/* * linux/fs/ext4/super.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "ext4.h" #include "ext4_extents.h" /* Needed for trace points definition */ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "mballoc.h" #define CREATE_TRACE_POINTS #include static struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; static struct ext4_lazy_init *ext4_li_info; static struct mutex ext4_li_mtx; static struct ext4_features *ext4_feat; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static int ext4_commit_super(struct super_block *sb, int sync); static void ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static void ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); 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 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); static inline int ext2_feature_set_ok(struct super_block *sb); static inline int ext3_feature_set_ok(struct super_block *sb); 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 = { .owner = THIS_MODULE, .name = "ext2", .mount = ext4_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext2"); MODULE_ALIAS("ext2"); #define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type) #else #define IS_EXT2_SB(sb) (0) #endif #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23) static struct file_system_type ext3_fs_type = { .owner = THIS_MODULE, .name = "ext3", .mount = ext4_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext3"); MODULE_ALIAS("ext3"); #define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type) #else #define IS_EXT3_SB(sb) (0) #endif static int ext4_verify_csum_type(struct super_block *sb, struct ext4_super_block *es) { if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) return 1; return es->s_checksum_type == EXT4_CRC32C_CHKSUM; } static __le32 ext4_superblock_csum(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); int offset = offsetof(struct ext4_super_block, s_checksum); __u32 csum; csum = ext4_chksum(sbi, ~0, (char *)es, offset); return cpu_to_le32(csum); } int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) return 1; return es->s_checksum == ext4_superblock_csum(sb, es); } void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) return; es->s_checksum = ext4_superblock_csum(sb, es); } void *ext4_kvmalloc(size_t size, gfp_t flags) { void *ret; ret = kmalloc(size, flags); if (!ret) ret = __vmalloc(size, flags, PAGE_KERNEL); return ret; } void *ext4_kvzalloc(size_t size, gfp_t flags) { void *ret; ret = kzalloc(size, flags); if (!ret) ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL); return ret; } void ext4_kvfree(void *ptr) { if (is_vmalloc_addr(ptr)) vfree(ptr); else kfree(ptr); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } __u32 ext4_free_group_clusters(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_free_blocks_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); } __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_free_inodes_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_used_dirs_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); } __u32 ext4_itable_unused_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_itable_unused_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); } void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_table_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); } void ext4_free_group_clusters_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16); } void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16); } void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16); } void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_itable_unused_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_itable_unused_hi = cpu_to_le16(count >> 16); } static void __save_error_info(struct super_block *sb, const char *func, unsigned int line) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); es->s_last_error_time = cpu_to_le32(get_seconds()); strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); es->s_last_error_line = cpu_to_le32(line); if (!es->s_first_error_time) { es->s_first_error_time = es->s_last_error_time; strncpy(es->s_first_error_func, func, sizeof(es->s_first_error_func)); es->s_first_error_line = cpu_to_le32(line); es->s_first_error_ino = es->s_last_error_ino; es->s_first_error_block = es->s_last_error_block; } /* * Start the daily error reporting function if it hasn't been * started already */ if (!es->s_error_count) mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ); le32_add_cpu(&es->s_error_count, 1); } static void save_error_info(struct super_block *sb, const char *func, unsigned int line) { __save_error_info(sb, func, line); ext4_commit_super(sb, 1); } /* * The del_gendisk() function uninitializes the disk-specific data * structures, including the bdi structure, without telling anyone * else. Once this happens, any attempt to call mark_buffer_dirty() * (for example, by ext4_commit_super), will cause a kernel OOPS. * This is a kludge to prevent these oops until we can put in a proper * hook in del_gendisk() to inform the VFS and file system layers. */ static int block_device_ejected(struct super_block *sb) { struct inode *bd_inode = sb->s_bdev->bd_inode; struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info; return bdi->dev == NULL; } 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; BUG_ON(txn->t_state == T_FINISHED); spin_lock(&sbi->s_md_lock); 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); spin_lock(&sbi->s_md_lock); } spin_unlock(&sbi->s_md_lock); } /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * * On ext2, we can store the error state of the filesystem in the * superblock. That is not possible on ext4, because we may have other * write ordering constraints on the superblock which prevent us from * writing it out straight away; and given that the journal is about to * be aborted, we can't rely on the current, or future, transactions to * write out the superblock safely. * * We'll just use the jbd2_journal_abort() error code to record an error in * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. */ static void ext4_handle_error(struct super_block *sb) { if (sb->s_flags & MS_RDONLY) return; if (!test_opt(sb, ERRORS_CONT)) { journal_t *journal = EXT4_SB(sb)->s_journal; EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; if (journal) jbd2_journal_abort(journal, -EIO); } if (test_opt(sb, ERRORS_RO)) { ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); sb->s_flags |= MS_RDONLY; } if (test_opt(sb, ERRORS_PANIC)) panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } void __ext4_error(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n", sb->s_id, function, line, current->comm, &vaf); va_end(args); save_error_info(sb, function, line); ext4_handle_error(sb); } void ext4_error_inode(struct inode *inode, const char *function, unsigned int line, ext4_fsblk_t block, const char *fmt, ...) { va_list args; struct va_format vaf; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; es->s_last_error_ino = cpu_to_le32(inode->i_ino); es->s_last_error_block = cpu_to_le64(block); save_error_info(inode->i_sb, function, line); va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%lu: block %llu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%lu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); ext4_handle_error(inode->i_sb); } void ext4_error_file(struct file *file, const char *function, unsigned int line, ext4_fsblk_t block, const char *fmt, ...) { va_list args; struct va_format vaf; struct ext4_super_block *es; struct inode *inode = file_inode(file); char pathname[80], *path; es = EXT4_SB(inode->i_sb)->s_es; es->s_last_error_ino = cpu_to_le32(inode->i_ino); save_error_info(inode->i_sb, function, line); path = d_path(&(file->f_path), pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: " "block %llu: comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, path, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: " "comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, path, &vaf); va_end(args); ext4_handle_error(inode->i_sb); } const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]) { char *errstr = NULL; switch (errno) { case -EIO: errstr = "IO failure"; break; case -ENOMEM: errstr = "Out of memory"; break; case -EROFS: if (!sb || (EXT4_SB(sb)->s_journal && EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)) errstr = "Journal has aborted"; else errstr = "Readonly filesystem"; break; default: /* If the caller passed in an extra buffer for unknown * errors, textualise them now. Else we just return * NULL. */ if (nbuf) { /* Check for truncated error codes... */ if (snprintf(nbuf, 16, "error %d", -errno) >= 0) errstr = nbuf; } break; } return errstr; } /* __ext4_std_error decodes expected errors from journaling functions * automatically and invokes the appropriate error response. */ void __ext4_std_error(struct super_block *sb, const char *function, unsigned int line, int errno) { char nbuf[16]; const char *errstr; /* Special case: if the error is EROFS, and we're not already * inside a transaction, then there's really no point in logging * an error. */ if (errno == -EROFS && journal_current_handle() == NULL && (sb->s_flags & MS_RDONLY)) return; errstr = ext4_decode_error(sb, errno, nbuf); printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n", sb->s_id, function, line, errstr); save_error_info(sb, function, line); ext4_handle_error(sb); } /* * ext4_abort is a much stronger failure handler than ext4_error. The * abort function may be used to deal with unrecoverable failures such * as journal IO errors or ENOMEM at a critical moment in log management. * * We unconditionally force the filesystem into an ABORT|READONLY state, * unless the error response on the fs has been set to panic in which * case we take the easy way out and panic immediately. */ void __ext4_abort(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) { va_list args; save_error_info(sb, function, line); va_start(args, fmt); printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id, function, line); vprintk(fmt, args); printk("\n"); va_end(args); if ((sb->s_flags & MS_RDONLY) == 0) { ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); sb->s_flags |= MS_RDONLY; EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; if (EXT4_SB(sb)->s_journal) jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); save_error_info(sb, function, line); } if (test_opt(sb, ERRORS_PANIC)) panic("EXT4-fs panic from previous error\n"); } void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf); va_end(args); } void __ext4_warning(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n", sb->s_id, function, line, &vaf); va_end(args); } void __ext4_grp_locked_error(const char *function, unsigned int line, struct super_block *sb, ext4_group_t grp, unsigned long ino, ext4_fsblk_t block, const char *fmt, ...) __releases(bitlock) __acquires(bitlock) { struct va_format vaf; va_list args; struct ext4_super_block *es = EXT4_SB(sb)->s_es; es->s_last_error_ino = cpu_to_le32(ino); es->s_last_error_block = cpu_to_le64(block); __save_error_info(sb, function, line); va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ", sb->s_id, function, line, grp); if (ino) printk(KERN_CONT "inode %lu: ", ino); if (block) printk(KERN_CONT "block %llu:", (unsigned long long) block); printk(KERN_CONT "%pV\n", &vaf); va_end(args); if (test_opt(sb, ERRORS_CONT)) { ext4_commit_super(sb, 0); return; } ext4_unlock_group(sb, grp); ext4_handle_error(sb); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the * filesystem will have already been marked read/only and the * journal has been aborted. We return 1 as a hint to callers * who might what to use the return value from * ext4_grp_locked_error() to distinguish between the * ERRORS_CONT and ERRORS_RO case, and perhaps return more * aggressively from the ext4 