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()
  ...

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

@@ -215,7 +215,6 @@ 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);
@@ -223,12 +222,13 @@ int ext4_setup_system_zone(struct super_block *sb)
 		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 @@ retry:
 	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 @@ retry:
 	 */
 	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 @@ retry:
 	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 @@ restart:
 	 * 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 @@ restart:
 
 	/*
 	 * 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);

fs/ext4/fsync.c

@@ -131,9 +131,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret = 0, err;
 	bool needs_barrier = false;
 	struct inode *inode = file->f_mapping->host;
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-	if (unlikely(ext4_forced_shutdown(sbi)))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	ASSERT(ext4_journal_current_handle() == NULL);
@@ -141,14 +140,14 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	trace_ext4_sync_file_enter(file, datasync);
 
 	if (sb_rdonly(inode->i_sb)) {
-		/* Make sure that we read updated s_mount_flags value */
+		/* Make sure that we read updated s_ext4_flags value */
 		smp_rmb();
-		if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))
+		if (ext4_forced_shutdown(inode->i_sb))
 			ret = -EROFS;
 		goto out;
 	}
 
-	if (!sbi->s_journal) {
+	if (!EXT4_SB(inode->i_sb)->s_journal) {
 		ret = ext4_fsync_nojournal(file, start, end, datasync,
 					   &needs_barrier);
 		if (needs_barrier)

fs/ext4/hash.c

@@ -300,7 +300,7 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
 	unsigned char *buff;
 	struct qstr qstr = {.name = name, .len = len };
 
-	if (len && IS_CASEFOLDED(dir) && um &&
+	if (len && IS_CASEFOLDED(dir) &&
 	   (!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir))) {
 		buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
 		if (!buff)

fs/ext4/ialloc.c

@@ -950,7 +950,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
 	sb = dir->i_sb;
 	sbi = EXT4_SB(sb);
 
-	if (unlikely(ext4_forced_shutdown(sbi)))
+	if (unlikely(ext4_forced_shutdown(sb)))
 		return ERR_PTR(-EIO);
 
 	ngroups = ext4_get_groups_count(sb);
@@ -1523,12 +1523,6 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 	int num, ret = 0, used_blks = 0;
 	unsigned long used_inos = 0;
 
-	/* This should not happen, but just to be sure check this */
-	if (sb_rdonly(sb)) {
-		ret = 1;
-		goto out;
-	}
-
 	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
 	if (!gdp || !grp)
 		goto out;

fs/ext4/inline.c

@@ -228,7 +228,7 @@ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
 	struct ext4_inode *raw_inode;
 	int cp_len = 0;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return;
 
 	BUG_ON(!EXT4_I(inode)->i_inline_off);

fs/ext4/inode.c

@@ -1114,7 +1114,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index;
 	unsigned from, to;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	trace_ext4_write_begin(inode, pos, len);
@@ -2213,8 +2213,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 		if (err < 0) {
 			struct super_block *sb = inode->i_sb;
 
-			if (ext4_forced_shutdown(EXT4_SB(sb)) ||
-			    ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
+			if (ext4_forced_shutdown(sb))
 				goto invalidate_dirty_pages;
 			/*
 			 * Let the uper layers retry transient errors.
@@ -2534,14 +2533,13 @@ static int ext4_do_writepages(struct mpage_da_data *mpd)
 	 * If the filesystem has aborted, it is read-only, so return
 	 * right away instead of dumping stack traces later on that
 	 * will obscure the real source of the problem.  We test
-	 * EXT4_MF_FS_ABORTED instead of sb->s_flag's SB_RDONLY because
+	 * fs shutdown state instead of sb->s_flag's SB_RDONLY because
 	 * the latter could be true if the filesystem is mounted
 	 * read-only, and in that case, ext4_writepages should
 	 * *never* be called, so if that ever happens, we would want
 	 * the stack trace.
 	 */
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
-		     ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) {
+	if (unlikely(ext4_forced_shutdown(mapping->host->i_sb))) {
 		ret = -EROFS;
 		goto out_writepages;
 	}
@@ -2759,7 +2757,7 @@ static int ext4_writepages(struct address_space *mapping,
 	int ret;
 	int alloc_ctx;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+	if (unlikely(ext4_forced_shutdown(sb)))
 		return -EIO;
 
