diff options
Diffstat (limited to 'fs/ext4/super.c')
| -rw-r--r-- | fs/ext4/super.c | 1111 |
1 files changed, 643 insertions, 468 deletions
diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 73547d2334fd..87205660c5d0 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -79,7 +79,6 @@ static int ext4_unfreeze(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static inline int ext2_feature_set_ok(struct super_block *sb); static inline int ext3_feature_set_ok(struct super_block *sb); -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 struct inode *ext4_get_journal_inode(struct super_block *sb, @@ -161,8 +160,14 @@ MODULE_ALIAS("ext3"); static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, - bh_end_io_t *end_io) + bh_end_io_t *end_io, bool simu_fail) { + if (simu_fail) { + clear_buffer_uptodate(bh); + unlock_buffer(bh); + return; + } + /* * buffer's verified bit is no longer valid after reading from * disk again due to write out error, clear it to make sure we @@ -176,7 +181,7 @@ static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, } void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, - bh_end_io_t *end_io) + bh_end_io_t *end_io, bool simu_fail) { BUG_ON(!buffer_locked(bh)); @@ -184,10 +189,11 @@ void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, unlock_buffer(bh); return; } - __ext4_read_bh(bh, op_flags, end_io); + __ext4_read_bh(bh, op_flags, end_io, simu_fail); } -int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io) +int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, + bh_end_io_t *end_io, bool simu_fail) { BUG_ON(!buffer_locked(bh)); @@ -196,7 +202,7 @@ int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io return 0; } - __ext4_read_bh(bh, op_flags, end_io); + __ext4_read_bh(bh, op_flags, end_io, simu_fail); wait_on_buffer(bh); if (buffer_uptodate(bh)) @@ -208,10 +214,10 @@ int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { lock_buffer(bh); if (!wait) { - ext4_read_bh_nowait(bh, op_flags, NULL); + ext4_read_bh_nowait(bh, op_flags, NULL, false); return 0; } - return ext4_read_bh(bh, op_flags, NULL); + return ext4_read_bh(bh, op_flags, NULL, false); } /* @@ -244,22 +250,38 @@ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags) { - return __ext4_sb_bread_gfp(sb, block, op_flags, __GFP_MOVABLE); + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, + ~__GFP_FS) | __GFP_MOVABLE; + + return __ext4_sb_bread_gfp(sb, block, op_flags, gfp); } struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block) { - return __ext4_sb_bread_gfp(sb, block, 0, 0); + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, + ~__GFP_FS); + + return __ext4_sb_bread_gfp(sb, block, 0, gfp); +} + +struct buffer_head *ext4_sb_bread_nofail(struct super_block *sb, + sector_t block) +{ + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, + ~__GFP_FS) | __GFP_MOVABLE | __GFP_NOFAIL; + + return __ext4_sb_bread_gfp(sb, block, 0, gfp); } void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { - struct buffer_head *bh = sb_getblk_gfp(sb, block, 0); + struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, + sb->s_blocksize, GFP_NOWAIT); if (likely(bh)) { if (trylock_buffer(bh)) - ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL); + ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL, false); brelse(bh); } } @@ -273,14 +295,12 @@ static int ext4_verify_csum_type(struct super_block *sb, return es->s_checksum_type == EXT4_CRC32C_CHKSUM; } -__le32 ext4_superblock_csum(struct super_block *sb, - struct ext4_super_block *es) +__le32 ext4_superblock_csum(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); + csum = ext4_chksum(~0, (char *)es, offset); return cpu_to_le32(csum); } @@ -288,20 +308,20 @@ __le32 ext4_superblock_csum(struct super_block *sb, static int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { - if (!ext4_has_metadata_csum(sb)) + if (!ext4_has_feature_metadata_csum(sb)) return 1; - return es->s_checksum == ext4_superblock_csum(sb, es); + return es->s_checksum == ext4_superblock_csum(es); } void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; - if (!ext4_has_metadata_csum(sb)) + if (!ext4_has_feature_metadata_csum(sb)) return; - es->s_checksum = ext4_superblock_csum(sb, es); + es->s_checksum = ext4_superblock_csum(es); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, @@ -339,9 +359,9 @@ __u32 ext4_free_group_clusters(struct super_block *sb, __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg) { - return le16_to_cpu(bg->bg_free_inodes_count_lo) | + return le16_to_cpu(READ_ONCE(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)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, @@ -395,9 +415,9 @@ void ext4_free_group_clusters_set(struct super_block *sb, 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); + WRITE_ONCE(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); + WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16)); } void ext4_used_dirs_set(struct super_block *sb, @@ -435,59 +455,69 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) /* - * 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. + * The ext4_maybe_update_superblock() function checks and updates the + * superblock if needed. + * + * This function is designed to update the on-disk superblock only under + * certain conditions to prevent excessive disk writes and unnecessary + * waking of the disk from sleep. The superblock will be updated if: + * 1. More than sbi->s_sb_update_sec (def: 1 hour) has passed since the last + * superblock update + * 2. More than sbi->s_sb_update_kb (def: 16MB) kbs have been written since the + * last superblock update. + * + * @sb: The superblock */ -static int block_device_ejected(struct super_block *sb) +static void ext4_maybe_update_superblock(struct super_block *sb) { - struct inode *bd_inode = sb->s_bdev->bd_inode; - struct backing_dev_info *bdi = inode_to_bdi(bd_inode); + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + journal_t *journal = sbi->s_journal; + time64_t now; + __u64 last_update; + __u64 lifetime_write_kbytes; + __u64 diff_size; + + if (ext4_emergency_state(sb) || sb_rdonly(sb) || + !(sb->s_flags & SB_ACTIVE) || !journal || + journal->j_flags & JBD2_UNMOUNT) + return; + + now = ktime_get_real_seconds(); + last_update = ext4_get_tstamp(es, s_wtime); - return bdi->dev == NULL; + if (likely(now - last_update < sbi->s_sb_update_sec)) + return; + + lifetime_write_kbytes = sbi->s_kbytes_written + + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - + sbi->s_sectors_written_start) >> 1); + + /* Get the number of kilobytes not written to disk to account + * for statistics and compare with a multiple of 16 MB. This + * is used to determine when the next superblock commit should + * occur (i.e. not more often than once per 16MB if there was + * less written in an hour). + */ + diff_size = lifetime_write_kbytes - le64_to_cpu(es->s_kbytes_written); + + if (diff_size > sbi->s_sb_update_kb) + schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } 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); ext4_process_freed_data(sb, txn->t_tid); - - 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); + ext4_maybe_update_superblock(sb); } -/* - * This writepage callback for write_cache_pages() - * takes care of a few cases after page cleaning. - * - * write_cache_pages() already checks for dirty pages - * and calls clear_page_dirty_for_io(), which we want, - * to write protect the pages. - * - * However, we may have to redirty a page (see below.) - */ -static int ext4_journalled_writepage_callback(struct folio *folio, - struct writeback_control *wbc, - void *data) +static bool ext4_journalled_writepage_needs_redirty(struct jbd2_inode *jinode, + struct folio *folio) { - transaction_t *transaction = (transaction_t *) data; struct buffer_head *bh, *head; struct journal_head *jh; @@ -508,15 +538,12 @@ static int ext4_journalled_writepage_callback(struct folio *folio, */ jh = bh2jh(bh); if (buffer_dirty(bh) || - (jh && (jh->b_transaction != transaction || - jh->b_next_transaction))) { - folio_redirty_for_writepage(wbc, folio); - goto out; - } + (jh && (jh->b_transaction != jinode->i_transaction || + jh->b_next_transaction))) + return true; } while ((bh = bh->b_this_page) != head); -out: - return AOP_WRITEPAGE_ACTIVATE; + return false; } static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode) @@ -528,10 +555,23 @@ static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode) .range_start = jinode->i_dirty_start, .range_end = jinode->i_dirty_end, }; + struct folio *folio = NULL; + int error; + + /* + * writeback_iter() already checks for dirty pages and calls + * folio_clear_dirty_for_io(), which we want to write protect the + * folios. + * + * However, we may have to redirty a folio sometimes. + */ + while ((folio = writeback_iter(mapping, &wbc, folio, &error))) { + if (ext4_journalled_writepage_needs_redirty(jinode, folio)) + folio_redirty_for_writepage(&wbc, folio); + folio_unlock(folio); + } - return write_cache_pages(mapping, &wbc, - ext4_journalled_writepage_callback, - jinode->i_transaction); + return error; } static int ext4_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) @@ -657,11 +697,8 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); - if (!continue_fs && !sb_rdonly(sb)) { - ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); - if (journal) - jbd2_journal_abort(journal, -EIO); - } + if (!continue_fs && !ext4_emergency_ro(sb) && journal) + jbd2_journal_abort(journal, -error); if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, error, ino, block, func, line); @@ -669,10 +706,14 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, * In case the fs should keep running, we need to writeout * superblock through the journal. Due to lock ordering * constraints, it may not be safe to do it right here so we - * defer superblock flushing to a workqueue. + * defer superblock flushing to a workqueue. We just need to be + * careful when the journal is already shutting down. If we get + * here in that case, just update the sb directly as the last + * transaction won't commit anyway. */ - if (continue_fs && journal) - schedule_work(&EXT4_SB(sb)->s_error_work); + if (continue_fs && journal && + !ext4_test_mount_flag(sb, EXT4_MF_JOURNAL_DESTROY)) + schedule_work(&EXT4_SB(sb)->s_sb_upd_work); else ext4_commit_super(sb); } @@ -687,22 +728,23 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, sb->s_id); } - if (sb_rdonly(sb) || continue_fs) + if (ext4_emergency_ro(sb) || continue_fs) return; ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* - * Make sure updated value of ->s_mount_flags will be visible before - * ->s_flags update + * We don't set SB_RDONLY because that requires sb->s_umount + * semaphore and setting it without proper remount procedure is + * confusing code such as freeze_super() leading to deadlocks + * and other problems. */ - smp_wmb(); - sb->s_flags |= SB_RDONLY; + set_bit(EXT4_FLAGS_EMERGENCY_RO, &EXT4_SB(sb)->s_ext4_flags); } -static void flush_stashed_error_work(struct work_struct *work) +static void update_super_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, - s_error_work); + s_sb_upd_work); journal_t *journal = sbi->s_journal; handle_t *handle; @@ -714,8 +756,11 @@ static void flush_stashed_error_work(struct work_struct *work) * We use directly jbd2 functions here to avoid recursing back into * ext4 error handling code during handling of previous errors. */ - if (!sb_rdonly(sbi->s_sb) && journal) { + if (!ext4_emergency_state(sbi->s_sb) && + !sb_rdonly(sbi->s_sb) && journal) { struct buffer_head *sbh = sbi->s_sbh; + bool call_notify_err = false; + handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; @@ -723,6 +768,10 @@ static void flush_stashed_error_work(struct work_struct *work) jbd2_journal_stop(handle); goto write_directly; } + + if (sbi->s_add_error_count > 0) + call_notify_err = true; + ext4_update_super(sbi->s_sb); if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " @@ -736,7 +785,10 @@ static void flush_stashed_error_work(struct work_struct *work) goto write_directly; } jbd2_journal_stop(handle); - ext4_notify_error_sysfs(sbi); + + if (call_notify_err) + ext4_notify_error_sysfs(sbi); + return; } write_directly: @@ -759,7 +811,7 @@ void __ext4_error(struct super_block *sb, const char *function, struct va_format vaf; va_list args; - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) + if (unlikely(ext4_emergency_state(sb))) return; trace_ext4_error(sb, function, line); @@ -784,7 +836,7 @@ void __ext4_error_inode(struct inode *inode, const char *function, va_list args; struct va_format vaf; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_emergency_state(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); @@ -819,7 +871,7 @@ void __ext4_error_file(struct file *file, const char *function, struct inode *inode = file_inode(file); char pathname[80], *path; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_emergency_state(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); @@ -899,7 +951,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, char nbuf[16]; const char *errstr; - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) + if (unlikely(ext4_emergency_state(sb))) return; /* Special case: if the error is EROFS, and we're not already @@ -993,7 +1045,7 @@ __acquires(bitlock) struct va_format vaf; va_list args; - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) + if (unlikely(ext4_emergency_state(sb))) return; trace_ext4_error(sb, function, line); @@ -1019,7 +1071,7 @@ __acquires(bitlock) if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - schedule_work(&EXT4_SB(sb)->s_error_work); + schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } return; } @@ -1097,26 +1149,6 @@ void ext4_update_dynamic_rev(struct super_block *sb) */ } -/* - * Open the external journal device - */ -static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb) -{ - struct block_device *bdev; - - bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb, - &fs_holder_ops); - if (IS_ERR(bdev)) - goto fail; - return bdev; - -fail: - ext4_msg(sb, KERN_ERR, - "failed to open journal device unknown-block(%u,%u) %ld", - MAJOR(dev), MINOR(dev), PTR_ERR(bdev)); - return NULL; -} - static inline struct inode *orphan_list_entry(struct list_head *l) { return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode; @@ -1251,10 +1283,10 @@ static void ext4_put_super(struct super_block *sb) * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL - * Unregister sysfs before flush sbi->s_error_work. + * Unregister sysfs before flush sbi->s_sb_upd_work. * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If * read metadata verify failed then will queue error work. - * flush_stashed_error_work will call start_this_handle may trigger + * update_super_work will call start_this_handle may trigger * BUG_ON. */ ext4_unregister_sysfs(sb); @@ -1266,18 +1298,17 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_li_request(sb); ext4_quotas_off(sb, EXT4_MAXQUOTAS); - flush_work(&sbi->s_error_work); destroy_workqueue(sbi->rsv_conversion_wq); ext4_release_orphan_info(sb); if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); - err = jbd2_journal_destroy(sbi->s_journal); - sbi->s_journal = NULL; + err = ext4_journal_destroy(sbi, sbi->s_journal); if ((err < 0) && !aborted) { ext4_abort(sb, -err, "Couldn't clean up the journal"); } - } + } else + flush_work(&sbi->s_sb_upd_work); ext4_es_unregister_shrinker(sbi); timer_shutdown_sync(&sbi->s_err_report); @@ -1285,16 +1316,20 @@ static void ext4_put_super(struct super_block *sb) ext4_mb_release(sb); ext4_ext_release(sb); - if (!sb_rdonly(sb) && !aborted) { - ext4_clear_feature_journal_needs_recovery(sb); - ext4_clear_feature_orphan_present(sb); - es->s_state = cpu_to_le16(sbi->s_mount_state); - } - if (!sb_rdonly(sb)) + if (!ext4_emergency_state(sb) && !sb_rdonly(sb)) { + if (!aborted) { + ext4_clear_feature_journal_needs_recovery(sb); + ext4_clear_feature_orphan_present(sb); + es->s_state = cpu_to_le16(sbi->s_mount_state); + } ext4_commit_super(sb); + } ext4_group_desc_free(sbi); ext4_flex_groups_free(sbi); + + WARN_ON_ONCE(!