function in question, with a * more appropriate error code. */ ext4_lock_group(sb, grp); return; } void ext4_update_dynamic_rev(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV) return; ext4_warning(sb, "updating to rev %d because of new feature flag, " "running e2fsck is recommended", EXT4_DYNAMIC_REV); es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO); es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE); es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV); /* leave es->s_feature_*compat flags alone */ /* es->s_uuid will be set by e2fsck if empty */ /* * The rest of the superblock fields should be zero, and if not it * means they are likely already in use, so leave them alone. We * can leave it up to e2fsck to clean up any inconsistencies there. */ } /* * Open the external journal device */ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb) { struct block_device *bdev; char b[BDEVNAME_SIZE]; bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb); if (IS_ERR(bdev)) goto fail; return bdev; fail: ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld", __bdevname(dev, b), PTR_ERR(bdev)); return NULL; } /* * Release the journal device */ static void ext4_blkdev_put(struct block_device *bdev) { blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); } static void ext4_blkdev_remove(struct ext4_sb_info *sbi) { struct block_device *bdev; bdev = sbi->journal_bdev; if (bdev) { ext4_blkdev_put(bdev); sbi->journal_bdev = NULL; } } static inline struct inode *orphan_list_entry(struct list_head *l) { return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode; } static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) { struct list_head *l; ext4_msg(sb, KERN_ERR, "sb orphan head is %d", le32_to_cpu(sbi->s_es->s_last_orphan)); printk(KERN_ERR "sb_info orphan list:\n"); list_for_each(l, &sbi->s_orphan) { struct inode *inode = orphan_list_entry(l); printk(KERN_ERR " " "inode %s:%lu at %p: mode %o, nlink %d, next %d\n", inode->i_sb->s_id, inode->i_ino, inode, inode->i_mode, inode->i_nlink, NEXT_ORPHAN(inode)); } } static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int i, err; ext4_unregister_li_request(sb); dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); flush_workqueue(sbi->dio_unwritten_wq); destroy_workqueue(sbi->dio_unwritten_wq); if (sbi->s_journal) { err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; if (err < 0) ext4_abort(sb, "Couldn't clean up the journal"); } ext4_es_unregister_shrinker(sb); del_timer(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); ext4_xattr_put_super(sb); if (!(sb->s_flags & MS_RDONLY)) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); } if (!(sb->s_flags & MS_RDONLY)) ext4_commit_super(sb, 1); if (sbi->s_proc) { remove_proc_entry("options", sbi->s_proc); remove_proc_entry(sb->s_id, ext4_proc_root); } kobject_del(&sbi->s_kobj); for (i = 0; i < sbi->s_gdb_count; i++) brelse(sbi->s_group_desc[i]); ext4_kvfree(sbi->s_group_desc); ext4_kvfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); percpu_counter_destroy(&sbi->s_extent_cache_cnt); brelse(sbi->s_sbh); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) kfree(sbi->s_qf_names[i]); #endif /* Debugging code just in case the in-memory inode orphan list * isn't empty. The on-disk one can be non-empty if we've * detected an error and taken the fs readonly, but the * in-memory list had better be clean by this point. */ if (!list_empty(&sbi->s_orphan)) dump_orphan_list(sb, sbi); J_ASSERT(list_empty(&sbi->s_orphan)); invalidate_bdev(sb->s_bdev); if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) { /* * Invalidate the journal device's buffers. We don't want them * floating about in memory - the physical journal device may * hotswapped, and it breaks the `ro-after' testing code. */ sync_blockdev(sbi->journal_bdev); invalidate_bdev(sbi->journal_bdev); ext4_blkdev_remove(sbi); } if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); sb->s_fs_info = NULL; /* * Now that we are completely done shutting down the * superblock, we need to actually destroy the kobject. */ kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); kfree(sbi); } static struct kmem_cache *ext4_inode_cachep; /* * Called inside transaction, so use GFP_NOFS */ static struct inode *ext4_alloc_inode(struct super_block *sb) { struct ext4_inode_info *ei; ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; ei->vfs_inode.i_version = 1; INIT_LIST_HEAD(&ei->i_prealloc_list); spin_lock_init(&ei->i_prealloc_lock); ext4_es_init_tree(&ei->i_es_tree); rwlock_init(&ei->i_es_lock); INIT_LIST_HEAD(&ei->i_es_lru); ei->i_es_lru_nr = 0; ei->i_reserved_data_blocks = 0; 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; #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_completed_io_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_ioend_count, 0); atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_unwritten_work, ext4_end_io_work); return &ei->vfs_inode; } static int ext4_drop_inode(struct inode *inode) { int drop = generic_drop_inode(inode); trace_ext4_drop_inode(inode, drop); return drop; } static void ext4_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } static void ext4_destroy_inode(struct inode *inode) { if (!list_empty(&(EXT4_I(inode)->i_orphan))) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): orphan list check failed!", inode->i_ino, EXT4_I(inode)); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, EXT4_I(inode), sizeof(struct ext4_inode_info), true); dump_stack(); } call_rcu(&inode->i_rcu, ext4_i_callback); } static void init_once(void *foo) { struct ext4_inode_info *ei = (struct ext4_inode_info *) foo; INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); init_rwsem(&ei->i_data_sem); inode_init_once(&ei->vfs_inode); } static int init_inodecache(void) { ext4_inode_cachep = kmem_cache_create("ext4_inode_cache", sizeof(struct ext4_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD), init_once); if (ext4_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(ext4_inode_cachep); } void ext4_clear_inode(struct inode *inode) { invalidate_inode_buffers(inode); clear_inode(inode); dquot_drop(inode); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); ext4_es_lru_del(inode); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); jbd2_free_inode(EXT4_I(inode)->jinode); EXT4_I(inode)->jinode = NULL; } } static struct inode *ext4_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { struct inode *inode; if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) return ERR_PTR(-ESTALE); if (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)) return ERR_PTR(-ESTALE); /* iget isn't really right if the inode is currently unallocated!! * * ext4_read_inode will return a bad_inode if the inode had been * deleted, so we should be safe. * * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ inode = ext4_iget(sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { iput(inode); return ERR_PTR(-ESTALE); } return inode; } static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } /* * Try to release metadata pages (indirect blocks, directories) which are * mapped via the block device. Since these pages could have journal heads * which would prevent try_to_free_buffers() from freeing them, we must use * jbd2 layer's try_to_free_buffers() function to release them. */ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, gfp_t wait) { journal_t *journal = EXT4_SB(sb)->s_journal; WARN_ON(PageChecked(page)); if (!page_has_buffers(page)) return 0; if (journal) return jbd2_journal_try_to_free_buffers(journal, page, wait & ~__GFP_WAIT); return try_to_free_buffers(page); } #ifdef CONFIG_QUOTA #define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group") #define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA)) static int ext4_write_dquot(struct dquot *dquot); static int ext4_acquire_dquot(struct dquot *dquot); static int ext4_release_dquot(struct dquot *dquot); 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, .write_dquot = ext4_write_dquot, .acquire_dquot = ext4_acquire_dquot, .release_dquot = ext4_release_dquot, .mark_dirty = ext4_mark_dquot_dirty, .write_info = ext4_write_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, }; static const struct quotactl_ops ext4_qctl_operations = { .quota_on = ext4_quota_on, .quota_off = ext4_quota_off, .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 }; 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 = { .alloc_inode = ext4_alloc_inode, .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .put_super = ext4_put_super, .sync_fs = ext4_sync_fs, .freeze_fs = ext4_freeze, .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, .remount_fs = ext4_remount, .show_options = ext4_show_options, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, #endif .bdev_try_to_free_page = bdev_try_to_free_page, }; static const struct super_operations ext4_nojournal_sops = { .alloc_inode = ext4_alloc_inode, .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .put_super = ext4_put_super, .statfs = ext4_statfs, .remount_fs = ext4_remount, .show_options = ext4_show_options, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, #endif .bdev_try_to_free_page = bdev_try_to_free_page, }; static const struct export_operations ext4_export_ops = { .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, .get_parent = ext4_get_parent, }; enum { Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro, Opt_nouid32, Opt_debug, Opt_removed, Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit, Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, }; static const match_table_t tokens = { {Opt_bsd_df, "bsddf"}, {Opt_minix_df, "minixdf"}, {Opt_grpid, "grpid"}, {Opt_grpid, "bsdgroups"}, {Opt_nogrpid, "nogrpid"}, {Opt_nogrpid, "sysvgroups"}, {Opt_resgid, "resgid=%u"}, {Opt_resuid, "resuid=%u"}, {Opt_sb, "sb=%u"}, {Opt_err_cont, "errors=continue"}, {Opt_err_panic, "errors=panic"}, {Opt_err_ro, "errors=remount-ro"}, {Opt_nouid32, "nouid32"}, {Opt_debug, "debug"}, {Opt_removed, "oldalloc"}, {Opt_removed, "orlov"}, {Opt_user_xattr, "user_xattr"}, {Opt_nouser_xattr, "nouser_xattr"}, {Opt_acl, "acl"}, {Opt_noacl, "noacl"}, {Opt_noload, "norecovery"}, {Opt_noload, "noload"}, {Opt_removed, "nobh"}, {Opt_removed, "bh"}, {Opt_commit, "commit=%u"}, {Opt_min_batch_time, "min_batch_time=%u"}, {Opt_max_batch_time, "max_batch_time=%u"}, {Opt_journal_dev, "journal_dev=%u"}, {Opt_journal_checksum, "journal_checksum"}, {Opt_journal_async_commit, "journal_async_commit"}, {Opt_abort, "abort"}, {Opt_data_journal, "data=journal"}, {Opt_data_ordered, "data=ordered"}, {Opt_data_writeback, "data=writeback"}, {Opt_data_err_abort, "data_err=abort"}, {Opt_data_err_ignore, "data_err=ignore"}, {Opt_offusrjquota, "usrjquota="}, {Opt_usrjquota, "usrjquota=%s"}, {Opt_offgrpjquota, "grpjquota="}, {Opt_grpjquota, "grpjquota=%s"}, {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, {Opt_grpquota, "grpquota"}, {Opt_noquota, "noquota"}, {Opt_quota, "quota"}, {Opt_usrquota, "usrquota"}, {Opt_barrier, "barrier=%u"}, {Opt_barrier, "barrier"}, {Opt_nobarrier, "nobarrier"}, {Opt_i_version, "i_version"}, {Opt_stripe, "stripe=%u"}, {Opt_delalloc, "delalloc"}, {Opt_nodelalloc, "nodelalloc"}, {Opt_removed, "mblk_io_submit"}, {Opt_removed, "nomblk_io_submit"}, {Opt_block_validity, "block_validity"}, {Opt_noblock_validity, "noblock_validity"}, {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, {Opt_journal_ioprio, "journal_ioprio=%u"}, {Opt_auto_da_alloc, "auto_da_alloc=%u"}, {Opt_auto_da_alloc, "auto_da_alloc"}, {Opt_noauto_da_alloc, "noauto_da_alloc"}, {Opt_dioread_nolock, "dioread_nolock"}, {Opt_dioread_lock, "dioread_lock"}, {Opt_discard, "discard"}, {Opt_nodiscard, "nodiscard"}, {Opt_init_itable, "init_itable=%u"}, {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ {Opt_removed, "noreservation"}, /* mount option from ext2/3 */ {Opt_removed, "journal=%u"}, /* mount option from ext2/3 */ {Opt_err, NULL}, }; static ext4_fsblk_t get_sb_block(void **data) { ext4_fsblk_t sb_block; char *options = (char *) *data; if (!options || strncmp(options, "sb=", 3) != 0) return 1; /* Default location */ options += 3; /* TODO: use simple_strtoll with >32bit ext4 */ sb_block = simple_strtoul(options, &options, 0); if (*options && *options != ',') { printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n", (char *) *data); return 1; } if (*options == ',') options++; *data = (void *) options; return sb_block; } #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) static char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n" "Contact linux-ext4@vger.kernel.org if you think we should keep it.