Merge tag 'ext4_for_linus-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Many ext4 and jbd2 cleanups and bug fixes:

   - Cleanups in the ext4 remount code when going to and from read-only

   - Cleanups in ext4's multiblock allocator

   - Cleanups in the jbd2 setup/mounting code paths

   - Performance improvements when appending to a delayed allocation file

   - Miscellaneous syzbot and other bug fixes"

* tag 'ext4_for_linus-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (60 commits)
  ext4: fix slab-use-after-free in ext4_es_insert_extent()
  libfs: remove redundant checks of s_encoding
  ext4: remove redundant checks of s_encoding
  ext4: reject casefold inode flag without casefold feature
  ext4: use LIST_HEAD() to initialize the list_head in mballoc.c
  ext4: do not mark inode dirty every time when appending using delalloc
  ext4: rename s_error_work to s_sb_upd_work
  ext4: add periodic superblock update check
  ext4: drop dio overwrite only flag and associated warning
  ext4: add correct group descriptors and reserved GDT blocks to system zone
  ext4: remove unused function declaration
  ext4: mballoc: avoid garbage value from err
  ext4: use sbi instead of EXT4_SB(sb) in ext4_mb_new_blocks_simple()
  ext4: change the type of blocksize in ext4_mb_init_cache()
  ext4: fix unttached inode after power cut with orphan file feature enabled
  jbd2: correct the end of the journal recovery scan range
  ext4: ext4_get_{dev}_journal return proper error value
  ext4: cleanup ext4_get_dev_journal() and ext4_get_journal()
  jbd2: jbd2_journal_init_{dev,inode} return proper error return value
  jbd2: drop useless error tag in jbd2_journal_wipe()
  ...

Author: torvalds

fs/ext4/balloc.c

@@ -913,11 +913,11 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
 }
 
 /*
- * This function returns the number of file system metadata clusters at
+ * This function returns the number of file system metadata blocks at
  * the beginning of a block group, including the reserved gdt blocks.
  */
-static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
-				     ext4_group_t block_group)
+unsigned int ext4_num_base_meta_blocks(struct super_block *sb,
+				       ext4_group_t block_group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	unsigned num;
@@ -935,8 +935,15 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
 	} else { /* For META_BG_BLOCK_GROUPS */
 		num += ext4_bg_num_gdb_meta(sb, block_group);
 	}
-	return EXT4_NUM_B2C(sbi, num);
+	return num;
 }
+
+static unsigned int ext4_num_base_meta_clusters(struct super_block *sb,
+						ext4_group_t block_group)
+{
+	return EXT4_NUM_B2C(EXT4_SB(sb), ext4_num_base_meta_blocks(sb, block_group));
+}
+
 /**
  *	ext4_inode_to_goal_block - return a hint for block allocation
  *	@inode: inode for block allocation

fs/ext4/block_validity.c

@@ -215,20 +215,20 @@ int ext4_setup_system_zone(struct super_block *sb)
 	struct ext4_system_blocks *system_blks;
 	struct ext4_group_desc *gdp;
 	ext4_group_t i;
-	int flex_size = ext4_flex_bg_size(sbi);
 	int ret;
 
 	system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL);
 	if (!system_blks)
 		return -ENOMEM;
 
 	for (i=0; i < ngroups; i++) {
+		unsigned int meta_blks = ext4_num_base_meta_blocks(sb, i);
+
 		cond_resched();
-		if (ext4_bg_has_super(sb, i) &&
-		    ((i < 5) || ((i % flex_size) == 0))) {
+		if (meta_blks != 0) {
 			ret = add_system_zone(system_blks,
 					ext4_group_first_block_no(sb, i),
-					ext4_bg_num_gdb(sb, i) + 1, 0);
+					meta_blks, 0);
 			if (ret)
 				goto err;
 		}

fs/ext4/crypto.c

@@ -33,6 +33,8 @@ int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
 
 #if IS_ENABLED(CONFIG_UNICODE)
 	err = ext4_fname_setup_ci_filename(dir, iname, fname);
+	if (err)
+		ext4_fname_free_filename(fname);
 #endif
 	return err;
 }
@@ -51,6 +53,8 @@ int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry,
 