(sbi->s_mount_state & EXT4_ERROR_FS) && + percpu_counter_sum(&sbi->s_dirtyclusters_counter)); ext4_percpu_param_destroy(sbi); #ifdef CONFIG_QUOTA for (int i = 0; i < EXT4_MAXQUOTAS; i++) @@ -1311,14 +1346,14 @@ static void ext4_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); - if (sbi->s_journal_bdev) { + if (sbi->s_journal_bdev_file) { /* * 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->s_journal_bdev); - invalidate_bdev(sbi->s_journal_bdev); + sync_blockdev(file_bdev(sbi->s_journal_bdev_file)); + invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); } ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); @@ -1337,8 +1372,6 @@ static void ext4_put_super(struct super_block *sb) */ 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); fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); @@ -1363,6 +1396,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) inode_set_iversion(&ei->vfs_inode, 1); ei->i_flags = 0; + ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ spin_lock_init(&ei->i_raw_lock); ei->i_prealloc_node = RB_ROOT; atomic_set(&ei->i_prealloc_active, 0); @@ -1373,6 +1407,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_es_all_nr = 0; ei->i_es_shk_nr = 0; ei->i_es_shrink_lblk = 0; + ei->i_es_seq = 0; ei->i_reserved_data_blocks = 0; spin_lock_init(&(ei->i_block_reservation_lock)); ext4_init_pending_tree(&ei->i_pending_tree); @@ -1385,16 +1420,15 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; - atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); ext4_fc_init_inode(&ei->vfs_inode); - mutex_init(&ei->i_fc_lock); + spin_lock_init(&ei->i_fc_lock); return &ei->vfs_inode; } static int ext4_drop_inode(struct inode *inode) { - int drop = generic_drop_inode(inode); + int drop = inode_generic_drop(inode); if (!drop) drop = fscrypt_drop_inode(inode); @@ -1415,9 +1449,9 @@ static void ext4_free_in_core_inode(struct inode *inode) static void ext4_destroy_inode(struct inode *inode) { - if (!list_empty(&(EXT4_I(inode)->i_orphan))) { + if (ext4_inode_orphan_tracked(inode)) { ext4_msg(inode->i_sb, KERN_ERR, - "Inode %lu (%p): orphan list check failed!", + "Inode %lu (%p): inode tracked as orphan!", inode->i_ino, EXT4_I(inode)); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, EXT4_I(inode), sizeof(struct ext4_inode_info), @@ -1425,7 +1459,8 @@ static void ext4_destroy_inode(struct inode *inode) dump_stack(); } - if (EXT4_I(inode)->i_reserved_data_blocks) + if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ERROR_FS) && + WARN_ON_ONCE(EXT4_I(inode)->i_reserved_data_blocks)) ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!", inode->i_ino, EXT4_I(inode), @@ -1446,14 +1481,19 @@ static void init_once(void *foo) init_rwsem(&ei->i_data_sem); inode_init_once(&ei->vfs_inode); ext4_fc_init_inode(&ei->vfs_inode); +#ifdef CONFIG_FS_ENCRYPTION + ei->i_crypt_info = NULL; +#endif +#ifdef CONFIG_FS_VERITY + ei->i_verity_info = NULL; +#endif } static int __init init_inodecache(void) { ext4_inode_cachep = kmem_cache_create_usercopy("ext4_inode_cache", sizeof(struct ext4_inode_info), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| - SLAB_ACCOUNT), + SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, offsetof(struct ext4_inode_info, i_data), sizeof_field(struct ext4_inode_info, i_data), init_once); @@ -1477,7 +1517,7 @@ void ext4_clear_inode(struct inode *inode) ext4_fc_del(inode); invalidate_inode_buffers(inode); clear_inode(inode); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { @@ -1552,7 +1592,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); -static struct dquot **ext4_get_dquots(struct inode *inode) +static struct dquot __rcu **ext4_get_dquots(struct inode *inode) { return EXT4_I(inode)->i_dquot; } @@ -1606,6 +1646,7 @@ static const struct super_operations ext4_sops = { }; static const struct export_operations ext4_export_ops = { + .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, .get_parent = ext4_get_parent, @@ -1675,10 +1716,6 @@ static const struct constant_table ext4_param_dax[] = { {} }; -/* String parameter that allows empty argument */ -#define fsparam_string_empty(NAME, OPT) \ - __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) - /* * Mount option specification * We don't use fsparam_flag_no because of the way we set the @@ -1693,8 +1730,8 @@ static const struct fs_parameter_spec ext4_param_specs[] = { fsparam_flag ("bsdgroups", Opt_grpid), fsparam_flag ("nogrpid", Opt_nogrpid), fsparam_flag ("sysvgroups", Opt_nogrpid), - fsparam_u32 ("resgid", Opt_resgid), - fsparam_u32 ("resuid", Opt_resuid), + fsparam_gid ("resgid", Opt_resgid), + fsparam_uid ("resuid", Opt_resuid), fsparam_u32 ("sb", Opt_sb), fsparam_enum ("errors", Opt_errors, ext4_param_errors), fsparam_flag ("nouid32", Opt_nouid32), @@ -1785,7 +1822,6 @@ static const struct fs_parameter_spec ext4_param_specs[] = { {} }; -#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) #define MOPT_SET 0x0001 #define MOPT_CLEAR 0x0002 @@ -1875,6 +1911,7 @@ static const struct mount_opts { {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, #endif + {Opt_abort, EXT4_MOUNT2_ABORT, MOPT_SET | MOPT_2}, {Opt_err, 0, 0} }; @@ -1943,8 +1980,6 @@ struct ext4_fs_context { unsigned int mask_s_mount_opt; unsigned int vals_s_mount_opt2; unsigned int mask_s_mount_opt2; - unsigned long vals_s_mount_flags; - unsigned long mask_s_mount_flags; unsigned int opt_flags; /* MOPT flags */ unsigned int spec; u32 s_max_batch_time; @@ -1980,6 +2015,9 @@ int ext4_init_fs_context(struct fs_context *fc) fc->fs_private = ctx; fc->ops = &ext4_context_ops; + /* i_version is always enabled now */ + fc->sb_flags |= SB_I_VERSION; + return 0; } @@ -2031,8 +2069,7 @@ static int unnote_qf_name(struct fs_context *fc, int qtype) { struct ext4_fs_context *ctx = fc->fs_private; - if (ctx->s_qf_names[qtype]) - kfree(ctx->s_qf_names[qtype]); + kfree(ctx->s_qf_names[qtype]); ctx->s_qf_names[qtype] = NULL; ctx->qname_spec |= 1 << qtype; @@ -2065,16 +2102,16 @@ static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param, } #define EXT4_SET_CTX(name) \ -static inline void ctx_set_##name(struct ext4_fs_context *ctx, \ - unsigned long flag) \ +static inline __maybe_unused \ +void ctx_set_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name |= flag; \ } #define EXT4_CLEAR_CTX(name) \ -static inline void ctx_clear_##name(struct ext4_fs_context *ctx, \ - unsigned long flag) \ +static inline __maybe_unused \ +void ctx_clear_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name &= ~flag; \ @@ -2095,20 +2132,12 @@ EXT4_SET_CTX(mount_opt2); EXT4_CLEAR_CTX(mount_opt2); EXT4_TEST_CTX(mount_opt2); -static inline void ctx_set_mount_flag(struct ext4_fs_context *ctx, int bit) -{ - set_bit(bit, &ctx->mask_s_mount_flags); - set_bit(bit, &ctx->vals_s_mount_flags); -} - static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; struct fs_parse_result result; const struct mount_opts *m; int is_remount; - kuid_t uid; - kgid_t gid; int token; token = fs_parse(fc, ext4_param_specs, param, &result); @@ -2164,9 +2193,6 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) ext4_msg(NULL, KERN_WARNING, "Ignoring removed %s option", param->key); return 0; - case Opt_abort: - ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED); - return 0; case Opt_inlinecrypt: #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT ctx_set_flags(ctx, SB_INLINECRYPT); @@ -2253,23 +2279,11 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->spec |= EXT4_SPEC_s_stripe; return 0; case Opt_resuid: - uid = make_kuid(current_user_ns(), result.uint_32); - if (!uid_valid(uid)) { - ext4_msg(NULL, KERN_ERR, "Invalid uid value %d", - result.uint_32); - return -EINVAL; - } - ctx->s_resuid = uid; + ctx->s_resuid = result.uid; ctx->spec |= EXT4_SPEC_s_resuid; return 0; case Opt_resgid: - gid = make_kgid(current_user_ns(), result.uint_32); - if (!gid_valid(gid)) { - ext4_msg(NULL, KERN_ERR, "Invalid gid value %d", - result.uint_32); - return -EINVAL; - } - ctx->s_resgid = gid; + ctx->s_resgid = result.gid; ctx->spec |= EXT4_SPEC_s_resgid; return 0; case Opt_journal_dev: @@ -2446,8 +2460,7 @@ static int parse_options(struct fs_context *fc, char *options) param.size = v_len; ret = ext4_parse_param(fc, ¶m); - if (param.string) - kfree(param.string); + kfree(param.string); if (ret < 0) return ret; } @@ -2464,7 +2477,7 @@ static int parse_apply_sb_mount_options(struct super_block *sb, struct ext4_fs_context *m_ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *s_mount_opts = NULL; + char s_mount_opts[64]; struct ext4_fs_context *s_ctx = NULL; struct fs_context *fc = NULL; int ret = -ENOMEM; @@ -2472,15 +2485,12 @@ static int parse_apply_sb_mount_options(struct super_block *sb, if (!sbi->s_es->s_mount_opts[0]) return 0; - s_mount_opts = kstrndup(sbi->s_es->s_mount_opts, - sizeof(sbi->s_es->s_mount_opts), - GFP_KERNEL); - if (!s_mount_opts) - return ret; + if (strscpy_pad(s_mount_opts, sbi->s_es->s_mount_opts) < 0) + return -E2BIG; fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); if (!fc) - goto out_free; + return -ENOMEM; s_ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); if (!s_ctx) @@ -2512,11 +2522,8 @@ parse_failed: ret = 0; out_free: - if (fc) { - ext4_fc_free(fc); - kfree(fc); - } - kfree(s_mount_opts); + ext4_fc_free(fc); + kfree(fc); return ret; } @@ -2754,15 +2761,6 @@ static int