\n"; #ifdef CONFIG_QUOTA static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) { struct ext4_sb_info *sbi = EXT4_SB(sb); char *qname; int ret = -1; if (sb_any_quota_loaded(sb) && !sbi->s_qf_names[qtype]) { ext4_msg(sb, KERN_ERR, "Cannot change journaled " "quota options when quota turned on"); return -1; } if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options " "when QUOTA feature is enabled"); return -1; } qname = match_strdup(args); if (!qname) { ext4_msg(sb, KERN_ERR, "Not enough memory for storing quotafile name"); return -1; } if (sbi->s_qf_names[qtype]) { if (strcmp(sbi->s_qf_names[qtype], qname) == 0) ret = 1; else ext4_msg(sb, KERN_ERR, "%s quota file already specified", QTYPE2NAME(qtype)); goto errout; } if (strchr(qname, '/')) { ext4_msg(sb, KERN_ERR, "quotafile must be on filesystem root"); goto errout; } sbi->s_qf_names[qtype] = qname; set_opt(sb, QUOTA); return 1; errout: kfree(qname); return ret; } static int clear_qf_name(struct super_block *sb, int qtype) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (sb_any_quota_loaded(sb) && sbi->s_qf_names[qtype]) { ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options" " when quota turned on"); return -1; } kfree(sbi->s_qf_names[qtype]); sbi->s_qf_names[qtype] = NULL; return 1; } #endif #define MOPT_SET 0x0001 #define MOPT_CLEAR 0x0002 #define MOPT_NOSUPPORT 0x0004 #define MOPT_EXPLICIT 0x0008 #define MOPT_CLEAR_ERR 0x0010 #define MOPT_GTE0 0x0020 #ifdef CONFIG_QUOTA #define MOPT_Q 0 #define MOPT_QFMT 0x0040 #else #define MOPT_Q MOPT_NOSUPPORT #define MOPT_QFMT MOPT_NOSUPPORT #endif #define MOPT_DATAJ 0x0080 #define MOPT_NO_EXT2 0x0100 #define MOPT_NO_EXT3 0x0200 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) static const struct mount_opts { int token; int mount_opt; int flags; } ext4_mount_opts[] = { {Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET}, {Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR}, {Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET}, {Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR}, {Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET}, {Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR}, {Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_SET}, {Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET}, {Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR}, {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_SET}, {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT | EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_EXT4_ONLY | MOPT_SET}, {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET}, {Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR}, {Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR}, {Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR}, {Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_NO_EXT2 | MOPT_SET}, {Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_NO_EXT2 | MOPT_CLEAR}, {Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET}, {Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR}, {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET}, {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR}, {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR}, {Opt_commit, 0, MOPT_GTE0}, {Opt_max_batch_time, 0, MOPT_GTE0}, {Opt_min_batch_time, 0, MOPT_GTE0}, {Opt_inode_readahead_blks, 0, MOPT_GTE0}, {Opt_init_itable, 0, MOPT_GTE0}, {Opt_stripe, 0, MOPT_GTE0}, {Opt_resuid, 0, MOPT_GTE0}, {Opt_resgid, 0, MOPT_GTE0}, {Opt_journal_dev, 0, MOPT_GTE0}, {Opt_journal_ioprio, 0, MOPT_GTE0}, {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, {Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, {Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET}, {Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR}, #ifdef CONFIG_EXT4_FS_POSIX_ACL {Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET}, {Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR}, #else {Opt_acl, 0, MOPT_NOSUPPORT}, {Opt_noacl, 0, MOPT_NOSUPPORT}, #endif {Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET}, {Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET}, {Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA, MOPT_SET | MOPT_Q}, {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA), MOPT_CLEAR | MOPT_Q}, {Opt_usrjquota, 0, MOPT_Q}, {Opt_grpjquota, 0, MOPT_Q}, {Opt_offusrjquota, 0, MOPT_Q}, {Opt_offgrpjquota, 0, MOPT_Q}, {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT}, {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_err, 0, 0} }; static int handle_mount_opt(struct super_block *sb, char *opt, int token, substring_t *args, unsigned long *journal_devnum, unsigned int *journal_ioprio, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); const struct mount_opts *m; kuid_t uid; kgid_t gid; int arg = 0; #ifdef CONFIG_QUOTA if (token == Opt_usrjquota) return set_qf_name(sb, USRQUOTA, &args[0]); else if (token == Opt_grpjquota) return set_qf_name(sb, GRPQUOTA, &args[0]); else if (token == Opt_offusrjquota) return clear_qf_name(sb, USRQUOTA); else if (token == Opt_offgrpjquota) return clear_qf_name(sb, GRPQUOTA); #endif switch (token) { case