 #if IS_ENABLED(CONFIG_UNICODE)
 	err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
+	if (err)
+		ext4_fname_free_filename(fname);
 #endif
 	return err;
 }

fs/ext4/ext4.h

@@ -176,9 +176,6 @@ enum criteria {
 	EXT4_MB_NUM_CRS
 };
 
-/* criteria below which we use fast block scanning and avoid unnecessary IO */
-#define CR_FAST CR_GOAL_LEN_SLOW
-
 /*
  * Flags used in mballoc's allocation_context flags field.
  *
@@ -1241,6 +1238,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT2_MB_OPTIMIZE_SCAN	0x00000080 /* Optimize group
 						    * scanning in mballoc
 						    */
+#define EXT4_MOUNT2_ABORT		0x00000100 /* Abort filesystem */
 
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
@@ -1258,10 +1256,8 @@ struct ext4_inode_info {
 
 #define ext4_test_and_set_bit		__test_and_set_bit_le
 #define ext4_set_bit			__set_bit_le
-#define ext4_set_bit_atomic		ext2_set_bit_atomic
 #define ext4_test_and_clear_bit		__test_and_clear_bit_le
 #define ext4_clear_bit			__clear_bit_le
-#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
 #define ext4_test_bit			test_bit_le
 #define ext4_find_next_zero_bit		find_next_zero_bit_le
 #define ext4_find_next_bit		find_next_bit_le
@@ -1708,10 +1704,13 @@ struct ext4_sb_info {
 	const char *s_last_error_func;
 	time64_t s_last_error_time;
 	/*
-	 * If we are in a context where we cannot update error information in
-	 * the on-disk superblock, we queue this work to do it.
+	 * If we are in a context where we cannot update the on-disk
+	 * superblock, we queue the work here.  This is used to update
+	 * the error information in the superblock, and for periodic
+	 * updates of the superblock called from the commit callback
+	 * function.
 	 */
-	struct work_struct s_error_work;
+	struct work_struct s_sb_upd_work;
 
 	/* Ext4 fast commit sub transaction ID */
 	atomic_t s_fc_subtid;
@@ -1804,7 +1803,6 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
  */
 enum {
 	EXT4_MF_MNTDIR_SAMPLED,
-	EXT4_MF_FS_ABORTED,	/* Fatal error detected */
 	EXT4_MF_FC_INELIGIBLE	/* Fast commit ineligible */
 };
 
@@ -2228,9 +2226,9 @@ extern int ext4_feature_set_ok(struct super_block *sb, int readonly);
 #define EXT4_FLAGS_SHUTDOWN	1
 #define EXT4_FLAGS_BDEV_IS_DAX	2
 
-static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
+static inline int ext4_forced_shutdown(struct super_block *sb)
 {
-	return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+	return test_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags);
 }
 
 /*
@@ -2708,7 +2706,6 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
 				    s64 nclusters, unsigned int flags);
 extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
-extern void ext4_check_blocks_bitmap(struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 						    ext4_group_t block_group,
 						    struct buffer_head ** bh);
@@ -2864,7 +2861,6 @@ extern void ext4_free_inode(handle_t *, struct inode *);
 extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
 extern unsigned long ext4_count_free_inodes(struct super_block *);
 extern unsigned long ext4_count_dirs(struct super_block *);
-extern void ext4_check_inodes_bitmap(struct super_block *);
 extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
 extern int ext4_init_inode_table(struct super_block *sb,
 				 ext4_group_t group, int barrier);
@@ -2907,7 +2903,6 @@ extern int ext4_mb_init(struct super_block *);
 extern int ext4_mb_release(struct super_block *);
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
-extern int ext4_mb_reserve_blocks(struct super_block *, int);
 extern void ext4_discard_preallocations(struct inode *, unsigned int);
 extern int __init ext4_init_mballoc(void);
 extern void ext4_exit_mballoc(void);
@@ -2930,6 +2925,10 @@ extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
 extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 		       int len, int state);
+static inline bool ext4_mb_cr_expensive(enum criteria cr)
+{
+	return cr >= CR_GOAL_LEN_SLOW;
+}
 
