diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 34ea4f1fa6ea..f7cbf574a875 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -494,6 +494,17 @@ Files in /sys/fs/ext4/ session_write_kbytes This file is read-only and shows the number of kilobytes of data that have been written to this filesystem since it was mounted. + + reserved_clusters This is RW file and contains number of reserved + clusters in the file system which will be used + in the specific situations to avoid costly + zeroout, unexpected ENOSPC, or possible data + loss. The default is 2% or 4096 clusters, + whichever is smaller and this can be changed + however it can never exceed number of clusters + in the file system. If there is not enough space + for the reserved space when mounting the file + mount will _not_ fail. .............................................................................. Ioctls @@ -587,6 +598,16 @@ Table of Ext4 specific ioctls bitmaps and inode table, the userspace tool thus just passes the new number of blocks. +EXT4_IOC_SWAP_BOOT Swap i_blocks and associated attributes + (like i_blocks, i_size, i_flags, ...) from + the specified inode with inode + EXT4_BOOT_LOADER_INO (#5). This is typically + used to store a boot loader in a secure part of + the filesystem, where it can't be changed by a + normal user by accident. + The data blocks of the previous boot loader + will be associated with the given inode. + .............................................................................. References diff --git a/fs/buffer.c b/fs/buffer.c index 10ef81e10b20..bc1fe14aaa3e 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2987,6 +2987,11 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) /* Take care of bh's that straddle the end of the device */ guard_bh_eod(rw, bio, bh); + if (buffer_meta(bh)) + rw |= REQ_META; + if (buffer_prio(bh)) + rw |= REQ_PRIO; + bio_get(bio); submit_bio(rw, bio); diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 987358740cb9..efea5d5c44ce 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -71,4 +71,5 @@ config EXT4_DEBUG Enables run-time debugging support for the ext4 filesystem. If you select Y here, then you will be able to turn on debugging - with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug" + with a command such as: + echo 1 > /sys/module/ext4/parameters/mballoc_debug diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 92e68b33fffd..d0f13eada0ed 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -29,6 +29,23 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb, * balloc.c contains the blocks allocation and deallocation routines */ +/* + * Calculate block group number for a given block number + */ +ext4_group_t ext4_get_group_number(struct super_block *sb, + ext4_fsblk_t block) +{ + ext4_group_t group; + + if (test_opt2(sb, STD_GROUP_SIZE)) + group = (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) + + block) >> + (EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3); + else + ext4_get_group_no_and_offset(sb, block, &group, NULL); + return group; +} + /* * Calculate the block group number and offset into the block/cluster * allocation bitmap, given a block number @@ -49,14 +66,18 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, } -static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block, - ext4_group_t block_group) +/* + * Check whether the 'block' lives within the 'block_group'. Returns 1 if so + * and 0 otherwise. + */ +static inline int ext4_block_in_group(struct super_block *sb, + ext4_fsblk_t block, + ext4_group_t block_group) { ext4_group_t actual_group; - ext4_get_group_no_and_offset(sb, block, &actual_group, NULL); - if (actual_group == block_group) - return 1; - return 0; + + actual_group = ext4_get_group_number(sb, block); + return (actual_group == block_group) ? 1 : 0; } /* Return the number of clusters used for file system metadata; this @@ -420,7 +441,7 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) trace_ext4_read_block_bitmap_load(sb, block_group); bh->b_end_io = ext4_end_bitmap_read; get_bh(bh); - submit_bh(READ, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); return bh; verify: ext4_validate_block_bitmap(sb, desc, block_group, bh); @@ -478,20 +499,22 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) static int ext4_has_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags) { - s64 free_clusters, dirty_clusters, root_clusters; + s64 free_clusters, dirty_clusters, rsv, resv_clusters; struct percpu_counter *fcc = &sbi->s_freeclusters_counter; struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter; free_clusters = percpu_counter_read_positive(fcc); dirty_clusters = percpu_counter_read_positive(dcc); + resv_clusters = atomic64_read(&sbi->s_resv_clusters); /* * r_blocks_count should always be multiple of the cluster ratio so * we are safe to do a plane bit shift only. */ - root_clusters = ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits; + rsv = (ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits) + + resv_clusters; - if (free_clusters - (nclusters + root_clusters + dirty_clusters) < + if (free_clusters - (nclusters + rsv + dirty_clusters) < EXT4_FREECLUSTERS_WATERMARK) { free_clusters = percpu_counter_sum_positive(fcc); dirty_clusters = percpu_counter_sum_positive(dcc); @@ -499,15 +522,21 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi, /* Check whether we have space after accounting for current * dirty clusters & root reserved clusters. */ - if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters)) + if (free_clusters >= (rsv + nclusters + dirty_clusters)) return 1; /* Hm, nope. Are (enough) root reserved clusters available? */ if (uid_eq(sbi->s_resuid, current_fsuid()) || (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) || capable(CAP_SYS_RESOURCE) || - (flags & EXT4_MB_USE_ROOT_BLOCKS)) { + (flags & EXT4_MB_USE_ROOT_BLOCKS)) { + if (free_clusters >= (nclusters + dirty_clusters + + resv_clusters)) + return 1; + } + /* No free blocks. Let's see if we can dip into reserved pool */ + if (flags & EXT4_MB_USE_RESERVED) { if (free_clusters >= (nclusters + dirty_clusters)) return 1; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index d8cd1f0f4661..f8d56e4254e0 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -46,7 +46,8 @@ static int is_dx_dir(struct inode *inode) if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_COMPAT_DIR_INDEX) && ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) || - ((inode->i_size >> sb->s_blocksize_bits) == 1))) + ((inode->i_size >> sb->s_blocksize_bits) == 1) || + ext4_has_inline_data(inode))) return 1; return 0; @@ -115,14 +116,6 @@ static int ext4_readdir(struct file *filp, int ret = 0; int dir_has_error = 0; - if (ext4_has_inline_data(inode)) { - int has_inline_data = 1; - ret = ext4_read_inline_dir(filp, dirent, filldir, - &has_inline_data); - if (has_inline_data) - return ret; - } - if (is_dx_dir(inode)) { err = ext4_dx_readdir(filp, dirent, filldir); if (err != ERR_BAD_DX_DIR) { @@ -136,6 +129,15 @@ static int ext4_readdir(struct file *filp, ext4_clear_inode_flag(file_inode(filp), EXT4_INODE_INDEX); } + + if (ext4_has_inline_data(inode)) { + int has_inline_data = 1; + ret = ext4_read_inline_dir(filp, dirent, filldir, + &has_inline_data); + if (has_inline_data) + return ret; + } + stored = 0; offset = filp->f_pos & (sb->s_blocksize - 1); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3b83cd604796..0aabb344b02e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -121,6 +121,8 @@ typedef unsigned int ext4_group_t; #define EXT4_MB_STREAM_ALLOC 0x0800 /* Use reserved root blocks if needed */ #define EXT4_MB_USE_ROOT_BLOCKS 0x1000 +/* Use blocks from reserved pool */ +#define EXT4_MB_USE_RESERVED 0x2000 struct ext4_allocation_request { /* target inode for block we're allocating */ @@ -196,19 +198,8 @@ struct mpage_da_data { #define EXT4_IO_END_ERROR 0x0002 #define EXT4_IO_END_DIRECT 0x0004 -struct ext4_io_page { - struct page *p_page; - atomic_t p_count; -}; - -#define MAX_IO_PAGES 128 - /* * For converting uninitialized extents on a work queue. - * - * 'page' is only used from the writepage() path; 'pages' is only used for - * buffered writes; they are used to keep page references until conversion - * takes place. For AIO/DIO, neither field is filled in. */ typedef struct ext4_io_end { struct list_head list; /* per-file finished IO list */ @@ -218,15 +209,13 @@ typedef struct ext4_io_end { ssize_t size; /* size of the extent */ struct kiocb *iocb; /* iocb struct for AIO */ int result; /* error value for AIO */ - int num_io_pages; /* for writepages() */ - struct ext4_io_page *pages[MAX_IO_PAGES]; /* for writepages() */ + atomic_t count; /* reference counter */ } ext4_io_end_t; struct ext4_io_submit { int io_op; struct bio *io_bio; ext4_io_end_t *io_end; - struct ext4_io_page *io_page; sector_t io_next_block; }; @@ -403,7 +392,7 @@ struct flex_groups { #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x004B80FF /* User modifiable flags */ +#define EXT4_FL_USER_MODIFIABLE 0x004380FF /* User modifiable flags */ /* Flags that should be inherited by new inodes from their parent. */ #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ @@ -557,9 +546,8 @@ enum { #define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002 #define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ EXT4_GET_BLOCKS_CREATE) - /* Caller is from the delayed allocation writeout path, - so set the magic i_delalloc_reserve_flag after taking the - inode allocation semaphore for */ + /* Caller is from the delayed allocation writeout path + * finally doing the actual allocation of delayed blocks */ #define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004 /* caller is from the direct IO path, request to creation of an unitialized extents if not allocated, split the uninitialized @@ -571,8 +559,9 @@ enum { /* Convert extent to initialized after IO complete */ #define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\ EXT4_GET_BLOCKS_CREATE_UNINIT_EXT) - /* Punch out blocks of an extent */ -#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020 + /* Eventual metadata allocation (due to growing extent tree) + * should not fail, so try to use reserved blocks for that.*/ +#define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020 /* Don't normalize allocation size (used for fallocate) */ #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Request will not result in inode size update (user for fallocate) */ @@ -616,6 +605,7 @@ enum { #define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12) #define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent) #define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64) +#define EXT4_IOC_SWAP_BOOT _IO('f', 17) #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -949,7 +939,7 @@ struct ext4_inode_info { #define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */ /* - * Mount flags + * Mount flags set via mount options or defaults */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ @@ -981,8 +971,16 @@ struct ext4_inode_info { #define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ #define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */ +/* + * Mount flags set either automatically (could not be set by mount option) + * based on per file system feature or property or in special cases such as + * distinguishing between explicit mount option definition and default. + */ #define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly specified delalloc */ +#define EXT4_MOUNT2_STD_GROUP_SIZE 0x00000002 /* We have standard group + size of blocksize * 8 + blocks */ #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -1179,6 +1177,7 @@ struct ext4_sb_info { unsigned int s_mount_flags; unsigned int s_def_mount_opt; ext4_fsblk_t s_sb_block; + atomic64_t s_resv_clusters; kuid_t s_resuid; kgid_t s_resgid; unsigned short s_mount_state; @@ -1333,6 +1332,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) return ino == EXT4_ROOT_INO || ino == EXT4_USR_QUOTA_INO || ino == EXT4_GRP_QUOTA_INO || + ino == EXT4_BOOT_LOADER_INO || ino == EXT4_JOURNAL_INO || ino == EXT4_RESIZE_INO || (ino >= EXT4_FIRST_INO(sb) && @@ -1374,6 +1374,7 @@ enum { EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read nolocking */ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ + EXT4_STATE_ORDERED_MODE, /* data=ordered mode */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ @@ -1784,9 +1785,6 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) */ #define ERR_BAD_DX_DIR -75000 -void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, - ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp); - /* * Timeout and state flag for lazy initialization inode thread. */ @@ -1908,6 +1906,13 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct buffer_head *bh); /* balloc.c */ +extern void ext4_get_group_no_and_offset(struct super_block *sb, + ext4_fsblk_t blocknr, + ext4_group_t *blockgrpp, + ext4_grpblk_t *offsetp); +extern ext4_group_t ext4_get_group_number(struct super_block *sb, + ext4_fsblk_t block); + extern void ext4_validate_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc, unsigned int block_group, @@ -2108,8 +2113,9 @@ extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, unsigned long nr_segs); extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk); -extern void ext4_ind_truncate(struct inode *inode); -extern int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length); +extern void ext4_ind_truncate(handle_t *, struct inode *inode); +extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode, + ext4_lblk_t first, ext4_lblk_t stop); /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); @@ -2117,6 +2123,7 @@ extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); +extern int ext4_ind_migrate(struct inode *inode); /* namei.c */ extern int ext4_dirent_csum_verify(struct inode *inode, @@ -2511,6 +2518,11 @@ extern int ext4_try_create_inline_dir(handle_t *handle, extern int ext4_read_inline_dir(struct file *filp, void *dirent, filldir_t filldir, int *has_inline_data); +extern int htree_inlinedir_to_tree(struct file *dir_file, + struct inode *dir, ext4_lblk_t block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash, + int *has_inline_data); extern struct buffer_head *ext4_find_inline_entry(struct inode *dir, const struct qstr *d_name, struct ext4_dir_entry_2 **res_dir, @@ -2547,6 +2559,24 @@ extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t, extern int ext4_handle_dirty_dirent_node(handle_t *handle, struct inode *inode, struct buffer_head *bh); +#define S_SHIFT 12 +static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { + [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, + [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR, + [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV, + [S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV, + [S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO, + [S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK, + [S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK, +}; + +static inline void ext4_set_de_type(struct super_block *sb, + struct ext4_dir_entry_2 *de, + umode_t mode) { + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE)) + de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; +} + /* symlink.c */ extern const struct inode_operations ext4_symlink_inode_operations; @@ -2573,9 +2603,9 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk); extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); -extern void ext4_ext_truncate(struct inode *); -extern int ext4_ext_punch_hole(struct file *file, loff_t offset, - loff_t length); +extern void ext4_ext_truncate(handle_t *, struct inode *); +extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t end); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); extern long ext4_fallocate(struct file *file, int mode, loff_t offset, @@ -2609,17 +2639,26 @@ extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, /* move_extent.c */ +extern void ext4_double_down_write_data_sem(struct inode *first, + struct inode *second); +extern void ext4_double_up_write_data_sem(struct inode *orig_inode, + struct inode *donor_inode); +void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2); +void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2); extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 start_orig, __u64 start_donor, __u64 len, __u64 *moved_len); /* page-io.c */ extern int __init ext4_init_pageio(void); -extern void ext4_add_complete_io(ext4_io_end_t *io_end); extern void ext4_exit_pageio(void); extern void ext4_ioend_shutdown(struct inode *); -extern void ext4_free_io_end(ext4_io_end_t *io); extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags); +extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end); +extern int ext4_put_io_end(ext4_io_end_t *io_end); +extern void ext4_put_io_end_defer(ext4_io_end_t *io_end); +extern void ext4_io_submit_init(struct ext4_io_submit *io, + struct writeback_control *wbc); extern void ext4_end_io_work(struct work_struct *work); extern void ext4_io_submit(struct ext4_io_submit *io); extern int ext4_bio_write_page(struct ext4_io_submit *io, diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 8643ff5bbeb7..51bc821ade90 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -270,5 +270,10 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, 0xffff); } +#define ext4_ext_dirty(handle, inode, path) \ + __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) +int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, + struct inode *inode, struct ext4_ext_path *path); + #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 7058975e3a55..451eb4045330 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -43,6 +43,8 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, { journal_t *journal; + might_sleep(); + trace_ext4_journal_start(sb, nblocks, _RET_IP_); if (sb->s_flags & MS_RDONLY) return ERR_PTR(-EROFS); @@ -113,6 +115,8 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line, { int err = 0; + might_sleep(); + if (ext4_handle_valid(handle)) { err = jbd2_journal_get_write_access(handle, bh); if (err) @@ -209,6 +213,10 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, { int err = 0; + might_sleep(); + + set_buffer_meta(bh); + set_buffer_prio(bh); if (ext4_handle_valid(handle)) { err = jbd2_journal_dirty_metadata(handle, bh); if (err) { diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 4c216b1bf20c..c8c6885406db 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -29,11 +29,13 @@ * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to - * 5 levels of tree + root which are stored in the inode. */ + * 5 levels of tree, data block (for each of these we need bitmap + group + * summaries), root which is stored in the inode, sb + */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ - ? 27U : 8U) + ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode @@ -194,16 +196,20 @@ static inline void ext4_journal_callback_add(handle_t *handle, * ext4_journal_callback_del: delete a registered callback * @handle: active journal transaction handle on which callback was registered * @jce: registered journal callback entry to unregister + * Return true if object was sucessfully removed */ -static inline void ext4_journal_callback_del(handle_t *handle, +static inline bool ext4_journal_callback_try_del(handle_t *handle, struct ext4_journal_cb_entry *jce) { + bool deleted; struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); spin_lock(&sbi->s_md_lock); + deleted = !list_empty(&jce->jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); + return deleted; } int diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9c6d06dcef8b..107936db244e 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -157,11 +157,8 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, * - ENOMEM * - EIO */ -#define ext4_ext_dirty(handle, inode, path) \ - __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) -static int __ext4_ext_dirty(const char *where, unsigned int line, - handle_t *handle, struct inode *inode, - struct ext4_ext_path *path) +int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, + struct inode *inode, struct ext4_ext_path *path) { int err; if (path->p_bh) { @@ -1813,39 +1810,101 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, } depth = ext_depth(inode); ex = path[depth].p_ext; + eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); return -EIO; } /* try to insert block into found extent and return */ - if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO) - && ext4_can_extents_be_merged(inode, ex, newext)) { - ext_debug("append [%d]%d block to %u:[%d]%d (from %llu)\n", - ext4_ext_is_uninitialized(newext), - ext4_ext_get_actual_len(newext), - le32_to_cpu(ex->ee_block), - ext4_ext_is_uninitialized(ex), - ext4_ext_get_actual_len(ex), - ext4_ext_pblock(ex)); - err = ext4_ext_get_access(handle, inode, path + depth); - if (err) - return err; + if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)) { /* - * ext4_can_extents_be_merged should have checked that either - * both extents are uninitialized, or both aren't. Thus we - * need to check only one of them here. + * Try to see whether we should rather test the extent on + * right from ex, or from the left of ex. This is because + * ext4_ext_find_extent() can return either extent on the + * left, or on the right from the searched position. This + * will make merging more effective. */ - if (ext4_ext_is_uninitialized(ex)) - uninitialized = 1; - ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + if (ex < EXT_LAST_EXTENT(eh) && + (le32_to_cpu(ex->ee_block) + + ext4_ext_get_actual_len(ex) < + le32_to_cpu(newext->ee_block))) { + ex += 1; + goto prepend; + } else if ((ex > EXT_FIRST_EXTENT(eh)) && + (le32_to_cpu(newext->ee_block) + + ext4_ext_get_actual_len(newext) < + le32_to_cpu(ex->ee_block))) + ex -= 1; + + /* Try to append newex to the ex */ + if (ext4_can_extents_be_merged(inode, ex, newext)) { + ext_debug("append [%d]%d block to %u:[%d]%d" + "(from %llu)\n", + ext4_ext_is_uninitialized(newext), + ext4_ext_get_actual_len(newext), + le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), + ext4_ext_get_actual_len(ex), + ext4_ext_pblock(ex)); + err = ext4_ext_get_access(handle, inode, + path + depth); + if (err) + return err; + + /* + * ext4_can_extents_be_merged should have checked + * that either both extents are uninitialized, or + * both aren't. Thus we need to check only one of + * them here. + */ + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); - if (uninitialized) - ext4_ext_mark_uninitialized(ex); - eh = path[depth].p_hdr; - nearex = ex; - goto merge; + if (uninitialized) + ext4_ext_mark_uninitialized(ex); + eh = path[depth].p_hdr; + nearex = ex; + goto merge; + } + +prepend: + /* Try to prepend newex to the ex */ + if (ext4_can_extents_be_merged(inode, newext, ex)) { + ext_debug("prepend %u[%d]%d block to %u:[%d]%d" + "(from %llu)\n", + le32_to_cpu(newext->ee_block), + ext4_ext_is_uninitialized(newext), + ext4_ext_get_actual_len(newext), + le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), + ext4_ext_get_actual_len(ex), + ext4_ext_pblock(ex)); + err = ext4_ext_get_access(handle, inode, + path + depth); + if (err) + return err; + + /* + * ext4_can_extents_be_merged should have checked + * that either both extents are uninitialized, or + * both aren't. Thus we need to check only one of + * them here. + */ + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex->ee_block = newext->ee_block; + ext4_ext_store_pblock(ex, ext4_ext_pblock(newext)); + ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + + ext4_ext_get_actual_len(newext)); + if (uninitialized) + ext4_ext_mark_uninitialized(ex); + eh = path[depth].p_hdr; + nearex = ex; + goto merge; + } } depth = ext_depth(inode); @@ -1880,8 +1939,8 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, * There is no free space in the found leaf. * We're gonna add a new leaf in the tree. */ - if (flag & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) - flags = EXT4_MB_USE_ROOT_BLOCKS; + if (flag & EXT4_GET_BLOCKS_METADATA_NOFAIL) + flags = EXT4_MB_USE_RESERVED; err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext); if (err) goto cleanup; @@ -2599,8 +2658,8 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path) return 1; } -static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, - ext4_lblk_t end) +int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t end) { struct super_block *sb = inode->i_sb; int depth = ext_depth(inode); @@ -2667,12 +2726,14 @@ again: /* * Split the extent in two so that 'end' is the last - * block in the first new extent + * block in the first new extent. Also we should not + * fail removing space due to ENOSPC so try to use + * reserved block if that happens. */ err = ext4_split_extent_at(handle, inode, path, - end + 1, split_flag, - EXT4_GET_BLOCKS_PRE_IO | - EXT4_GET_BLOCKS_PUNCH_OUT_EXT); + end + 1, split_flag, + EXT4_GET_BLOCKS_PRE_IO | + EXT4_GET_BLOCKS_METADATA_NOFAIL); if (err < 0) goto out; @@ -3147,35 +3208,35 @@ out: static int ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, - struct ext4_ext_path *path) + struct ext4_ext_path *path, + int flags) { struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; struct ext4_extent zero_ex; - struct ext4_extent *ex; + struct ext4_extent *ex, *abut_ex; ext4_lblk_t ee_block, eof_block; - unsigned int ee_len, depth; - int allocated, max_zeroout = 0; + unsigned int ee_len, depth, map_len = map->m_len; + int allocated = 0, max_zeroout = 0; int err = 0; int split_flag = 0; ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical" "block %llu, max_blocks %u\n", inode->i_ino, - (unsigned long long)map->m_lblk, map->m_len); + (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; - if (eof_block < map->m_lblk + map->m_len) - eof_block = map->m_lblk + map->m_len; + if (eof_block < map->m_lblk + map_len) + eof_block = map->m_lblk + map_len; depth = ext_depth(inode); eh = path[depth].p_hdr; ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); - allocated = ee_len - (map->m_lblk - ee_block); zero_ex.ee_len = 0; trace_ext4_ext_convert_to_initialized_enter(inode, map, ex); @@ -3186,77 +3247,121 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, /* * Attempt to transfer newly initialized blocks from the currently - * uninitialized extent to its left neighbor. This is much cheaper + * uninitialized extent to its neighbor. This is much cheaper * than an insertion followed by a merge as those involve costly - * memmove() calls. This is the common case in steady state for - * workloads doing fallocate(FALLOC_FL_KEEP_SIZE) followed by append - * writes. + * memmove() calls. Transferring to the left is the common case in + * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE) + * followed by append writes. * * Limitations of the current logic: - * - L1: we only deal with writes at the start of the extent. - * The approach could be extended to writes at the end - * of the extent but this scenario was deemed less common. - * - L2: we do not deal with writes covering the whole extent. + * - L1: we do not deal with writes covering the whole extent. * This would require removing the extent if the transfer * is possible. - * - L3: we only attempt to merge with an extent stored in the + * - L2: we only attempt to merge with an extent stored in the * same extent tree node. */ - if ((map->m_lblk == ee_block) && /*L1*/ - (map->m_len < ee_len) && /*L2*/ - (ex > EXT_FIRST_EXTENT(eh))) { /*L3*/ - struct ext4_extent *prev_ex; + if ((map->m_lblk == ee_block) && + /* See if we can merge left */ + (map_len < ee_len) && /*L1*/ + (ex > EXT_FIRST_EXTENT(eh))) { /*L2*/ ext4_lblk_t prev_lblk; ext4_fsblk_t prev_pblk, ee_pblk; - unsigned int prev_len, write_len; + unsigned int prev_len; - prev_ex = ex - 1; - prev_lblk = le32_to_cpu(prev_ex->ee_block); - prev_len = ext4_ext_get_actual_len(prev_ex); - prev_pblk = ext4_ext_pblock(prev_ex); + abut_ex = ex - 1; + prev_lblk = le32_to_cpu(abut_ex->ee_block); + prev_len = ext4_ext_get_actual_len(abut_ex); + prev_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); - write_len = map->m_len; /* - * A transfer of blocks from 'ex' to 'prev_ex' is allowed + * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: - * - C1: prev_ex is initialized, - * - C2: prev_ex is logically abutting ex, - * - C3: prev_ex is physically abutting ex, - * - C4: prev_ex can receive the additional blocks without + * - C1: abut_ex is initialized, + * - C2: abut_ex is logically abutting ex, + * - C3: abut_ex is physically abutting ex, + * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ - if ((!ext4_ext_is_uninitialized(prev_ex)) && /*C1*/ + if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/ ((prev_lblk + prev_len) == ee_block) && /*C2*/ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/ - (prev_len < (EXT_INIT_MAX_LEN - write_len))) { /*C4*/ + (prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; trace_ext4_ext_convert_to_initialized_fastpath(inode, - map, ex, prev_ex); + map, ex, abut_ex); - /* Shift the start of ex by 'write_len' blocks */ - ex->ee_block = cpu_to_le32(ee_block + write_len); - ext4_ext_store_pblock(ex, ee_pblk + write_len); - ex->ee_len = cpu_to_le16(ee_len - write_len); + /* Shift the start of ex by 'map_len' blocks */ + ex->ee_block = cpu_to_le32(ee_block + map_len); + ext4_ext_store_pblock(ex, ee_pblk + map_len); + ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_uninitialized(ex); /* Restore the flag */ - /* Extend prev_ex by 'write_len' blocks */ - prev_ex->ee_len = cpu_to_le16(prev_len + write_len); - - /* Mark the block containing both extents as dirty */ - ext4_ext_dirty(handle, inode, path + depth); - - /* Update path to point to the right extent */ - path[depth].p_ext = prev_ex; + /* Extend abut_ex by 'map_len' blocks */ + abut_ex->ee_len = cpu_to_le16(prev_len + map_len); /* Result: number of initialized blocks past m_lblk */ - allocated = write_len; - goto out; + allocated = map_len; + } + } else if (((map->m_lblk + map_len) == (ee_block + ee_len)) && + (map_len < ee_len) && /*L1*/ + ex < EXT_LAST_EXTENT(eh)) { /*L2*/ + /* See if we can merge right */ + ext4_lblk_t next_lblk; + ext4_fsblk_t next_pblk, ee_pblk; + unsigned int next_len; + + abut_ex = ex + 1; + next_lblk = le32_to_cpu(abut_ex->ee_block); + next_len = ext4_ext_get_actual_len(abut_ex); + next_pblk = ext4_ext_pblock(abut_ex); + ee_pblk = ext4_ext_pblock(ex); + + /* + * A transfer of blocks from 'ex' to 'abut_ex' is allowed + * upon those conditions: + * - C1: abut_ex is initialized, + * - C2: abut_ex is logically abutting ex, + * - C3: abut_ex is physically abutting ex, + * - C4: abut_ex can receive the additional blocks without + * overflowing the (initialized) length limit. + */ + if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/ + ((map->m_lblk + map_len) == next_lblk) && /*C2*/ + ((ee_pblk + ee_len) == next_pblk) && /*C3*/ + (next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + + trace_ext4_ext_convert_to_initialized_fastpath(inode, + map, ex, abut_ex); + + /* Shift the start of abut_ex by 'map_len' blocks */ + abut_ex->ee_block = cpu_to_le32(next_lblk - map_len); + ext4_ext_store_pblock(abut_ex, next_pblk - map_len); + ex->ee_len = cpu_to_le16(ee_len - map_len); + ext4_ext_mark_uninitialized(ex); /* Restore the flag */ + + /* Extend abut_ex by 'map_len' blocks */ + abut_ex->ee_len = cpu_to_le16(next_len + map_len); + + /* Result: number of initialized blocks past m_lblk */ + allocated = map_len; } } + if (allocated) { + /* Mark the block containing both extents as dirty */ + ext4_ext_dirty(handle, inode, path + depth); + + /* Update path to point to the right extent */ + path[depth].p_ext = abut_ex; + goto out; + } else + allocated = ee_len - (map->m_lblk - ee_block); WARN_ON(map->m_lblk < ee_block); /* @@ -3330,7 +3435,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, } allocated = ext4_split_extent(handle, inode, path, - &split_map, split_flag, 0); + &split_map, split_flag, flags); if (allocated < 0) err = allocated; @@ -3650,6 +3755,12 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, flags, allocated); ext4_ext_show_leaf(inode, path); + /* + * When writing into uninitialized space, we should not fail to + * allocate metadata blocks for the new extent block if needed. + */ + flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL; + trace_ext4_ext_handle_uninitialized_extents(inode, map, flags, allocated, newblock); @@ -3713,7 +3824,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, } /* buffered write, writepage time, convert*/ - ret = ext4_ext_convert_to_initialized(handle, inode, map, path); + ret = ext4_ext_convert_to_initialized(handle, inode, map, path, flags); if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); out: @@ -4257,47 +4368,12 @@ out3: return err ? err : allocated; } -void ext4_ext_truncate(struct inode *inode) +void ext4_ext_truncate(handle_t *handle, struct inode *inode) { - struct address_space *mapping = inode->i_mapping; struct super_block *sb = inode->i_sb; ext4_lblk_t last_block; - handle_t *handle; - loff_t page_len; int err = 0; - /* - * finish any pending end_io work so we won't run the risk of - * converting any truncated blocks to initialized later - */ - ext4_flush_unwritten_io(inode); - - /* - * probably first extent we're gonna free will be last in block - */ - err = ext4_writepage_trans_blocks(inode); - handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, err); - if (IS_ERR(handle)) - return; - - if (inode->i_size % PAGE_CACHE_SIZE != 0) { - page_len = PAGE_CACHE_SIZE - - (inode->i_size & (PAGE_CACHE_SIZE - 1)); - - err = ext4_discard_partial_page_buffers(handle, - mapping, inode->i_size, page_len, 0); - - if (err) - goto out_stop; - } - - if (ext4_orphan_add(handle, inode)) - goto out_stop; - - down_write(&EXT4_I(inode)->i_data_sem); - - ext4_discard_preallocations(inode); - /* * TODO: optimization is possible here. * Probably we need not scan at all, @@ -4313,29 +4389,6 @@ void ext4_ext_truncate(struct inode *inode) err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); - - /* In a multi-transaction truncate, we only make the final - * transaction synchronous. - */ - if (IS_SYNC(inode)) - ext4_handle_sync(handle); - - up_write(&EXT4_I(inode)->i_data_sem); - -out_stop: - /* - * If this was a simple ftruncate() and the file will remain alive, - * then we need to clear up the orphan record which we created above. - * However, if this was a real unlink then we were called by - * ext4_delete_inode(), and we allow that function to clean up the - * orphan info for us. - */ - if (inode->i_nlink) - ext4_orphan_del(handle, inode); - - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - ext4_journal_stop(handle); } static void ext4_falloc_update_inode(struct inode *inode, @@ -4623,187 +4676,6 @@ static int ext4_xattr_fiemap(struct inode *inode, return (error < 0 ? error : 0); } -/* - * ext4_ext_punch_hole - * - * Punches a hole of "length" bytes in a file starting - * at byte "offset" - * - * @inode: The inode of the file to punch a hole in - * @offset: The starting byte offset of the hole - * @length: The length of the hole - * - * Returns the number of blocks removed or negative on err - */ -int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) -{ - struct inode *inode = file_inode(file); - struct super_block *sb = inode->i_sb; - ext4_lblk_t first_block, stop_block; - struct address_space *mapping = inode->i_mapping; - handle_t *handle; - loff_t first_page, last_page, page_len; - loff_t first_page_offset, last_page_offset; - int credits, err = 0; - - /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - err = filemap_write_and_wait_range(mapping, - offset, offset + length - 1); - - if (err) - return err; - } - - mutex_lock(&inode->i_mutex); - /* It's not possible punch hole on append only file */ - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { - err = -EPERM; - goto out_mutex; - } - if (IS_SWAPFILE(inode)) { - err = -ETXTBSY; - goto out_mutex; - } - - /* No need to punch hole beyond i_size */ - if (offset >= inode->i_size) - goto out_mutex; - - /* - * If the hole extends beyond i_size, set the hole - * to end after the page that contains i_size - */ - if (offset + length > inode->i_size) { - length = inode->i_size + - PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) - - offset; - } - - first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - last_page = (offset + length) >> PAGE_CACHE_SHIFT; - - first_page_offset = first_page << PAGE_CACHE_SHIFT; - last_page_offset = last_page << PAGE_CACHE_SHIFT; - - /* Now release the pages */ - if (last_page_offset > first_page_offset) { - truncate_pagecache_range(inode, first_page_offset, - last_page_offset - 1); - } - - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - err = ext4_flush_unwritten_io(inode); - if (err) - goto out_dio; - inode_dio_wait(inode); - - credits = ext4_writepage_trans_blocks(inode); - handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - goto out_dio; - } - - - /* - * Now we need to zero out the non-page-aligned data in the - * pages at the start and tail of the hole, and unmap the buffer - * heads for the block aligned regions of the page that were - * completely zeroed. - */ - if (first_page > last_page) { - /* - * If the file space being truncated is contained within a page - * just zero out and unmap the middle of that page - */ - err = ext4_discard_partial_page_buffers(handle, - mapping, offset, length, 0); - - if (err) - goto out; - } else { - /* - * zero out and unmap the partial page that contains - * the start of the hole - */ - page_len = first_page_offset - offset; - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, mapping, - offset, page_len, 0); - if (err) - goto out; - } - - /* - * zero out and unmap the partial page that contains - * the end of the hole - */ - page_len = offset + length - last_page_offset; - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, mapping, - last_page_offset, page_len, 0); - if (err) - goto out; - } - } - - /* - * If i_size is contained in the last page, we need to - * unmap and zero the partial page after i_size - */ - if (inode->i_size >> PAGE_CACHE_SHIFT == last_page && - inode->i_size % PAGE_CACHE_SIZE != 0) { - - page_len = PAGE_CACHE_SIZE - - (inode->i_size & (PAGE_CACHE_SIZE - 1)); - - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, - mapping, inode->i_size, page_len, 0); - - if (err) - goto out; - } - } - - first_block = (offset + sb->s_blocksize - 1) >> - EXT4_BLOCK_SIZE_BITS(sb); - stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); - - /* If there are no blocks to remove, return now */ - if (first_block >= stop_block) - goto out; - - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); - - err = ext4_es_remove_extent(inode, first_block, - stop_block - first_block); - err = ext4_ext_remove_space(inode, first_block, stop_block - 1); - - ext4_discard_preallocations(inode); - - if (IS_SYNC(inode)) - ext4_handle_sync(handle); - - up_write(&EXT4_I(inode)->i_data_sem); - -out: - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - ext4_journal_stop(handle); -out_dio: - ext4_inode_resume_unlocked_dio(inode); -out_mutex: - mutex_unlock(&inode->i_mutex); - return err; -} - int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 3278e64e57b6..e0ba8a408def 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -166,8 +166,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(journal, commit_tid)) needs_barrier = true; - jbd2_log_start_commit(journal, commit_tid); - ret = jbd2_log_wait_commit(journal, commit_tid); + ret = jbd2_complete_transaction(journal, commit_tid); if (needs_barrier) { err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); if (!ret) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 6c5bb8d993fe..00a818d67b54 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -166,7 +166,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) trace_ext4_load_inode_bitmap(sb, block_group); bh->b_end_io = ext4_end_bitmap_read; get_bh(bh); - submit_bh(READ, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { put_bh(bh); @@ -666,6 +666,23 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, ei = EXT4_I(inode); sbi = EXT4_SB(sb); + /* + * Initalize owners and quota early so that we don't have to account + * for quota initialization worst case in standard inode creating + * transaction + */ + if (owner) { + inode->i_mode = mode; + i_uid_write(inode, owner[0]); + i_gid_write(inode, owner[1]); + } else if (test_opt(sb, GRPID)) { + inode->i_mode = mode; + inode->i_uid = current_fsuid(); + inode->i_gid = dir->i_gid; + } else + inode_init_owner(inode, dir, mode); + dquot_initialize(inode); + if (!goal) goal = sbi->s_inode_goal; @@ -697,7 +714,7 @@ got_group: gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp) - goto fail; + goto out; /* * Check free inodes count before loading bitmap. @@ -711,7 +728,7 @@ got_group: brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); if (!inode_bitmap_bh) - goto fail; + goto out; repeat_in_this_group: ino = ext4_find_next_zero_bit((unsigned long *) @@ -733,13 +750,16 @@ repeat_in_this_group: handle_type, nblocks); if (IS_ERR(handle)) { err = PTR_ERR(handle); - goto fail; + ext4_std_error(sb, err); + goto out; } } BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode_bitmap_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } ext4_lock_group(sb, group); ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data); ext4_unlock_group(sb, group); @@ -755,8 +775,10 @@ repeat_in_this_group: got: BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && @@ -768,7 +790,8 @@ got: err = ext4_journal_get_write_access(handle, block_bitmap_bh); if (err) { brelse(block_bitmap_bh); - goto fail; + ext4_std_error(sb, err); + goto out; } BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); @@ -787,14 +810,18 @@ got: ext4_unlock_group(sb, group); brelse(block_bitmap_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } } BUFFER_TRACE(group_desc_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, group_desc_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } /* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { @@ -840,8 +867,10 @@ got: BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) @@ -851,16 +880,6 @@ got: flex_group = ext4_flex_group(sbi, group); atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes); } - if (owner) { - inode->i_mode = mode; - i_uid_write(inode, owner[0]); - i_gid_write(inode, owner[1]); - } else if (test_opt(sb, GRPID)) { - inode->i_mode = mode; - inode->i_uid = current_fsuid(); - inode->i_gid = dir->i_gid; - } else - inode_init_owner(inode, dir, mode); inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* This is the optimal IO size (for stat), not the fs block size */ @@ -889,7 +908,9 @@ got: * twice. */ err = -EIO; - goto fail; + ext4_error(sb, "failed to insert inode %lu: doubly allocated?", + inode->i_ino); + goto out; } spin_lock(&sbi->s_next_gen_lock); inode->i_generation = sbi->s_next_generation++; @@ -899,7 +920,6 @@ got: if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { __u32 csum; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, @@ -918,7 +938,6 @@ got: ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); ret = inode; - dquot_initialize(inode); err = dquot_alloc_inode(inode); if (err) goto fail_drop; @@ -952,24 +971,17 @@ got: ext4_debug("allocating inode %lu\n", inode->i_ino); trace_ext4_allocate_inode(inode, dir, mode); - goto really_out; -fail: - ext4_std_error(sb, err); -out: - iput(inode); - ret = ERR_PTR(err); -really_out: brelse(inode_bitmap_bh); return ret; fail_free_drop: dquot_free_inode(inode); - fail_drop: - dquot_drop(inode); - inode->i_flags |= S_NOQUOTA; clear_nlink(inode); unlock_new_inode(inode); +out: + dquot_drop(inode); + inode->i_flags |= S_NOQUOTA; iput(inode); brelse(inode_bitmap_bh); return ERR_PTR(err); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index a04183127ef0..98be6f697463 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -291,131 +291,6 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, return count; } -/** - * ext4_alloc_blocks: multiple allocate blocks needed for a branch - * @handle: handle for this transaction - * @inode: inode which needs allocated blocks - * @iblock: the logical block to start allocated at - * @goal: preferred physical block of allocation - * @indirect_blks: the number of blocks need to allocate for indirect - * blocks - * @blks: number of desired blocks - * @new_blocks: on return it will store the new block numbers for - * the indirect blocks(if needed) and the first direct block, - * @err: on return it will store the error code - * - * This function will return the number of blocks allocated as - * requested by the passed-in parameters. - */ -static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, - ext4_lblk_t iblock, ext4_fsblk_t goal, - int indirect_blks, int blks, - ext4_fsblk_t new_blocks[4], int *err) -{ - struct ext4_allocation_request ar; - int target, i; - unsigned long count = 0, blk_allocated = 0; - int index = 0; - ext4_fsblk_t current_block = 0; - int ret = 0; - - /* - * Here we try to allocate the requested multiple blocks at once, - * on a best-effort basis. - * To build a branch, we should allocate blocks for - * the indirect blocks(if not allocated yet), and at least - * the first direct block of this branch. That's the - * minimum number of blocks need to allocate(required) - */ - /* first we try to allocate the indirect blocks */ - target = indirect_blks; - while (target > 0) { - count = target; - /* allocating blocks for indirect blocks and direct blocks */ - current_block = ext4_new_meta_blocks(handle, inode, goal, - 0, &count, err); - if (*err) - goto failed_out; - - if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) { - EXT4_ERROR_INODE(inode, - "current_block %llu + count %lu > %d!", - current_block, count, - EXT4_MAX_BLOCK_FILE_PHYS); - *err = -EIO; - goto failed_out; - } - - target -= count; - /* allocate blocks for indirect blocks */ - while (index < indirect_blks && count) { - new_blocks[index++] = current_block++; - count--; - } - if (count > 0) { - /* - * save the new block number - * for the first direct block - */ - new_blocks[index] = current_block; - WARN(1, KERN_INFO "%s returned more blocks than " - "requested\n", __func__); - break; - } - } - - target = blks - count ; - blk_allocated = count; - if (!target) - goto allocated; - /* Now allocate data blocks */ - memset(&ar, 0, sizeof(ar)); - ar.inode = inode; - ar.goal = goal; - ar.len = target; - ar.logical = iblock; - if (S_ISREG(inode->i_mode)) - /* enable in-core preallocation only for regular files */ - ar.flags = EXT4_MB_HINT_DATA; - - current_block = ext4_mb_new_blocks(handle, &ar, err); - if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) { - EXT4_ERROR_INODE(inode, - "current_block %llu + ar.len %d > %d!", - current_block, ar.len, - EXT4_MAX_BLOCK_FILE_PHYS); - *err = -EIO; - goto failed_out; - } - - if (*err && (target == blks)) { - /* - * if the allocation failed and we didn't allocate - * any blocks before - */ - goto failed_out; - } - if (!*err) { - if (target == blks) { - /* - * save the new block number - * for the first direct block - */ - new_blocks[index] = current_block; - } - blk_allocated += ar.len; - } -allocated: - /* total number of blocks allocated for direct blocks */ - ret = blk_allocated; - *err = 0; - return ret; -failed_out: - for (i = 0; i < index; i++) - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); - return ret; -} - /** * ext4_alloc_branch - allocate and set up a chain of blocks. * @handle: handle for this transaction @@ -448,60 +323,59 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, int *blks, ext4_fsblk_t goal, ext4_lblk_t *offsets, Indirect *branch) { - int blocksize = inode->i_sb->s_blocksize; - int i, n = 0; - int err = 0; - struct buffer_head *bh; - int num; - ext4_fsblk_t new_blocks[4]; - ext4_fsblk_t current_block; + struct ext4_allocation_request ar; + struct buffer_head * bh; + ext4_fsblk_t b, new_blocks[4]; + __le32 *p; + int i, j, err, len = 1; - num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks, - *blks, new_blocks, &err); - if (err) - return err; - - branch[0].key = cpu_to_le32(new_blocks[0]); /* - * metadata blocks and data blocks are allocated. + * Set up for the direct block allocation */ - for (n = 1; n <= indirect_blks; n++) { - /* - * Get buffer_head for parent block, zero it out - * and set the pointer to new one, then send - * parent to disk. - */ - bh = sb_getblk(inode->i_sb, new_blocks[n-1]); + memset(&ar, 0, sizeof(ar)); + ar.inode = inode; + ar.len = *blks; + ar.logical = iblock; + if (S_ISREG(inode->i_mode)) + ar.flags = EXT4_MB_HINT_DATA; + + for (i = 0; i <= indirect_blks; i++) { + if (i == indirect_blks) { + ar.goal = goal; + new_blocks[i] = ext4_mb_new_blocks(handle, &ar, &err); + } else + goal = new_blocks[i] = ext4_new_meta_blocks(handle, inode, + goal, 0, NULL, &err); + if (err) { + i--; + goto failed; + } + branch[i].key = cpu_to_le32(new_blocks[i]); + if (i == 0) + continue; + + bh = branch[i].bh = sb_getblk(inode->i_sb, new_blocks[i-1]); if (unlikely(!bh)) { err = -ENOMEM; goto failed; } - - branch[n].bh = bh; lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); err = ext4_journal_get_create_access(handle, bh); if (err) { - /* Don't brelse(bh) here; it's done in - * ext4_journal_forget() below */ unlock_buffer(bh); goto failed; } - memset(bh->b_data, 0, blocksize); - branch[n].p = (__le32 *) bh->b_data + offsets[n]; - branch[n].key = cpu_to_le32(new_blocks[n]); - *branch[n].p = branch[n].key; - if (n == indirect_blks) { - current_block = new_blocks[n]; - /* - * End of chain, update the last new metablock of - * the chain to point to the new allocated - * data blocks numbers - */ - for (i = 1; i < num; i++) - *(branch[n].p + i) = cpu_to_le32(++current_block); - } + memset(bh->b_data, 0, bh->b_size); + p = branch[i].p = (__le32 *) bh->b_data + offsets[i]; + b = new_blocks[i]; + + if (i == indirect_blks) + len = ar.len; + for (j = 0; j < len; j++) + *p++ = cpu_to_le32(b++); + BUFFER_TRACE(bh, "marking uptodate"); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -511,25 +385,16 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, if (err) goto failed; } - *blks = num; - return err; + *blks = ar.len; + return 0; failed: - /* Allocation failed, free what we already allocated */ - ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0); - for (i = 1; i <= n ; i++) { - /* - * branch[i].bh is newly allocated, so there is no - * need to revoke the block, which is why we don't - * need to set EXT4_FREE_BLOCKS_METADATA. - */ - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, - EXT4_FREE_BLOCKS_FORGET); + for (; i >= 0; i--) { + if (i != indirect_blks && branch[i].bh) + ext4_forget(handle, 1, inode, branch[i].bh, + branch[i].bh->b_blocknr); + ext4_free_blocks(handle, inode, NULL, new_blocks[i], + (i == indirect_blks) ? ar.len : 1, 0); } - for (i = n+1; i < indirect_blks; i++) - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); - - ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0); - return err; } @@ -941,26 +806,9 @@ int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk) * be able to restart the transaction at a conventient checkpoint to make * sure we don't overflow the journal. * - * start_transaction gets us a new handle for a truncate transaction, - * and extend_transaction tries to extend the existing one a bit. If + * Try to extend this transaction for the purposes of truncation. If * extend fails, we need to propagate the failure up and restart the * transaction in the top-level truncate loop. --sct - */ -static handle_t *start_transaction(struct inode *inode) -{ - handle_t *result; - - result = ext4_journal_start(inode, EXT4_HT_TRUNCATE, - ext4_blocks_for_truncate(inode)); - if (!IS_ERR(result)) - return result; - - ext4_std_error(inode->i_sb, PTR_ERR(result)); - return result; -} - -/* - * Try to extend this transaction for the purposes of truncation. * * Returns 0 if we managed to create more room. If we can't create more * room, and the transaction must be restarted we return 1. @@ -1353,68 +1201,30 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, } } -void ext4_ind_truncate(struct inode *inode) +void ext4_ind_truncate(handle_t *handle, struct inode *inode) { - handle_t *handle; struct ext4_inode_info *ei = EXT4_I(inode); __le32 *i_data = ei->i_data; int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); - struct address_space *mapping = inode->i_mapping; ext4_lblk_t offsets[4]; Indirect chain[4]; Indirect *partial; __le32 nr = 0; int n = 0; ext4_lblk_t last_block, max_block; - loff_t page_len; unsigned blocksize = inode->i_sb->s_blocksize; - int err; - - handle = start_transaction(inode); - if (IS_ERR(handle)) - return; /* AKPM: return what? */ last_block = (inode->i_size + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); - if (inode->i_size % PAGE_CACHE_SIZE != 0) { - page_len = PAGE_CACHE_SIZE - - (inode->i_size & (PAGE_CACHE_SIZE - 1)); - - err = ext4_discard_partial_page_buffers(handle, - mapping, inode->i_size, page_len, 0); - - if (err) - goto out_stop; - } - if (last_block != max_block) { n = ext4_block_to_path(inode, last_block, offsets, NULL); if (n == 0) - goto out_stop; /* error */ + return; } - /* - * OK. This truncate is going to happen. We add the inode to the - * orphan list, so that if this truncate spans multiple transactions, - * and we crash, we will resume the truncate when the filesystem - * recovers. It also marks the inode dirty, to catch the new size. - * - * Implication: the file must always be in a sane, consistent - * truncatable state while each transaction commits. - */ - if (ext4_orphan_add(handle, inode)) - goto out_stop; - - /* - * From here we block out all ext4_get_block() callers who want to - * modify the block allocation tree. - */ - down_write(&ei->i_data_sem); - - ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); /* @@ -1431,7 +1241,7 @@ void ext4_ind_truncate(struct inode *inode) * It is unnecessary to free any data blocks if last_block is * equal to the indirect block limit. */ - goto out_unlock; + return; } else if (n == 1) { /* direct blocks */ ext4_free_data(handle, inode, NULL, i_data+offsets[0], i_data + EXT4_NDIR_BLOCKS); @@ -1491,31 +1301,6 @@ do_indirects: case EXT4_TIND_BLOCK: ; } - -out_unlock: - up_write(&ei->i_data_sem); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - - /* - * In a multi-transaction truncate, we only make the final transaction - * synchronous - */ - if (IS_SYNC(inode)) - ext4_handle_sync(handle); -out_stop: - /* - * If this was a simple ftruncate(), and the file will remain alive - * then we need to clear up the orphan record which we created above. - * However, if this was a real unlink then we were called by - * ext4_delete_inode(), and we allow that function to clean up the - * orphan info for us. - */ - if (inode->i_nlink) - ext4_orphan_del(handle, inode); - - ext4_journal_stop(handle); - trace_ext4_truncate_exit(inode); } static int free_hole_blocks(handle_t *handle, struct inode *inode, @@ -1569,8 +1354,8 @@ err: return ret; } -static int ext4_free_hole_blocks(handle_t *handle, struct inode *inode, - ext4_lblk_t first, ext4_lblk_t stop) +int ext4_free_hole_blocks(handle_t *handle, struct inode *inode, + ext4_lblk_t first, ext4_lblk_t stop) { int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); int level, ret = 0; @@ -1604,157 +1389,3 @@ err: return ret; } -int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length) -{ - struct inode *inode = file_inode(file); - struct super_block *sb = inode->i_sb; - ext4_lblk_t first_block, stop_block; - struct address_space *mapping = inode->i_mapping; - handle_t *handle = NULL; - loff_t first_page, last_page, page_len; - loff_t first_page_offset, last_page_offset; - int err = 0; - - /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - err = filemap_write_and_wait_range(mapping, - offset, offset + length - 1); - if (err) - return err; - } - - mutex_lock(&inode->i_mutex); - /* It's not possible punch hole on append only file */ - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { - err = -EPERM; - goto out_mutex; - } - if (IS_SWAPFILE(inode)) { - err = -ETXTBSY; - goto out_mutex; - } - - /* No need to punch hole beyond i_size */ - if (offset >= inode->i_size) - goto out_mutex; - - /* - * If the hole extents beyond i_size, set the hole - * to end after the page that contains i_size - */ - if (offset + length > inode->i_size) { - length = inode->i_size + - PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) - - offset; - } - - first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - last_page = (offset + length) >> PAGE_CACHE_SHIFT; - - first_page_offset = first_page << PAGE_CACHE_SHIFT; - last_page_offset = last_page << PAGE_CACHE_SHIFT; - - /* Now release the pages */ - if (last_page_offset > first_page_offset) { - truncate_pagecache_range(inode, first_page_offset, - last_page_offset - 1); - } - - /* Wait all existing dio works, newcomers will block on i_mutex */ - inode_dio_wait(inode); - - handle = start_transaction(inode); - if (IS_ERR(handle)) - goto out_mutex; - - /* - * Now we need to zero out the non-page-aligned data in the - * pages at the start and tail of the hole, and unmap the buffer - * heads for