ext4_check_opt_consistency(struct fs_context *fc, return -EINVAL; } - if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DIOREAD_NOLOCK)) { - int blocksize = - BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); - if (blocksize < PAGE_SIZE) - ext4_msg(NULL, KERN_WARNING, "Warning: mounting with an " - "experimental mount option 'dioread_nolock' " - "for blocksize < PAGE_SIZE"); - } - err = ext4_check_test_dummy_encryption(fc, sb); if (err) return err; @@ -2782,6 +2780,13 @@ static int ext4_check_opt_consistency(struct fs_context *fc, } if (is_remount) { + if (!sbi->s_journal && + ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT)) { + ext4_msg(NULL, KERN_WARNING, + "Remounting fs w/o journal so ignoring data_err option"); + ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT); + } + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { ext4_msg(NULL, KERN_ERR, "can't mount with " @@ -2820,8 +2825,6 @@ static void ext4_apply_options(struct fs_context *fc, struct super_block *sb) sbi->s_mount_opt |= ctx->vals_s_mount_opt; sbi->s_mount_opt2 &= ~ctx->mask_s_mount_opt2; sbi->s_mount_opt2 |= ctx->vals_s_mount_opt2; - sbi->s_mount_flags &= ~ctx->mask_s_mount_flags; - sbi->s_mount_flags |= ctx->vals_s_mount_flags; sb->s_flags &= ~ctx->mask_s_flags; sb->s_flags |= ctx->vals_s_flags; @@ -2966,11 +2969,11 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, } 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) + ext4_get_resuid(es) != 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) + ext4_get_resgid(es) != 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); @@ -2986,6 +2989,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, 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 (nodefs && sb->s_flags & SB_I_VERSION) + SEQ_OPTS_PUTS("i_version"); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & @@ -3034,6 +3039,15 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PUTS("mb_optimize_scan=1"); } + if (nodefs && !test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) + SEQ_OPTS_PUTS("prefetch_block_bitmaps"); + + if (ext4_emergency_ro(sb)) + SEQ_OPTS_PUTS("emergency_ro"); + + if (ext4_forced_shutdown(sb)) + SEQ_OPTS_PUTS("shutdown"); + ext4_show_quota_options(seq, sb); return 0; } @@ -3050,7 +3064,7 @@ int ext4_seq_options_show(struct seq_file *seq, void *offset) seq_puts(seq, sb_rdonly(sb) ? "ro" : "rw"); rc = _ext4_show_options(seq, sb, 1); - seq_puts(seq, "\n"); + seq_putc(seq, '\n'); return rc; } @@ -3201,19 +3215,19 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, __le32 le_group = cpu_to_le32(block_group); struct ext4_sb_info *sbi = EXT4_SB(sb); - if (ext4_has_metadata_csum(sbi->s_sb)) { + if (ext4_has_feature_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __u32 csum32; __u16 dummy_csum = 0; - csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group, + csum32 = ext4_chksum(sbi->s_csum_seed, (__u8 *)&le_group, sizeof(le_group)); - csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset); - csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum, + csum32 = ext4_chksum(csum32, (__u8 *)gdp, offset); + csum32 = ext4_chksum(csum32, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); if (offset < sbi->s_desc_size) - csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset, + csum32 = ext4_chksum(csum32, (__u8 *)gdp + offset, sbi->s_desc_size - offset); crc = csum32 & 0xFFFF; @@ -3581,14 +3595,12 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#if !IS_ENABLED(CONFIG_UNICODE) - if (ext4_has_feature_casefold(sb)) { + if (!IS_ENABLED(CONFIG_UNICODE) && ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " "mounted without CONFIG_UNICODE"); return 0; } -#endif if (readonly) return 1; @@ -3631,7 +3643,7 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) */ static void print_daily_error_info(struct timer_list *t) { - struct ext4_sb_info *sbi = from_timer(sbi, t, s_err_report); + struct ext4_sb_info *sbi = timer_container_of(sbi, t, s_err_report); struct super_block *sb = sbi->s_sb; struct ext4_super_block *es = sbi->s_es; @@ -3691,7 +3703,8 @@ static int ext4_run_li_request(struct ext4_li_request *elr) if (group >= elr->lr_next_group) { ret = 1; if (elr->lr_first_not_zeroed != ngroups && - !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) { + !ext4_emergency_state(sb) && !sb_rdonly(sb) && + test_opt(sb, INIT_INODE_TABLE)) { elr->lr_next_group = elr->lr_first_not_zeroed; elr->lr_mode = EXT4_LI_MODE_ITABLE; ret = 0; @@ -3715,12 +3728,12 @@ static int ext4_run_li_request(struct ext4_li_request *elr) ret = 1; if (!ret) { - start_time = ktime_get_real_ns(); + start_time = ktime_get_ns(); ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { - elr->lr_timeout = nsecs_to_jiffies((ktime_get_real_ns() - start_time) * + elr->lr_timeout = nsecs_to_jiffies((ktime_get_ns() - start_time) * EXT4_SB(elr->lr_super)->s_li_wait_mult); } elr->lr_next_sched = jiffies + elr->lr_timeout; @@ -3780,8 +3793,9 @@ static int ext4_lazyinit_thread(void *arg) cont_thread: while (true) { - next_wakeup = MAX_JIFFY_OFFSET; + bool next_wakeup_initialized = false; + next_wakeup = 0; mutex_lock(&eli->li_list_mtx); if (list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); @@ -3794,8 +3808,11 @@ cont_thread: lr_request); if (time_before(jiffies, elr->lr_next_sched)) { - if (time_before(elr->lr_next_sched, next_wakeup)) + if (!next_wakeup_initialized || + time_before(elr->lr_next_sched, next_wakeup)) { next_wakeup = elr->lr_next_sched; + next_wakeup_initialized = true; + } continue; } if (down_read_trylock(&elr->lr_super->s_umount)) { @@ -3823,16 +3840,18 @@ cont_thread: elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); } - if (time_before(elr->lr_next_sched, next_wakeup)) + if (!next_wakeup_initialized || + time_before(elr->lr_next_sched, next_wakeup)) { next_wakeup = elr->lr_next_sched; + next_wakeup_initialized = true; + } } mutex_unlock(&eli->li_list_mtx); try_to_freeze(); cur = jiffies; - if ((time_after_eq(cur, next_wakeup)) || - (MAX_JIFFY_OFFSET == next_wakeup)) { + if (!next_wakeup_initialized || time_after_eq(cur, next_wakeup)) { cond_resched(); continue; } @@ -3990,7 +4009,7 @@ int ext4_register_li_request(struct super_block *sb, goto out; } - if (sb_rdonly(sb) || + if (ext4_emergency_state(sb) || sb_rdonly(sb) || (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) && (first_not_zeroed == ngroups || !test_opt(sb, INIT_INODE_TABLE)))) goto out; @@ -4053,7 +4072,7 @@ static int set_journal_csum_feature_set(struct super_block *sb) int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (ext4_has_metadata_csum(sb)) { + if (ext4_has_feature_metadata_csum(sb)) { /* journal checksum v3 */ compat = 0; incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; @@ -4172,7 +4191,7 @@ int ext4_calculate_overhead(struct super_block *sb) unsigned int j_blocks, j_inum = le32_to_cpu(es->s_journal_inum); ext4_group_t i, ngroups = ext4_get_groups_count(sb); ext4_fsblk_t overhead = 0; - char *buf = (char *) get_zeroed_page(GFP_NOFS); + char *buf = kvmalloc(sb->s_blocksize, GFP_NOFS | __GFP_ZERO); if (!buf) return -ENOMEM; @@ -4197,7 +4216,7 @@ int ext4_calculate_overhead(struct super_block *sb) blks = count_overhead(sb, i, buf); overhead += blks; if (blks) - memset(buf, 0, PAGE_SIZE); + memset(buf, 0, sb->s_blocksize); cond_resched(); } @@ -4205,12 +4224,12 @@ int ext4_calculate_overhead(struct super_block *sb) * Add the internal journal blocks whether the journal has been * loaded or not */ - if (sbi->s_journal && !sbi->s_journal_bdev) + if (sbi->s_journal && !sbi->s_journal_bdev_file) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); - if (j_inode) { + if (!IS_ERR(j_inode)) { j_blocks = j_inode->i_size >> sb->s_blocksize_bits; overhead += EXT4_NUM_B2C(sbi, j_blocks); iput(j_inode); @@ -4220,7 +4239,7 @@ int ext4_calculate_overhead(struct super_block *sb) } sbi->s_overhead = overhead; smp_wmb(); - free_page((unsigned long) buf); + kvfree(buf); return 0; } @@ -4341,7 +4360,7 @@ static void ext4_set_def_opts(struct super_block *sb, if (ext4_has_feature_fast_commit(sb)) set_opt2(sb, JOURNAL_FAST_COMMIT); /* don't forget to enable journal_csum when metadata_csum is enabled. */ - if (ext4_has_metadata_csum(sb)) + if (ext4_has_feature_metadata_csum(sb)) set_opt(sb, JOURNAL_CHECKSUM); if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) @@ -4373,8 +4392,7 @@ static void ext4_set_def_opts(struct super_block *sb, ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0)) set_opt(sb, DELALLOC); - if (sb->s_blocksize == PAGE_SIZE) - set_opt(sb, DIOREAD_NOLOCK); + set_opt(sb, DIOREAD_NOLOCK); } static int ext4_handle_clustersize(struct super_block *sb) @@ -4394,22 +4412,6 @@ static int ext4_handle_clustersize(struct super_block *sb) } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); - sbi->s_clusters_per_group = - le32_to_cpu(es->s_clusters_per_group); - if (sbi->s_clusters_per_group > sb->s_blocksize * 8) { - ext4_msg(sb, KERN_ERR, - "#clusters per group too big: %lu", - sbi->s_clusters_per_group); - return -EINVAL; - } - if (sbi->s_blocks_per_group != - (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) { - ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and " - "clusters per group (%lu) inconsistent", - sbi->s_blocks_per_group, - sbi->s_clusters_per_group); - return -EINVAL; - } } else { if (clustersize != sb->s_blocksize) { ext4_msg(sb, KERN_ERR, @@ -4423,9 +4425,21 @@ static int ext4_handle_clustersize(struct super_block *sb) sbi->s_blocks_per_group); return -EINVAL; } - sbi->s_clusters_per_group = sbi->s_blocks_per_group; sbi->s_cluster_bits = 0; } + sbi->s_clusters_per_group = le32_to_cpu(es->s_clusters_per_group); + if (sbi->s_clusters_per_group > sb->s_blocksize * 8) { + ext4_msg(sb, KERN_ERR, "#clusters per group too big: %lu", + sbi->s_clusters_per_group); + return -EINVAL; + } + if (sbi->s_blocks_per_group != + (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) { + ext4_msg(sb, KERN_ERR, + "blocks per group (%lu) and clusters per group (%lu) inconsistent", + sbi->s_blocks_per_group, sbi->s_clusters_per_group); + return -EINVAL; + } sbi->s_cluster_ratio = clustersize / sb->s_blocksize; /* Do we have standard group size of clustersize * 8 blocks ? */ @@ -4435,6 +4449,39 @@ static int ext4_handle_clustersize(struct super_block *sb) return 0; } +/* + * ext4_atomic_write_init: Initializes filesystem min & max atomic write units. + * With non-bigalloc filesystem awu will be based upon filesystem blocksize + * & bdev awu units. + * With bigalloc it will be based upon bigalloc cluster size & bdev awu units. + * @sb: super block + */ +static void ext4_atomic_write_init(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct block_device *bdev = sb->s_bdev; + unsigned int clustersize = EXT4_CLUSTER_SIZE(sb); + + if (!bdev_can_atomic_write(bdev)) + return; + + if (!ext4_has_feature_extents(sb)) + return; + + sbi->s_awu_min = max(sb->s_blocksize, + bdev_atomic_write_unit_min_bytes(bdev)); + sbi->s_awu_max = min(clustersize, + bdev_atomic_write_unit_max_bytes(bdev)); + if (sbi->s_awu_min && sbi->s_awu_max && + sbi->s_awu_min <= sbi->s_awu_max) { + ext4_msg(sb, KERN_NOTICE, "Supports (experimental) DIO atomic writes awu_min: %u, awu_max: %u", + sbi->s_awu_min, sbi->s_awu_max); + } else { + sbi->s_awu_min = 0; + sbi->s_awu_max = 0; + } +} + static void ext4_fast_commit_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -4448,7 +4495,7 @@ static void ext4_fast_commit_init(struct super_block *sb) sbi->s_fc_bytes = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); sbi->s_fc_ineligible_tid = 0; - spin_lock_init(&sbi->s_fc_lock); + mutex_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; sbi->s_fc_replay_state.fc_regions_size = 0; @@ -4598,15 +4645,6 @@ static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_blo ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, ext4_orphan_file_block_trigger); - /* Load the checksum driver */ - sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(sbi->s_chksum_driver)) { - int ret = PTR_ERR(sbi->s_chksum_driver); - ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); - sbi->s_chksum_driver = NULL; - return ret; - } - /* Check superblock checksum */ if (!ext4_superblock_csum_verify(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " @@ -4617,8 +4655,9 @@ static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_blo /* Precompute checksum seed for all metadata */ if (ext4_has_feature_csum_seed(sb)) sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); - else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) - sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, + else if (ext4_has_feature_metadata_csum(sb) || + ext4_has_feature_ea_inode(sb)) + sbi->s_csum_seed = ext4_chksum(~0, es->s_uuid, sizeof(es->s_uuid)); return 0; } @@ -4948,10 +4987,7 @@ static int ext4_load_and_init_journal(struct super_block *sb, return 0; out: - /* flush s_error_work before journal destroy. */ - flush_work(&sbi->s_error_work); - jbd2_journal_destroy(sbi->s_journal); - sbi->s_journal = NULL; + ext4_journal_destroy(sbi, sbi->s_journal); return -EINVAL; } @@ -4988,6 +5024,59 @@ static int ext4_check_journal_data_mode(struct super_block *sb) return 0; } +static const char *ext4_has_journal_option(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) + return "journal_async_commit"; + if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) + return "journal_checksum"; + if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) + return "commit="; + if (EXT4_MOUNT_DATA_FLAGS & + (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) + return "data="; + if (test_opt(sb, DATA_ERR_ABORT)) + return "data_err=abort"; + return NULL; +} + +/* + * Limit the maximum folio order to 2048 blocks to prevent overestimation + * of reserve handle credits during the folio writeback in environments + * where the PAGE_SIZE exceeds 4KB. + */ +#define EXT4_MAX_PAGECACHE_ORDER(sb) \ + umin(MAX_PAGECACHE_ORDER, (11 + (sb)->s_blocksize_bits - PAGE_SHIFT)) +static void ext4_set_max_mapping_order(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) + sbi->s_max_folio_order = sbi->s_min_folio_order; + else + sbi->s_max_folio_order = EXT4_MAX_PAGECACHE_ORDER(sb); +} + +static int ext4_check_large_folio(struct super_block *sb) +{ + const char *err_str = NULL; + + if (ext4_has_feature_encrypt(sb)) + err_str = "encrypt"; + + if (!err_str) { + ext4_set_max_mapping_order(sb); + } else if (sb->s_blocksize > PAGE_SIZE) { + ext4_msg(sb, KERN_ERR, "bs(%lu) > ps(%lu) unsupported for %s", + sb->s_blocksize, PAGE_SIZE, err_str); + return -EINVAL; + } + + return 0; +} + static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb, int silent) { @@ -5055,11 +5144,8 @@ static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb, * If the default block size is not the same as the real block size, * we need to reload it. */ - if (sb->s_blocksize == blocksize) { - *lsb = logical_sb_block; - sbi->s_sbh = bh; - return 0; - } + if (sb->s_blocksize == blocksize) + goto success; /* * bh must be released before kill_bdev(), otherwise @@ -5090,6 +5176,9 @@ static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb, ext4_msg(sb, KERN_ERR, "Magic mismatch, very weird!"); goto out; } + +success: + sbi->s_min_folio_order = get_order(blocksize); *lsb = logical_sb_block; sbi->s_sbh = bh; return 0; @@ -5098,16 +5187,27 @@ out: return ret; } -static void ext4_hash_info_init(struct super_block *sb) +static int ext4_hash_info_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; unsigned int i; + sbi->s_def_hash_version = es->s_def_hash_version; + + if (sbi->s_def_hash_version > DX_HASH_LAST) { + ext4_msg(sb, KERN_ERR, + "Invalid default hash set in the superblock"); + return -EINVAL; + } else if (sbi->s_def_hash_version == DX_HASH_SIPHASH) { + ext4_msg(sb, KERN_ERR, + "SIPHASH is not a valid default hash value"); + return -EINVAL; + } + for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); - sbi->s_def_hash_version = es->s_def_hash_version; if (ext4_has_feature_dir_index(sb)) { i = le32_to_cpu(es->s_flags); if (i & EXT2_FLAGS_UNSIGNED_HASH) @@ -5125,6 +5225,7 @@ static void ext4_hash_info_init(struct super_block *sb) #endif } } + return 0; } static int ext4_block_group_meta_init(struct super_block *sb, int silent) @@ -5176,6 +5277,18 @@ static int ext4_block_group_meta_init(struct super_block *sb, int silent) return 0; } +/* + * It's hard to get stripe aligned blocks if stripe is not aligned with + * cluster, just disable stripe and alert user to simplify code and avoid + * stripe aligned allocation which will rarely succeed. + */ +static bool ext4_is_stripe_incompatible(struct super_block *sb, unsigned long stripe) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + return (stripe > 0 && sbi->s_cluster_ratio > 1 && + stripe % sbi->s_cluster_ratio != 0); +} + static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) { struct ext4_super_block *es = NULL; @@ -5190,7 +5303,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) /* Set defaults for the variables that will be set during parsing */ if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) - ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + ctx->journal_ioprio = EXT4_DEF_JOURNAL_IOPRIO; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sectors_written_start = @@ -5209,11 +5322,13 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_set_def_opts(sb, es); - sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); - sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); + sbi->s_resuid = make_kuid(&init_user_ns, ext4_get_resuid(es)); + sbi->s_resgid = make_kgid(&init_user_ns, ext4_get_resuid(es)); sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; + sbi->s_sb_update_kb = EXT4_DEF_SB_UPDATE_INTERVAL_KB; + sbi->s_sb_update_sec = EXT4_DEF_SB_UPDATE_INTERVAL_SEC; /* * set default s_li_wait_mult for lazyinit, for the case there is @@ -5238,6 +5353,10 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_apply_options(fc, sb); + err = ext4_check_large_folio(sb); + if (err < 0) + goto failed_mount; + err = ext4_encoding_init(sb, es); if (err) goto failed_mount; @@ -5249,8 +5368,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); - /* i_version is always enabled now */ - sb->s_flags |= SB_I_VERSION; + /* HSM events are allowed by default. */ + sb->s_iflags |= SB_I_ALLOW_HSM; err = ext4_check_feature_compatibility(sb, es, silent); if (err) @@ -5260,7 +5379,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (err) goto failed_mount; - ext4_hash_info_init(sb); + err = ext4_hash_info_init(sb); + if (err) + goto failed_mount; err = ext4_handle_clustersize(sb); if (err) @@ -5272,7 +5393,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); - INIT_WORK(&sbi->s_error_work, flush_stashed_error_work); + INIT_WORK(&sbi->s_sb_upd_work, update_super_work); err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); if (err) @@ -5283,13 +5404,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) goto failed_mount3; sbi->s_stripe = ext4_get_stripe_size(sbi); - /* - * It's hard to get stripe aligned blocks if stripe is not aligned with - * cluster, just disable stripe and alert user to simpfy code and avoid - * stripe aligned allocation which will rarely successes. - */ - if (sbi->s_stripe > 0 && sbi->s_cluster_ratio > 1 && - sbi->s_stripe % sbi->s_cluster_ratio != 0) { + if (ext4_is_stripe_incompatible(sb, sbi->s_stripe)) { ext4_msg(sb, KERN_WARNING, "stripe (%lu) is not aligned with cluster size (%u), " "stripe is disabled", @@ -5318,11 +5433,15 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif - memcpy(&sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); + super_set_uuid(sb, es->s_uuid, sizeof(es->s_uuid)); + super_set_sysfs_name_bdev(sb); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); + spin_lock_init(&sbi->s_bdev_wb_lock); + + ext4_atomic_write_init(sb); ext4_fast_commit_init(sb); sb->s_root = NULL; @@ -5346,36 +5465,25 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) err = ext4_load_and_init_journal(sb, es, ctx); if (err) goto failed_mount3a; + if (bdev_read_only(sb->s_bdev)) + needs_recovery = 0; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); goto failed_mount3a; } else { + const char *journal_option; + /* Nojournal mode, all journal mount options are illegal */ - if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "journal_async_commit, fs mounted w/o journal"); + journal_option = ext4_has_journal_option(sb); + if (journal_option != NULL) { + ext4_msg(sb, KERN_ERR, + "can't mount with %s, fs mounted w/o journal", + journal_option); goto failed_mount3a; } - if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "journal_checksum, fs mounted w/o journal"); - goto failed_mount3a; - } - if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "commit=%lu, fs mounted w/o journal", - sbi->s_commit_interval / HZ); - goto failed_mount3a; - } - if (EXT4_MOUNT_DATA_FLAGS & - (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "data=, fs mounted w/o journal"); - goto failed_mount3a; - } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); @@ -5456,6 +5564,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) goto failed_mount4; } + generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); @@ -5527,19 +5636,15 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (err) goto failed_mount6; - err = ext4_register_sysfs(sb); - if (err) - goto failed_mount7; - err = ext4_init_orphan_info(sb); if (err) - goto failed_mount8; + goto failed_mount7; #ifdef CONFIG_QUOTA /* Enable quota usage during mount. */ if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) { err = ext4_enable_quotas(sb); if (err) - goto failed_mount9; + goto failed_mount8; } #endif /* CONFIG_QUOTA */ @@ -5547,8 +5652,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) * Save the original bdev mapping's wb_err value which could be * used to detect the metadata async write error. */ - spin_lock_init(&sbi->s_bdev_wb_lock); - errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, + errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err, &sbi->s_bdev_wb_err); EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); @@ -5565,12 +5669,14 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_msg(sb, KERN_INFO, "recovery complete"); err = ext4_mark_recovery_complete(sb, es); if (err) - goto failed_mount10; + goto failed_mount9; } - if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) + if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) { ext4_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but the device does not support discard"); + clear_opt(sb, DISCARD); + } if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ @@ -5582,15 +5688,17 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) atomic_set(&sbi->s_warning_count, 0); atomic_set(&sbi->s_msg_count, 0); + /* Register sysfs after all initializations are complete. */ + err = ext4_register_sysfs(sb); + if (err) + goto failed_mount9; + return 0; -failed_mount10: +failed_mount9: ext4_quotas_off(sb, EXT4_MAXQUOTAS); -failed_mount9: __maybe_unused +failed_mount8: __maybe_unused ext4_release_orphan_info(sb); -failed_mount8: - ext4_unregister_sysfs(sb); - kobject_put(&sbi->s_kobj); failed_mount7: ext4_unregister_li_request(sb); failed_mount6: @@ -5615,23 +5723,17 @@ failed_mount_wq: sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { - /* flush s_error_work before journal destroy. */ - flush_work(&sbi->s_error_work); - jbd2_journal_destroy(sbi->s_journal); - sbi->s_journal = NULL; + ext4_journal_destroy(sbi, sbi->s_journal); } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: - /* flush s_error_work before sbi destroy */ - flush_work(&sbi->s_error_work); - del_timer_sync(&sbi->s_err_report); + /* flush s_sb_upd_work before sbi destroy */ + flush_work(&sbi->s_sb_upd_work); ext4_stop_mmpd(sbi); + timer_delete_sync(&sbi->s_err_report); ext4_group_desc_free(sbi); failed_mount: - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); - #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif @@ -5642,9 +5744,9 @@ failed_mount: #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); brelse(sbi->s_sbh); - if (sbi->s_journal_bdev) { - invalidate_bdev(sbi->s_journal_bdev); - blkdev_put(sbi->s_journal_bdev, sb); + if (sbi->s_journal_bdev_file) { + invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); + bdev_fput(sbi->s_journal_bdev_file); } out_fail: invalidate_bdev(sb->s_bdev); @@ -5726,10 +5828,6 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal) journal->j_flags |= JBD2_BARRIER; else journal->j_flags &= ~JBD2_BARRIER; - if (test_opt(sb, DATA_ERR_ABORT)) - journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR; - else - journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR; /* * Always enable journal cycle record option, letting the journal * records log transactions continuously between each mount. @@ -5751,22 +5849,22 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, journal_inode = ext4_iget(sb, journal_inum, EXT4_IGET_SPECIAL); if (IS_ERR(journal_inode)) { ext4_msg(sb, KERN_ERR, "no journal found"); - return NULL; + return ERR_CAST(journal_inode); } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); ext4_msg(sb, KERN_ERR, "journal inode is deleted"); - return NULL; + return ERR_PTR(-EFSCORRUPTED); } - - ext4_debug("Journal inode found at %p: %lld bytes\n", - journal_inode, journal_inode->i_size); if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); - return NULL; + return ERR_PTR(-EFSCORRUPTED); } + + ext4_debug("Journal inode found at %p: %lld bytes\n", + journal_inode, journal_inode->i_size); return journal_inode; } @@ -5785,31 +5883,28 @@ static int ext4_journal_bmap(journal_t *journal, sector_t *block) ext4_msg(journal->j_inode->i_sb, KERN_CRIT, "journal bmap failed: block %llu ret %d\n", *block, ret); - jbd2_journal_abort(journal, ret ? ret : -EIO); + jbd2_journal_abort(journal, ret ? ret : -EFSCORRUPTED); return ret; } *block = map.m_pblk; return 0; } -static journal_t *ext4_get_journal(struct super_block *sb, - unsigned int journal_inum) +static journal_t *ext4_open_inode_journal(struct super_block *sb, + unsigned int journal_inum) { struct inode *journal_inode; journal_t *journal; - if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) - return NULL; - journal_inode = ext4_get_journal_inode(sb, journal_inum); - if (!journal_inode) - return NULL; + if (IS_ERR(journal_inode)) + return ERR_CAST(journal_inode); journal = jbd2_journal_init_inode(journal_inode); - if (!journal) { + if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "Could not load journal inode"); iput(journal_inode); - return NULL; + return ERR_CAST(journal); } journal->j_private = sb; journal->j_bmap = ext4_journal_bmap; @@ -5817,43 +5912,47 @@ static journal_t *ext4_get_journal(struct super_block *sb, return journal; } -static journal_t *ext4_get_dev_journal(struct super_block *sb, - dev_t j_dev) +static struct file *ext4_get_journal_blkdev(struct super_block *sb, + dev_t j_dev, ext4_fsblk_t *j_start, + ext4_fsblk_t *j_len) { struct buffer_head *bh; - journal_t *journal; - ext4_fsblk_t start; - ext4_fsblk_t len; + struct block_device *bdev; + struct file *bdev_file; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; struct ext4_super_block *es; - struct block_device *bdev; - - if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) - return NULL; + int errno; - /* see get_tree_bdev why this is needed and safe */ - up_write(&sb->s_umount); - bdev = ext4_blkdev_get(j_dev, sb); - down_write(&sb->s_umount); - if (bdev == NULL) - return NULL; + bdev_file = bdev_file_open_by_dev(j_dev, + BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES, + sb, &fs_holder_ops); + if (IS_ERR(bdev_file)) { + ext4_msg(sb, KERN_ERR, + "failed to open journal device unknown-block(%u,%u) %ld", + MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_file)); + return bdev_file; + } + bdev = file_bdev(bdev_file); blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { ext4_msg(sb, KERN_ERR, "blocksize too small for journal device"); + errno = -EINVAL; goto out_bdev; } sb_block = EXT4_MIN_BLOCK_SIZE / blocksize; offset = EXT4_MIN_BLOCK_SIZE % blocksize; - set_blocksize(bdev, blocksize); - if (!(bh = __bread(bdev, sb_block, blocksize))) { + set_blocksize(bdev_file, blocksize); + bh = __bread(bdev, sb_block, blocksize); + if (!bh) { ext4_msg(sb, KERN_ERR, "couldn't read superblock of " "external journal"); + errno = -EINVAL; goto out_bdev; } @@ -5861,57 +5960,74 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { - ext4_msg(sb, KERN_ERR, "external journal has " - "bad superblock"); - brelse(bh); - goto out_bdev; + ext4_msg(sb, KERN_ERR, "external journal has bad superblock"); + errno = -EFSCORRUPTED; + goto out_bh; } if ((le32_to_cpu(es->s_feature_ro_compat) & EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && - es->s_checksum != ext4_superblock_csum(sb, es)) { - ext4_msg(sb, KERN_ERR, "external journal has " - "corrupt superblock"); - brelse(bh); - goto out_bdev; + es->s_checksum != ext4_superblock_csum(es)) { + ext4_msg(sb, KERN_ERR, "external journal has corrupt superblock"); + errno = -EFSCORRUPTED; + goto out_bh; } if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { ext4_msg(sb, KERN_ERR, "journal UUID does not match"); - brelse(bh); - goto out_bdev; + errno = -EFSCORRUPTED; + goto out_bh; } - len = ext4_blocks_count(es); - start = sb_block + 1; - brelse(bh); /* we're done with the superblock */ + *j_start = sb_block + 1; + *j_len = ext4_blocks_count(es); + brelse(bh); + return bdev_file; - journal = jbd2_journal_init_dev(bdev, sb->s_bdev, - start, len, blocksize); - if (!journal) { +out_bh: + brelse(bh); +out_bdev: + bdev_fput(bdev_file); + return ERR_PTR(errno); +} + +static journal_t *ext4_open_dev_journal(struct super_block *sb, + dev_t j_dev) +{ + journal_t *journal; + ext4_fsblk_t j_start; + ext4_fsblk_t j_len; + struct file *bdev_file; + int errno = 0; + + bdev_file = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); + if (IS_ERR(bdev_file)) + return ERR_CAST(bdev_file); + + journal = jbd2_journal_init_dev(file_bdev(bdev_file), sb->s_bdev, j_start, + j_len, sb->s_blocksize); + if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); + errno = PTR_ERR(journal); goto out_bdev; } - journal->j_private = sb; - if (ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO, true)) { - ext4_msg(sb, KERN_ERR, "I/O error on journal device"); - goto out_journal; - } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { ext4_msg(sb, KERN_ERR, "External journal has more than one " "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); + errno = -EINVAL; goto out_journal; } - EXT4_SB(sb)->s_journal_bdev = bdev; + journal->j_private = sb; + EXT4_SB(sb)->s_journal_bdev_file = bdev_file; ext4_init_journal_params(sb, journal); return journal; out_journal: - jbd2_journal_destroy(journal); + ext4_journal_destroy(EXT4_SB(sb), journal); out_bdev: - blkdev_put(bdev, sb); - return NULL; + bdev_fput(bdev_file); + return ERR_PTR(errno); } static int ext4_load_journal(struct super_block *sb, @@ -5943,13 +6059,13 @@ static int ext4_load_journal(struct super_block *sb, } if (journal_inum) { - journal = ext4_get_journal(sb, journal_inum); - if (!journal) - return -EINVAL; + journal = ext4_open_inode_journal(sb, journal_inum); + if (IS_ERR(journal)) + return PTR_ERR(journal); } else { - journal = ext4_get_dev_journal(sb, journal_dev); - if (!journal) - return -EINVAL; + journal = ext4_open_dev_journal(sb, journal_dev); + if (IS_ERR(journal)) + return PTR_ERR(journal); } journal_dev_ro = bdev_read_only(journal->j_dev); @@ -6025,8 +6141,7 @@ static int ext4_load_journal(struct super_block *sb, EXT4_SB(sb)->s_journal = journal; err = ext4_clear_journal_err(sb, es); if (err) { - EXT4_SB(sb)->s_journal = NULL; - jbd2_journal_destroy(journal); + ext4_journal_destroy(EXT4_SB(sb), journal); return err; } @@ -6044,7 +6159,7 @@ static int ext4_load_journal(struct super_block *sb, return 0; err_out: - jbd2_journal_destroy(journal); + ext4_journal_destroy(EXT4_SB(sb), journal); return err; } @@ -6066,7 +6181,7 @@ static void ext4_update_super(struct super_block *sb) * the clock is set in the future, and this will cause e2fsck * to complain and force a full file system check. */ - if (!(sb->s_flags & SB_RDONLY)) + if (!sb_rdonly(sb)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = cpu_to_le64(sbi->s_kbytes_written + @@ -6088,8 +6203,8 @@ static void ext4_update_super(struct super_block *sb) __ext4_update_tstamp(&es->s_first_error_time, &es->s_first_error_time_hi, sbi->s_first_error_time); - strncpy(es->s_first_error_func, sbi->s_first_error_func, - sizeof(es->s_first_error_func)); + strtomem_pad(es->s_first_error_func, + sbi->s_first_error_func, 0); es->s_first_error_line = cpu_to_le32(sbi->s_first_error_line); es->s_first_error_ino = @@ -6102,8 +6217,7 @@ static void ext4_update_super(struct super_block *sb) __ext4_update_tstamp(&es->s_last_error_time, &es->s_last_error_time_hi, sbi->s_last_error_time); - strncpy(es->s_last_error_func, sbi->s_last_error_func, - sizeof(es->s_last_error_func)); + strtomem_pad(es->s_last_error_func, sbi->s_last_error_func, 0); es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line); es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino); es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block); @@ -6130,8 +6244,6 @@ static int ext4_commit_super(struct super_block *sb) if (!sbh) return -EINVAL; - if (block_device_ejected(sb)) - return -ENODEV; ext4_update_super(sb); @@ -6264,13 +6376,7 @@ static int ext4_clear_journal_err(struct super_block *sb, */ int ext4_force_commit(struct super_block *sb) { - journal_t *journal; - - if (sb_rdonly(sb)) - return 0; - - journal = EXT4_SB(sb)->s_journal; - return ext4_journal_force_commit(journal); + return ext4_journal_force_commit(EXT4_SB(sb)->s_journal); } static int ext4_sync_fs(struct super_block *sb, int wait) @@ -6280,8 +6386,9 @@ static int ext4_sync_fs(struct super_block *sb, int wait) bool needs_barrier = false; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (unlikely(ext4_forced_shutdown(sbi))) - return 0; + ret = ext4_emergency_state(sb); + if (unlikely(ret)) + return ret; trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->rsv_conversion_wq); @@ -6329,12 +6436,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) static int ext4_freeze(struct super_block *sb) { int error = 0; - journal_t *journal; - - if (sb_rdonly(sb)) - return 0; - - journal = EXT4_SB(sb)->s_journal; + journal_t *journal = EXT4_SB(sb)->s_journal; if (journal) { /* Now we set up the journal barrier. */ @@ -6368,7 +6470,7 @@ out: */ static int ext4_unfreeze(struct super_block *sb) { - if (sb_rdonly(sb) || ext4_forced_shutdown(EXT4_SB(sb))) + if (ext4_emergency_state(sb)) return 0; if (EXT4_SB(sb)->s_journal) { @@ -6407,6 +6509,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; + int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -6443,11 +6546,29 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) ctx->journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; else - ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + ctx->journal_ioprio = EXT4_DEF_JOURNAL_IOPRIO; } + if ((ctx->spec & EXT4_SPEC_s_stripe) && + ext4_is_stripe_incompatible(sb, ctx->s_stripe)) { + ext4_msg(sb, KERN_WARNING, + "stripe (%lu) is not aligned with cluster size (%u), " + "stripe is disabled", + ctx->s_stripe, sbi->s_cluster_ratio); + ctx->s_stripe = 0; + } + + /* + * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause + * two calls to ext4_should_dioread_nolock() to return inconsistent + * values, triggering WARN_ON in ext4_add_complete_io(). we grab + * here s_writepages_rwsem to avoid race between writepages ops and + * remount. + */ + alloc_ctx = ext4_writepages_down_write(sb); ext4_apply_options(fc, sb); + ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -6484,8 +6605,12 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) goto restore_opts; } - if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) - ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); + if ((old_opts.s_mount_opt & EXT4_MOUNT_DELALLOC) && + !test_opt(sb, DELALLOC)) { + ext4_msg(sb, KERN_ERR, "can't disable delalloc during remount"); + err = -EINVAL; + goto restore_opts; + } sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); @@ -6498,10 +6623,10 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } /* Flush outstanding errors before changing fs state */ - flush_work(&sbi->s_error_work); + flush_work(&sbi->s_sb_upd_work); if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) { - if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) { + if (ext4_emergency_state(sb)) { err = -EROFS; goto restore_opts; } @@ -6655,6 +6780,14 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); + /* + * Handle aborting the filesystem as the last thing during remount to + * avoid obsure errors during remount when some option changes fail to + * apply due to shutdown filesystem. + */ + if (test_opt2(sb, ABORT)) + ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); + return 0; restore_opts: @@ -6662,9 +6795,11 @@ restore_opts: * If there was a failing r/w to ro transition, we may need to * re-enable quota */ - if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) && + if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); + + alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -6673,6 +6808,8 @@ restore_opts: sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + ext4_writepages_up_write(sb, alloc_ctx); + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA @@ -6694,6 +6831,7 @@ static int ext4_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; int ret; + bool old_ro = sb_rdonly(sb); fc->s_fs_info = EXT4_SB(sb); @@ -6705,9 +6843,9 @@ static int ext4_reconfigure(struct fs_context *fc) if (ret < 0) return ret; - ext4_msg(sb, KERN_INFO, "re-mounted %pU %s. Quota mode: %s.", - &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", - ext4_quota_mode(sb)); + ext4_msg(sb, KERN_INFO, "re-mounted %pU%s.", + &sb->s_uuid, + (old_ro != sb_rdonly(sb)) ? (sb_rdonly(sb) ? " ro" : " r/w") : ""); return 0; } @@ -6731,22 +6869,29 @@ static int ext4_statfs_project(struct super_block *sb, dquot->dq_dqb.dqb_bhardlimit); limit >>= sb->s_blocksize_bits; - if (limit && buf->f_blocks > limit) { + if (limit) { + uint64_t remaining = 0; + curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; - buf->f_blocks = limit; - buf->f_bfree = buf->f_bavail = - (buf->f_blocks > curblock) ? - (buf->f_blocks - curblock) : 0; + if (limit > curblock) + remaining = limit - curblock; + + buf->f_blocks = min(buf->f_blocks, limit); + buf->f_bfree = min(buf->f_bfree, remaining); + buf->f_bavail = min(buf->f_bavail, remaining); } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); - if (limit && buf->f_files > limit) { - buf->f_files = limit; - buf->f_ffree = - (buf->f_files > dquot->dq_dqb.dqb_curinodes) ? - (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; + if (limit) { + uint64_t remaining = 0; + + if (limit > dquot->dq_dqb.dqb_curinodes) + remaining = limit - dquot->dq_dqb.dqb_curinodes; + + buf->f_files = min(buf->f_files, limit); + buf->f_ffree = min(buf->f_ffree, remaining); } spin_unlock(&dquot->dq_dqb_lock); @@ -6815,6 +6960,10 @@ static int ext4_write_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to commit dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6831,6 +6980,10 @@ static int ext4_acquire_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to acquire dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6841,18 +6994,39 @@ static int ext4_release_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; + bool freeze_protected = false; + + /* + * Trying to sb_start_intwrite() in a running transaction + * can result in a deadlock. Further, running transactions + * are already protected from freezing. + */ + if (!ext4_journal_current_handle()) { + sb_start_intwrite(dquot->dq_sb); + freeze_protected = true; + } handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); + if (freeze_protected) + sb_end_intwrite(dquot->dq_sb); return PTR_ERR(handle); } ret = dquot_release(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to release dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; + + if (freeze_protected) + sb_end_intwrite(dquot->dq_sb); + return ret; } @@ -7071,6 +7245,13 @@ static int ext4_quota_off(struct super_block *sb, int type) err = dquot_quota_off(sb, type); if (err || ext4_has_feature_quota(sb)) goto out_put; + /* + * When the filesystem was remounted read-only first, we cannot cleanup + * inode flags here. Bad luck but people should be using QUOTA feature + * these days anyway. + */ + if (sb_rdonly(sb)) + goto out_put; inode_lock(inode); /* @@ -7085,7 +7266,7 @@ static int ext4_quota_off(struct super_block *sb, int type) } EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out_unlock: @@ -7183,7 +7364,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, } lock_buffer(bh); memcpy(bh->b_data+offset, data, len); - flush_dcache_page(bh->b_page); + flush_dcache_folio(bh->b_folio); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); brelse(bh); @@ -7258,12 +7439,12 @@ static inline int ext3_feature_set_ok(struct super_block *sb) static void ext4_kill_sb(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct block_device *journal_bdev = sbi ? sbi->s_journal_bdev : NULL; + struct file *bdev_file = sbi ? sbi->s_journal_bdev_file : NULL; kill_block_super(sb); - if (journal_bdev) - blkdev_put(journal_bdev, sb); + if (bdev_file) + bdev_fput(bdev_file); } static struct file_system_type ext4_fs_type = { @@ -7272,16 +7453,14 @@ static struct file_system_type ext4_fs_type = { .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, - .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME | + FS_LBS, }; MODULE_ALIAS_FS("ext4"); -/* Shared across all ext4 file systems */ -wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; - static int __init ext4_init_fs(void) { - int i, err; + int err; ratelimit_state_init(&ext4_mount_msg_ratelimit, 30 * HZ, 64); ext4_li_info = NULL; @@ -7289,9 +7468,6 @@ static int __init ext4_init_fs(void) /* Build-time check for flags consistency */ ext4_check_flag_values(); - for (i = 0; i < EXT4_WQ_HASH_SZ; i++) - init_waitqueue_head(&ext4__ioend_wq[i]); - err = ext4_init_es(); if (err) return err; @@ -7378,6 +7554,5 @@ static void __exit ext4_exit_fs(void) MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crc32c"); module_init(ext4_init_fs) module_exit(ext4_exit_fs) |