 /* inode.c */
 void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
@@ -2983,7 +2982,6 @@ extern void ext4_evict_inode(struct inode *);
 extern void ext4_clear_inode(struct inode *);
 extern int  ext4_file_getattr(struct mnt_idmap *, const struct path *,
 			      struct kstat *, u32, unsigned int);
-extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
@@ -3090,6 +3088,8 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno,
 extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 					     ext4_group_t block_group,
 					     unsigned int flags);
+extern unsigned int ext4_num_base_meta_blocks(struct super_block *sb,
+					      ext4_group_t block_group);
 
 extern __printf(7, 8)
 void __ext4_error(struct super_block *, const char *, unsigned int, bool,
@@ -3531,8 +3531,6 @@ extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
 /* inline.c */
 extern int ext4_get_max_inline_size(struct inode *inode);
 extern int ext4_find_inline_data_nolock(struct inode *inode);
-extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
-				 unsigned int len);
 extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
 
 int ext4_readpage_inline(struct inode *inode, struct folio *folio);

fs/ext4/ext4_jbd2.c

@@ -67,11 +67,12 @@ static int ext4_journal_check_start(struct super_block *sb)
 
 	might_sleep();
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+	if (unlikely(ext4_forced_shutdown(sb)))
 		return -EIO;
 
-	if (sb_rdonly(sb))
+	if (WARN_ON_ONCE(sb_rdonly(sb)))
 		return -EROFS;
+
 	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
 	journal = EXT4_SB(sb)->s_journal;
 	/*

fs/ext4/extents_status.c

@@ -878,23 +878,29 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 	err1 = __es_remove_extent(inode, lblk, end, NULL, es1);
 	if (err1 != 0)
 		goto error;
+	/* Free preallocated extent if it didn't get used. */
+	if (es1) {
+		if (!es1->es_len)
+			__es_free_extent(es1);
+		es1 = NULL;
+	}
 
 	err2 = __es_insert_extent(inode, &newes, es2);
 	if (err2 == -ENOMEM && !ext4_es_must_keep(&newes))
 		err2 = 0;
 	if (err2 != 0)
 		goto error;
+	/* Free preallocated extent if it didn't get used. */
+	if (es2) {
+		if (!es2->es_len)
+			__es_free_extent(es2);
+		es2 = NULL;
+	}
 
 	if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) &&
 	    (status & EXTENT_STATUS_WRITTEN ||
 	     status & EXTENT_STATUS_UNWRITTEN))
 		__revise_pending(inode, lblk, len);
-
-	/* es is pre-allocated but not used, free it. */
-	if (es1 && !es1->es_len)
-		__es_free_extent(es1);
-	if (es2 && !es2->es_len)
-		__es_free_extent(es2);
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	if (err1 || err2)
@@ -1491,8 +1497,12 @@ void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	 */
 	write_lock(&EXT4_I(inode)->i_es_lock);
 	err = __es_remove_extent(inode, lblk, end, &reserved, es);
-	if (es && !es->es_len)
-		__es_free_extent(es);
+	/* Free preallocated extent if it didn't get used. */
+	if (es) {
+		if (!es->es_len)
+			__es_free_extent(es);
+		es = NULL;
+	}
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	if (err)
 		goto retry;
@@ -2047,19 +2057,25 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
 	err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1);
 	if (err1 != 0)
 		goto error;
+	/* Free preallocated extent if it didn't get used. */
+	if (es1) {
+		if (!es1->es_len)
+			__es_free_extent(es1);
+		es1 = NULL;
+	}
 