the block aligned regions of the page that were - * completely zerod. - */ - if (first_page > last_page) { - /* - * If the file space being truncated is contained within a page - * just zero out and unmap the middle of that page - */ - err = ext4_discard_partial_page_buffers(handle, - mapping, offset, length, 0); - if (err) - goto out; - } else { - /* - * Zero out and unmap the paritial page that contains - * the start of the hole - */ - page_len = first_page_offset - offset; - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, mapping, - offset, page_len, 0); - if (err) - goto out; - } - - /* - * Zero out and unmap the partial page that contains - * the end of the hole - */ - page_len = offset + length - last_page_offset; - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, mapping, - last_page_offset, page_len, 0); - if (err) - goto out; - } - } - - /* - * If i_size contained in the last page, we need to - * unmap and zero the paritial page after i_size - */ - if (inode->i_size >> PAGE_CACHE_SHIFT == last_page && - inode->i_size % PAGE_CACHE_SIZE != 0) { - page_len = PAGE_CACHE_SIZE - - (inode->i_size & (PAGE_CACHE_SIZE - 1)); - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, - mapping, inode->i_size, page_len, 0); - if (err) - goto out; - } - } - - first_block = (offset + sb->s_blocksize - 1) >> - EXT4_BLOCK_SIZE_BITS(sb); - stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); - - if (first_block >= stop_block) - goto out; - - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); - - err = ext4_es_remove_extent(inode, first_block, - stop_block - first_block); - err = ext4_free_hole_blocks(handle, inode, first_block, stop_block); - - ext4_discard_preallocations(inode); - - if (IS_SYNC(inode)) - ext4_handle_sync(handle); - - up_write(&EXT4_I(inode)->i_data_sem); - -out: - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - ext4_journal_stop(handle); - -out_mutex: - mutex_unlock(&inode->i_mutex); - - return err; -} diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index c0fd1a123f7d..3e2bf873e8a8 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -19,7 +19,8 @@ #define EXT4_XATTR_SYSTEM_DATA "data" #define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS)) -#define EXT4_INLINE_DOTDOT_SIZE 4 +#define EXT4_INLINE_DOTDOT_OFFSET 2 +#define EXT4_INLINE_DOTDOT_SIZE 4 int ext4_get_inline_size(struct inode *inode) { @@ -1289,6 +1290,120 @@ out: return ret; } +/* + * This function fills a red-black tree with information from an + * inlined dir. It returns the number directory entries loaded + * into the tree. If there is an error it is returned in err. + */ +int htree_inlinedir_to_tree(struct file *dir_file, + struct inode *dir, ext4_lblk_t block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash, + int *has_inline_data) +{ + int err = 0, count = 0; + unsigned int parent_ino; + int pos; + struct ext4_dir_entry_2 *de; + struct inode *inode = file_inode(dir_file); + int ret, inline_size = 0; + struct ext4_iloc iloc; + void *dir_buf = NULL; + struct ext4_dir_entry_2 fake; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ret; + + down_read(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + up_read(&EXT4_I(inode)->xattr_sem); + *has_inline_data = 0; + goto out; + } + + inline_size = ext4_get_inline_size(inode); + dir_buf = kmalloc(inline_size, GFP_NOFS); + if (!dir_buf) { + ret = -ENOMEM; + up_read(&EXT4_I(inode)->xattr_sem); + goto out; + } + + ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); + up_read(&EXT4_I(inode)->xattr_sem); + if (ret < 0) + goto out; + + pos = 0; + parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); + while (pos < inline_size) { + /* + * As inlined dir doesn't store any information about '.' and + * only the inode number of '..' is stored, we have to handle + * them differently. + */ + if (pos == 0) { + fake.inode = cpu_to_le32(inode->i_ino); + fake.name_len = 1; + strcpy(fake.name, "."); + fake.rec_len = ext4_rec_len_to_disk( + EXT4_DIR_REC_LEN(fake.name_len), + inline_size); + ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); + de = &fake; + pos = EXT4_INLINE_DOTDOT_OFFSET; + } else if (pos == EXT4_INLINE_DOTDOT_OFFSET) { + fake.inode = cpu_to_le32(parent_ino); + fake.name_len = 2; + strcpy(fake.name, ".."); + fake.rec_len = ext4_rec_len_to_disk( + EXT4_DIR_REC_LEN(fake.name_len), + inline_size); + ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); + de = &fake; + pos = EXT4_INLINE_DOTDOT_SIZE; + } else { + de = (struct ext4_dir_entry_2 *)(dir_buf + pos); + pos += ext4_rec_len_from_disk(de->rec_len, inline_size); + if (ext4_check_dir_entry(inode, dir_file, de, + iloc.bh, dir_buf, + inline_size, pos)) { + ret = count; + goto out; + } + } + + ext4fs_dirhash(de->name, de->name_len, hinfo); + if ((hinfo->hash < start_hash) || + ((hinfo->hash == start_hash) && + (hinfo->minor_hash < start_minor_hash))) + continue; + if (de->inode == 0) + continue; + err = ext4_htree_store_dirent(dir_file, + hinfo->hash, hinfo->minor_hash, de); + if (err) { + count = err; + goto out; + } + count++; + } + ret = count; +out: + kfree(dir_buf); + brelse(iloc.bh); + return ret; +} + +/* + * So this function is called when the volume is mkfsed with + * dir_index disabled. In order to keep f_pos persistent + * after we convert from an inlined dir to a blocked based, + * we just pretend that we are a normal dir and return the + * offset as if '.' and '..' really take place. + * + */ int ext4_read_inline_dir(struct file *filp, void *dirent, filldir_t filldir, int *has_inline_data) @@ -1302,6 +1417,7 @@ int ext4_read_inline_dir(struct file *filp, int ret, inline_size = 0; struct ext4_iloc iloc; void *dir_buf = NULL; + int dotdot_offset, dotdot_size, extra_offset, extra_size; ret = ext4_get_inode_loc(inode, &iloc); if (ret) @@ -1330,8 +1446,21 @@ int ext4_read_inline_dir(struct file *filp, sb = inode->i_sb; stored = 0; parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); + offset = filp->f_pos; - while (!error && !stored && filp->f_pos < inode->i_size) { + /* + * dotdot_offset and dotdot_size is the real offset and + * size for ".." and "." if the dir is block based while + * the real size for them are only EXT4_INLINE_DOTDOT_SIZE. + * So we will use extra_offset and extra_size to indicate them + * during the inline dir iteration. + */ + dotdot_offset = EXT4_DIR_REC_LEN(1); + dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2); + extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE; + extra_size = extra_offset + inline_size; + + while (!error && !stored && filp->f_pos < extra_size) { revalidate: /* * If the version has changed since the last call to @@ -1340,15 +1469,23 @@ revalidate: * dir to make sure. */ if (filp->f_version != inode->i_version) { - for (i = 0; - i < inode->i_size && i < offset;) { + for (i = 0; i < extra_size && i < offset;) { + /* + * "." is with offset 0 and + * ".." is dotdot_offset. + */ if (!i) { - /* skip "." and ".." if needed. */ - i += EXT4_INLINE_DOTDOT_SIZE; + i = dotdot_offset; + continue; + } else if (i == dotdot_offset) { + i = dotdot_size; continue; } + /* for other entry, the real offset in + * the buf has to be tuned accordingly. + */ de = (struct ext4_dir_entry_2 *) - (dir_buf + i); + (dir_buf + i - extra_offset); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at @@ -1356,43 +1493,47 @@ revalidate: * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, - inline_size) < EXT4_DIR_REC_LEN(1)) + extra_size) < EXT4_DIR_REC_LEN(1)) break; i += ext4_rec_len_from_disk(de->rec_len, - inline_size); + extra_size); } offset = i; filp->f_pos = offset; filp->f_version = inode->i_version; } - while (!error && filp->f_pos < inode->i_size) { + while (!error && filp->f_pos < extra_size) { if (filp->f_pos == 0) { error = filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR); if (error) break; stored++; + filp->f_pos = dotdot_offset; + continue; + } - error = filldir(dirent, "..", 2, 0, parent_ino, - DT_DIR); + if (filp->f_pos == dotdot_offset) { + error = filldir(dirent, "..", 2, + dotdot_offset, + parent_ino, DT_DIR); if (error) break; stored++; - filp->f_pos = offset = EXT4_INLINE_DOTDOT_SIZE; + filp->f_pos = dotdot_size; continue; } - de = (struct ext4_dir_entry_2 *)(dir_buf + offset); + de = (struct ext4_dir_entry_2 *) + (dir_buf + filp->f_pos - extra_offset); if (ext4_check_dir_entry(inode, filp, de, iloc.bh, dir_buf, - inline_size, offset)) { + extra_size, filp->f_pos)) { ret = stored; goto out; } - offset += ext4_rec_len_from_disk(de->rec_len, - inline_size); if (le32_to_cpu(de->inode)) { /* We might block in the next section * if the data destination is @@ -1415,9 +1556,8 @@ revalidate: stored++; } filp->f_pos += ext4_rec_len_from_disk(de->rec_len, - inline_size); + extra_size); } - offset = 0; } out: kfree(dir_buf); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b3a5213bc73e..793d44b84d7f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -55,21 +55,21 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, __u16 csum_hi = 0; __u32 csum; - csum_lo = raw->i_checksum_lo; + csum_lo = le16_to_cpu(raw->i_checksum_lo); raw->i_checksum_lo = 0; if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) { - csum_hi = raw->i_checksum_hi; + csum_hi = le16_to_cpu(raw->i_checksum_hi); raw->i_checksum_hi = 0; } csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, EXT4_INODE_SIZE(inode->i_sb)); - raw->i_checksum_lo = csum_lo; + raw->i_checksum_lo = cpu_to_le16(csum_lo); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) - raw->i_checksum_hi = csum_hi; + raw->i_checksum_hi = cpu_to_le16(csum_hi); return csum; } @@ -210,8 +210,7 @@ void ext4_evict_inode(struct inode *inode) journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; - jbd2_log_start_commit(journal, commit_tid); - jbd2_log_wait_commit(journal, commit_tid); + jbd2_complete_transaction(journal, commit_tid); filemap_write_and_wait(&inode->i_data); } truncate_inode_pages(&inode->i_data, 0); @@ -1081,20 +1080,42 @@ retry_journal: /* For write_end() in data=journal mode */ static int write_end_fn(handle_t *handle, struct buffer_head *bh) { + int ret; if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; set_buffer_uptodate(bh); - return ext4_handle_dirty_metadata(handle, NULL, bh); + ret = ext4_handle_dirty_metadata(handle, NULL, bh); + clear_buffer_meta(bh); + clear_buffer_prio(bh); + return ret; } -static int ext4_generic_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) +/* + * We need to pick up the new inode size which generic_commit_write gave us + * `file' can be NULL - eg, when called from page_symlink(). + * + * ext4 never places buffers on inode->i_mapping->private_list. metadata + * buffers are managed internally. + */ +static int ext4_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { - int i_size_changed = 0; - struct inode *inode = mapping->host; handle_t *handle = ext4_journal_current_handle(); + struct inode *inode = mapping->host; + int ret = 0, ret2; + int i_size_changed = 0; + + trace_ext4_write_end(inode, pos, len, copied); + if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) { + ret = ext4_jbd2_file_inode(handle, inode); + if (ret) { + unlock_page(page); + page_cache_release(page); + goto errout; + } + } if (ext4_has_inline_data(inode)) copied = ext4_write_inline_data_end(inode, pos, len, @@ -1105,7 +1126,7 @@ static int ext4_generic_write_end(struct file *file, /* * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_mutex. + * cannot change under us because we hole i_mutex. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. @@ -1115,10 +1136,10 @@ static int ext4_generic_write_end(struct file *file, i_size_changed = 1; } - if (pos + copied > EXT4_I(inode)->i_disksize) { + if (pos + copied > EXT4_I(inode)->i_disksize) { /* We need to mark inode dirty even if * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) + * but greater than i_disksize. (hint delalloc) */ ext4_update_i_disksize(inode, (pos + copied)); i_size_changed = 1; @@ -1135,87 +1156,15 @@ static int ext4_generic_write_end(struct file *file, if (i_size_changed) ext4_mark_inode_dirty(handle, inode); - return copied; -} - -/* - * We need to pick up the new inode size which generic_commit_write gave us - * `file' can be NULL - eg, when called from page_symlink(). - * - * ext4 never places buffers on inode->i_mapping->private_list. metadata - * buffers are managed internally. - */ -static int ext4_ordered_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - handle_t *handle = ext4_journal_current_handle(); - struct inode *inode = mapping->host; - int ret = 0, ret2; - - trace_ext4_ordered_write_end(inode, pos, len, copied); - ret = ext4_jbd2_file_inode(handle, inode); - - if (ret == 0) { - ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - copied = ret2; - if (pos + len > inode->i_size && ext4_can_truncate(inode)) - /* if we have allocated more blocks and copied - * less. We will have blocks allocated outside - * inode->i_size. So truncate them - */ - ext4_orphan_add(handle, inode); - if (ret2 < 0) - ret = ret2; - } else { - unlock_page(page); - page_cache_release(page); - } - - ret2 = ext4_journal_stop(handle); - if (!ret) - ret = ret2; - - if (pos + len > inode->i_size) { - ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might still be - * on the orphan list; we need to make sure the inode - * is removed from the orphan list in that case. - */ - if (inode->i_nlink) - ext4_orphan_del(NULL, inode); - } - - - return ret ? ret : copied; -} - -static int ext4_writeback_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - handle_t *handle = ext4_journal_current_handle(); - struct inode *inode = mapping->host; - int ret = 0, ret2; - - trace_ext4_writeback_write_end(inode, pos, len, copied); - ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - copied = ret2; + if (copied < 0) + ret = copied; if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); - - if (ret2 < 0) - ret = ret2; - +errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; @@ -1538,7 +1487,10 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, struct ext4_io_submit io_submit; BUG_ON(mpd->next_page <= mpd->first_page); - memset(&io_submit, 0, sizeof(io_submit)); + ext4_io_submit_init(&io_submit, mpd->wbc); + io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_submit.io_end) + return -ENOMEM; /* * We need to start from the first_page to the next_page - 1 * to make sure we also write the mapped dirty buffer_heads. @@ -1626,6 +1578,8 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, pagevec_release(&pvec); } ext4_io_submit(&io_submit); + /* Drop io_end reference we got from init */ + ext4_put_io_end_defer(io_submit.io_end); return ret; } @@ -1670,22 +1624,25 @@ static void ext4_print_free_blocks(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct super_block *sb = inode->i_sb; + struct ext4_inode_info *ei = EXT4_I(inode); ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld", EXT4_C2B(EXT4_SB(inode->i_sb), - ext4_count_free_clusters(inode->i_sb))); + ext4_count_free_clusters(sb))); ext4_msg(sb, KERN_CRIT, "Free/Dirty block details"); ext4_msg(sb, KERN_CRIT, "free_blocks=%lld", - (long long) EXT4_C2B(EXT4_SB(inode->i_sb), + (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_freeclusters_counter))); ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld", - (long long) EXT4_C2B(EXT4_SB(inode->i_sb), + (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_dirtyclusters_counter))); ext4_msg(sb, KERN_CRIT, "Block reservation details"); ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u", - EXT4_I(inode)->i_reserved_data_blocks); + ei->i_reserved_data_blocks); ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u", - EXT4_I(inode)->i_reserved_meta_blocks); + ei->i_reserved_meta_blocks); + ext4_msg(sb, KERN_CRIT, "i_allocated_meta_blocks=%u", + ei->i_allocated_meta_blocks); return; } @@ -1740,12 +1697,21 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) */ map.m_lblk = next; map.m_len = max_blocks; - get_blocks_flags = EXT4_GET_BLOCKS_CREATE; + /* + * We're in delalloc path and it is possible that we're going to + * need more metadata blocks than previously reserved. However + * we must not fail because we're in writeback and there is + * nothing we can do about it so it might result in data loss. + * So use reserved blocks to allocate metadata if possible. + */ + get_blocks_flags = EXT4_GET_BLOCKS_CREATE | + EXT4_GET_BLOCKS_METADATA_NOFAIL; if (ext4_should_dioread_nolock(mpd->inode)) get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; if (mpd->b_state & (1 << BH_Delay)) get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; + blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags); if (blks < 0) { struct super_block *sb = mpd->inode->i_sb; @@ -2272,9 +2238,16 @@ static int ext4_writepage(struct page *page, */ return __ext4_journalled_writepage(page, len); - memset(&io_submit, 0, sizeof(io_submit)); + ext4_io_submit_init(&io_submit, wbc); + io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_submit.io_end) { + redirty_page_for_writepage(wbc, page); + return -ENOMEM; + } ret = ext4_bio_write_page(&io_submit, page, len, wbc); ext4_io_submit(&io_submit); + /* Drop io_end reference we got from init */ + ext4_put_io_end_defer(io_submit.io_end); return ret; } @@ -2661,7 +2634,7 @@ out_writepages: static int ext4_nonda_switch(struct super_block *sb) { - s64 free_blocks, dirty_blocks; + s64 free_clusters, dirty_clusters; struct ext4_sb_info *sbi = EXT4_SB(sb); /* @@ -2672,17 +2645,18 @@ static int ext4_nonda_switch(struct super_block *sb) * Delalloc need an accurate free block accounting. So switch * to non delalloc when we are near to error range. */ - free_blocks = EXT4_C2B(sbi, - percpu_counter_read_positive(&sbi->s_freeclusters_counter)); - dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); + free_clusters = + percpu_counter_read_positive(&sbi->s_freeclusters_counter); + dirty_clusters = + percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); /* * Start pushing delalloc when 1/2 of free blocks are dirty. */ - if (dirty_blocks && (free_blocks < 2 * dirty_blocks)) + if (dirty_clusters && (free_clusters < 2 * dirty_clusters)) try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE); - if (2 * free_blocks < 3 * dirty_blocks || - free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) { + if (2 * free_clusters < 3 * dirty_clusters || + free_clusters < (dirty_clusters + EXT4_FREECLUSTERS_WATERMARK)) { /* * free block count is less than 150% of dirty blocks * or free blocks is less than watermark @@ -2818,18 +2792,9 @@ static int ext4_da_write_end(struct file *file, unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; - if (write_mode == FALL_BACK_TO_NONDELALLOC) { - switch (ext4_inode_journal_mode(inode)) { - case EXT4_INODE_ORDERED_DATA_MODE: - return ext4_ordered_write_end(file, mapping, pos, - len, copied, page, fsdata); - case EXT4_INODE_WRITEBACK_DATA_MODE: - return ext4_writeback_write_end(file, mapping, pos, - len, copied, page, fsdata); - default: - BUG(); - } - } + if (write_mode == FALL_BACK_TO_NONDELALLOC) + return ext4_write_end(file, mapping, pos, + len, copied, page, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); start = pos & (PAGE_CACHE_SIZE - 1); @@ -3113,9 +3078,13 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, struct inode *inode = file_inode(iocb->ki_filp); ext4_io_end_t *io_end = iocb->private; - /* if not async direct IO or dio with 0 bytes write, just return */ - if (!io_end || !size) - goto out; + /* if not async direct IO just return */ + if (!io_end) { + inode_dio_done(inode); + if (is_async) + aio_complete(iocb, ret, 0); + return; + } ext_debug("ext4_end_io_dio(): io_end 0x%p " "for inode %lu, iocb 0x%p, offset %llu, size %zd\n", @@ -3123,25 +3092,13 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, size); iocb->private = NULL; - - /* if not aio dio with unwritten extents, just free io and return */ - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - ext4_free_io_end(io_end); -out: - inode_dio_done(inode); - if (is_async) - aio_complete(iocb, ret, 0); - return; - } - io_end->offset = offset; io_end->size = size; if (is_async) { io_end->iocb = iocb; io_end->result = ret; } - - ext4_add_complete_io(io_end); + ext4_put_io_end_defer(io_end); } /* @@ -3175,6 +3132,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, get_block_t *get_block_func = NULL; int dio_flags = 0; loff_t final_size = offset + count; + ext4_io_end_t *io_end = NULL; /* Use the old path for reads and writes beyond i_size. */ if (rw != WRITE || final_size > inode->i_size) @@ -3213,13 +3171,16 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, iocb->private = NULL; ext4_inode_aio_set(inode, NULL); if (!is_sync_kiocb(iocb)) { - ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS); + io_end = ext4_init_io_end(inode, GFP_NOFS); if (!io_end) { ret = -ENOMEM; goto retake_lock; } io_end->flag |= EXT4_IO_END_DIRECT; - iocb->private = io_end; + /* + * Grab reference for DIO. Will be dropped in ext4_end_io_dio() + */ + iocb->private = ext4_get_io_end(io_end); /* * we save the io structure for current async direct * IO, so that later ext4_map_blocks() could flag the @@ -3243,26 +3204,27 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, NULL, dio_flags); - if (iocb->private) - ext4_inode_aio_set(inode, NULL); /* - * The io_end structure takes a reference to the inode, that - * structure needs to be destroyed and the reference to the - * inode need to be dropped, when IO is complete, even with 0 - * byte write, or failed. - * - * In the successful AIO DIO case, the io_end structure will - * be destroyed and the reference to the inode will be dropped - * after the end_io call back function is called. - * - * In the case there is 0 byte write, or error case, since VFS - * direct IO won't invoke the end_io call back function, we - * need to free the end_io structure here. + * Put our reference to io_end. This can free the io_end structure e.g. + * in sync IO case or in case of error. It can even perform extent + * conversion if all bios we submitted finished before we got here. + * Note that in that case iocb->private can be already set to NULL + * here. */ - if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) { - ext4_free_io_end(iocb->private); - iocb->private = NULL; - } else if (ret > 0 && !overwrite && ext4_test_inode_state(inode, + if (io_end) { + ext4_inode_aio_set(inode, NULL); + ext4_put_io_end(io_end); + /* + * In case of error or no write ext4_end_io_dio() was not + * called so we have to put iocb's reference. + */ + if (ret <= 0 && ret != -EIOCBQUEUED) { + WARN_ON(iocb->private != io_end); + ext4_put_io_end(io_end); + iocb->private = NULL; + } + } + if (ret > 0 && !overwrite && ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN)) { int err; /* @@ -3334,27 +3296,12 @@ static int ext4_journalled_set_page_dirty(struct page *page) return __set_page_dirty_nobuffers(page); } -static const struct address_space_operations ext4_ordered_aops = { +static const struct address_space_operations ext4_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, .write_begin = ext4_write_begin, - .write_end = ext4_ordered_write_end, - .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, - .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, -}; - -static const struct address_space_operations ext4_writeback_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_writepage, - .write_begin = ext4_write_begin, - .write_end = ext4_writeback_write_end, + .write_end = ext4_write_end, .bmap = ext4_bmap, .invalidatepage = ext4_invalidatepage, .releasepage = ext4_releasepage, @@ -3399,23 +3346,21 @@ void ext4_set_aops(struct inode *inode) { switch (ext4_inode_journal_mode(inode)) { case EXT4_INODE_ORDERED_DATA_MODE: - if (test_opt(inode->i_sb, DELALLOC)) - inode->i_mapping->a_ops = &ext4_da_aops; - else - inode->i_mapping->a_ops = &ext4_ordered_aops; + ext4_set_inode_state(inode, EXT4_STATE_ORDERED_MODE); break; case EXT4_INODE_WRITEBACK_DATA_MODE: - if (test_opt(inode->i_sb, DELALLOC)) - inode->i_mapping->a_ops = &ext4_da_aops; - else - inode->i_mapping->a_ops = &ext4_writeback_aops; + ext4_clear_inode_state(inode, EXT4_STATE_ORDERED_MODE); break; case EXT4_INODE_JOURNAL_DATA_MODE: inode->i_mapping->a_ops = &ext4_journalled_aops; - break; + return; default: BUG(); } + if (test_opt(inode->i_sb, DELALLOC)) + inode->i_mapping->a_ops = &ext4_da_aops; + else + inode->i_mapping->a_ops = &ext4_aops; } @@ -3646,20 +3591,190 @@ int ext4_can_truncate(struct inode *inode) int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { struct inode *inode = file_inode(file); + struct super_block *sb = inode->i_sb; + ext4_lblk_t first_block, stop_block; + struct address_space *mapping = inode->i_mapping; + loff_t first_page, last_page, page_len; + loff_t first_page_offset, last_page_offset; + handle_t *handle; + unsigned int credits; + int ret = 0; + if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; - if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - return ext4_ind_punch_hole(file, offset, length); - - if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) { + if (EXT4_SB(sb)->s_cluster_ratio > 1) { /* TODO: Add support for bigalloc file systems */ return -EOPNOTSUPP; } trace_ext4_punch_hole(inode, offset, length); - return ext4_ext_punch_hole(file, offset, length); + /* + * Write out all dirty pages to avoid race conditions + * Then release them. + */ + if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { + ret = filemap_write_and_wait_range(mapping, offset, + offset + length - 1); + if (ret) + return ret; + } + + mutex_lock(&inode->i_mutex); + /* It's not possible punch hole on append only file */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { + ret = -EPERM; + goto out_mutex; + } + if (IS_SWAPFILE(inode)) { + ret = -ETXTBSY; + goto out_mutex; + } + + /* No need to punch hole beyond i_size */ + if (offset >= inode->i_size) + goto out_mutex; + + /* + * If the hole extends beyond i_size, set the hole + * to end after the page that contains i_size + */ + if (offset + length > inode->i_size) { + length = inode->i_size + + PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) - + offset; + } + + first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + last_page = (offset + length) >> PAGE_CACHE_SHIFT; + + first_page_offset = first_page << PAGE_CACHE_SHIFT; + last_page_offset = last_page << PAGE_CACHE_SHIFT; + + /* Now release the pages */ + if (last_page_offset > first_page_offset) { + truncate_pagecache_range(inode, first_page_offset, + last_page_offset - 1); + } + + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + ret = ext4_flush_unwritten_io(inode); + if (ret) + goto out_dio; + inode_dio_wait(inode); + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + credits = ext4_writepage_trans_blocks(inode); + else + credits = ext4_blocks_for_truncate(inode); + handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + ext4_std_error(sb, ret); + goto out_dio; + } + + /* + * Now we need to zero out the non-page-aligned data in the + * pages at the start and tail of the hole, and unmap the + * buffer heads for the block aligned regions of the page that + * were completely zeroed. + */ + if (first_page > last_page) { + /* + * If the file space being truncated is contained + * within a page just zero out and unmap the middle of + * that page + */ + ret = ext4_discard_partial_page_buffers(handle, + mapping, offset, length, 0); + + if (ret) + goto out_stop; + } else { + /* + * zero out and unmap the partial page that contains + * the start of the hole + */ + page_len = first_page_offset - offset; + if (page_len > 0) { + ret = ext4_discard_partial_page_buffers(handle, mapping, + offset, page_len, 0); + if (ret) + goto out_stop; + } + + /* + * zero out and unmap the partial page that contains + * the end of the hole + */ + page_len = offset + length - last_page_offset; + if (page_len > 0) { + ret = ext4_discard_partial_page_buffers(handle, mapping, + last_page_offset, page_len, 0); + if (ret) + goto out_stop; + } + } + + /* + * If i_size is contained in the last page, we need to + * unmap and zero the partial page after i_size + */ + if (inode->i_size >> PAGE_CACHE_SHIFT == last_page && + inode->i_size % PAGE_CACHE_SIZE != 0) { + page_len = PAGE_CACHE_SIZE - + (inode->i_size & (PAGE_CACHE_SIZE - 1)); + + if (page_len > 0) { + ret = ext4_discard_partial_page_buffers(handle, + mapping, inode->i_size, page_len, 0); + + if (ret) + goto out_stop; + } + } + + first_block = (offset + sb->s_blocksize - 1) >> + EXT4_BLOCK_SIZE_BITS(sb); + stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); + + /* If there are no blocks to remove, return now */ + if (first_block >= stop_block) + goto out_stop; + + down_write(&EXT4_I(inode)->i_data_sem); + ext4_discard_preallocations(inode); + + ret = ext4_es_remove_extent(inode, first_block, + stop_block - first_block); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_stop; + } + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + ret = ext4_ext_remove_space(inode, first_block, + stop_block - 1); + else + ret = ext4_free_hole_blocks(handle, inode, first_block, + stop_block); + + ext4_discard_preallocations(inode); + up_write(&EXT4_I(inode)->i_data_sem); + if (IS_SYNC(inode)) + ext4_handle_sync(handle); + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); +out_stop: + ext4_journal_stop(handle); +out_dio: + ext4_inode_resume_unlocked_dio(inode); +out_mutex: + mutex_unlock(&inode->i_mutex); + return ret; } /* @@ -3692,6 +3807,19 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) */ void ext4_truncate(struct inode *inode) { + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned int credits; + handle_t *handle; + struct address_space *mapping = inode->i_mapping; + loff_t page_len; + + /* + * There is a possibility that we're either freeing the inode + * or it completely new indode. In those cases we might not + * have i_mutex locked because it's not necessary. + */ + if (!(inode->i_state & (I_NEW|I_FREEING))) + WARN_ON(!mutex_is_locked(&inode->i_mutex)); trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) @@ -3710,10 +3838,72 @@ void ext4_truncate(struct inode *inode) return; } + /* + * finish any pending end_io work so we won't run the risk of + * converting any truncated blocks to initialized later + */ + ext4_flush_unwritten_io(inode); + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ext4_ext_truncate(inode); + credits = ext4_writepage_trans_blocks(inode); else - ext4_ind_truncate(inode); + credits = ext4_blocks_for_truncate(inode); + + handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); + if (IS_ERR(handle)) { + ext4_std_error(inode->i_sb, PTR_ERR(handle)); + return; + } + + if (inode->i_size % PAGE_CACHE_SIZE != 0) { + page_len = PAGE_CACHE_SIZE - + (inode->i_size & (PAGE_CACHE_SIZE - 1)); + + if (ext4_discard_partial_page_buffers(handle, + mapping, inode->i_size, page_len, 0)) + goto out_stop; + } + + /* + * We add the inode to the orphan list, so that if this + * truncate spans multiple transactions, and we crash, we will + * resume the truncate when the filesystem recovers. It also + * marks the inode dirty, to catch the new size. + * + * Implication: the file must always be in a sane, consistent + * truncatable state while each transaction commits. + */ + if (ext4_orphan_add(handle, inode)) + goto out_stop; + + down_write(&EXT4_I(inode)->i_data_sem); + + ext4_discard_preallocations(inode); + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + ext4_ext_truncate(handle, inode); + else + ext4_ind_truncate(handle, inode); + + up_write(&ei->i_data_sem); + + if (IS_SYNC(inode)) + ext4_handle_sync(handle); + +out_stop: + /* + * If this was a simple ftruncate() and the file will remain alive, + * then we need to clear up the orphan record which we created above. + * However, if this was a real unlink then we were called by + * ext4_delete_inode(), and we allow that function to clean up the + * orphan info for us. + */ + if (inode->i_nlink) + ext4_orphan_del(handle, inode); + + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); trace_ext4_truncate_exit(inode); } @@ -3821,13 +4011,14 @@ make_io: if (EXT4_SB(sb)->s_inode_readahead_blks) { ext4_fsblk_t b, end, table; unsigned num; + __u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks; table = ext4_inode_table(sb, gdp); /* s_inode_readahead_blks is always a power of 2 */ - b = block & ~(EXT4_SB(sb)->s_inode_readahead_blks-1); + b = block & ~((ext4_fsblk_t) ra_blks - 1); if (table > b) b = table; - end = b + EXT4_SB(sb)->s_inode_readahead_blks; + end = b + ra_blks; num = EXT4_INODES_PER_GROUP(sb); if (ext4_has_group_desc_csum(sb)) num -= ext4_itable_unused_count(sb, gdp); @@ -4024,8 +4215,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) * NeilBrown 1999oct15 */ if (inode->i_nlink == 0) { - if (inode->i_mode == 0 || - !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) { + if ((inode->i_mode == 0 || + !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) && + ino != EXT4_BOOT_LOADER_INO) { /* this inode is deleted */ ret = -ESTALE; goto bad_inode; @@ -4033,7 +4225,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) /* The only unlinked inodes we let through here have * valid i_mode and are being read by the orphan * recovery code: that's fine, we're about to complete - * the process of deleting those. */ + * the process of deleting those. + * OR it is the EXT4_BOOT_LOADER_INO which is + * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); @@ -4153,6 +4347,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) else init_special_inode(inode, inode->i_mode, new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); + } else if (ino == EXT4_BOOT_LOADER_INO) { + make_bad_inode(inode); } else { ret = -EIO; EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 721f4d33e148..9491ac0590f7 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -17,9 +17,201 @@ #include #include "ext4_jbd2.h" #include "ext4.h" +#include "ext4_extents.h" #define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1) +/** + * Swap memory between @a and @b for @len bytes. + * + * @a: pointer to first memory area + * @b: pointer to second memory area + * @len: number of bytes to swap + * + */ +static void memswap(void *a, void *b, size_t len) +{ + unsigned char *ap, *bp; + unsigned char tmp; + + ap = (unsigned char *)a; + bp = (unsigned char *)b; + while (len-- > 0) { + tmp = *ap; + *ap = *bp; + *bp = tmp; + ap++; + bp++; + } +} + +/** + * Swap i_data and associated attributes between @inode1 and @inode2. + * This function is used for the primary swap between inode1 and inode2 + * and also to revert this primary swap in case of errors. + * + * Therefore you have to make sure, that calling this method twice + * will revert all changes. + * + * @inode1: pointer to first inode + * @inode2: pointer to second inode + */ +static void swap_inode_data(struct inode *inode1, struct inode *inode2) +{ + loff_t isize; + struct ext4_inode_info *ei1; + struct ext4_inode_info *ei2; + + ei1 = EXT4_I(inode1); + ei2 = EXT4_I(inode2); + + memswap(&inode1->i_flags, &inode2->i_flags, sizeof(inode1->i_flags)); + memswap(&inode1->i_version, &inode2->i_version, + sizeof(inode1->i_version)); + memswap(&inode1->i_blocks, &inode2->i_blocks, + sizeof(inode1->i_blocks)); + memswap(&inode1->i_bytes, &inode2->i_bytes, sizeof(inode1->i_bytes)); + memswap(&inode1->i_atime, &inode2->i_atime, sizeof(inode1->i_atime)); + memswap(&inode1->i_mtime, &inode2->i_mtime, sizeof(inode1->i_mtime)); + + memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); + memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags)); + memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize)); + memswap(&ei1->i_es_tree, &ei2->i_es_tree, sizeof(ei1->i_es_tree)); + memswap(&ei1->i_es_lru_nr, &ei2->i_es_lru_nr, sizeof(ei1->i_es_lru_nr)); + + isize = i_size_read(inode1); + i_size_write(inode1, i_size_read(inode2)); + i_size_write(inode2, isize); +} + +/** + * Swap the information from the given @inode and the inode + * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other + * important fields of the inodes. + * + * @sb: the super block of the filesystem + * @inode: the inode to swap with EXT4_BOOT_LOADER_INO + * + */ +static long swap_inode_boot_loader(struct super_block *sb, + struct inode *inode) +{ + handle_t *handle; + int err; + struct inode *inode_bl; + struct ext4_inode_info *ei; + struct ext4_inode_info *ei_bl; + struct ext4_sb_info *sbi; + + if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) { + err = -EINVAL; + goto swap_boot_out; + } + + if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto swap_boot_out; + } + + sbi = EXT4_SB(sb); + ei = EXT4_I(inode); + + inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO); + if (IS_ERR(inode_bl)) { + err = PTR_ERR(inode_bl); + goto swap_boot_out; + } + ei_bl = EXT4_I(inode_bl); + + filemap_flush(inode->i_mapping); + filemap_flush(inode_bl->i_mapping); + + /* Protect orig inodes against a truncate and make sure, + * that only 1 swap_inode_boot_loader is running. */ + ext4_inode_double_lock(inode, inode_bl); + + truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages(&inode_bl->i_data, 0); + + /* Wait for all existing dio workers */ + ext4_inode_block_unlocked_dio(inode); + ext4_inode_block_unlocked_dio(inode_bl); + inode_dio_wait(inode); + inode_dio_wait(inode_bl); + + handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); + if (IS_ERR(handle)) { + err = -EINVAL; + goto swap_boot_out; + } + + /* Protect extent tree against block allocations via delalloc */ + ext4_double_down_write_data_sem(inode, inode_bl); + + if (inode_bl->i_nlink == 0) { + /* this inode has never been used as a BOOT_LOADER */ + set_nlink(inode_bl, 1); + i_uid_write(inode_bl, 0); + i_gid_write(inode_bl, 0); + inode_bl->i_flags = 0; + ei_bl->i_flags = 0; + inode_bl->i_version = 1; + i_size_write(inode_bl, 0); + inode_bl->i_mode = S_IFREG; + if (EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_EXTENTS)) { + ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); + ext4_ext_tree_init(handle, inode_bl); + } else + memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data)); + } + + swap_inode_data(inode, inode_bl); + + inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode); + + spin_lock(&sbi->s_next_gen_lock); + inode->i_generation = sbi->s_next_generation++; + inode_bl->i_generation = sbi->s_next_generation++; + spin_unlock(&sbi->s_next_gen_lock); + + ext4_discard_preallocations(inode); + + err = ext4_mark_inode_dirty(handle, inode); + if (err < 0) { + ext4_warning(inode->i_sb, + "couldn't mark inode #%lu dirty (err %d)", + inode->i_ino, err); + /* Revert all changes: */ + swap_inode_data(inode, inode_bl); + } else { + err = ext4_mark_inode_dirty(handle, inode_bl); + if (err < 0) { + ext4_warning(inode_bl->i_sb, + "couldn't mark inode #%lu dirty (err %d)", + inode_bl->i_ino, err); + /* Revert all changes: */ + swap_inode_data(inode, inode_bl); + ext4_mark_inode_dirty(handle, inode); + } + } + + ext4_journal_stop(handle); + + ext4_double_up_write_data_sem(inode, inode_bl); + + ext4_inode_resume_unlocked_dio(inode); + ext4_inode_resume_unlocked_dio(inode_bl); + + ext4_inode_double_unlock(inode, inode_bl); + + iput(inode_bl); + +swap_boot_out: + return err; +} + long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -83,17 +275,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (!capable(CAP_SYS_RESOURCE)) goto flags_out; } - if (oldflags & EXT4_EXTENTS_FL) { - /* We don't support clearning extent flags */ - if (!