Opt_noacl: case Opt_nouser_xattr: ext4_msg(sb, KERN_WARNING, deprecated_msg, opt, "3.5"); break; case Opt_sb: return 1; /* handled by get_sb_block() */ case Opt_removed: ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt); return 1; case Opt_abort: sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; return 1; case Opt_i_version: sb->s_flags |= MS_I_VERSION; return 1; } for (m = ext4_mount_opts; m->token != Opt_err; m++) if (token == m->token) break; if (m->token == Opt_err) { ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" " "or missing value", opt); return -1; } if ((m->flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) { ext4_msg(sb, KERN_ERR, "Mount option \"%s\" incompatible with ext2", opt); return -1; } if ((m->flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) { ext4_msg(sb, KERN_ERR, "Mount option \"%s\" incompatible with ext3", opt); return -1; } if (args->from && match_int(args, &arg)) return -1; if (args->from && (m->flags & MOPT_GTE0) && (arg < 0)) return -1; if (m->flags & MOPT_EXPLICIT) set_opt2(sb, EXPLICIT_DELALLOC); if (m->flags & MOPT_CLEAR_ERR) clear_opt(sb, ERRORS_MASK); if (token == Opt_noquota && sb_any_quota_loaded(sb)) { ext4_msg(sb, KERN_ERR, "Cannot change quota " "options when quota turned on"); return -1; } if (m->flags & MOPT_NOSUPPORT) { ext4_msg(sb, KERN_ERR, "%s option not supported", opt); } else if (token == Opt_commit) { if (arg == 0) arg = JBD2_DEFAULT_MAX_COMMIT_AGE; sbi->s_commit_interval = HZ * arg; } else if (token == Opt_max_batch_time) { if (arg == 0) arg = EXT4_DEF_MAX_BATCH_TIME; sbi->s_max_batch_time = arg; } else if (token == Opt_min_batch_time) { sbi->s_min_batch_time = arg; } else if (token == Opt_inode_readahead_blks) { if (arg && (arg > (1 << 30) || !is_power_of_2(arg))) { ext4_msg(sb, KERN_ERR, "EXT4-fs: inode_readahead_blks must be " "0 or a power of 2 smaller than 2^31"); return -1; } sbi->s_inode_readahead_blks = arg; } else if (token == Opt_init_itable) { set_opt(sb, INIT_INODE_TABLE); if (!args->from) arg = EXT4_DEF_LI_WAIT_MULT; sbi->s_li_wait_mult = arg; } else if (token == Opt_max_dir_size_kb) { sbi->s_max_dir_size_kb = arg; } else if (token == Opt_stripe) { sbi->s_stripe = arg; } else if (token == Opt_resuid) { uid = make_kuid(current_user_ns(), arg); if (!uid_valid(uid)) { ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg); return -1; } sbi->s_resuid = uid; } else if (token == Opt_resgid) { gid = make_kgid(current_user_ns(), arg); if (!gid_valid(gid)) { ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg); return -1; } sbi->s_resgid = gid; } else if (token == Opt_journal_dev) { if (is_remount) { ext4_msg(sb, KERN_ERR, "Cannot specify journal on remount"); return -1; } *journal_devnum = arg; } else if (token == Opt_journal_ioprio) { if (arg > 7) { ext4_msg(sb, KERN_ERR, "Invalid journal IO priority" " (must be 0-7)"); return -1; } *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg); } else if (m->flags & MOPT_DATAJ) { if (is_remount) { if (!sbi->s_journal) ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option"); else if (test_opt(sb, DATA_FLAGS) != m->mount_opt) { ext4_msg(sb, KERN_ERR, "Cannot change data mode on remount"); return -1; } } else { clear_opt(sb, DATA_FLAGS); sbi->s_mount_opt |= m->mount_opt; } #ifdef CONFIG_QUOTA } else if (m->flags & MOPT_QFMT) { if (sb_any_quota_loaded(sb) && sbi->s_jquota_fmt != m->mount_opt) { ext4_msg(sb, KERN_ERR, "Cannot change journaled " "quota options when quota turned on"); return -1; } if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options " "when QUOTA feature is enabled"); return -1; } sbi->s_jquota_fmt = m->mount_opt; #endif } else { if (!args->from) arg = 1; if (m->flags & MOPT_CLEAR) arg = !arg; else if (unlikely(!(m->flags & MOPT_SET))) { ext4_msg(sb, KERN_WARNING, "buggy handling of option %s", opt); WARN_ON(1); return -1; } if (arg != 0) sbi->s_mount_opt |= m->mount_opt; else sbi->s_mount_opt &= ~m->mount_opt; } return 1; } static int parse_options(char *options, struct super_block *sb, unsigned long *journal_devnum, unsigned int *journal_ioprio, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); char *p; substring_t args[MAX_OPT_ARGS]; int token; if (!options) return 1; while ((p = strsep(&options, ",")) != NULL) { if (!*p) continue; /* * Initialize args struct so we know whether arg was * found; some options take optional arguments. */ args[0].to = args[0].from = NULL; token = match_token(p, tokens, args); if (handle_mount_opt(sb, p, token, args, journal_devnum, journal_ioprio, is_remount) < 0) return 0; } #ifdef CONFIG_QUOTA if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) { ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA " "feature is enabled"); return 0; } if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) clear_opt(sb, USRQUOTA); if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA]) clear_opt(sb, GRPQUOTA); if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) { ext4_msg(sb, KERN_ERR, "old and new quota " "format mixing"); return 0; } if (!sbi->s_jquota_fmt) { ext4_msg(sb, KERN_ERR, "journaled quota format " "not specified"); return 0; } } else { if (sbi->s_jquota_fmt) { ext4_msg(sb, KERN_ERR, "journaled quota format " "specified with no journaling " "enabled"); return 0; } } #endif if (test_opt(sb, DIOREAD_NOLOCK)) { int blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (blocksize < PAGE_CACHE_SIZE) { ext4_msg(sb, KERN_ERR, "can't mount with " "dioread_nolock if block size != PAGE_SIZE"); return 0; } } return 1; } static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb) { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); if (sbi->s_jquota_fmt) { char *fmtname = ""; switch (sbi->s_jquota_fmt) { case QFMT_VFS_OLD: fmtname = "vfsold"; break; case QFMT_VFS_V0: fmtname = "vfsv0"; break; case QFMT_VFS_V1: fmtname = "vfsv1"; break; } seq_printf(seq, ",jqfmt=%s", fmtname); } if (sbi->s_qf_names[USRQUOTA]) seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]); if (sbi->s_qf_names[GRPQUOTA]) seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]); if (test_opt(sb, USRQUOTA)) seq_puts(seq, ",usrquota"); if (test_opt(sb, GRPQUOTA)) seq_puts(seq, ",grpquota"); #endif } static const char *token2str(int token) { const struct match_token *t; for (t = tokens; t->token != Opt_err; t++) if (t->token == token && !strchr(t->pattern, '=')) break; return t->pattern; } /* * Show an option if * - it's set to a non-default value OR * - if the per-sb default is different from the global default */ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, int nodefs) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int def_errors, def_mount_opt = nodefs ? 