 	err2 = __es_insert_extent(inode, &newes, es2);
 	if (err2 != 0)
 		goto error;
+	/* Free preallocated extent if it didn't get used. */
+	if (es2) {
+		if (!es2->es_len)
+			__es_free_extent(es2);
+		es2 = NULL;
+	}
 
 	if (allocated)
 		__insert_pending(inode, lblk);
-
-	/* es is pre-allocated but not used, free it. */
-	if (es1 && !es1->es_len)
-		__es_free_extent(es1);
-	if (es2 && !es2->es_len)
-		__es_free_extent(es2);
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	if (err1 || err2)

fs/ext4/file.c

@@ -131,7 +131,7 @@ static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	if (!iov_iter_count(to))
@@ -153,7 +153,7 @@ static ssize_t ext4_file_splice_read(struct file *in, loff_t *ppos,
 {
 	struct inode *inode = file_inode(in);
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 	return filemap_splice_read(in, ppos, pipe, len, flags);
 }
@@ -476,6 +476,11 @@ static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
 	 * required to change security info in file_modified(), for extending
 	 * I/O, any form of non-overwrite I/O, and unaligned I/O to unwritten
 	 * extents (as partial block zeroing may be required).
+	 *
+	 * Note that unaligned writes are allowed under shared lock so long as
+	 * they are pure overwrites. Otherwise, concurrent unaligned writes risk
+	 * data corruption due to partial block zeroing in the dio layer, and so
+	 * the I/O must occur exclusively.
 	 */
 	if (*ilock_shared &&
 	    ((!IS_NOSEC(inode) || *extend || !overwrite ||
@@ -492,21 +497,12 @@ static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
 
 	/*
 	 * Now that locking is settled, determine dio flags and exclusivity
-	 * requirements. Unaligned writes are allowed under shared lock so long
-	 * as they are pure overwrites. Set the iomap overwrite only flag as an
-	 * added precaution in this case. Even though this is unnecessary, we
-	 * can detect and warn on unexpected -EAGAIN if an unsafe unaligned
-	 * write is ever submitted.
-	 *
-	 * Otherwise, concurrent unaligned writes risk data corruption due to
-	 * partial block zeroing in the dio layer, and so the I/O must occur
-	 * exclusively. The inode lock is already held exclusive if the write is
-	 * non-overwrite or extending, so drain all outstanding dio and set the
-	 * force wait dio flag.
+	 * requirements. We don't use DIO_OVERWRITE_ONLY because we enforce
+	 * behavior already. The inode lock is already held exclusive if the
+	 * write is non-overwrite or extending, so drain all outstanding dio and
+	 * set the force wait dio flag.
 	 */
-	if (*ilock_shared && unaligned_io) {
-		*dio_flags = IOMAP_DIO_OVERWRITE_ONLY;
-	} else if (!*ilock_shared && (unaligned_io || *extend)) {
+	if (!*ilock_shared && (unaligned_io || *extend)) {
 		if (iocb->ki_flags & IOCB_NOWAIT) {
 			ret = -EAGAIN;
 			goto out;
@@ -608,7 +604,6 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		iomap_ops = &ext4_iomap_overwrite_ops;
 	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
 			   dio_flags, NULL, 0);
-	WARN_ON_ONCE(ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT));
 	if (ret == -ENOTBLK)
 		ret = 0;
 
@@ -709,7 +704,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 #ifdef CONFIG_FS_DAX
@@ -806,10 +801,9 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct dax_device *dax_dev = sbi->s_daxdev;
+	struct dax_device *dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
 
-	if (unlikely(ext4_forced_shutdown(sbi)))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	/*
@@ -885,7 +879,7 @@ static int ext4_file_open(struct inode *inode, struct file *filp)
 {
 	int ret;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt);