diff options
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/balloc.c | 65 | ||||
-rw-r--r-- | fs/ext4/bitmap.c | 18 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 26 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.c | 8 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.h | 25 | ||||
-rw-r--r-- | fs/ext4/extents.c | 52 | ||||
-rw-r--r-- | fs/ext4/file.c | 121 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 5 | ||||
-rw-r--r-- | fs/ext4/inode.c | 151 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 26 | ||||
-rw-r--r-- | fs/ext4/mmp.c | 6 | ||||
-rw-r--r-- | fs/ext4/namei.c | 15 | ||||
-rw-r--r-- | fs/ext4/resize.c | 7 | ||||
-rw-r--r-- | fs/ext4/super.c | 371 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 11 |
15 files changed, 630 insertions, 277 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index cee7812..1b50890 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -280,14 +280,18 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } -static int ext4_valid_block_bitmap(struct super_block *sb, - struct ext4_group_desc *desc, - unsigned int block_group, - struct buffer_head *bh) +/* + * Return the block number which was discovered to be invalid, or 0 if + * the block bitmap is valid. + */ +static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) { ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; - ext4_fsblk_t bitmap_blk; + ext4_fsblk_t blk; ext4_fsblk_t group_first_block; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { @@ -297,37 +301,33 @@ static int ext4_valid_block_bitmap(struct super_block *sb, * or it has to also read the block group where the bitmaps * are located to verify they are set. */ - return 1; + return 0; } group_first_block = ext4_group_first_block_no(sb, block_group); /* check whether block bitmap block number is set */ - bitmap_blk = ext4_block_bitmap(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_block_bitmap(sb, desc); + offset = blk - group_first_block; if (!ext4_test_bit(offset, bh->b_data)) /* bad block bitmap */ - goto err_out; + return blk; /* check whether the inode bitmap block number is set */ - bitmap_blk = ext4_inode_bitmap(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_inode_bitmap(sb, desc); + offset = blk - group_first_block; if (!ext4_test_bit(offset, bh->b_data)) /* bad block bitmap */ - goto err_out; + return blk; /* check whether the inode table block number is set */ - bitmap_blk = ext4_inode_table(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_inode_table(sb, desc); + offset = blk - group_first_block; next_zero_bit = ext4_find_next_zero_bit(bh->b_data, offset + EXT4_SB(sb)->s_itb_per_group, offset); - if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group) - /* good bitmap for inode tables */ - return 1; - -err_out: - ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu", - block_group, bitmap_blk); + if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group) + /* bad bitmap for inode tables */ + return blk; return 0; } @@ -336,14 +336,26 @@ void ext4_validate_block_bitmap(struct super_block *sb, unsigned int block_group, struct buffer_head *bh) { + ext4_fsblk_t blk; + if (buffer_verified(bh)) return; ext4_lock_group(sb, block_group); - if (ext4_valid_block_bitmap(sb, desc, block_group, bh) && - ext4_block_bitmap_csum_verify(sb, block_group, desc, bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8)) - set_buffer_verified(bh); + blk = ext4_valid_block_bitmap(sb, desc, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: invalid block bitmap", + block_group, blk); + return; + } + if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, + desc, bh, EXT4_BLOCKS_PER_GROUP(sb) / 8))) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); + return; + } + set_buffer_verified(bh); ext4_unlock_group(sb, block_group); } @@ -609,7 +621,8 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) if (bitmap_bh == NULL) continue; - x = ext4_count_free(bitmap_bh, sb->s_blocksize); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_BLOCKS_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n", i, ext4_free_group_clusters(sb, gdp), x); bitmap_count += x; diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index b319721..5c2d181 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -11,24 +11,11 @@ #include <linux/jbd2.h> #include "ext4.h" -#ifdef EXT4FS_DEBUG - -static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0}; - -unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars) +unsigned int ext4_count_free(char *bitmap, unsigned int numchars) { - unsigned int i, sum = 0; - - if (!map) - return 0; - for (i = 0; i < numchars; i++) - sum += nibblemap[map->b_data[i] & 0xf] + - nibblemap[(map->b_data[i] >> 4) & 0xf]; - return sum; + return numchars * BITS_PER_BYTE - memweight(bitmap, numchars); } -#endif /* EXT4FS_DEBUG */ - int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz) @@ -92,7 +79,6 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, if (provided == calculated) return 1; - ext4_error(sb, "Bad block bitmap checksum: block_group = %u", group); return 0; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cfc4e01..c3411d4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -571,6 +571,8 @@ enum { #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Request will not result in inode size update (user for fallocate) */ #define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 + /* Do not take i_data_sem locking in ext4_map_blocks */ +#define EXT4_GET_BLOCKS_NO_LOCK 0x0100 /* * Flags used by ext4_free_blocks @@ -1161,8 +1163,7 @@ struct ext4_sb_info { unsigned long s_desc_per_block; /* Number of group descriptors per block */ ext4_group_t s_groups_count; /* Number of groups in the fs */ ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */ - unsigned long