs_root *, u64, struct btrfs_inode_ref *, - char *); -int __btrfs_lookup_inode(const struct __btrfs_root *, struct btrfs_key *, - struct btrfs_inode_item *, struct __btrfs_root *); -int __btrfs_readlink(const struct __btrfs_root *, u64, char *); int btrfs_readlink(struct btrfs_root *root, u64 ino, char *target); -u64 __btrfs_lookup_path(struct __btrfs_root *, u64, const char *, u8 *, - struct btrfs_inode_item *, int); -u64 __btrfs_file_read(const struct __btrfs_root *, u64, u64, u64, char *); int btrfs_file_read(struct btrfs_root *root, u64 ino, u64 file_offset, u64 len, char *dest);

/* subvolume.c */ u64 btrfs_get_default_subvol_objectid(void);

-/* extent-io.c */ -u64 __btrfs_read_extent_inline(struct __btrfs_path *, - struct btrfs_file_extent_item *, u64, u64, - char *); -u64 __btrfs_read_extent_reg(struct __btrfs_path *, struct btrfs_file_extent_item *, - u64, u64, char *); - #endif /* !__BTRFS_BTRFS_H__ */ diff --git a/fs/btrfs/chunk-map.c b/fs/btrfs/chunk-map.c deleted file mode 100644 index bff83e4dc8..0000000000 --- a/fs/btrfs/chunk-map.c +++ /dev/null @@ -1,178 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * BTRFS filesystem implementation for U-Boot - * - * 2017 Marek Behun, CZ.NIC, marek.behun@nic.cz - */ - -#include "btrfs.h" -#include <log.h> -#include <malloc.h> - -struct chunk_map_item { - struct rb_node node; - u64 logical; - u64 length; - u64 physical; -}; - -static int add_chunk_mapping(struct btrfs_key *key, struct btrfs_chunk *chunk) -{ - struct btrfs_stripe *stripe; - u64 block_profile = chunk->type & BTRFS_BLOCK_GROUP_PROFILE_MASK; - struct rb_node **new = &(btrfs_info.chunks_root.rb_node), *prnt = NULL; - struct chunk_map_item *map_item; - - if (block_profile && block_profile != BTRFS_BLOCK_GROUP_DUP) { - printf("%s: unsupported chunk profile %llu\n", __func__, - block_profile); - return -1; - } else if (!chunk->length) { - printf("%s: zero length chunk\n", __func__); - return -1; - } - - stripe = &chunk->stripe; - btrfs_stripe_to_cpu(stripe); - - while (*new) { - struct chunk_map_item *this; - - this = rb_entry(*new, struct chunk_map_item, node); - - prnt = *new; - if (key->offset < this->logical) { - new = &((*new)->rb_left); - } else if (key->offset > this->logical) { - new = &((*new)->rb_right); - } else { - debug("%s: Logical address %llu already in map!\n", - __func__, key->offset); - return 0; - } - } - - map_item = malloc(sizeof(struct chunk_map_item)); - if (!map_item) - return -1; - - map_item->logical = key->offset; - map_item->length = chunk->length; - map_item->physical = le64_to_cpu(chunk->stripe.offset); - rb_link_node(&map_item->node, prnt, new); - rb_insert_color(&map_item->node, &btrfs_info.chunks_root); - - debug("%s: Mapping %llu to %llu\n", __func__, map_item->logical, - map_item->physical); - - return 0; -} - -u64 btrfs_map_logical_to_physical(u64 logical) -{ - struct rb_node *node = btrfs_info.chunks_root.rb_node; - - while (node) { - struct chunk_map_item *item; - - item = rb_entry(node, struct chunk_map_item, node); - - if (item->logical > logical) - node = node->rb_left; - else if (logical >= item->logical + item->length) - node = node->rb_right; - else - return item->physical + logical - item->logical; - } - - printf("%s: Cannot map logical address %llu to physical\n", __func__, - logical); - - return -1ULL; -} - -void btrfs_chunk_map_exit(void) -{ - struct rb_node *now, *next; - struct chunk_map_item *item; - - for (now = rb_first_postorder(&btrfs_info.chunks_root); now; now = next) - { - item = rb_entry(now, struct chunk_map_item, node); - next = rb_next_postorder(now); - free(item); - } -} - -int btrfs_chunk_map_init(void) -{ - u8 sys_chunk_array_copy[sizeof(btrfs_info.sb.sys_chunk_array)]; - u8 * const start = sys_chunk_array_copy; - u8 * const end = start + btrfs_info.sb.sys_chunk_array_size; - u8 *cur; - struct btrfs_key *key; - struct btrfs_chunk *chunk; - - btrfs_info.chunks_root = RB_ROOT; - - memcpy(sys_chunk_array_copy, btrfs_info.sb.sys_chunk_array, - sizeof(sys_chunk_array_copy)); - - for (cur = start; cur < end;) { - key = (struct btrfs_key *) cur; - cur += sizeof(struct btrfs_key); - chunk = (struct btrfs_chunk *) cur; - - btrfs_key_to_cpu(key); - btrfs_chunk_to_cpu(chunk); - - if (key->type != BTRFS_CHUNK_ITEM_KEY) { - printf("%s: invalid key type %u\n", __func__, - key->type); - return -1; - } - - if (add_chunk_mapping(key, chunk)) - return -1; - - cur += sizeof(struct btrfs_chunk); - cur += sizeof(struct btrfs_stripe) * (chunk->num_stripes - 1); - } - - return 0; -} - -int __btrfs_read_chunk_tree(void) -{ - struct __btrfs_path path; - struct btrfs_key key, *found_key; - struct btrfs_chunk *chunk; - int res = 0; - - key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; - key.type = BTRFS_CHUNK_ITEM_KEY; - key.offset = 0; - - if (btrfs_search_tree(&btrfs_info.chunk_root, &key, &path)) - return -1; - - do { - found_key = btrfs_path_leaf_key(&path); - if (btrfs_comp_keys_type(&key, found_key)) - continue; - - chunk = btrfs_path_item_ptr(&path, struct btrfs_chunk); - btrfs_chunk_to_cpu(chunk); - if (add_chunk_mapping(found_key, chunk)) { - res = -1; - break; - } - } while (!(res = btrfs_next_slot(&path))); - - __btrfs_free_path(&path); - - if (res < 0) - return -1; - - return 0; -} diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 59e4a94cb2..23efefa199 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -115,7 +115,7 @@ static u32 decompress_zlib(const u8 *_cbuf, u32 clen, u8 *dbuf, u32 dlen) while (stream.total_in < clen) { stream.next_in = cbuf + stream.total_in; stream.avail_in = min((u32) (clen - stream.total_in), - (u32) btrfs_info.sb.sectorsize); + current_fs_info->sectorsize);

ret = inflate(&stream, Z_NO_FLUSH); if (ret != Z_OK) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 98c08d353a..5ffced9160 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -70,296 +70,6 @@ void btrfs_release_path(struct btrfs_path *p) memset(p, 0, sizeof(*p)); }

-int __btrfs_comp_keys(struct btrfs_key *a, struct btrfs_key *b) -{ - if (a->objectid > b->objectid) - return 1; - if (a->objectid < b->objectid) - return -1; - if (a->type > b->type) - return 1; - if (a->type < b->type) - return -1; - if (a->offset > b->offset) - return 1; - if (a->offset < b->offset) - return -1; - return 0; -} - -int btrfs_comp_keys_type(struct btrfs_key *a, struct btrfs_key *b) -{ - if (a->objectid > b->objectid) - return 1; - if (a->objectid < b->objectid) - return -1; - if (a->type > b->type) - return 1; - if (a->type < b->type) - return -1; - return 0; -} - -/* - * search for key in the extent_buffer. The items start at offset p, - * and they are item_size apart. There are 'max' items in p. - * - * the slot in the array is returned via slot, and it points to - * the place where you would insert key if it is not found in - * the array. - * - * slot may point to max if the key is bigger than all of the keys - */ -static int __generic_bin_search(void *addr, int item_size, struct btrfs_key *key, - int max, int *slot) -{ - int low = 0, high = max, mid, ret; - struct btrfs_key *tmp; - - while (low < high) { - mid = (low + high) / 2; - - tmp = (struct btrfs_key *) ((u8 *) addr + mid*item_size); - ret = __btrfs_comp_keys(tmp, key); - - if (ret < 0) { - low = mid + 1; - } else if (ret > 0) { - high = mid; - } else { - *slot = mid; - return 0; - } - } - - *slot = low; - return 1; -} - -int __btrfs_bin_search(union btrfs_tree_node *p, struct btrfs_key *key, - int *slot) -{ - void *addr; - unsigned long size; - - if (p->header.level) { - addr = p->node.ptrs; - size = sizeof(struct btrfs_key_ptr); - } else { - addr = p->leaf.items; - size = sizeof(struct btrfs_item); - } - - return __generic_bin_search(addr, size, key, p->header.nritems, slot); -} - -static void clear_path(struct __btrfs_path *p) -{ - int i; - - for (i = 0; i < BTRFS_MAX_LEVEL; ++i) { - p->nodes[i] = NULL; - p->slots[i] = 0; - } -} - -void __btrfs_free_path(struct __btrfs_path *p) -{ - int i; - - for (i = 0; i < BTRFS_MAX_LEVEL; ++i) { - if (p->nodes[i]) - free(p->nodes[i]); - } - - clear_path(p); -} - -static int read_tree_node(u64 physical, union btrfs_tree_node **buf) -{ - ALLOC_CACHE_ALIGN_BUFFER(struct btrfs_header, hdr, - sizeof(struct btrfs_header)); - unsigned long size, offset = sizeof(*hdr); - union btrfs_tree_node *res; - u32 i; - - if (!btrfs_devread(physical, sizeof(*hdr), hdr)) - return -1; - - btrfs_header_to_cpu(hdr); - - if (hdr->level) - size = sizeof(struct btrfs_node) - + hdr->nritems * sizeof(struct btrfs_key_ptr); - else - size = btrfs_info.sb.nodesize; - - res = malloc_cache_aligned(size); - if (!res) { - debug("%s: malloc failed\n", __func__); - return -1; - } - - if (!btrfs_devread(physical + offset, size - offset, - ((u8 *) res) + offset)) { - free(res); - return -1; - } - - memcpy(&res->header, hdr, sizeof(*hdr)); - if (hdr->level) - for (i = 0; i < hdr->nritems; ++i) - btrfs_key_ptr_to_cpu(&res->node.ptrs[i]); - else - for (i = 0; i < hdr->nritems; ++i) - btrfs_item_to_cpu(&res->leaf.items[i]); - - *buf = res; - - return 0; -} - -int btrfs_search_tree(const struct __btrfs_root *root, struct btrfs_key *key, - struct __btrfs_path *p) -{ - u8 lvl, prev_lvl; - int i, slot, ret; - u64 logical, physical; - union btrfs_tree_node *buf; - - clear_path(p); - - logical = root->bytenr; - - for (i = 0; i < BTRFS_MAX_LEVEL; ++i) { - physical = btrfs_map_logical_to_physical(logical); - if (physical == -1ULL) - goto err; - - if (read_tree_node(physical, &buf)) - goto err; - - lvl = buf->header.level; - if (i && prev_lvl != lvl + 1) { - printf("%s: invalid level in header at %llu\n", - __func__, logical); - goto err; - } - prev_lvl = lvl; - - ret = __btrfs_bin_search(buf, key, &slot); - if (ret < 0) - goto err; - if (ret && slot > 0 && lvl) - slot -= 1; - - p->slots[lvl] = slot; - p->nodes[lvl] = buf; - - if (lvl) { - logical = buf->node.ptrs[slot].blockptr; - } else { - /* - * The path might be invalid if: - * cur leaf max < searched value < next leaf min - * - * Jump to the next valid element if it exists. - */ - if (slot >= buf->header.nritems) - if (btrfs_next_slot(p) < 0) - goto err; - break; - } - } - - return 0; -err: - __btrfs_free_path(p); - return -1; -} - -static int jump_leaf(struct __btrfs_path *path, int dir) -{ - struct __btrfs_path p; - u32 slot; - int level = 1, from_level, i; - - dir = dir >= 0 ? 1 : -1; - - p = *path; - - while (level < BTRFS_MAX_LEVEL) { - if (!p.nodes[level]) - return 1; - - slot = p.slots[level]; - if ((dir > 0 && slot + dir >= p.nodes[level]->header.nritems) - || (dir < 0 && !slot)) - level++; - else - break; - } - - if (level == BTRFS_MAX_LEVEL) - return 1; - - p.slots[level] = slot + dir; - level--; - from_level = level; - - while (level >= 0) { - u64 logical, physical; - - slot = p.slots[level + 1]; - logical = p.nodes[level + 1]->node.ptrs[slot].blockptr; - physical = btrfs_map_logical_to_physical(logical); - if (physical == -1ULL) - goto err; - - if (read_tree_node(physical, &p.nodes[level])) - goto err; - - if (dir > 0) - p.slots[level] = 0; - else - p.slots[level] = p.nodes[level]->header.nritems - 1; - level--; - } - - /* Free rewritten nodes in path */ - for (i = 0; i <= from_level; ++i) - free(path->nodes[i]); - - *path = p; - return 0; - -err: - /* Free rewritten nodes in p */ - for (i = level + 1; i <= from_level; ++i) - free(p.nodes[i]); - return -1; -} - -int btrfs_prev_slot(struct __btrfs_path *p) -{ - if (!p->slots[0]) - return jump_leaf(p, -1); - - p->slots[0]--; - return 0; -} - -int btrfs_next_slot(struct __btrfs_path *p) -{ - struct btrfs_leaf *leaf = &p->nodes[0]->leaf; - - if (p->slots[0] + 1 >= leaf->header.nritems) - return jump_leaf(p, 1); - - p->slots[0]++; - return 0; -} - int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2) { if (k1->objectid > k2->objectid) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index c4b25189dc..219c410b18 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1204,69 +1204,6 @@ union btrfs_tree_node { struct btrfs_node node; };

-struct __btrfs_path { - union btrfs_tree_node *nodes[BTRFS_MAX_LEVEL]; - u32 slots[BTRFS_MAX_LEVEL]; -}; - -struct __btrfs_root { - u64 objectid; - u64 bytenr; - u64 root_dirid; -}; - -int __btrfs_comp_keys(struct btrfs_key *, struct btrfs_key *); -int btrfs_comp_keys_type(struct btrfs_key *, struct btrfs_key *); -int __btrfs_bin_search(union btrfs_tree_node *, struct btrfs_key *, int *); -void __btrfs_free_path(struct __btrfs_path *); -int btrfs_search_tree(const struct __btrfs_root *, struct btrfs_key *, - struct __btrfs_path *); -int btrfs_prev_slot(struct __btrfs_path *); -int btrfs_next_slot(struct __btrfs_path *); - -static inline struct btrfs_key *btrfs_path_leaf_key(struct __btrfs_path *p) { - /* At tree read time we have converted the endian for btrfs_disk_key */ - return (struct btrfs_key *)&p->nodes[0]->leaf.items[p->slots[0]].key; -} - -static inline struct btrfs_key * -btrfs_search_tree_key_type(const struct __btrfs_root *root, u64 objectid, - u8 type, struct __btrfs_path *path) -{ - struct btrfs_key key, *res; - - key.objectid = objectid; - key.type = type; - key.offset = 0; - - if (btrfs_search_tree(root, &key, path)) - return NULL; - - res = btrfs_path_leaf_key(path); - if (btrfs_comp_keys_type(&key, res)) { - __btrfs_free_path(path); - return NULL; - } - - return res; -} - -static inline u32 btrfs_path_item_size(struct __btrfs_path *p) -{ - return p->nodes[0]->leaf.items[p->slots[0]].size; -} - -static inline void *__btrfs_leaf_data(struct btrfs_leaf *leaf, u32 slot) -{ - return ((u8 *) leaf) + sizeof(struct btrfs_header) - + leaf->items[slot].offset; -} - -static inline void *btrfs_path_leaf_data(struct __btrfs_path *p) -{ - return __btrfs_leaf_data(&p->nodes[0]->leaf, p->slots[0]); -} - #define btrfs_path_item_ptr(p,t) \ ((t *) btrfs_path_leaf_data((p)))

diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 1a3929afdc..aab197a6d5 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -114,85 +114,6 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, return btrfs_match_dir_item_name(root, path, name, name_len); }

-static int __verify_dir_item(struct btrfs_dir_item *item, u32 start, u32 total) -{ - u16 max_len = BTRFS_NAME_LEN; - u32 end; - - if (item->type >= BTRFS_FT_MAX) { - printf("%s: invalid dir item type: %i\n", __func__, item->type); - return 1; - } - - if (item->type == BTRFS_FT_XATTR) - max_len = 255; /* XATTR_NAME_MAX */ - - end = start + sizeof(*item) + item->name_len; - if (item->name_len > max_len || end > total) { - printf("%s: invalid dir item name len: %u\n", __func__, - item->name_len); - return 1; - } - - return 0; -} - -static struct btrfs_dir_item * -__btrfs_match_dir_item_name(struct __btrfs_path *path, const char *name, - int name_len) -{ - struct btrfs_dir_item *item; - u32 total_len, cur = 0, this_len; - const char *name_ptr; - - item = btrfs_path_item_ptr(path, struct btrfs_dir_item); - - total_len = btrfs_path_item_size(path); - - while (cur < total_len) { - btrfs_dir_item_to_cpu(item); - this_len = sizeof(*item) + item->name_len + item->data_len; - name_ptr = (const char *) (item + 1); - - if (__verify_dir_item(item, cur, total_len)) - return NULL; - if (item->name_len == name_len && !memcmp(name_ptr, name, - name_len)) - return item; - - cur += this_len; - item = (struct btrfs_dir_item *) ((u8 *) item + this_len); - } - - return NULL; -} - -int __btrfs_lookup_dir_item(const struct __btrfs_root *root, u64 dir, - const char *name, int name_len, - struct btrfs_dir_item *item) -{ - struct __btrfs_path path; - struct btrfs_key key; - struct btrfs_dir_item *res = NULL; - - key.objectid = dir; - key.type = BTRFS_DIR_ITEM_KEY; - key.offset = btrfs_name_hash(name, name_len); - - if (btrfs_search_tree(root, &key, &path)) - return -1; - - if (btrfs_comp_keys_type(&key, btrfs_path_leaf_key(&path))) - goto out; - - res = __btrfs_match_dir_item_name(&path, name, name_len); - if (res) - *item = *res; -out: - __btrfs_free_path(&path); - return res ? 0 : -1; -} - int btrfs_iter_dir(struct btrfs_root *root, u64 ino, btrfs_iter_dir_callback_t callback) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4da1b80038..01e7cee520 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -310,36 +310,6 @@ int btrfs_read_dev_super(struct blk_desc *desc, struct disk_partition *part, return 0; }

-int btrfs_read_superblock(void) -{ - ALLOC_CACHE_ALIGN_BUFFER(char, raw_sb, BTRFS_SUPER_INFO_SIZE); - struct btrfs_super_block *sb = (struct btrfs_super_block *) raw_sb; - int ret; - - - btrfs_info.sb.generation = 0; - - ret = btrfs_read_dev_super(btrfs_blk_desc, btrfs_part_info, sb); - if (ret < 0) { - pr_debug("%s: No valid BTRFS superblock found!\n", __func__); - return ret; - } - btrfs_super_block_to_cpu(sb); - memcpy(&btrfs_info.sb, sb, sizeof(*sb)); - - if (btrfs_info.sb.num_devices != 1) { - printf("%s: Unsupported number of devices (%lli). This driver " - "only supports filesystem on one device.\n", __func__, - btrfs_info.sb.num_devices); - return -1; - } - - pr_debug("Chosen superblock with generation = %llu\n", - btrfs_info.sb.generation); - - return 0; -} - static int __csum_tree_block_size(struct extent_buffer *buf, u16 csum_size, int verify, int silent, u16 csum_type) { diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 424bb01dcd..a347912078 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -10,9 +10,6 @@ #define BTRFS_SUPER_INFO_OFFSET SZ_64K #define BTRFS_SUPER_INFO_SIZE SZ_4K

-/* U-boot specific */ -int btrfs_read_superblock(void); - /* From btrfs-progs */ int read_whole_eb(struct btrfs_fs_info *info, struct extent_buffer *eb, int mirror); struct extent_buffer* read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, diff --git a/fs/btrfs/extent-io.c b/fs/btrfs/extent-io.c index ccf4da3177..774e29eb60 100644 --- a/fs/btrfs/extent-io.c +++ b/fs/btrfs/extent-io.c @@ -14,122 +14,6 @@ #include "extent-io.h" #include "disk-io.h"

-u64 __btrfs_read_extent_inline(struct __btrfs_path *path, - struct btrfs_file_extent_item *extent, u64 offset, - u64 size, char *out) -{ - u32 clen, dlen, orig_size = size, res; - const char *cbuf; - char *dbuf; - const int data_off = offsetof(struct btrfs_file_extent_item, - disk_bytenr); - - clen = btrfs_path_item_size(path) - data_off; - cbuf = (const char *) extent + data_off; - dlen = extent->ram_bytes; - - if (offset > dlen) - return -1ULL; - - if (size > dlen - offset) - size = dlen - offset; - - if (extent->compression == BTRFS_COMPRESS_NONE) { - memcpy(out, cbuf + offset, size); - return size; - } - - if (dlen > orig_size) { - dbuf = malloc(dlen); - if (!dbuf) - return -1ULL; - } else { - dbuf = out; - } - - res = btrfs_decompress(extent->compression, cbuf, clen, dbuf, dlen); - if (res == -1 || res != dlen) - goto err; - - if (dlen > orig_size) { - memcpy(out, dbuf + offset, size); - free(dbuf); - } else if (offset) { - memmove(out, dbuf + offset, size); - } - - return size; - -err: - if (dlen > orig_size) - free(dbuf); - return -1ULL; -} - -u64 __btrfs_read_extent_reg(struct __btrfs_path *path, - struct btrfs_file_extent_item *extent, u64 offset, - u64 size, char *out) -{ - u64 physical, clen, dlen, orig_size = size; - u32 res; - char *cbuf, *dbuf; - - clen = extent->disk_num_bytes; - dlen = extent->num_bytes; - - if (offset > dlen) - return -1ULL; - - if (size > dlen - offset) - size = dlen - offset; - - /* sparse extent */ - if (extent->disk_bytenr == 0) { - memset(out, 0, size); - return size; - } - - physical = btrfs_map_logical_to_physical(extent->disk_bytenr); - if (physical == -1ULL) - return -1ULL; - - if (extent->compression == BTRFS_COMPRESS_NONE) { - physical += extent->offset + offset; - if (!btrfs_devread(physical, size, out)) - return -1ULL; - - return size; - } - - cbuf = malloc_cache_aligned(dlen > size ? clen + dlen : clen); - if (!cbuf) - return -1ULL; - - if (dlen > orig_size) - dbuf = cbuf + clen; - else - dbuf = out; - - if (!btrfs_devread(physical, clen, cbuf)) - goto err; - - res = btrfs_decompress(extent->compression, cbuf, clen, dbuf, dlen); - if (res == -1) - goto err; - - if (dlen > orig_size) - memcpy(out, dbuf + offset, size); - else - memmove(out, dbuf + offset, size); - - free(cbuf); - return res; - -err: - free(cbuf); - return -1ULL; -} - void extent_io_tree_init(struct extent_io_tree *tree) { cache_tree_init(&tree->state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0c2b2b5705..ff330280e0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -12,81 +12,6 @@ #include "disk-io.h" #include "volumes.h"

-u64 __btrfs_lookup_inode_ref(struct __btrfs_root *root, u64 inr, - struct btrfs_inode_ref *refp, char *name) -{ - struct __btrfs_path path; - struct btrfs_key *key; - struct btrfs_inode_ref *ref; - u64 res = -1ULL; - - key = btrfs_search_tree_key_type(root, inr, BTRFS_INODE_REF_KEY, - &path); - - if (!key) - return -1ULL; - - ref = btrfs_path_item_ptr(&path, struct btrfs_inode_ref); - btrfs_inode_ref_to_cpu(ref); - - if (refp) - *refp = *ref; - - if (name) { - if (ref->name_len > BTRFS_NAME_LEN) { - printf("%s: inode name too long: %u\n", __func__, - ref->name_len); - goto out; - } - - memcpy(name, ref + 1, ref->name_len); - } - - res = key->offset; -out: - __btrfs_free_path(&path); - return res; -} - -int __btrfs_lookup_inode(const struct __btrfs_root *root, - struct btrfs_key *location, - struct btrfs_inode_item *item, - struct __btrfs_root *new_root) -{ - struct __btrfs_root tmp_root = *root; - struct __btrfs_path path; - int res = -1; - - if (location->type == BTRFS_ROOT_ITEM_KEY) { - if (btrfs_find_root(location->objectid, &tmp_root, NULL)) - return -1; - - location->objectid = tmp_root.root_dirid; - location->type = BTRFS_INODE_ITEM_KEY; - location->offset = 0; - } - - if (btrfs_search_tree(&tmp_root, location, &path)) - return res; - - if (__btrfs_comp_keys(location, btrfs_path_leaf_key(&path))) - goto out; - - if (item) { - *item = *btrfs_path_item_ptr(&path, struct btrfs_inode_item); - btrfs_inode_item_to_cpu(item); - } - - if (new_root) - *new_root = tmp_root; - - res = 0; - -out: - __btrfs_free_path(&path); - return res; -} - /* * Read the content of symlink inode @ino of @root, into @target. * NOTE: @target will not be \0 termiated, caller should handle it properly. @@ -143,28 +68,6 @@ out: return ret; }

-int __btrfs_readlink(const struct __btrfs_root *root, u64 inr, char *target) -{ - struct btrfs_root *subvolume; - struct btrfs_fs_info *fs_info = current_fs_info; - struct btrfs_key key; - int ret; - - ASSERT(fs_info); - key.objectid = root->objectid; - key.type = BTRFS_ROOT_ITEM_KEY; - key.offset = (u64)-1; - subvolume = btrfs_read_fs_root(fs_info, &key); - if (IS_ERR(subvolume)) - return -1; - - ret = btrfs_readlink(subvolume, inr, target); - if (ret < 0) - return -1; - target[ret] = '\0'; - return 0; -} - static int lookup_root_ref(struct btrfs_fs_info *fs_info, u64 rootid, u64 *root_ret, u64 *dir_ret) { @@ -274,58 +177,6 @@ out: return ret; }

-/* inr must be a directory (for regular files with multiple hard links this - function returns only one of the parents of the file) */ -static u64 __get_parent_inode(struct __btrfs_root *root, u64 inr, - struct btrfs_inode_item *inode_item) -{ - struct btrfs_key key; - u64 res; - - if (inr == BTRFS_FIRST_FREE_OBJECTID) { - if (root->objectid != btrfs_info.fs_root.objectid) { - u64 parent; - struct btrfs_root_ref ref; - - parent = btrfs_lookup_root_ref(root->objectid, &ref, - NULL); - if (parent == -1ULL) - return -1ULL; - - if (btrfs_find_root(parent, root, NULL)) - return -1ULL; - - inr = ref.dirid; - } - - if (inode_item) { - key.objectid = inr; - key.type = BTRFS_INODE_ITEM_KEY; - key.offset = 0; - - if (__btrfs_lookup_inode(root, &key, inode_item, NULL)) - return -1ULL; - } - - return inr; - } - - res = __btrfs_lookup_inode_ref(root, inr, NULL, NULL); - if (res == -1ULL) - return -1ULL; - - if (inode_item) { - key.objectid = res; - key.type = BTRFS_INODE_ITEM_KEY; - key.offset = 0; - - if (__btrfs_lookup_inode(root, &key, inode_item, NULL)) - return -1ULL; - } - - return res; -} - static inline int next_length(const char *path) { int res = 0; @@ -493,180 +344,6 @@ next: return ret; }