0 : sbi->s_def_mount_opt; const struct mount_opts *m; char sep = nodefs ? '\n' : ','; #define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep) #define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg) if (sbi->s_sb_block != 1) SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block); for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || (m->flags & MOPT_CLEAR_ERR)) continue; if (!(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt))) continue; /* skip if same as the default */ if ((want_set && (sbi->s_mount_opt & m->mount_opt) != m->mount_opt) || (!want_set && (sbi->s_mount_opt & m->mount_opt))) continue; /* select Opt_noFoo vs Opt_Foo */ SEQ_OPTS_PRINT("%s", token2str(m->token)); } if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) SEQ_OPTS_PRINT("resuid=%u", from_kuid_munged(&init_user_ns, sbi->s_resuid)); if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) SEQ_OPTS_PRINT("resgid=%u", from_kgid_munged(&init_user_ns, sbi->s_resgid)); def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors); if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO) SEQ_OPTS_PUTS("errors=remount-ro"); if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE) SEQ_OPTS_PUTS("errors=continue"); if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC) SEQ_OPTS_PUTS("errors=panic"); if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ); if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); if (sb->s_flags & MS_I_VERSION) SEQ_OPTS_PUTS("i_version"); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ def_mount_opt)) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) SEQ_OPTS_PUTS("data=journal"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) SEQ_OPTS_PUTS("data=ordered"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) SEQ_OPTS_PUTS("data=writeback"); } if (nodefs || sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS) SEQ_OPTS_PRINT("inode_readahead_blks=%u", sbi->s_inode_readahead_blks); if (nodefs || (test_opt(sb, INIT_INODE_TABLE) && (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT))) SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult); if (nodefs || sbi->s_max_dir_size_kb) SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); ext4_show_quota_options(seq, sb); return 0; } static int ext4_show_options(struct seq_file *seq, struct dentry *root) { return _ext4_show_options(seq, root->d_sb, 0); } static int options_seq_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; int rc; seq_puts(seq, (sb->s_flags & MS_RDONLY) ? "ro" : "rw"); rc = _ext4_show_options(seq, sb, 1); seq_puts(seq, "\n"); return rc; } static int options_open_fs(struct inode *inode, struct file *file) { return single_open(file, options_seq_show, PDE_DATA(inode)); } static const struct file_operations ext4_seq_options_fops = { .owner = THIS_MODULE, .open = options_open_fs, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int read_only) { struct ext4_sb_info *sbi = EXT4_SB(sb); int res = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); res = MS_RDONLY; } if (read_only) goto done; if (!(sbi->s_mount_state & EXT4_VALID_FS)) ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, " "running e2fsck is recommended"); else if ((sbi->s_mount_state & EXT4_ERROR_FS)) ext4_msg(sb, KERN_WARNING, "warning: mounting fs with errors, " "running e2fsck is recommended"); else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 && le16_to_cpu(es->s_mnt_count) >= (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) ext4_msg(sb, KERN_WARNING, "warning: maximal mount count reached, " "running e2fsck is recommended"); else if (le32_to_cpu(es->s_checkinterval) && (le32_to_cpu(es->s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= get_seconds())) ext4_msg(sb, KERN_WARNING, "warning: checktime reached, " "running e2fsck is recommended"); if (!sbi->s_journal) es->s_state &= cpu_to_le16(~EXT4_VALID_FS); if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); es->s_mtime = cpu_to_le32(get_seconds()); ext4_update_dynamic_rev(sb); if (sbi->s_journal) EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); ext4_commit_super(sb, 1); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " "bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n", sb->s_blocksize, sbi->s_groups_count, EXT4_BLOCKS_PER_GROUP(sb), EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); cleancache_init_fs(sb); return res; } int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct flex_groups *new_groups; int size; if (!sbi->s_log_groups_per_flex) return 0; size = ext4_flex_group(sbi, ngroup - 1) + 1; if (size <= sbi->s_flex_groups_allocated) return 0; size = roundup_pow_of_two(size * sizeof(struct flex_groups)); new_groups = ext4_kvzalloc(size, GFP_KERNEL); if (!new_groups) { ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", size / (int) sizeof(struct flex_groups)); return -ENOMEM; } if (sbi->s_flex_groups) { memcpy(new_groups, sbi->s_flex_groups, (sbi->s_flex_groups_allocated * sizeof(struct flex_groups))); ext4_kvfree(sbi->s_flex_groups); } sbi->s_flex_groups = new_groups; sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups); return 0; } static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; ext4_group_t flex_group; unsigned int groups_per_flex = 0; int i, err; sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) { sbi->s_log_groups_per_flex = 0; return 1; } groups_per_flex = 1U << sbi->s_log_groups_per_flex; err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count); if (err) goto failed; for (i = 0; i < sbi->s_groups_count; i++) { gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); atomic_add(ext4_free_inodes_count(sb, gdp), &sbi->s_flex_groups[flex_group].free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), &sbi->s_flex_groups[flex_group].free_clusters); atomic_add(ext4_used_dirs_count(sb, gdp), &sbi->s_flex_groups[flex_group].used_dirs); } return 1; failed: return 0; } static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, struct ext4_group_desc *gdp) { int offset; __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); if ((sbi->s_es->s_feature_ro_compat & cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) { /* Use new metadata_csum algorithm */ __le16 save_csum; __u32 csum32; 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 = save_csum; crc = csum32 & 0xFFFF; goto out; } /* old crc16 code */ offset = offsetof(struct ext4_group_desc, bg_checksum); crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ if ((sbi->s_es->s_feature_incompat & cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) && offset < le16_to_cpu(sbi->s_es->s_desc_size)) crc = crc16(crc, (__u8 *)gdp + offset, le16_to_cpu(sbi->s_es->s_desc_size) - offset); out: return cpu_to_le16(crc); } int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (ext4_has_group_desc_csum(sb) && (gdp->bg_checksum != ext4_group_desc_csum(EXT4_SB(sb), block_group, gdp))) return 0; return 1; } void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (!ext4_has_group_desc_csum(sb)) return; gdp->bg_checksum = ext4_group_desc_csum(EXT4_SB(sb), block_group, gdp); } /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; int flexbg_flag = 0; ext4_group_t i, grp = sbi->s_groups_count; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) flexbg_flag = 1; ext4_debug("Checking group descriptors"); for (i = 0; i < sbi->s_groups_count; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); if ((grp == sbi->s_groups_count) && !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) grp = i; block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " "(block %llu)!", i, block_bitmap); return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " "(block %llu)!", i, inode_bitmap); return 0; } inode_table = ext4_inode_table(sb, gdp); if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u not in group " "(block %llu)!", i, inode_table); return 0; } ext4_lock_group(sb, i); if (!ext4_group_desc_csum_verify(sb, i, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Checksum for group %u failed (%u!=%u)", i, le16_to_cpu(ext4_group_desc_csum(sbi, i, gdp)), le16_to_cpu(gdp->bg_checksum)); if (!(sb->s_flags & MS_RDONLY)) { ext4_unlock_group(sb, i); return 0; } } ext4_unlock_group(sb, i); if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } if (NULL != first_not_zeroed) *first_not_zeroed = grp; ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, ext4_count_free_clusters(sb))); sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb)); return 1; } /* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at * the superblock) which were deleted from all directories, but held open by * a process at the time of a crash. We walk the list and try to delete these * inodes at recovery time (only with a read-write filesystem). * * In order to keep the orphan inode chain consistent during traversal (in * case of crash during recovery), we link each inode into the superblock * orphan list_head and handle it the same way as an inode deletion during * normal operation (which journals the operations for us). * * We only do an iget() and an iput() on each inode, which is very safe if we * accidentally point at an in-use or already deleted inode. The worst that * can happen in this case is that we get a "bit already cleared" message from * ext4_free_inode(). The only reason we would point at a wrong inode is if * e2fsck was run on this filesystem, and it must have already done the orphan * inode cleanup for us, so we can safely abort without any further action. */ static void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es) { unsigned int s_flags = sb->s_flags; int nr_orphans = 0, nr_truncates = 0; #ifdef CONFIG_QUOTA int i; #endif if (!es->s_last_orphan) { jbd_debug(4, "no orphan inodes to clean up\n"); return; } if (bdev_read_only(sb->s_bdev)) { ext4_msg(sb, KERN_ERR, "write access " "unavailable, skipping orphan cleanup"); return; } /* Check if feature set would not allow a r/w mount */ if (!ext4_feature_set_ok(sb, 0)) { ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to " "unknown ROCOMPAT features"); return; } if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { /* don't clear list on RO mount w/ errors */ if (es->s_last_orphan && !(s_flags & MS_RDONLY)) { jbd_debug(1, "Errors on filesystem, " "clearing orphan list.\n"); es->s_last_orphan = 0; } jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); return; } if (s_flags & MS_RDONLY) { ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs"); sb->s_flags &= ~MS_RDONLY; } #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ sb->s_flags |= MS_ACTIVE; /* Turn on quotas so that they are updated correctly */ for (i = 0; i < MAXQUOTAS; i++) { if (EXT4_SB(sb)->s_qf_names[i]) { int ret = ext4_quota_on_mount(sb, i); if (ret < 0) ext4_msg(sb, KERN_ERR, "Cannot turn on journaled " "quota: error %d", ret); } } #endif while (es->s_last_orphan) { struct inode *inode; inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)); if (IS_ERR(inode)) { es->s_last_orphan = 0; break; } list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan); dquot_initialize(inode); if (in