From: Wang Xiaoguang <wangxg.f...@cn.fujitsu.com> Introduce the header for btrfs online(write time) de-duplication framework and needed header.
The new de-duplication framework is going to support 2 different dedupe methods and 1 dedupe hash. Signed-off-by: Qu Wenruo <quwen...@cn.fujitsu.com> Signed-off-by: Wang Xiaoguang <wangxg.f...@cn.fujitsu.com> --- fs/btrfs/ctree.h | 7 +++ fs/btrfs/dedupe.h | 149 +++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/disk-io.c | 1 + include/uapi/linux/btrfs.h | 16 +++++ 4 files changed, 173 insertions(+) create mode 100644 fs/btrfs/dedupe.h diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 101c3cf..8f70f53d 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1091,6 +1091,13 @@ struct btrfs_fs_info { struct list_head pinned_chunks; int creating_free_space_tree; + + /* + * Inband de-duplication related structures + */ + unsigned long dedupe_enabled:1; + struct btrfs_dedupe_info *dedupe_info; + struct mutex dedupe_ioctl_lock; }; struct btrfs_subvolume_writers { diff --git a/fs/btrfs/dedupe.h b/fs/btrfs/dedupe.h new file mode 100644 index 0000000..d7b1a77 --- /dev/null +++ b/fs/btrfs/dedupe.h @@ -0,0 +1,149 @@ +/* + * Copyright (C) 2015 Fujitsu. All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#ifndef __BTRFS_DEDUPE__ +#define __BTRFS_DEDUPE__ + +#include <linux/btrfs.h> +#include <linux/wait.h> +#include <crypto/hash.h> + +static int btrfs_dedupe_sizes[] = { 32 }; + +/* + * For caller outside of dedupe.c + * + * Different dedupe backends should have their own hash structure + */ +struct btrfs_dedupe_hash { + u64 bytenr; + u32 num_bytes; + + /* last field is a variable length array of dedupe hash */ + u8 hash[]; +}; + +struct btrfs_dedupe_info { + /* dedupe blocksize */ + u64 blocksize; + u16 backend; + u16 hash_type; + + struct crypto_shash *dedupe_driver; + + /* + * Use mutex to portect both backends + * Even for in-memory backends, the rb-tree can be quite large, + * so mutex is better for such use case. + */ + struct mutex lock; + + /* following members are only used in in-memory backend */ + struct rb_root hash_root; + struct rb_root bytenr_root; + struct list_head lru_list; + u64 limit_nr; + u64 current_nr; +}; + +struct btrfs_trans_handle; + +static inline int btrfs_dedupe_hash_hit(struct btrfs_dedupe_hash *hash) +{ + return (hash && hash->bytenr); +} + +int btrfs_dedupe_hash_size(u16 type); +struct btrfs_dedupe_hash *btrfs_dedupe_alloc_hash(u16 type); + +/* + * Initial inband dedupe info + * Called at dedupe enable time. + * + * Return 0 for success + * Return <0 for any error + * (from unsupported param to tree creation error for some backends) + */ +int btrfs_dedupe_enable(struct btrfs_fs_info *fs_info, u16 type, u16 backend, + u64 blocksize, u64 limit_nr, u64 limit_mem); + +/* + * Disable dedupe and invalidate all its dedupe data. + * Called at dedupe disable time. + * + * Return 0 for success + * Return <0 for any error + * (tree operation error for some backends) + */ +int btrfs_dedupe_disable(struct btrfs_fs_info *fs_info); + +/* + * Calculate hash for dedupe. + * Caller must ensure [start, start + dedupe_bs) has valid data. + * + * Return 0 for success + * Return <0 for any error + * (error from hash codes) + */ +int btrfs_dedupe_calc_hash(struct btrfs_fs_info *fs_info, + struct inode *inode, u64 start, + struct btrfs_dedupe_hash *hash); + +/* + * Search for duplicated extents by calculated hash + * Caller must call btrfs_dedupe_calc_hash() first to get the hash. + * + * @inode: the inode for we are writing + * @file_pos: offset inside the inode + * As we will increase extent ref immediately after a hash match, + * we need @file_pos and @inode in this case. + * + * Return > 0 for a hash match, and the extent ref will be + * *INCREASED*, and hash->bytenr/num_bytes will record the existing + * extent data. + * Return 0 for a hash miss. Nothing is done + * Return <0 for any error + * (tree operation error for some backends) + */ +int btrfs_dedupe_search(struct btrfs_fs_info *fs_info, + struct inode *inode, u64 file_pos, + struct btrfs_dedupe_hash *hash); + +/* + * Add a dedupe hash into dedupe info + * Return 0 for success + * Return <0 for any error + * (tree operation error for some backends) + */ +int btrfs_dedupe_add(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, + struct btrfs_dedupe_hash *hash); + +/* + * Remove a dedupe hash from dedupe info + * Return 0 for success + * Return <0 for any error + * (tree operation error for some backends) + * + * NOTE: if hash deletion error is not handled well, it will lead + * to corrupted fs, as later dedupe write can points to non-exist or even + * wrong extent. + */ +int btrfs_dedupe_del(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr); +#endif diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1142127..dccd608 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2593,6 +2593,7 @@ int open_ctree(struct super_block *sb, mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); mutex_init(&fs_info->cleaner_delayed_iput_mutex); + mutex_init(&fs_info->dedupe_ioctl_lock); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 2bdd1e3..1279bf0 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -619,6 +619,22 @@ struct btrfs_ioctl_get_dev_stats { __u64 unused[128 - 2 - BTRFS_DEV_STAT_VALUES_MAX]; /* pad to 1k */ }; +/* In-band dedupe related */ +#define BTRFS_DEDUPE_BACKEND_INMEMORY 0 +#define BTRFS_DEDUPE_BACKEND_ONDISK 1 + +/* Only support inmemory yet, so count is still only 1 */ +#define BTRFS_DEDUPE_BACKEND_COUNT 1 + +/* Dedup block size limit and default value */ +#define BTRFS_DEDUPE_BLOCKSIZE_MAX (8 * 1024 * 1024) +#define BTRFS_DEDUPE_BLOCKSIZE_MIN (16 * 1024) +#define BTRFS_DEDUPE_BLOCKSIZE_DEFAULT (128 * 1024) + +/* Hash algorithm, only support SHA256 yet */ +#define BTRFS_DEDUPE_HASH_SHA256 0 + + #define BTRFS_QUOTA_CTL_ENABLE 1 #define BTRFS_QUOTA_CTL_DISABLE 2 #define BTRFS_QUOTA_CTL_RESCAN__NOTUSED 3 -- 2.8.3 -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html