s_overhead_last; /* Last calculated overhead */ - unsigned long s_blocks_last; /* Last seen block count */ + unsigned long s_overhead; /* # of fs overhead clusters */ unsigned int s_cluster_ratio; /* Number of blocks per cluster */ unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */ loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ @@ -1314,6 +1315,8 @@ static inline struct timespec ext4_current_time(struct inode *inode) 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_JOURNAL_INO || ino == EXT4_RESIZE_INO || (ino >= EXT4_FIRST_INO(sb) && @@ -1496,7 +1499,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ + EXT4_FEATURE_RO_COMPAT_QUOTA) /* * Default values for user and/or group using reserved blocks @@ -1663,10 +1667,12 @@ static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, { struct { struct shash_desc shash; - char ctx[crypto_shash_descsize(sbi->s_chksum_driver)]; + char ctx[4]; } desc; int err; + BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); + desc.shash.tfm = sbi->s_chksum_driver; desc.shash.flags = 0; *(u32 *)desc.ctx = crc; @@ -1852,7 +1858,7 @@ struct mmpd_data { # define NORET_AND noreturn, /* bitmap.c */ -extern unsigned int ext4_count_free(struct buffer_head *, unsigned); +extern unsigned int ext4_count_free(char *bitmap, unsigned numchars); void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz); @@ -2037,6 +2043,7 @@ extern int ext4_group_extend(struct super_block *sb, extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); /* super.c */ +extern int ext4_calculate_overhead(struct super_block *sb); extern int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es); extern void ext4_superblock_csum_set(struct super_block *sb, @@ -2321,15 +2328,6 @@ static inline void ext4_unlock_group(struct super_block *sb, spin_unlock(ext4_group_lock_ptr(sb, group)); } -static inline void ext4_mark_super_dirty(struct super_block *sb) -{ - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - - ext4_superblock_csum_set(sb, es); - if (EXT4_SB(sb)->s_journal == NULL) - sb->s_dirt =1; -} - /* * Block validity checking */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 90f7c2e..bfa65b4 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -138,8 +138,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, } int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb, - int now) + handle_t *handle, struct super_block *sb) { struct buffer_head *bh = EXT4_SB(sb)->s_sbh; int err = 0; @@ -151,11 +150,10 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, if (err) ext4_journal_abort_handle(where, line, __func__, bh, handle, err); - } else if (now) { + } else { ext4_superblock_csum_set(sb, (struct ext4_super_block *)bh->b_data); mark_buffer_dirty(bh); - } else - sb->s_dirt = 1; + } return err; } diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index f440e8f1..56d258c 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -87,14 +87,20 @@ #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ -#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0) +#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ -#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0) - -#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0) +#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ + +3+DQUOT_INIT_REWRITE) : 0) + +#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ + +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 @@ -213,8 +219,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, struct buffer_head *bh); int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb, - int now); + handle_t *handle, struct super_block *sb); #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) @@ -226,10 +231,8 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) -#define ext4_handle_dirty_super_now(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 1) #define ext4_handle_dirty_super(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 0) + __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 91341ec..aabbb3f 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1891,11 +1891,10 @@ has_space: nearex->ee_len = newext->ee_len; merge: - /* try to merge extents to the right */ + /* try to merge extents */ if (!(flag & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(inode, path, nearex); - /* try to merge extents to the left */ /* time to correct all indexes above */ err = ext4_ext_correct_indexes(handle, inode, path); @@ -2570,10 +2569,10 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, { struct super_block *sb = inode->i_sb; int depth = ext_depth(inode); - struct ext4_ext_path *path; + struct ext4_ext_path *path = NULL; ext4_fsblk_t partial_cluster = 0; handle_t *handle; - int i, err; + int i = 0, err; ext_debug("truncate since %u to %u\n", start, end); @@ -2606,8 +2605,12 @@ again: } depth = ext_depth(inode); ex = path[depth].p_ext; - if (!ex) + if (!ex) { + ext4_ext_drop_refs(path); + kfree(path); + path = NULL; goto cont; + } ee_block = le32_to_cpu(ex->ee_block); @@ -2637,8 +2640,6 @@ again: if (err < 0) goto out; } - ext4_ext_drop_refs(path); - kfree(path); } cont: @@ -2647,19 +2648,28 @@ cont: * after i_size and walking into the tree depth-wise. */ depth = ext_depth(inode); - path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS); - if (path == NULL) { - ext4_journal_stop(handle); - return -ENOMEM; - } - path[0].p_depth = depth; - path[0].p_hdr = ext_inode_hdr(inode); + if (path) { + int k = i = depth; + while (--k > 0) + path[k].p_block = + le16_to_cpu(path[k].p_hdr->eh_entries)+1; + } else { + path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), + GFP_NOFS); + if (path == NULL) { + ext4_journal_stop(handle); + return -ENOMEM; + } + path[0].p_depth = depth; + path[0].p_hdr = ext_inode_hdr(inode); + i = 0; - if (ext4_ext_check(inode, path[0].p_hdr, depth)) { - err = -EIO; - goto out; + if (ext4_ext_check(inode, path[0].p_hdr, depth)) { + err = -EIO; + goto out; + } } - i = err = 0; + err = 0; while (i >= 0 && err == 0) { if (i == depth) { @@ -2773,8 +2783,10 @@ cont: out: ext4_ext_drop_refs(path); kfree(path); - if (err == -EAGAIN) + if (err == -EAGAIN) { + path = NULL; goto again; + } ext4_journal_stop(handle); return err; @@ -4420,6 +4432,8 @@ retry: ext4_falloc_update_inode(inode, mode, new_size, (map.m_flags & EXT4_MAP_NEW)); ext4_mark_inode_dirty(handle, inode); + if ((file->f_flags & O_SYNC) && ret >= max_blocks) + ext4_handle_sync(handle); ret2 = ext4_journal_stop(handle); if (ret2) break; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 782eecb..3b0e3bd 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -90,11 +90,91 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov, } static ssize_t +ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + struct blk_plug plug; + int unaligned_aio = 0; + ssize_t ret; + int overwrite = 0; + size_t length = iov_length(iov, nr_segs); + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && + !is_sync_kiocb(iocb)) + unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos); + + /* Unaligned direct AIO must be serialized; see comment above */ + if (unaligned_aio) { + static unsigned long unaligned_warn_time; + + /* Warn about this once per day */ + if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ)) + ext4_msg(inode->i_sb, KERN_WARNING, + "Unaligned AIO/DIO on inode %ld by %s; " + "performance will be poor.", + inode->i_ino, current->comm); + mutex_lock(ext4_aio_mutex(inode)); + ext4_aiodio_wait(inode); + } + + BUG_ON(iocb->ki_pos != pos); + + mutex_lock(&inode->i_mutex); + blk_start_plug(&plug); + + iocb->private = &overwrite; + + /* check whether we do a DIO overwrite or not */ + if (ext4_should_dioread_nolock(inode) && !unaligned_aio && + !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) { + struct ext4_map_blocks map; + unsigned int blkbits = inode->i_blkbits; + int err, len; + + map.m_lblk = pos >> blkbits; + map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits) + - map.m_lblk; + len = map.m_len; + + err = ext4_map_blocks(NULL, inode, &map, 0); + /* + * 'err==len' means that all of blocks has been preallocated no + * matter they are initialized or not. For excluding + * uninitialized extents, we need to check m_flags. There are + * two conditions that indicate for initialized extents. + * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned; + * 2) If we do a real lookup, non-flags are returned. + * So we should check these two conditions. + */ + if (err == len && (map.m_flags & EXT4_MAP_MAPPED)) + overwrite = 1; + } + + ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + mutex_unlock(&inode->i_mutex); + + if (ret > 0 || ret == -EIOCBQUEUED) { + ssize_t err; + + err = generic_write_sync(file, pos, ret); + if (err < 0 && ret > 0) + ret = err; + } + blk_finish_plug(&plug); + + if (unaligned_aio) + mutex_unlock(ext4_aio_mutex(inode)); + + return ret; +} + +static ssize_t ext4_file_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; - int unaligned_aio = 0; ssize_t ret; /* @@ -114,29 +194,12 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, nr_segs = iov_shorten((struct iovec *)iov, nr_segs, sbi->s_bitmap_maxbytes - pos); } - } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) && - !is_sync_kiocb(iocb))) { - unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos); } - /* Unaligned direct AIO must be serialized; see comment above */ - if (unaligned_aio) { - static unsigned long unaligned_warn_time; - - /* Warn about this once per day */ - if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ)) - ext4_msg(inode->i_sb, KERN_WARNING, - "Unaligned AIO/DIO on inode %ld by %s; " - "performance will be poor.", - inode->i_ino, current->comm); - mutex_lock(ext4_aio_mutex(inode)); - ext4_aiodio_wait(inode); - } - - ret = generic_file_aio_write(iocb, iov, nr_segs, pos); - - if (unaligned_aio) - mutex_unlock(ext4_aio_mutex(inode)); + if (unlikely(iocb->ki_filp->f_flags & O_DIRECT)) + ret = ext4_file_dio_write(iocb, iov, nr_segs, pos); + else + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); return ret; } @@ -181,9 +244,21 @@ static int ext4_file_open(struct inode * inode, struct file * filp) path.dentry = mnt->mnt_root; cp = d_path(&path, buf, sizeof(buf)); if (!IS_ERR(cp)) { + handle_t *handle; + int err; + + handle = ext4_journal_start_sb(sb, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) { + ext4_journal_stop(handle); + return err; + } strlcpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); - ext4_mark_super_dirty(sb); + ext4_handle_dirty_super(handle, sb); + ext4_journal_stop(handle); } } /* diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index d48e8b1..26154b8 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -315,7 +315,6 @@ out: err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!fatal) fatal = err; - ext4_mark_super_dirty(sb); } else ext4_error(sb, "bit already cleared for inode %lu", ino); @@ -830,7 +829,6 @@ got: percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); - ext4_mark_super_dirty(sb); if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); @@ -1054,7 +1052,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) if (!bitmap_bh) continue; - x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 189dae6..c862ee5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -233,6 +233,11 @@ void ext4_evict_inode(struct inode *inode) if (is_bad_inode(inode)) goto no_delete; + /* + * Protect us against freezing - iput() caller didn't have to have any + * protection against it + */ + sb_start_intwrite(inode->i_sb); handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); @@ -242,6 +247,7 @@ void ext4_evict_inode(struct inode *inode) * cleaned up. */ ext4_orphan_del(NULL, inode); + sb_end_intwrite(inode->i_sb); goto no_delete; } @@ -273,6 +279,7 @@ void ext4_evict_inode(struct inode *inode) stop_handle: ext4_journal_stop(handle); ext4_orphan_del(NULL, inode); + sb_end_intwrite(inode->i_sb); goto no_delete; } } @@ -301,6 +308,7 @@ void ext4_evict_inode(struct inode *inode) else ext4_free_inode(handle, inode); ext4_journal_stop(handle); + sb_end_intwrite(inode->i_sb); return; no_delete: ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ @@ -346,6 +354,15 @@ void ext4_da_update_reserve_space(struct inode *inode, used = ei->i_reserved_data_blocks; } + if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) { + ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d " + "with only %d reserved metadata blocks\n", __func__, + inode->i_ino, ei->i_allocated_meta_blocks, + ei->i_reserved_meta_blocks); + WARN_ON(1); + ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks; + } + /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks; @@ -544,7 +561,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, * Try to see if we can get the block without requesting a new * file system block. */ - down_read((&EXT4_I(inode)->i_data_sem)); + if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) + down_read((&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); @@ -552,7 +570,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } - up_read((&EXT4_I(inode)->i_data_sem)); + if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) + up_read((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { int ret = check_block_validity(inode, map); @@ -1171,6 +1190,17 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; int ret; + ext4_lblk_t save_last_lblock; + int save_len; + + /* + * We will charge metadata quota at writeout time; this saves + * us from metadata over-estimation, though we may go over by + * a small amount in the end. Here we just reserve for data. + */ + ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); + if (ret) + return ret; /* * recalculate the amount of metadata blocks to reserve @@ -1179,32 +1209,31 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) */ repeat: spin_lock(&ei->i_block_reservation_lock); + /* + * ext4_calc_metadata_amount() has side effects, which we have + * to be prepared undo if we fail to claim space. + */ + save_len = ei->i_da_metadata_calc_len; + save_last_lblock = ei->i_da_metadata_calc_last_lblock; md_needed = EXT4_NUM_B2C(sbi, ext4_calc_metadata_amount(inode, lblock)); trace_ext4_da_reserve_space(inode, md_needed); - spin_unlock(&ei->i_block_reservation_lock); /* - * We will charge metadata quota at writeout time; this saves - * us from metadata over-estimation, though we may go over by - * a small amount in the end. Here we just reserve for data. - */ - ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); - if (ret) - return ret; - /* * We do still charge estimated metadata to the sb though; * we cannot afford to run out of free blocks. */ if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) { - dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); + ei->i_da_metadata_calc_len = save_len; + ei->i_da_metadata_calc_last_lblock = save_last_lblock; + spin_unlock(&ei->i_block_reservation_lock); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { yield(); goto repeat; } + dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); return -ENOSPC; } - spin_lock(&ei->i_block_reservation_lock); ei->i_reserved_data_blocks++; ei->i_reserved_meta_blocks += md_needed; spin_unlock(&ei->i_block_reservation_lock); @@ -1941,7 +1970,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); * This function can get called via... * - ext4_da_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) - * - shrink_page_list via pdflush (no journal handle) + * - shrink_page_list via the kswapd/direct reclaim (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) * * We don't do any block allocation in this function. If we have page with @@ -2818,6 +2847,32 @@ static int ext4_get_block_write(struct inode *inode, sector_t iblock, EXT4_GET_BLOCKS_IO_CREATE_EXT); } +static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int flags) +{ + handle_t *handle = ext4_journal_current_handle(); + struct ext4_map_blocks map; + int ret = 0; + + ext4_debug("ext4_get_block_write_nolock: inode %lu, flag %d\n", + inode->i_ino, flags); + + flags = EXT4_GET_BLOCKS_NO_LOCK; + + map.m_lblk = iblock; + map.m_len = bh_result->b_size >> inode->i_blkbits; + + ret = ext4_map_blocks(handle, inode, &map, flags); + if (ret > 0) { + map_bh(bh_result, inode->i_sb, map.m_pblk); + bh_result->b_state = (bh_result->b_state & ~EXT4_MAP_FLAGS) | + map.m_flags; + bh_result->b_size = inode->i_sb->s_blocksize * map.m_len; + ret = 0; + } + return ret; +} + static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private, int ret, bool is_async) @@ -2966,6 +3021,18 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, loff_t final_size = offset + count; if (rw == WRITE && final_size <= inode->i_size) { + int overwrite = 0; + + BUG_ON(iocb->private == NULL); + + /* If we do a overwrite dio, i_mutex locking can be released */ + overwrite = *((int *)iocb->private); + + if (overwrite) { + down_read(&EXT4_I(inode)->i_data_sem); + mutex_unlock(&inode->i_mutex); + } + /* * We could direct write to holes and fallocate. * @@ -2991,8 +3058,10 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, if (!is_sync_kiocb(iocb)) { ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) - return -ENOMEM; + if (!io_end) { + ret = -ENOMEM; + goto retake_lock; + } io_end->flag |= EXT4_IO_END_DIRECT; iocb->private = io_end; /* @@ -3005,13 +3074,22 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, EXT4_I(inode)->cur_aio_dio = iocb->private; } - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext4_get_block_write, - ext4_end_io_dio, - NULL, - DIO_LOCKING); + if (overwrite) + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iov, + offset, nr_segs, + ext4_get_block_write_nolock, + ext4_end_io_dio, + NULL, + 0); + else + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iov, + offset, nr_segs, + ext4_get_block_write, + ext4_end_io_dio, + NULL, + DIO_LOCKING); if (iocb->private) EXT4_I(inode)->cur_aio_dio = NULL; /* @@ -3031,7 +3109,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) { ext4_free_io_end(iocb->private); iocb->private = NULL; - } else if (ret > 0 && ext4_test_inode_state(inode, + } else if (ret > 0 && !overwrite && ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN)) { int err; /* @@ -3044,6 +3122,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, ret = err; ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); } + + retake_lock: + /* take i_mutex locking again if we do a ovewrite dio */ + if (overwrite) { + up_read(&EXT4_I(inode)->i_data_sem); + mutex_lock(&inode->i_mutex); + } + return ret; } @@ -4034,7 +4120,7 @@ static int ext4_do_update_inode(handle_t *handle, EXT4_SET_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_LARGE_FILE); ext4_handle_sync(handle); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); } } raw_inode->i_generation = cpu_to_le32(inode->i_generation); @@ -4503,14 +4589,6 @@ static int ext4_expand_extra_isize(struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) { @@ -4701,11 +4779,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) get_block_t *get_block; int retries = 0; - /* - * This check is racy but catches the common case. We rely on - * __block_page_mkwrite() to do a reliable check. - */ - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); + sb_start_pagefault(inode->i_sb); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && @@ -4773,5 +4847,6 @@ retry_alloc: out_ret: ret = block_page_mkwrite_return(ret); out: + sb_end_pagefault(inode->i_sb); return ret; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 8683141..08778f6 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -969,7 +969,6 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, block++; pnum = block / blocks_per_page; - poff = block % blocks_per_page; page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); if (!page) return -EIO; @@ -2077,8 +2076,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) struct super_block *sb = seq->private; ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; - int err; + int err, buddy_loaded = 0; struct ext4_buddy e4b; + struct ext4_group_info *grinfo; struct sg { struct ext4_group_info info; ext4_grpblk_t counters[16]; @@ -2095,15 +2095,21 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); - err = ext4_mb_load_buddy(sb, group, &e4b); - if (err) { - seq_printf(seq, "#%-5u: I/O error\n", group); - return 0; + grinfo = ext4_get_group_info(sb, group); + /* Load the group info in memory only if not already loaded. */ + if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { + err = ext4_mb_load_buddy(sb, group, &e4b); + if (err) { + seq_printf(seq, "#%-5u: I/O error\n", group); + return 0; + } + buddy_loaded = 1; } - ext4_lock_group(sb, group); + memcpy(&sg, ext4_get_group_info(sb, group), i); - ext4_unlock_group(sb, group); - ext4_mb_unload_buddy(&e4b); + + if (buddy_loaded) + ext4_mb_unload_buddy(&e4b); seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free, sg.info.bb_fragments, sg.info.bb_first_free); @@ -2825,7 +2831,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); out_err: - ext4_mark_super_dirty(sb); brelse(bitmap_bh); return err; } @@ -4694,7 +4699,6 @@ do_more: put_bh(bitmap_bh); goto do_more; } - ext4_mark_super_dirty(sb); error_return: brelse(bitmap_bh); ext4_std_error(sb, err); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index f99a131..fe7c63f 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -44,6 +44,11 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) { struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); + /* + * We protect against freezing so that we don't create dirty buffers + * on frozen filesystem. + */ + sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); mark_buffer_dirty(bh); lock_buffer(bh); @@ -51,6 +56,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) get_bh(bh); submit_bh(WRITE_SYNC, bh); wait_on_buffer(bh); + sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) return 1; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d0d3f0e..2a42cc0 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2397,7 +2397,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) /* Insert this inode at the head of the on-disk orphan list... */ NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan); EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; @@ -2470,7 +2470,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) if (err) goto out_brelse; sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); - err = ext4_handle_dirty_super_now(handle, inode->i_sb); + err = ext4_handle_dirty_super(handle, inode->i_sb); } else { struct ext4_iloc iloc2; struct inode *i_prev = @@ -2918,8 +2918,15 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) = cpu_to_le32(new_dir->i_ino); BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata"); - retval = ext4_handle_dirty_dirent_node(handle, old_inode, - dir_bh); + if (is_dx(old_inode)) { + retval = ext4_handle_dirty_dx_node(handle, + old_inode, + dir_bh); + } else { + retval = ext4_handle_dirty_dirent_node(handle, + old_inode, + dir_bh); + } if (retval) { ext4_std_error(old_dir->i_sb, retval); goto end_rename; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 7ea6cbb..41f6ef6 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -798,7 +798,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, ext4_kvfree(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); if (err) ext4_std_error(sb, err); @@ -1272,6 +1272,11 @@ static void ext4_update_super(struct super_block *sb, &sbi->s_flex_groups[flex_group].free_inodes); } + /* + * Update the fs overhead information + */ + ext4_calculate_overhead(sb); + if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: added group %u:" "%llu blocks(%llu free %llu reserved)\n", flex_gd->count, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d875940..c6e0cb3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -74,7 +74,6 @@ static const char *ext4_decode_error(struct super_block *sb, int errno, static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); -static void ext4_write_super(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data); @@ -327,38 +326,17 @@ static void ext4_put_nojournal(handle_t *handle) /* * Wrappers for jbd2_journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - * - * To avoid j_barrier hold in userspace when a user calls freeze(), - * ext4 prevents a new handle from being started by s_frozen, which - * is in an upper layer. */ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) { journal_t *journal; - handle_t *handle; trace_ext4_journal_start(sb, nblocks, _RET_IP_); if (sb->s_flags & MS_RDONLY) return ERR_PTR(-EROFS); + WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); journal = EXT4_SB(sb)->s_journal; - handle = ext4_journal_current_handle(); - - /* - * If a handle has been started, it should be allowed to - * finish, otherwise deadlock could happen between freeze - * and others(e.g. truncate) due to the restart of the - * journal handle if the filesystem is forzen and active - * handles are not stopped. - */ - if (!handle) - vfs_check_frozen(sb, SB_FREEZE_TRANS); - if (!journal) return ext4_get_nojournal(); /* @@ -373,12 +351,6 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) return jbd2_journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * jbd2_journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) { struct super_block *sb; @@ -896,7 +868,7 @@ static void ext4_put_super(struct super_block *sb) EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); } - if (sb->s_dirt || !(sb->s_flags & MS_RDONLY)) + if (!(sb->s_flags & MS_RDONLY)) ext4_commit_super(sb, 1); if (sbi->s_proc) { @@ -976,6 +948,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_reserved_meta_blocks = 0; ei->i_allocated_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; + ei->i_da_metadata_calc_last_lblock = 0; spin_lock_init(&(ei->i_block_reservation_lock)); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; @@ -1137,12 +1110,18 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, struct path *path); +static int ext4_quota_on_sysfile(struct super_block *sb, int type, + int format_id); static int ext4_quota_off(struct super_block *sb, int type); +static int ext4_quota_off_sysfile(struct super_block *sb, int type); static int ext4_quota_on_mount(struct super_block *sb, int type); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); +static int ext4_quota_enable(struct super_block *sb, int type, int format_id, + unsigned int flags); +static int ext4_enable_quotas(struct super_block *sb); static const struct dquot_operations ext4_quota_operations = { .get_reserved_space = ext4_get_reserved_space, @@ -1164,6 +1143,16 @@ static const struct quotactl_ops ext4_qctl_operations = { .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk }; + +static const struct quotactl_ops ext4_qctl_sysfile_operations = { + .quota_on_meta = ext4_quota_on_sysfile, + .quota_off = ext4_quota_off_sysfile, + .quota_sync = dquot_quota_sync, + .get_info = dquot_get_dqinfo, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk +}; #endif static const struct super_operations ext4_sops = { @@ -1194,7 +1183,6 @@ static const struct super_operations ext4_nojournal_sops = { .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, - .write_super = ext4_write_super, .put_super = ext4_put_super, .statfs = ext4_statfs, .remount_fs = ext4_remount, @@ -2661,6 +2649,16 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) "extents feature\n"); return 0; } + +#ifndef CONFIG_QUOTA + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && + !readonly) { + ext4_msg(sb, KERN_ERR, + "Filesystem with quota feature cannot be mounted RDWR " + "without CONFIG_QUOTA"); + return 0; + } +#endif /* CONFIG_QUOTA */ return 1; } @@ -2723,6 +2721,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr) sb = elr->lr_super; ngroups = EXT4_SB(sb)->s_groups_count; + sb_start_write(sb); for (group = elr->lr_next_group; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { @@ -2749,6 +2748,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr) elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; } + sb_end_write(sb); return ret; } @@ -3085,6 +3085,118 @@ static int set_journal_csum_feature_set(struct super_block *sb) return ret; } +/* + * Note: calculating the overhead so we can be compatible with + * historical BSD practice is quite difficult in the face of + * clusters/bigalloc. This is because multiple metadata blocks from + * different block group can end up in the same allocation cluster. + * Calculating the exact overhead in the face of clustered allocation + * requires either O(all block bitmaps) in memory or O(number of block + * groups**2) in time. We will still calculate the superblock for + * older file systems --- and if we come across with a bigalloc file + * system with zero in s_overhead_clusters the estimate will be close to + * correct especially for very large cluster sizes --- but for newer + * file systems, it's better to calculate this figure once at mkfs + * time, and store it in the superblock. If the superblock value is + * present (even for non-bigalloc file systems), we will use it. + */ +static int count_overhead(struct super_block *sb, ext4_group_t grp, + char *buf) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp; + ext4_fsblk_t first_block, last_block, b; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + int s, j, count = 0; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) + return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + sbi->s_itb_per_group + 2); + + first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + + (grp * EXT4_BLOCKS_PER_GROUP(sb)); + last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; + for (i = 0; i < ngroups; i++) { + gdp = ext4_get_group_desc(sb, i, NULL); + b = ext4_block_bitmap(sb, gdp); + if (b >= first_block && b <= last_block) { + ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); + count++; + } + b = ext4_inode_bitmap(sb, gdp); + if (b >= first_block && b <= last_block) { + ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); + count++; + } + b = ext4_inode_table(sb, gdp); + if (b >= first_block && b + sbi->s_itb_per_group <= last_block) + for (j = 0; j < sbi->s_itb_per_group; j++, b++) { + int c = EXT4_B2C(sbi, b - first_block); + ext4_set_bit(c, buf); + count++; + } + if (i != grp) + continue; + s = 0; + if (ext4_bg_has_super(sb, grp)) { + ext4_set_bit(s++, buf); + count++; + } + for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) { + ext4_set_bit(EXT4_B2C(sbi, s++), buf); + count++; + } + } + if (!count) + return 0; + return EXT4_CLUSTERS_PER_GROUP(sb) - + ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8); +} + +/* + * Compute the overhead and stash it in sbi->s_overhead + */ +int ext4_calculate_overhead(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + ext4_fsblk_t overhead = 0; + char *buf = (char *) get_zeroed_page(GFP_KERNEL); + + memset(buf, 0, PAGE_SIZE); + if (!buf) + return -ENOMEM; + + /* + * Compute the overhead (FS structures). This is constant + * for a given filesystem unless the number of block groups + * changes so we cache the previous value until it does. + */ + + /* + * All of the blocks before first_data_block are overhead + */ + overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); + + /* + * Add the overhead found in each block group + */ + for (i = 0; i < ngroups; i++) { + int blks; + + blks = count_overhead(sb, i, buf); + overhead += blks; + if (blks) + memset(buf, 0, PAGE_SIZE); + cond_resched(); + } + sbi->s_overhead = overhead; + smp_wmb(); + free_page((unsigned long) buf); + return 0; +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) { char *orig_data = kstrdup(data, GFP_KERNEL); @@ -3640,6 +3752,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->s_qcop = &ext4_qctl_operations; sb->dq_op = &ext4_quota_operations; + + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { + /* Use qctl operations for hidden quota files. */ + sb->s_qcop = &ext4_qctl_sysfile_operations; + } #endif memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); @@ -3735,6 +3852,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) no_journal: /* + * Get the # of file system overhead blocks from the + * superblock if present. + */ + if (es->s_overhead_clusters) + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + else { + ret = ext4_calculate_overhead(sb); + if (ret) + goto failed_mount_wq; + } + + /* * The maximum number of concurrent works can be high and * concurrency isn't really necessary. Limit it to 1. */ @@ -3840,6 +3969,16 @@ no_journal: } else descr = "out journal"; +#ifdef CONFIG_QUOTA + /* Enable quota usage during mount. */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && + !(sb->s_flags & MS_RDONLY)) { + ret = ext4_enable_quotas(sb); + if (ret) + goto failed_mount7; + } +#endif /* CONFIG_QUOTA */ + ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts, *sbi->s_es->s_mount_opts ? "; " : "", orig_data); @@ -4203,7 +4342,6 @@ static int ext4_commit_super(struct super_block *sb, int sync) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &EXT4_SB(sb)->s_freeinodes_counter)); - sb->s_dirt = 0; BUFFER_TRACE(sbh, "marking dirty"); ext4_superblock_csum_set(sb, es); mark_buffer_dirty(sbh); @@ -4286,6 +4424,7 @@ static void ext4_clear_journal_err(struct super_block *sb, ext4_commit_super(sb, 1); jbd2_journal_clear_err(journal); + jbd2_journal_update_sb_errno(journal); } } @@ -4302,21 +4441,12 @@ int ext4_force_commit(struct super_block *sb) return 0; journal = EXT4_SB(sb)->s_journal; - if (journal) { - vfs_check_frozen(sb, SB_FREEZE_TRANS); + if (journal) ret = ext4_journal_force_commit(journal); - } return ret; } -static void ext4_write_super(struct super_block *sb) -{ - lock_super(sb); - ext4_commit_super(sb, 1); - unlock_super(sb); -} - static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; @@ -4342,9 +4472,8 @@ static int ext4_sync_fs(struct super_block *sb, int wait) * gives us a chance to flush the journal completely and mark the fs clean. * * Note that only this function cannot bring a filesystem to be in a clean - * state independently, because ext4 prevents a new handle from being started - * by @sb->s_frozen, which stays in an upper layer. It thus needs help from - * the upper layer. + * state independently. It relies on upper layer to stop all data & metadata + * modifications. */ static int ext4_freeze(struct super_block *sb) { @@ -4371,7 +4500,7 @@ static int ext4_freeze(struct super_block *sb) EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); error = ext4_commit_super(sb, 1); out: - /* we rely on s_frozen to stop further updates */ + /* we rely on upper layer to stop further updates */ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); return error; } @@ -4567,16 +4696,26 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal == NULL) ext4_commit_super(sb, 1); + unlock_super(sb); #ifdef