(flags & EXT4_EXTENTS_FL)) { - err = -EOPNOTSUPP; - goto flags_out; - } - } else if (flags & EXT4_EXTENTS_FL) { - /* migrate the file */ + if ((flags ^ oldflags) & EXT4_EXTENTS_FL) migrate = 1; - flags &= ~EXT4_EXTENTS_FL; - } if (flags & EXT4_EOFBLOCKS_FL) { /* we don't support adding EOFBLOCKS flag */ @@ -137,8 +320,13 @@ flags_err: err = ext4_change_inode_journal_flag(inode, jflag); if (err) goto flags_out; - if (migrate) - err = ext4_ext_migrate(inode); + if (migrate) { + if (flags & EXT4_EXTENTS_FL) + err = ext4_ext_migrate(inode); + else + err = ext4_ind_migrate(inode); + } + flags_out: mutex_unlock(&inode->i_mutex); mnt_drop_write_file(filp); @@ -357,9 +545,13 @@ group_add_out: return err; } + case EXT4_IOC_SWAP_BOOT: + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + return swap_inode_boot_loader(sb, inode); + case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; - struct super_block *sb = inode->i_sb; int err = 0, err2 = 0; ext4_group_t o_group = EXT4_SB(sb)->s_groups_count; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index ee6614bdb639..a11ea4d6164c 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -405,6 +405,12 @@ static inline void mb_clear_bit(int bit, void *addr) ext4_clear_bit(bit, addr); } +static inline int mb_test_and_clear_bit(int bit, void *addr) +{ + addr = mb_correct_addr_and_bit(&bit, addr); + return ext4_test_and_clear_bit(bit, addr); +} + static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; @@ -764,6 +770,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, spin_unlock(&EXT4_SB(sb)->s_bal_lock); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) { + ext4_set_bits(buddy, 0, count); + } + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -860,8 +884,6 @@ static int ext4_mb_init_cache(struct page *page, char *incore) first_block = page->index * blocks_per_page; for (i = 0; i < blocks_per_page; i++) { - int group; - group = (first_block + i) >> 1; if (group >= ngroups) break; @@ -1011,6 +1033,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) struct page *page; int ret = 0; + might_sleep(); mb_debug(1, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); /* @@ -1082,6 +1105,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; + might_sleep(); mb_debug(1, "load group %u\n", group); blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; @@ -1244,6 +1268,33 @@ static void mb_clear_bits(void *bm, int cur, int len) } } +/* clear bits in given range + * will return first found zero bit if any, -1 otherwise + */ +static int mb_test_and_clear_bits(void *bm, int cur, int len) +{ + __u32 *addr; + int zero_bit = -1; + + len = cur + len; + while (cur < len) { + if ((cur & 31) == 0 && (len - cur) >= 32) { + /* fast path: clear whole word at once */ + addr = bm + (cur >> 3); + if (*addr != (__u32)(-1) && zero_bit == -1) + zero_bit = cur + mb_find_next_zero_bit(addr, 32, 0); + *addr = 0; + cur += 32; + continue; + } + if (!mb_test_and_clear_bit(cur, bm) && zero_bit == -1) + zero_bit = cur; + cur++; + } + + return zero_bit; +} + void ext4_set_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1262,17 +1313,90 @@ void ext4_set_bits(void *bm, int cur, int len) } } -static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, - int first, int count) +/* + * _________________________________________________________________ */ + +static inline int mb_buddy_adjust_border(int* bit, void* bitmap, int side) { - int block = 0; - int max = 0; - int order; - void *buddy; - void *buddy2; + if (mb_test_bit(*bit + side, bitmap)) { + mb_clear_bit(*bit, bitmap); + (*bit) -= side; + return 1; + } + else { + (*bit) += side; + mb_set_bit(*bit, bitmap); + return -1; + } +} + +static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last) +{ + int max; + int order = 1; + void *buddy = mb_find_buddy(e4b, order, &max); + + while (buddy) { + void *buddy2; + + /* Bits in range [first; last] are known to be set since + * corresponding blocks were allocated. Bits in range + * (first; last) will stay set because they form buddies on + * upper layer. We just deal with borders if they don't + * align with upper layer and then go up. + * Releasing entire group is all about clearing + * single bit of highest order buddy. + */ + + /* Example: + * --------------------------------- + * | 1 | 1 | 1 | 1 | + * --------------------------------- + * | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | + * --------------------------------- + * 0 1 2 3 4 5 6 7 + * \_____________________/ + * + * Neither [1] nor [6] is aligned to above layer. + * Left neighbour [0] is free, so mark it busy, + * decrease bb_counters and extend range to + * [0; 6] + * Right neighbour [7] is busy. It can't be coaleasced with [6], so + * mark [6] free, increase bb_counters and shrink range to + * [0; 5]. + * Then shift range to [0; 2], go up and do the same. + */ + + + if (first & 1) + e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&first, buddy, -1); + if (!(last & 1)) + e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&last, buddy, 1); + if (first > last) + break; + order++; + + if (first == last || !(buddy2 = mb_find_buddy(e4b, order, &max))) { + mb_clear_bits(buddy, first, last - first + 1); + e4b->bd_info->bb_counters[order - 1] += last - first + 1; + break; + } + first >>= 1; + last >>= 1; + buddy = buddy2; + } +} + +static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, + int first, int count) +{ + int left_is_free = 0; + int right_is_free = 0; + int block; + int last = first + count - 1; struct super_block *sb = e4b->bd_sb; - BUG_ON(first + count > (sb->s_blocksize << 3)); + BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); @@ -1281,67 +1405,54 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first < e4b->bd_info->bb_first_free) e4b->bd_info->bb_first_free = first; - /* let's maintain fragments counter */ + /* access memory sequentially: check left neighbour, + * clear range and then check right neighbour + */ if (first != 0) - block = !mb_test_bit(first - 1, e4b->bd_bitmap); - if (first + count < EXT4_SB(sb)->s_mb_maxs[0]) - max = !mb_test_bit(first + count, e4b->bd_bitmap); - if (block && max) + left_is_free = !mb_test_bit(first - 1, e4b->bd_bitmap); + block = mb_test_and_clear_bits(e4b->bd_bitmap, first, count); + if (last + 1 < EXT4_SB(sb)->s_mb_maxs[0]) + right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap); + + if (unlikely(block != -1)) { + ext4_fsblk_t blocknr; + + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); + blocknr += EXT4_C2B(EXT4_SB(sb), block); + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, + blocknr, + "freeing already freed block " + "(bit %u)", block); + mb_regenerate_buddy(e4b); + goto done; + } + + /* let's maintain fragments counter */ + if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; - else if (!block && !max) + else if (!left_is_free && !right_is_free) e4b->bd_info->bb_fragments++; - /* let's maintain buddy itself */ - while (count-- > 0) { - block = first++; - order = 0; - - if (!mb_test_bit(block, e4b->bd_bitmap)) { - ext4_fsblk_t blocknr; - - blocknr = ext4_group_first_block_no(sb, e4b->bd_group); - blocknr += EXT4_C2B(EXT4_SB(sb), block); - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block " - "(bit %u)", block); - } - mb_clear_bit(block, e4b->bd_bitmap); - e4b->bd_info->bb_counters[order]++; - - /* start of the buddy */ - buddy = mb_find_buddy(e4b, order, &max); - - do { - block &= ~1UL; - if (mb_test_bit(block, buddy) || - mb_test_bit(block + 1, buddy)) - break; - - /* both the buddies are free, try to coalesce them */ - buddy2 = mb_find_buddy(e4b, order + 1, &max); - - if (!buddy2) - break; - - if (order > 0) { - /* for special purposes, we don't set - * free bits in bitmap */ - mb_set_bit(block, buddy); - mb_set_bit(block + 1, buddy); - } - e4b->bd_info->bb_counters[order]--; - e4b->bd_info->bb_counters[order]--; - - block = block >> 1; - order++; - e4b->bd_info->bb_counters[order]++; - - mb_clear_bit(block, buddy2); - buddy = buddy2; - } while (1); + /* buddy[0] == bd_bitmap is a special case, so handle + * it right away and let mb_buddy_mark_free stay free of + * zero order checks. + * Check if neighbours are to be coaleasced, + * adjust bitmap bb_counters and borders appropriately. + */ + if (first & 1) { + first += !left_is_free; + e4b->bd_info->bb_counters[0] += left_is_free ? -1 : 1; } + if (!(last & 1)) { + last -= !right_is_free; + e4b->bd_info->bb_counters[0] += right_is_free ? -1 : 1; + } + + if (first <= last) + mb_buddy_mark_free(e4b, first >> 1, last >> 1); + +done: mb_set_largest_free_order(sb, e4b->bd_info); mb_check_buddy(e4b); } @@ -3342,7 +3453,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, if (pa->pa_type == MB_GROUP_PA) grp_blk--; - ext4_get_group_no_and_offset(sb, grp_blk, &grp, NULL); + grp = ext4_get_group_number(sb, grp_blk); /* * possible race: @@ -3807,7 +3918,7 @@ repeat: list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { BUG_ON(pa->pa_type != MB_INODE_PA); - ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL); + group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { @@ -4069,7 +4180,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) { - ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL); + group = ext4_get_group_number(sb, pa->pa_pstart); if (ext4_mb_load_buddy(sb, group, &e4b)) { ext4_error(sb, "Error loading buddy information for %u", group); @@ -4217,6 +4328,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, unsigned int inquota = 0; unsigned int reserv_clstrs = 0; + might_sleep(); sb = ar->inode->i_sb; sbi = EXT4_SB(sb); @@ -4420,11 +4532,11 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); - if (can_merge(entry, new_entry)) { + if (can_merge(entry, new_entry) && + ext4_journal_callback_try_del(handle, &entry->efd_jce)) { new_entry->efd_start_cluster = entry->efd_start_cluster; new_entry->efd_count += entry->efd_count; rb_erase(node, &(db->bb_free_root)); - ext4_journal_callback_del(handle, &entry->efd_jce); kmem_cache_free(ext4_free_data_cachep, entry); } } @@ -4432,10 +4544,10 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); - if (can_merge(new_entry, entry)) { + if (can_merge(new_entry, entry) && + ext4_journal_callback_try_del(handle, &entry->efd_jce)) { new_entry->efd_count += entry->efd_count; rb_erase(node, &(db->bb_free_root)); - ext4_journal_callback_del(handle, &entry->efd_jce); kmem_cache_free(ext4_free_data_cachep, entry); } } @@ -4470,6 +4582,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, int err = 0; int ret; + might_sleep(); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 480acf4a085f..49e8bdff9163 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -426,7 +426,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode) return retval; } return retval; - } int ext4_ext_migrate(struct inode *inode) @@ -606,3 +605,64 @@ out: return retval; } + +/* + * Migrate a simple extent-based inode to use the i_blocks[] array + */ +int ext4_ind_migrate(struct inode *inode) +{ + struct ext4_extent_header *eh; + struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_extent *ex; + unsigned int i, len; + ext4_fsblk_t blk; + handle_t *handle; + int ret; + + if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_INCOMPAT_EXTENTS) || + (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + return -EINVAL; + + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_BIGALLOC)) + return -EOPNOTSUPP; + + handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + down_write(&EXT4_I(inode)->i_data_sem); + ret = ext4_ext_check_inode(inode); + if (ret) + goto errout; + + eh = ext_inode_hdr(inode); + ex = EXT_FIRST_EXTENT(eh); + if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS || + eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) { + ret = -EOPNOTSUPP; + goto errout; + } + if (eh->eh_entries == 0) + blk = len = 0; + else { + len = le16_to_cpu(ex->ee_len); + blk = ext4_ext_pblock(ex); + if (len > EXT4_NDIR_BLOCKS) { + ret = -EOPNOTSUPP; + goto errout; + } + } + + ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); + memset(ei->i_data, 0, sizeof(ei->i_data)); + for (i=0; i < len; i++) + ei->i_data[i] = cpu_to_le32(blk++); + ext4_mark_inode_dirty(handle, inode); +errout: + ext4_journal_stop(handle); + up_write(&EXT4_I(inode)->i_data_sem); + return ret; +} diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index f9b551561d2c..214461e42a05 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -7,7 +7,7 @@ #include "ext4.h" /* Checksumming functions */ -static __u32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) +static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) { struct ext4_sb_info *sbi = EXT4_SB(sb); int offset = offsetof(struct mmp_struct, mmp_checksum); @@ -54,7 +54,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); - submit_bh(WRITE_SYNC, bh); + submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) @@ -86,7 +86,7 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh, get_bh(*bh); lock_buffer(*bh); (*bh)->b_end_io = end_buffer_read_sync; - submit_bh(READ_SYNC, *bh); + submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh); wait_on_buffer(*bh); if (!buffer_uptodate(*bh)) { brelse(*bh); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 33e1c086858b..3dcbf364022f 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -144,12 +144,13 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, } /** - * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem + * ext4_double_down_write_data_sem - Acquire two inodes' write lock + * of i_data_sem * * Acquire write lock of i_data_sem of the two inodes */ -static void -double_down_write_data_sem(struct inode *first, struct inode *second) +void +ext4_double_down_write_data_sem(struct inode *first, struct inode *second) { if (first < second) { down_write(&EXT4_I(first)->i_data_sem); @@ -162,14 +163,15 @@ double_down_write_data_sem(struct inode *first, struct inode *second) } /** - * double_up_write_data_sem - Release two inodes' write lock of i_data_sem + * ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem * * @orig_inode: original inode structure to be released its lock first * @donor_inode: donor inode structure to be released its lock second * Release write lock of i_data_sem of two inodes (orig and donor). */ -static void -double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) +void +ext4_double_up_write_data_sem(struct inode *orig_inode, + struct inode *donor_inode) { up_write(&EXT4_I(orig_inode)->i_data_sem); up_write(&EXT4_I(donor_inode)->i_data_sem); @@ -407,18 +409,7 @@ mext_insert_extents(handle_t *handle, struct inode *orig_inode, mext_insert_inside_block(o_start, o_end, start_ext, new_ext, end_ext, eh, range_to_move); - if (depth) { - ret = ext4_handle_dirty_metadata(handle, orig_inode, - orig_path->p_bh); - if (ret) - return ret; - } else { - ret = ext4_mark_inode_dirty(handle, orig_inode); - if (ret < 0) - return ret; - } - - return 0; + return ext4_ext_dirty(handle, orig_inode, orig_path); } /** @@ -737,6 +728,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, donor_off += dext_alen; orig_off += dext_alen; + BUG_ON(replaced_count > count); /* Already moved the expected blocks */ if (replaced_count >= count) break; @@ -814,7 +806,13 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2, page_cache_release(page[0]); return -ENOMEM; } - + /* + * grab_cache_page_write_begin() may not wait on page's writeback if + * BDI not demand that. But it is reasonable to be very conservative + * here and explicitly wait on page's writeback + */ + wait_on_page_writeback(page[0]); + wait_on_page_writeback(page[1]); if (inode1 > inode2) { struct page *tmp; tmp = page[0]; @@ -856,7 +854,6 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { - int err = 0; err = ext4_get_block(inode, block, bh, 0); if (err) { SetPageError(page); @@ -976,7 +973,7 @@ again: * necessary, just swap data blocks between orig and donor. */ if (uninit) { - double_down_write_data_sem(orig_inode, donor_inode); + ext4_double_down_write_data_sem(orig_inode, donor_inode); /* If any of extents in range became initialized we have to * fallback to data copying */ uninit = mext_check_coverage(orig_inode, orig_blk_offset, @@ -990,7 +987,7 @@ again: goto drop_data_sem; if (!uninit) { - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); goto data_copy; } if ((page_has_private(pagep[0]) && @@ -1004,7 +1001,7 @@ again: donor_inode, orig_blk_offset, block_len_in_page, err); drop_data_sem: - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); goto unlock_pages; } data_copy: @@ -1033,7 +1030,7 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, from + replaced_size, + *err = __block_write_begin(pagep[0], from, replaced_size, ext4_get_block); if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); @@ -1065,11 +1062,11 @@ repair_branches: * Extents are swapped already, but we are not able to copy data. * Try to swap extents to it's original places */ - double_down_write_data_sem(orig_inode, donor_inode); + ext4_double_down_write_data_sem(orig_inode, donor_inode); replaced_count = mext_replace_branches(handle, donor_inode, orig_inode, orig_blk_offset, block_len_in_page, &err2); - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); if (replaced_count != block_len_in_page) { EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset), "Unable to copy data block," @@ -1209,15 +1206,15 @@ mext_check_arguments(struct inode *orig_inode, } /** - * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2 + * ext4_inode_double_lock - Lock i_mutex on both @inode1 and @inode2 * * @inode1: the inode structure * @inode2: the inode structure * * Lock two inodes' i_mutex */ -static void -mext_inode_double_lock(struct inode *inode1, struct inode *inode2) +void +ext4_inode_double_lock(struct inode *inode1, struct inode *inode2) { BUG_ON(inode1 == inode2); if (inode1 < inode2) { @@ -1230,15 +1227,15 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2) } /** - * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2 + * ext4_inode_double_unlock - Release i_mutex on both @inode1 and @inode2 * * @inode1: the inode that is released first * @inode2: the inode that is released second * */ -static void -mext_inode_double_unlock(struct inode *inode1, struct inode *inode2) +void +ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2) { mutex_unlock(&inode1->i_mutex); mutex_unlock(&inode2->i_mutex); @@ -1333,7 +1330,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, return -EINVAL; } /* Protect orig and donor inodes against a truncate */ - mext_inode_double_lock(orig_inode, donor_inode); + ext4_inode_double_lock(orig_inode, donor_inode); /* Wait for all existing dio workers */ ext4_inode_block_unlocked_dio(orig_inode); @@ -1342,7 +1339,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, inode_dio_wait(donor_inode); /* Protect extent tree against block allocations via delalloc */ - double_down_write_data_sem(orig_inode, donor_inode); + ext4_double_down_write_data_sem(orig_inode, donor_inode); /* Check the filesystem environment whether move_extent can be done */ ret = mext_check_arguments(orig_inode, donor_inode, orig_start, donor_start, &len); @@ -1466,7 +1463,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, * b. racing with ->readpage, ->write_begin, and ext4_get_block * in move_extent_per_page */ - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); while (orig_page_offset <= seq_end_page) { @@ -1500,7 +1497,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, block_len_in_page = rest_blocks; } - double_down_write_data_sem(orig_inode, donor_inode); + ext4_double_down_write_data_sem(orig_inode, donor_inode); if (ret < 0) break; @@ -1538,10 +1535,10 @@ out: ext4_ext_drop_refs(holecheck_path); kfree(holecheck_path); } - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); ext4_inode_resume_unlocked_dio(orig_inode); ext4_inode_resume_unlocked_dio(donor_inode); - mext_inode_double_unlock(orig_inode, donor_inode); + ext4_inode_double_unlock(orig_inode, donor_inode); return ret; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 3825d6aa8336..6653fc35ecb7 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -416,15 +416,16 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent, { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); - __u32 csum, old_csum; + __u32 csum; + __le32 save_csum; int size; size = count_offset + (count * sizeof(struct dx_entry)); - old_csum = t->dt_checksum; + save_csum = t->dt_checksum; t->dt_checksum = 0; csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size); csum = ext4_chksum(sbi, csum, (__u8 *)t, sizeof(struct dx_tail)); - t->dt_checksum = old_csum; + t->dt_checksum = save_csum; return cpu_to_le32(csum); } @@ -971,6 +972,17 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; + if (ext4_has_inline_data(dir)) { + int has_inline_data = 1; + count = htree_inlinedir_to_tree(dir_file, dir, 0, + &hinfo, start_hash, + start_minor_hash, + &has_inline_data); + if (has_inline_data) { + *next_hash = ~0; + return count; + } + } count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo, start_hash, start_minor_hash); *next_hash = ~0; @@ -1455,24 +1467,6 @@ struct dentry *ext4_get_parent(struct dentry *child) return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino)); } -#define S_SHIFT 12 -static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { - [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, - [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR, - [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV, - [S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV, - [S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO, - [S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK, - [S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK, -}; - -static inline void ext4_set_de_type(struct super_block *sb, - struct ext4_dir_entry_2 *de, - umode_t mode) { - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE)) - de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; -} - /* * Move count entries from end of map between two memory locations. * Returns pointer to last entry moved. @@ -2251,8 +2245,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, dquot_initialize(dir); credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); @@ -2286,8 +2279,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry, dquot_initialize(dir); credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); @@ -2396,8 +2388,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) dquot_initialize(dir); credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: inode = ext4_new_inode_start_handle(dir, S_IFDIR | mode, &dentry->d_name, @@ -2826,8 +2817,7 @@ static int ext4_symlink(struct inode *dir, * quota blocks, sb is already counted in previous macros). */ credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb); + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; } retry: inode = ext4_new_inode_start_handle(dir, S_IFLNK|S_IRWXUGO, diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 047a6de04a0a..5929cd0baa20 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -29,25 +29,19 @@ #include "xattr.h" #include "acl.h" -static struct kmem_cache *io_page_cachep, *io_end_cachep; +static struct kmem_cache *io_end_cachep; int __init ext4_init_pageio(void) { - io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT); - if (io_page_cachep == NULL) - return -ENOMEM; io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT); - if (io_end_cachep == NULL) { - kmem_cache_destroy(io_page_cachep); + if (io_end_cachep == NULL) return -ENOMEM; - } return 0; } void ext4_exit_pageio(void) { kmem_cache_destroy(io_end_cachep); - kmem_cache_destroy(io_page_cachep); } /* @@ -67,29 +61,28 @@ void ext4_ioend_shutdown(struct inode *inode) cancel_work_sync(&EXT4_I(inode)->i_unwritten_work); } -static void put_io_page(struct ext4_io_page *io_page) +static void ext4_release_io_end(ext4_io_end_t *io_end) { - if (atomic_dec_and_test(&io_page->p_count)) { - end_page_writeback(io_page->p_page); - put_page(io_page->p_page); - kmem_cache_free(io_page_cachep, io_page); - } + BUG_ON(!list_empty(&io_end->list)); + BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN); + + if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count)) + wake_up_all(ext4_ioend_wq(io_end->inode)); + if (io_end->flag & EXT4_IO_END_DIRECT) + inode_dio_done(io_end->inode); + if (io_end->iocb) + aio_complete(io_end->iocb, io_end->result, 0); + kmem_cache_free(io_end_cachep, io_end); } -void ext4_free_io_end(ext4_io_end_t *io) +static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) { - int i; + struct inode *inode = io_end->inode; - BUG_ON(!io); - BUG_ON(!list_empty(&io->list)); - BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN); - - for (i = 0; i < io->num_io_pages; i++) - put_io_page(io->pages[i]); - io->num_io_pages = 0; - if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count)) - wake_up_all(ext4_ioend_wq(io->inode)); - kmem_cache_free(io_end_cachep, io); + io_end->flag &= ~EXT4_IO_END_UNWRITTEN; + /* Wake up anyone waiting on unwritten extent conversion */ + if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) + wake_up_all(ext4_ioend_wq(inode)); } /* check a range of space and convert unwritten extents to written. */ @@ -112,13 +105,8 @@ static int ext4_end_io(ext4_io_end_t *io) "(inode %lu, offset %llu, size %zd, error %d)", inode->i_ino, offset, size, ret); } - /* Wake up anyone waiting on unwritten extent conversion */ - if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) - wake_up_all(ext4_ioend_wq(inode)); - if (io->flag & EXT4_IO_END_DIRECT) - inode_dio_done(inode); - if (io->iocb) - aio_complete(io->iocb, io->result, 0); + ext4_clear_io_unwritten_flag(io); + ext4_release_io_end(io); return ret; } @@ -149,7 +137,7 @@ static void dump_completed_IO(struct inode *inode) } /* Add the io_end to per-inode completed end_io list. */ -void ext4_add_complete_io(ext4_io_end_t *io_end) +static void ext4_add_complete_io(ext4_io_end_t *io_end) { struct ext4_inode_info *ei = EXT4_I(io_end->inode); struct workqueue_struct *wq; @@ -186,8 +174,6 @@ static int ext4_do_flush_completed_IO(struct inode *inode) err = ext4_end_io(io); if (unlikely(!ret && err)) ret = err; - io->flag &= ~EXT4_IO_END_UNWRITTEN; - ext4_free_io_end(io); } return ret; } @@ -219,10 +205,43 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) atomic_inc(&EXT4_I(inode)->i_ioend_count); io->inode = inode; INIT_LIST_HEAD(&io->list); + atomic_set(&io->count, 1); } return io; } +void ext4_put_io_end_defer(ext4_io_end_t *io_end) +{ + if (atomic_dec_and_test(&io_end->count)) { + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) { + ext4_release_io_end(io_end); + return; + } + ext4_add_complete_io(io_end); + } +} + +int ext4_put_io_end(ext4_io_end_t *io_end) +{ + int err = 0; + + if (atomic_dec_and_test(&io_end->count)) { + if (io_end->flag & EXT4_IO_END_UNWRITTEN) { + err = ext4_convert_unwritten_extents(io_end->inode, + io_end->offset, io_end->size); + ext4_clear_io_unwritten_flag(io_end); + } + ext4_release_io_end(io_end); + } + return err; +} + +ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end) +{ + atomic_inc(&io_end->count); + return io_end; +} + /* * Print an buffer I/O error compatible with the fs/buffer.c. This * provides compatibility with dmesg scrapers that look for a specific @@ -243,45 +262,56 @@ static void ext4_end_bio(struct bio *bio, int error) ext4_io_end_t *io_end = bio->bi_private; struct inode *inode; int i; + int blocksize; sector_t bi_sector = bio->bi_sector; BUG_ON(!io_end); + inode = io_end->inode; + blocksize = 1 << inode->i_blkbits; bio->bi_private = NULL; bio->bi_end_io = NULL; if (test_bit(BIO_UPTODATE, &bio->bi_flags)) error = 0; - bio_put(bio); - - for (i = 0; i < io_end->num_io_pages; i++) { - struct page *page = io_end->pages[i]->p_page; + for (i = 0; i < bio->bi_vcnt; i++) { + struct bio_vec *bvec = &bio->bi_io_vec[i]; + struct page *page = bvec->bv_page; struct buffer_head *bh, *head; - loff_t offset; - loff_t io_end_offset; + unsigned bio_start = bvec->bv_offset; + unsigned bio_end = bio_start + bvec->bv_len; + unsigned under_io = 0; + unsigned long flags; + + if (!page) + continue; if (error) { SetPageError(page); set_bit(AS_EIO, &page->mapping->flags); - head = page_buffers(page); - BUG_ON(!head); - - io_end_offset = io_end->offset + io_end->size; - - offset = (sector_t) page->index << PAGE_CACHE_SHIFT; - bh = head; - do { - if ((offset >= io_end->offset) && - (offset+bh->b_size <= io_end_offset)) - buffer_io_error(bh); - - offset += bh->b_size; - bh = bh->b_this_page; - } while (bh != head); } - - put_io_page(io_end->pages[i]); + bh = head = page_buffers(page); + /* + * We check all buffers in the page under BH_Uptodate_Lock + * to avoid races with other end io clearing async_write flags + */ + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &head->b_state); + do { + if (bh_offset(bh) < bio_start || + bh_offset(bh) + blocksize > bio_end) { + if (buffer_async_write(bh)) + under_io++; + continue; + } + clear_buffer_async_write(bh); + if (error) + buffer_io_error(bh); + } while ((bh = bh->b_this_page) != head); + bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); + local_irq_restore(flags); + if (!under_io) + end_page_writeback(page); } - io_end->num_io_pages = 0; - inode = io_end->inode; + bio_put(bio); if (error) { io_end->flag |= EXT4_IO_END_ERROR; @@ -294,12 +324,7 @@ static void ext4_end_bio(struct bio *bio, int error) bi_sector >> (inode->i_blkbits - 9)); } - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - ext4_free_io_end(io_end); - return; - } - - ext4_add_complete_io(io_end); + ext4_put_io_end_defer(io_end); } void ext4_io_submit(struct ext4_io_submit *io) @@ -313,76 +338,59 @@ void ext4_io_submit(struct ext4_io_submit *io) bio_put(io->io_bio); } io->io_bio = NULL; - io->io_op = 0; +} + +void ext4_io_submit_init(struct ext4_io_submit *io, + struct writeback_control *wbc) +{ + io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); + io->io_bio = NULL; io->io_end = NULL; } -static int io_submit_init(struct ext4_io_submit *io, - struct inode *inode, - struct writeback_control *wbc, - struct buffer_head *bh) +static int io_submit_init_bio(struct ext4_io_submit *io, + struct buffer_head *bh) { - ext4_io_end_t *io_end; - struct page *page = bh->b_page; int nvecs = bio_get_nr_vecs(bh->b_bdev); struct bio *bio; - io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) - return -ENOMEM; bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES)); bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_bdev = bh->b_bdev; - bio->bi_private = io->io_end = io_end; bio->bi_end_io = ext4_end_bio; - - io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh); - + bio->bi_private = ext4_get_io_end(io->io_end); + if (!io->io_end->size) + io->io_end->offset = (bh->b_page->index << PAGE_CACHE_SHIFT) + + bh_offset(bh); io->io_bio = bio; - io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); io->io_next_block = bh->b_blocknr; return 0; } static int io_submit_add_bh(struct ext4_io_submit *io, - struct ext4_io_page *io_page, struct inode *inode, - struct writeback_control *wbc, struct buffer_head *bh) { ext4_io_end_t *io_end; int ret; - if (buffer_new(bh)) { - clear_buffer_new(bh); - unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); - } - if (io->io_bio && bh->b_blocknr != io->io_next_block) { submit_and_retry: ext4_io_submit(io); } if (io->io_bio == NULL) { - ret = io_submit_init(io, inode, wbc, bh); + ret = io_submit_init_bio(io, bh); if (ret) return ret; } - io_end = io->io_end; - if ((io_end->num_io_pages >= MAX_IO_PAGES) && - (io_end->pages[io_end->num_io_pages-1] != io_page)) - goto submit_and_retry; - if (buffer_uninit(bh)) - ext4_set_io_unwritten_flag(inode, io_end); - io->io_end->size += bh->b_size; - io->io_next_block++; ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; - if ((io_end->num_io_pages == 0) || - (io_end->pages[io_end->num_io_pages-1] != io_page)) { - io_end->pages[io_end->num_io_pages++] = io_page; - atomic_inc(&io_page->p_count); - } + io_end = io->io_end; + if (test_clear_buffer_uninit(bh)) + ext4_set_io_unwritten_flag(inode, io_end); + io_end->size += bh->b_size; + io->io_next_block++; return 0; } @@ -392,33 +400,29 @@ int ext4_bio_write_page(struct ext4_io_submit *io, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; - unsigned block_start, block_end, blocksize; - struct ext4_io_page *io_page; + unsigned block_start, blocksize; struct buffer_head *bh, *head; int ret = 0; + int nr_submitted = 0; blocksize = 1 << inode->i_blkbits; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); - io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS); - if (!io_page) { - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return -ENOMEM; - } - io_page->p_page = page; - atomic_set(&io_page->p_count, 1); - get_page(page); set_page_writeback(page); ClearPageError(page); - for (bh = head = page_buffers(page), block_start = 0; - bh != head || !block_start; - block_start = block_end, bh = bh->b_this_page) { - - block_end = block_start + blocksize; + /* + * In the first loop we prepare and mark buffers to submit. We have to + * mark all buffers in the page before submitting so that + * end_page_writeback() cannot be called from ext4_bio_end_io() when IO + * on the first buffer finishes and we are still working on submitting + * the second buffer. + */ + bh = head = page_buffers(page); + do { + block_start = bh_offset(bh); if (block_start >= len) { /* * Comments copied from block_write_full_page_endio: @@ -431,7 +435,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io, * mapped, and writes to that region are not written * out to the file." */ - zero_user_segment(page, block_start, block_end); + zero_user_segment(page, block_start, + block_start + blocksize); clear_buffer_dirty(bh); set_buffer_uptodate(bh); continue; @@ -445,7 +450,19 @@ int ext4_bio_write_page(struct ext4_io_submit *io, ext4_io_submit(io); continue; } - ret = io_submit_add_bh(io, io_page, inode, wbc, bh); + if (buffer_new(bh)) { + clear_buffer_new(bh); + unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); + } + set_buffer_async_write(bh); + } while ((bh = bh->b_this_page) != head); + + /* Now submit buffers to write */ + bh = head = page_buffers(page); + do { + if (!buffer_async_write(bh)) + continue; + ret = io_submit_add_bh(io, inode, bh); if (ret) { /* * We only get here on ENOMEM. Not much else @@ -455,17 +472,20 @@ int ext4_bio_write_page(struct ext4_io_submit *io, redirty_page_for_writepage(wbc, page); break; } + nr_submitted++; clear_buffer_dirty(bh); + } while ((bh = bh->b_this_page) != head); + + /* Error stopped previous loop? Clean up buffers... */ + if (ret) { + do { + clear_buffer_async_write(bh); + bh = bh->b_this_page; + } while (bh != head); } unlock_page(page); - /* - * If the page was truncated before we could do the writeback, - * or we had a memory allocation error while trying to write - * the first buffer head, we won't have submitted any pages for - * I/O. In that case we need to make sure we've cleared the - * PageWriteback bit from the page to prevent the system from - * wedging later on. - */ - put_io_page(io_page); + /* Nothing submitted - we have to end page writeback */ + if (!nr_submitted) + end_page_writeback(page); return ret; } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c169477a62c9..b27c96d01965 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -272,7 +272,7 @@ next_group: if (start_blk >= last_blk) goto next_group; group_data[bb_index].block_bitmap = start_blk++; - ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL); + group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count--; if (flexbg_size > 1) @@ -284,7 +284,7 @@ next_group: if (start_blk >= last_blk) goto next_group; group_data[ib_index].inode_bitmap = start_blk++; - ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL); + group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count--; if (flexbg_size > 1) @@ -296,7 +296,7 @@ next_group: if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk) goto next_group; group_data[it_index].inode_table = start_blk; - ext4_get_group_no_and_offset(sb, start_blk, &group, NULL); + group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count -= EXT4_SB(sb)->s_itb_per_group; @@ -392,7 +392,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, ext4_group_t group; int err; - ext4_get_group_no_and_offset(sb, block, &group, NULL); + group = ext4_get_group_number(sb, block); start = ext4_group_first_block_no(sb, group); group -= flex_gd->groups[0].group; @@ -1341,6 +1341,8 @@ static void ext4_update_super(struct super_block *sb, /* Update the global fs size fields */ sbi->s_groups_count += flex_gd->count; + sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, + (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); /* Update the reserved block counts only once the new group is * active. */ @@ -1879,7 +1881,11 @@ retry: /* Nothing need to do */ return 0; - ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset); + n_group = ext4_get_group_number(sb, n_blocks_count - 1); + if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) { + ext4_warning(sb, "resize would cause inodes_count overflow"); + return -EINVAL; + } ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset); n_desc_blocks = num_desc_blocks(sb, n_group + 1); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5d6d53578124..dbc7c090c13a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -81,6 +81,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly); static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); +static int ext4_reserve_clusters(struct ext4_sb_info *, ext4_fsblk_t); #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23) static struct file_system_type ext2_fs_type = { @@ -353,10 +354,13 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); int error = is_journal_aborted(journal); - struct ext4_journal_cb_entry *jce, *tmp; + struct ext4_journal_cb_entry *jce; + BUG_ON(txn->t_state == T_FINISHED); spin_lock(&sbi->s_md_lock); - list_for_each_entry_safe(jce, tmp, &txn->t_private_list, jce_list) { + while (!list_empty(&txn->t_private_list)) { + jce = list_entry(txn->t_private_list.next, + struct ext4_journal_cb_entry, jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); jce->jce_func(sb, jce, error); @@ -1948,16 +1952,16 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, if ((sbi->s_es->s_feature_ro_compat & cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) { /* Use new metadata_csum algorithm */ - __u16 old_csum; + __le16 save_csum; __u32 csum32; - old_csum = gdp->bg_checksum; + save_csum = gdp->bg_checksum; gdp->bg_checksum = 0; csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group, sizeof(le_group)); csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, sbi->s_desc_size); - gdp->bg_checksum = old_csum; + gdp->bg_checksum = save_csum; crc = csum32 & 0xFFFF; goto out; @@ -2379,17 +2383,15 @@ struct ext4_attr { int offset; }; -static int parse_strtoul(const char *buf, - unsigned long max, unsigned long *value) +static int parse_strtoull(const char *buf, + unsigned long long max, unsigned long long *value) { - char *endp; + int ret; - *value = simple_strtoul(skip_spaces(buf), &endp, 0); - endp = skip_spaces(endp); - if (*endp || *value > max) - return -EINVAL; - - return 0; + ret = kstrtoull(skip_spaces(buf), 0, value); + if (!ret && *value > max) + ret = -EINVAL; + return ret; } static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a, @@ -2431,11 +2433,13 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a, const char *buf, size_t count) { unsigned long t; + int ret; - if (parse_strtoul(buf, 0x40000000, &t)) - return -EINVAL; + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; - if (t && !is_power_of_2(t)) + if (t && (!is_power_of_2(t) || t > 0x40000000)) return -EINVAL; sbi->s_inode_readahead_blks = t; @@ -2456,13 +2460,36 @@ static ssize_t sbi_ui_store(struct ext4_attr *a, { unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset); unsigned long t; + int ret; - if (parse_strtoul(buf, 0xffffffff, &t)) - return -EINVAL; + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; *ui = t; return count; } +static ssize_t reserved_clusters_show(struct ext4_attr *a, + struct ext4_sb_info *sbi, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long) atomic64_read(&sbi->s_resv_clusters)); +} + +static ssize_t reserved_clusters_store(struct ext4_attr *a, + struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + unsigned long long val; + int ret; + + if (parse_strtoull(buf, -1ULL, &val)) + return -EINVAL; + ret = ext4_reserve_clusters(sbi, val); + + return ret ? ret : count; +} + static ssize_t trigger_test_error(struct ext4_attr *a, struct ext4_sb_info *sbi, const char *buf, size_t count) @@ -2500,6 +2527,7 @@ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) EXT4_RO_ATTR(delayed_allocation_blocks); EXT4_RO_ATTR(session_write_kbytes); EXT4_RO_ATTR(lifetime_write_kbytes); +EXT4_RW_ATTR(reserved_clusters); EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show, inode_readahead_blks_store, s_inode_readahead_blks); EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); @@ -2517,6 +2545,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(delayed_allocation_blocks), ATTR_LIST(session_write_kbytes), ATTR_LIST(lifetime_write_kbytes), + ATTR_LIST(reserved_clusters), ATTR_LIST(inode_readahead_blks), ATTR_LIST(inode_goal), ATTR_LIST(mb_stats), @@ -3192,6 +3221,40 @@ int ext4_calculate_overhead(struct super_block *sb) return 0; } + +static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi) +{ + ext4_fsblk_t resv_clusters; + + /* + * By default we reserve 2% or 4096 clusters, whichever is smaller. + * This should cover the situations where we can not afford to run + * out of space like for example punch hole, or converting + * uninitialized extents in delalloc path. In most cases such + * allocation would require 1, or 2 blocks, higher numbers are + * very rare. + */ + resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits; + + do_div(resv_clusters, 50); + resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); + + return resv_clusters; +} + + +static int ext4_reserve_clusters(struct ext4_sb_info *sbi, ext4_fsblk_t count) +{ + ext4_fsblk_t clusters = ext4_blocks_count(sbi->s_es) >> + sbi->s_cluster_bits; + + if (count >= clusters) + return -EINVAL; + + atomic64_set(&sbi->s_resv_clusters, count); + return 0; +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) { char *orig_data = kstrdup(data, GFP_KERNEL); @@ -3526,6 +3589,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); + /* Do we have standard group size of blocksize * 8 blocks ? */ + if (sbi->s_blocks_per_group == blocksize << 3) + set_opt2(sb, STD_GROUP_SIZE); + for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; @@ -3698,6 +3765,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_err_report.function = print_daily_error_info; sbi->s_err_report.data = (unsigned long) sb; + /* Register extent status tree shrinker */ + ext4_es_register_shrinker(sb); + err = percpu_counter_init(&sbi->s_freeclusters_counter, ext4_count_free_clusters(sb)); if (!err) { @@ -3723,9 +3793,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_max_writeback_mb_bump = 128; sbi->s_extent_max_zeroout_kb = 32; - /* Register extent status tree shrinker */ - ext4_es_register_shrinker(sb); - /* * set up enough so that it can read an inode */ @@ -3911,6 +3978,13 @@ no_journal: "available"); } + err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi)); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for " + "reserved pool", ext4_calculate_resv_clusters(sbi)); + goto failed_mount4a; + } + err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " @@ -4010,6 +4084,7 @@ failed_mount_wq: sbi->s_journal = NULL; } failed_mount3: + ext4_es_unregister_shrinker(sb); del_timer(&sbi->s_err_report); if (sbi->s_flex_groups) ext4_kvfree(sbi->s_flex_groups); @@ -4177,7 +4252,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, goto out_bdev; } journal->j_private = sb; - ll_rw_block(READ, 1, &journal->j_sb_buffer); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &journal->j_sb_buffer); wait_on_buffer(journal->j_sb_buffer); if (!buffer_uptodate(journal->j_sb_buffer)) { ext4_msg(sb, KERN_ERR, "I/O error on journal device"); @@ -4742,9 +4817,10 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; - ext4_fsblk_t overhead = 0; + ext4_fsblk_t overhead = 0, resv_blocks; u64 fsid; s64 bfree; + resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters)); if (!test_opt(sb, MINIX_DF)) overhead = sbi->s_overhead; @@ -4756,8 +4832,9 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0)); - buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); - if (buf->f_bfree < ext4_r_blocks_count(es)) + buf->f_bavail = buf->f_bfree - + (ext4_r_blocks_count(es) + resv_blocks); + if (buf->f_bfree < (ext4_r_blocks_count(es) + resv_blocks)) buf->f_bavail = 0; buf->f_files = le32_to_cpu(es->s_inodes_count); buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); @@ -4945,6 +5022,8 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, return PTR_ERR(qf_inode); } + /* Don't account quota for quota files to avoid recursion */ + qf_inode->i_flags |= S_NOQUOTA; err = dquot_enable(qf_inode, type, format_id, flags); iput(qf_inode); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 3a120b277240..c081e34f717f 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -122,17 +122,18 @@ static __le32 ext4_xattr_block_csum(struct inode *inode, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - __u32 csum, old; + __u32 csum; + __le32 save_csum; + __le64 dsk_block_nr = cpu_to_le64(block_nr); - old = hdr->h_checksum; + save_csum = hdr->h_checksum; hdr->h_checksum = 0; - block_nr = cpu_to_le64(block_nr); - csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr, - sizeof(block_nr)); + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr, + sizeof(dsk_block_nr)); csum = ext4_chksum(sbi, csum, (__u8 *)hdr, EXT4_BLOCK_SIZE(inode->i_sb)); - hdr->h_checksum = old; + hdr->h_checksum = save_csum; return cpu_to_le32(csum); } diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index aa25deb5c6cd..c767dbdd7fc4 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -22,6 +22,7 @@ #define EXT4_XATTR_INDEX_LUSTRE 5 #define EXT4_XATTR_INDEX_SECURITY 6 #define EXT4_XATTR_INDEX_SYSTEM 7 +#define EXT4_XATTR_INDEX_RICHACL 8 struct ext4_xattr_header { __le32 h_magic; /* magic number for identification */ diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 750c70148eff..0f53946f13c1 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -382,7 +382,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) int space_left = 0; int first_tag = 0; int tag_flag; - int i, to_free = 0; + int i; int tag_bytes = journal_tag_bytes(journal); struct buffer_head *cbh = NULL; /* For transactional checksums */ __u32 crc32_sum = ~0; @@ -1134,7 +1134,7 @@ restart_loop: journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged; spin_unlock(&journal->j_history_lock); - commit_transaction->t_state = T_FINISHED; + commit_transaction->t_state = T_COMMIT_CALLBACK; J_ASSERT(commit_transaction == journal->j_committing_transaction); journal->j_commit_sequence = commit_transaction->t_tid; journal->j_committing_transaction = NULL; @@ -1149,38 +1149,44 @@ restart_loop: journal->j_average_commit_time*3) / 4; else journal->j_average_commit_time = commit_time; + write_unlock(&journal->j_state_lock); - if (commit_transaction->t_checkpoint_list == NULL && - commit_transaction->t_checkpoint_io_list == NULL) { - __jbd2_journal_drop_transaction(journal, commit_transaction); - to_free = 1; + if (journal->j_checkpoint_transactions == NULL) { + journal->j_checkpoint_transactions = commit_transaction; + commit_transaction->t_cpnext = commit_transaction; + commit_transaction->t_cpprev = commit_transaction; } else { - if (journal->j_checkpoint_transactions == NULL) { - journal->j_checkpoint_transactions = commit_transaction; - commit_transaction->t_cpnext = commit_transaction; - commit_transaction->t_cpprev = commit_transaction; - } else { - commit_transaction->t_cpnext = - journal->j_checkpoint_transactions; - commit_transaction->t_cpprev = - commit_transaction->t_cpnext->t_cpprev; - commit_transaction->t_cpnext->t_cpprev = + commit_transaction->t_cpnext = + journal->j_checkpoint_transactions; + commit_transaction->t_cpprev = + commit_transaction->t_cpnext->t_cpprev; + commit_transaction->t_cpnext->t_cpprev = + commit_transaction; + commit_transaction->t_cpprev->t_cpnext = commit_transaction; - commit_transaction->t_cpprev->t_cpnext = - commit_transaction; - } } spin_unlock(&journal->j_list_lock); - + /* Drop all spin_locks because commit_callback may be block. + * __journal_remove_checkpoint() can not destroy transaction + * under us because it is not marked as T_FINISHED yet */ if (journal->j_commit_callback) journal->j_commit_callback(journal, commit_transaction); trace_jbd2_end_commit(journal, commit_transaction); jbd_debug(1, "JBD2: commit %d complete, head %d\n", journal->j_commit_sequence, journal->j_tail_sequence); - if (to_free) - jbd2_journal_free_transaction(commit_transaction); + write_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + commit_transaction->t_state = T_FINISHED; + /* Recheck checkpoint lists after j_list_lock was dropped */ + if (commit_transaction->t_checkpoint_list == NULL && + commit_transaction->t_checkpoint_io_list == NULL) { + __jbd2_journal_drop_transaction(journal, commit_transaction); + jbd2_journal_free_transaction(commit_transaction); + } + spin_unlock(&journal->j_list_lock); + write_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_done_commit); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 8b220f1ab54f..f6c5ba027f4f 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -707,6 +707,37 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) return err; } +/* + * When this function returns the transaction corresponding to tid + * will be completed. If the transaction has currently running, start + * committing that transaction before waiting for it to complete. If + * the transaction id is stale, it is by definition already completed, + * so just return SUCCESS. + */ +int jbd2_complete_transaction(journal_t *journal, tid_t tid) +{ + int need_to_wait = 1; + + read_lock(&journal->j_state_lock); + if (journal->j_running_transaction && + journal->j_running_transaction->t_tid == tid) { + if (journal->j_commit_request != tid) { + /* transaction not yet started, so request it */ + read_unlock(&journal->j_state_lock); + jbd2_log_start_commit(journal, tid); + goto wait_commit; + } + } else if (!(journal->j_committing_transaction && + journal->j_committing_transaction->t_tid == tid)) + need_to_wait = 0; + read_unlock(&journal->j_state_lock); + if (!need_to_wait) + return 0; +wait_commit: + return jbd2_log_wait_commit(journal, tid); +} +EXPORT_SYMBOL(jbd2_complete_transaction); + /* * Log buffer allocation routines: */ diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 325bc019ed88..10f524c59ea8 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -332,7 +332,6 @@ static handle_t *new_handle(int nblocks) handle_t *handle = jbd2_alloc_handle(GFP_NOFS); if (!handle) return NULL; - memset(handle, 0, sizeof(*handle)); handle->h_buffer_credits = nblocks; handle->h_ref = 1; @@ -640,6 +639,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, int error; char *frozen_buffer = NULL; int need_copy = 0; + unsigned long start_lock, time_lock; if (is_handle_aborted(handle)) return -EROFS; @@ -655,9 +655,16 @@ repeat: /* @@@ Need to check for errors here at some point. */ + start_lock = jiffies; lock_buffer(bh); jbd_lock_bh_state(bh); + /* If it takes too long to lock the buffer, trace it */ + time_lock = jbd2_time_diff(start_lock, jiffies); + if (time_lock > HZ/10) + trace_jbd2_lock_buffer_stall(bh->b_bdev->bd_dev, + jiffies_to_msecs(time_lock)); + /* We now hold the buffer lock so it is safe to query the buffer * state. Is the buffer dirty? * diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 4c16c4a88d47..9e52b0626b39 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -34,6 +34,8 @@ enum bh_state_bits { BH_Write_EIO, /* I/O error on write */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ + BH_Meta, /* Buffer contains metadata */ + BH_Prio, /* Buffer should be submitted with REQ_PRIO */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities @@ -124,6 +126,8 @@ BUFFER_FNS(Delay, delay) BUFFER_FNS(Boundary, boundary) BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) +BUFFER_FNS(Meta, meta) +BUFFER_FNS(Prio, prio) #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 50e5a5e6a712..6e051f472edb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -480,6 +480,7 @@ struct transaction_s T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, + T_COMMIT_CALLBACK, T_FINISHED } t_state; @@ -1144,7 +1145,7 @@ extern struct kmem_cache *jbd2_handle_cache; static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) { - return kmem_cache_alloc(jbd2_handle_cache, gfp_flags); + return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); } static inline void jbd2_free_handle(handle_t *handle) @@ -1200,6 +1201,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_journal_force_commit_nested(journal_t *journal); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); +int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h index c18b46f8aeeb..13a3da25ff07 100644 --- a/include/linux/journal-head.h +++ b/include/linux/journal-head.h @@ -31,21 +31,14 @@ struct journal_head { /* * Journalling list for this buffer [jbd_lock_bh_state()] */ - unsigned b_jlist; + unsigned b_jlist:4; /* * This flag signals the buffer has been modified by * the currently running transaction * [jbd_lock_bh_state()] */ - unsigned b_modified; - - /* - * This feild tracks the last transaction id in which this buffer - * has been cowed - * [jbd_lock_bh_state()] - */ - tid_t b_cow_tid; + unsigned b_modified:1; /* * Copy of the buffer data frozen for writing to the log. diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 4ee471003859..d0e686402df8 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -257,15 +257,7 @@ DECLARE_EVENT_CLASS(ext4__write_end, __entry->pos, __entry->len, __entry->copied) ); -DEFINE_EVENT(ext4__write_end, ext4_ordered_write_end, - - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int copied), - - TP_ARGS(inode, pos, len, copied) -); - -DEFINE_EVENT(ext4__write_end, ext4_writeback_write_end, +DEFINE_EVENT(ext4__write_end, ext4_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), @@ -1956,7 +1948,7 @@ TRACE_EVENT(ext4_remove_blocks, __entry->to = to; __entry->partial = partial_cluster; __entry->ee_pblk = ext4_ext_pblock(ex); - __entry->ee_lblk = cpu_to_le32(ex->ee_block); + __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_len = ext4_ext_get_actual_len(ex); ), @@ -2060,7 +2052,7 @@ TRACE_EVENT(ext4_ext_remove_space, TRACE_EVENT(ext4_ext_remove_space_done, TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth, - ext4_lblk_t partial, unsigned short eh_entries), + ext4_lblk_t partial, __le16 eh_entries), TP_ARGS(inode, start, depth, partial, eh_entries), @@ -2079,7 +2071,7 @@ TRACE_EVENT(ext4_ext_remove_space_done, __entry->start = start; __entry->depth = depth; __entry->partial = partial; - __entry->eh_entries = eh_entries; + __entry->eh_entries = le16_to_cpu(eh_entries); ), TP_printk("dev %d,%d ino %lu since %u depth %d partial %u " diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index 070df49e4a1d..c1d1f3eb242d 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -358,6 +358,27 @@ TRACE_EVENT(jbd2_write_superblock, MINOR(__entry->dev), __entry->write_op) ); +TRACE_EVENT(jbd2_lock_buffer_stall, + + TP_PROTO(dev_t dev, unsigned long stall_ms), + + TP_ARGS(dev, stall_ms), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field(unsigned long, stall_ms ) + ), + + TP_fast_assign( + __entry->dev = dev; + __entry->stall_ms = stall_ms; + ), + + TP_printk("dev %d,%d stall_ms %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->stall_ms) +); + #endif /* _TRACE_JBD2_H */ /* This part must be outside protection */