-u64 __btrfs_lookup_path(struct __btrfs_root *root, u64 inr, const char *path, - u8 *type_p, struct btrfs_inode_item *inode_item_p, - int symlink_limit) -{ - struct btrfs_dir_item item; - struct btrfs_inode_item inode_item; - u8 type = BTRFS_FT_DIR; - int len, have_inode = 0; - const char *cur = path; - - if (*cur == '/') { - ++cur; - inr = root->root_dirid; - } - - do { - cur = skip_current_directories(cur); - - len = next_length(cur); - if (len > BTRFS_NAME_LEN) { - printf("%s: Name too long at "%.*s"\n", __func__, - BTRFS_NAME_LEN, cur); - return -1ULL; - } - - if (len == 1 && cur[0] == '.') - break; - - if (len == 2 && cur[0] == '.' && cur[1] == '.') { - cur += 2; - inr = __get_parent_inode(root, inr, &inode_item); - if (inr == -1ULL) - return -1ULL; - - type = BTRFS_FT_DIR; - continue; - } - - if (!*cur) - break; - - if (__btrfs_lookup_dir_item(root, inr, cur, len, &item)) - return -1ULL; - - type = item.type; - have_inode = 1; - if (__btrfs_lookup_inode(root, (struct btrfs_key *)&item.location, - &inode_item, root)) - return -1ULL; - - if (item.type == BTRFS_FT_SYMLINK && symlink_limit >= 0) { - char *target; - - if (!symlink_limit) { - printf("%s: Too much symlinks!\n", __func__); - return -1ULL; - } - - target = malloc(min(inode_item.size + 1, - (u64) btrfs_info.sb.sectorsize)); - if (!target) - return -1ULL; - - if (__btrfs_readlink(root, item.location.objectid, - target)) { - free(target); - return -1ULL; - } - - inr = __btrfs_lookup_path(root, inr, target, &type, - &inode_item, symlink_limit - 1); - - free(target); - - if (inr == -1ULL) - return -1ULL; - } else if (item.type != BTRFS_FT_DIR && cur[len]) { - printf("%s: "%.*s" not a directory\n", __func__, - (int) (cur - path + len), path); - return -1ULL; - } else { - inr = item.location.objectid; - } - - cur += len; - } while (*cur); - - if (type_p) - *type_p = type; - - if (inode_item_p) { - if (!have_inode) { - struct btrfs_key key; - - key.objectid = inr; - key.type = BTRFS_INODE_ITEM_KEY; - key.offset = 0; - - if (__btrfs_lookup_inode(root, &key, &inode_item, NULL)) - return -1ULL; - } - - *inode_item_p = inode_item; - } - - return inr; -} - -u64 __btrfs_file_read(const struct __btrfs_root *root, u64 inr, u64 offset, - u64 size, char *buf) -{ - struct __btrfs_path path; - struct btrfs_key key; - struct btrfs_file_extent_item *extent; - int res = 0; - u64 rd, rd_all = -1ULL; - - key.objectid = inr; - key.type = BTRFS_EXTENT_DATA_KEY; - key.offset = offset; - - if (btrfs_search_tree(root, &key, &path)) - return -1ULL; - - if (__btrfs_comp_keys(&key, btrfs_path_leaf_key(&path)) < 0) { - if (btrfs_prev_slot(&path)) - goto out; - - if (btrfs_comp_keys_type(&key, btrfs_path_leaf_key(&path))) - goto out; - } - - rd_all = 0; - - do { - if (btrfs_comp_keys_type(&key, btrfs_path_leaf_key(&path))) - break; - - extent = btrfs_path_item_ptr(&path, - struct btrfs_file_extent_item); - - if (extent->type == BTRFS_FILE_EXTENT_INLINE) { - btrfs_file_extent_item_to_cpu_inl(extent); - rd = __btrfs_read_extent_inline(&path, extent, offset, - size, buf); - } else { - btrfs_file_extent_item_to_cpu(extent); - rd = __btrfs_read_extent_reg(&path, extent, offset, size, - buf); - } - - if (rd == -1ULL) { - printf("%s: Error reading extent\n", __func__); - rd_all = -1; - goto out; - } - - offset = 0; - buf += rd; - rd_all += rd; - size -= rd; - - if (!size) - break; - } while (!(res = btrfs_next_slot(&path))); - - if (res) - return -1ULL; - -out: - __btrfs_free_path(&path); - return rd_all; -} - /* * Read out inline extent. * diff --git a/fs/btrfs/root.c b/fs/btrfs/root.c deleted file mode 100644 index a424966df6..0000000000 --- a/fs/btrfs/root.c +++ /dev/null @@ -1,92 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * BTRFS filesystem implementation for U-Boot - * - * 2017 Marek Behun, CZ.NIC, marek.behun@nic.cz - */ - -#include "btrfs.h" - -static void read_root_item(struct __btrfs_path *p, struct btrfs_root_item *item) -{ - u32 len; - int reset = 0; - - len = btrfs_path_item_size(p); - memcpy(item, btrfs_path_item_ptr(p, struct btrfs_root_item), len); - btrfs_root_item_to_cpu(item); - - if (len < sizeof(*item)) - reset = 1; - if (!reset && item->generation != item->generation_v2) { - if (item->generation_v2 != 0) - printf("%s: generation != generation_v2 in root item", - __func__); - reset = 1; - } - if (reset) { - memset(&item->generation_v2, 0, - sizeof(*item) - offsetof(struct btrfs_root_item, - generation_v2)); - } -} - -int btrfs_find_root(u64 objectid, struct __btrfs_root *root, - struct btrfs_root_item *root_item) -{ - struct __btrfs_path path; - struct btrfs_root_item my_root_item; - - if (!btrfs_search_tree_key_type(&btrfs_info.tree_root, objectid, - BTRFS_ROOT_ITEM_KEY, &path)) - return -1; - - if (!root_item) - root_item = &my_root_item; - read_root_item(&path, root_item); - - if (root) { - root->objectid = objectid; - root->bytenr = root_item->bytenr; - root->root_dirid = root_item->root_dirid; - } - - __btrfs_free_path(&path); - return 0; -} - -u64 btrfs_lookup_root_ref(u64 subvolid, struct btrfs_root_ref *refp, char *name) -{ - struct __btrfs_path path; - struct btrfs_key *key; - struct btrfs_root_ref *ref; - u64 res = -1ULL; - - key = btrfs_search_tree_key_type(&btrfs_info.tree_root, subvolid, - BTRFS_ROOT_BACKREF_KEY, &path); - - if (!key) - return -1ULL; - - ref = btrfs_path_item_ptr(&path, struct btrfs_root_ref); - btrfs_root_ref_to_cpu(ref); - - if (refp) - *refp = *ref; - - if (name) { - if (ref->name_len > BTRFS_NAME_LEN) { - printf("%s: volume name too long: %u\n", __func__, - ref->name_len); - goto out; - } - - memcpy(name, ref + 1, ref->name_len); - } - - res = key->offset; -out: - __btrfs_free_path(&path); - return res; -} - diff --git a/fs/btrfs/subvolume.c b/fs/btrfs/subvolume.c index 6fc28d53e5..2815673bcd 100644 --- a/fs/btrfs/subvolume.c +++ b/fs/btrfs/subvolume.c @@ -221,117 +221,6 @@ out: return ret; }