CONFIG_QUOTA /* Release old quota file names */ for (i = 0; i < MAXQUOTAS; i++) if (old_opts.s_qf_names[i] && old_opts.s_qf_names[i] != sbi->s_qf_names[i]) kfree(old_opts.s_qf_names[i]); + if (enable_quota) { + if (sb_any_quota_suspended(sb)) + dquot_resume(sb, -1); + else if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_QUOTA)) { + err = ext4_enable_quotas(sb); + if (err) { + lock_super(sb); + goto restore_opts; + } + } + } #endif - unlock_super(sb); - if (enable_quota) - dquot_resume(sb, -1); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); @@ -4605,67 +4744,21 @@ restore_opts: return err; } -/* - * Note: calculating the overhead so we can be compatible with - * historical BSD practice is quite difficult in the face of - * clusters/bigalloc. This is because multiple metadata blocks from - * different block group can end up in the same allocation cluster. - * Calculating the exact overhead in the face of clustered allocation - * requires either O(all block bitmaps) in memory or O(number of block - * groups**2) in time. We will still calculate the superblock for - * older file systems --- and if we come across with a bigalloc file - * system with zero in s_overhead_clusters the estimate will be close to - * correct especially for very large cluster sizes --- but for newer - * file systems, it's better to calculate this figure once at mkfs - * time, and store it in the superblock. If the superblock value is - * present (even for non-bigalloc file systems), we will use it. - */ 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; - struct ext4_group_desc *gdp; + ext4_fsblk_t overhead = 0; u64 fsid; s64 bfree; - if (test_opt(sb, MINIX_DF)) { - sbi->s_overhead_last = 0; - } else if (es->s_overhead_clusters) { - sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters); - } else if (sbi->s_blocks_last != ext4_blocks_count(es)) { - ext4_group_t i, ngroups = ext4_get_groups_count(sb); - ext4_fsblk_t overhead = 0; - - /* - * Compute the overhead (FS structures). This is constant - * for a given filesystem unless the number of block groups - * changes so we cache the previous value until it does. - */ - - /* - * All of the blocks before first_data_block are - * overhead - */ - overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); - - /* - * Add the overhead found in each block group - */ - for (i = 0; i < ngroups; i++) { - gdp = ext4_get_group_desc(sb, i, NULL); - overhead += ext4_num_overhead_clusters(sb, i, gdp); - cond_resched(); - } - sbi->s_overhead_last = overhead; - smp_wmb(); - sbi->s_blocks_last = ext4_blocks_count(es); - } + if (!test_opt(sb, MINIX_DF)) + overhead = sbi->s_overhead; buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; - buf->f_blocks = (ext4_blocks_count(es) - - EXT4_C2B(sbi, sbi->s_overhead_last)); + buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, sbi->s_overhead); bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ @@ -4835,6 +4928,74 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, return dquot_quota_on(sb, type, format_id, path); } +static int ext4_quota_enable(struct super_block *sb, int type, int format_id, + unsigned int flags) +{ + int err; + struct inode *qf_inode; + unsigned long qf_inums[MAXQUOTAS] = { + le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) + }; + + BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)); + + if (!qf_inums[type]) + return -EPERM; + + qf_inode = ext4_iget(sb, qf_inums[type]); + if (IS_ERR(qf_inode)) { + ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]); + return PTR_ERR(qf_inode); + } + + err = dquot_enable(qf_inode, type, format_id, flags); + iput(qf_inode); + + return err; +} + +/* Enable usage tracking for all quota types. */ +static int ext4_enable_quotas(struct super_block *sb) +{ + int type, err = 0; + unsigned long qf_inums[MAXQUOTAS] = { + le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) + }; + + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; + for (type = 0; type < MAXQUOTAS; type++) { + if (qf_inums[type]) { + err = ext4_quota_enable(sb, type, QFMT_VFS_V1, + DQUOT_USAGE_ENABLED); + if (err) { + ext4_warning(sb, + "Failed to enable quota (type=%d) " + "tracking. Please run e2fsck to fix.", + type); + return err; + } + } + } + return 0; +} + +/* + * quota_on function that is used when QUOTA feature is set. + */ +static int ext4_quota_on_sysfile(struct super_block *sb, int type, + int format_id) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) + return -EINVAL; + + /* + * USAGE was enabled at mount time. Only need to enable LIMITS now. + */ + return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED); +} + static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; @@ -4861,6 +5022,18 @@ out: return dquot_quota_off(sb, type); } +/* + * quota_off function that is used when QUOTA feature is set. + */ +static int ext4_quota_off_sysfile(struct super_block *sb, int type) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) + return -EINVAL; + + /* Disable only the limits. */ + return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); +} + /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index e56c9ed..2cdb98d 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -127,19 +127,16 @@ static __le32 ext4_xattr_block_csum(struct inode *inode, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - struct ext4_inode_info *ei = EXT4_I(inode); __u32 csum, old; old = hdr->h_checksum; hdr->h_checksum = 0; - if (le32_to_cpu(hdr->h_refcount) != 1) { - block_nr = cpu_to_le64(block_nr); - csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr, - sizeof(block_nr)); - } else - csum = ei->i_csum_seed; + 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, csum, (__u8 *)hdr, EXT4_BLOCK_SIZE(inode->i_sb)); + hdr->h_checksum = old; return cpu_to_le32(csum); } |