-static int get_subvol_name(u64 subvolid, char *name, int max_len) -{ - struct btrfs_root_ref rref; - struct btrfs_inode_ref iref; - struct __btrfs_root root; - u64 dir; - char tmp[BTRFS_NAME_LEN]; - char *ptr; - - ptr = name + max_len - 1; - *ptr = '\0'; - - while (subvolid != BTRFS_FS_TREE_OBJECTID) { - subvolid = btrfs_lookup_root_ref(subvolid, &rref, tmp); - - if (subvolid == -1ULL) - return -1; - - ptr -= rref.name_len + 1; - if (ptr < name) - goto too_long; - - memcpy(ptr + 1, tmp, rref.name_len); - *ptr = '/'; - - if (btrfs_find_root(subvolid, &root, NULL)) - return -1; - - dir = rref.dirid; - - while (dir != BTRFS_FIRST_FREE_OBJECTID) { - dir = __btrfs_lookup_inode_ref(&root, dir, &iref, tmp); - - if (dir == -1ULL) - return -1; - - ptr -= iref.name_len + 1; - if (ptr < name) - goto too_long; - - memcpy(ptr + 1, tmp, iref.name_len); - *ptr = '/'; - } - } - - if (ptr == name + max_len - 1) { - name[0] = '/'; - name[1] = '\0'; - } else { - memmove(name, ptr, name + max_len - ptr); - } - - return 0; - -too_long: - printf("%s: subvolume name too long\n", __func__); - return -1; -} - -u64 btrfs_get_default_subvol_objectid(void) -{ - struct btrfs_dir_item item; - - if (__btrfs_lookup_dir_item(&btrfs_info.tree_root, - btrfs_info.sb.root_dir_objectid, "default", 7, - &item)) - return BTRFS_FS_TREE_OBJECTID; - return item.location.objectid; -} - -static void list_subvols(u64 tree, char *nameptr, int max_name_len, int level) -{ - struct btrfs_key key, *found_key; - struct __btrfs_path path; - struct btrfs_root_ref *ref; - int res; - - key.objectid = tree; - key.type = BTRFS_ROOT_REF_KEY; - key.offset = 0; - - if (btrfs_search_tree(&btrfs_info.tree_root, &key, &path)) - return; - - do { - found_key = btrfs_path_leaf_key(&path); - if (btrfs_comp_keys_type(&key, found_key)) - break; - - ref = btrfs_path_item_ptr(&path, struct btrfs_root_ref); - btrfs_root_ref_to_cpu(ref); - - printf("ID %llu parent %llu name ", found_key->offset, tree); - if (nameptr && !get_subvol_name(found_key->offset, nameptr, - max_name_len)) - printf("%s\n", nameptr); - else - printf("%.*s\n", (int) ref->name_len, - (const char *) (ref + 1)); - - if (level > 0) - list_subvols(found_key->offset, nameptr, max_name_len, - level - 1); - else - printf("%s: Too much recursion, maybe skipping some " - "subvolumes\n", __func__); - } while (!(res = btrfs_next_slot(&path))); - - __btrfs_free_path(&path); -} - void btrfs_list_subvols(void) { struct btrfs_fs_info *fs_info = current_fs_info;