 	alloc_ctx = ext4_writepages_down_read(sb);
@@ -2798,16 +2796,16 @@ static int ext4_dax_writepages(struct address_space *mapping,
 	int ret;
 	long nr_to_write = wbc->nr_to_write;
 	struct inode *inode = mapping->host;
-	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 	int alloc_ctx;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	alloc_ctx = ext4_writepages_down_read(inode->i_sb);
 	trace_ext4_writepages(inode, wbc);
 
-	ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
+	ret = dax_writeback_mapping_range(mapping,
+					  EXT4_SB(inode->i_sb)->s_daxdev, wbc);
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
 	ext4_writepages_up_read(inode->i_sb, alloc_ctx);
@@ -2857,7 +2855,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index;
 	struct inode *inode = mapping->host;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	index = pos >> PAGE_SHIFT;
@@ -2937,14 +2935,73 @@ static int ext4_da_should_update_i_disksize(struct folio *folio,
 	return 1;
 }
 
+static int ext4_da_do_write_end(struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page)
+{
+	struct inode *inode = mapping->host;
+	loff_t old_size = inode->i_size;
+	bool disksize_changed = false;
+	loff_t new_i_size;
+
+	/*
+	 * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
+	 * flag, which all that's needed to trigger page writeback.
+	 */
+	copied = block_write_end(NULL, mapping, pos, len, copied, page, NULL);
+	new_i_size = pos + copied;
+
+	/*
+	 * It's important to update i_size while still holding page lock,
+	 * because page writeout could otherwise come in and zero beyond
+	 * i_size.
+	 *
+	 * Since we are holding inode lock, we are sure i_disksize <=
+	 * i_size. We also know that if i_disksize < i_size, there are
+	 * delalloc writes pending in the range up to i_size. If the end of
+	 * the current write is <= i_size, there's no need to touch
+	 * i_disksize since writeback will push i_disksize up to i_size
+	 * eventually. If the end of the current write is > i_size and
+	 * inside an allocated block which ext4_da_should_update_i_disksize()
+	 * checked, we need to update i_disksize here as certain
+	 * ext4_writepages() paths not allocating blocks and update i_disksize.
+	 */
+	if (new_i_size > inode->i_size) {
+		unsigned long end;
+
+		i_size_write(inode, new_i_size);
+		end = (new_i_size - 1) & (PAGE_SIZE - 1);
+		if (copied && ext4_da_should_update_i_disksize(page_folio(page), end)) {
+			ext4_update_i_disksize(inode, new_i_size);
+			disksize_changed = true;
+		}
+	}
+
+	unlock_page(page);
+	put_page(page);
+
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
+
+	if (disksize_changed) {
+		handle_t *handle;
+
+		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+		ext4_mark_inode_dirty(handle, inode);
+		ext4_journal_stop(handle);
+	}
+
+	return copied;
+}
+
 static int ext4_da_write_end(struct file *file,
 			     struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned copied,
 			     struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
-	loff_t new_i_size;
-	unsigned long start, end;
 	int write_mode = (int)(unsigned long)fsdata;
 	struct folio *folio = page_folio(page);
 
@@ -2963,30 +3020,7 @@ static int ext4_da_write_end(struct file *file,
 	if (unlikely(copied < len) && !PageUptodate(page))
 		copied = 0;
 
-	start = pos & (PAGE_SIZE - 1);
-	end = start + copied - 1;
-
-	/*
-	 * Since we are holding inode lock, we are sure i_disksize <=
-	 * i_size. We also know that if i_disksize < i_size, there are
-	 * delalloc writes pending in the range upto i_size. If the end of
-	 * the current write is <= i_size, there's no need to touch
-	 * i_disksize since writeback will push i_disksize upto i_size
-	 * eventually. If the end of the current write is > i_size and
-	 * inside an allocated block (ext4_da_should_update_i_disksize()
-	 * check), we need to update i_disksize here as certain
-	 * ext4_writepages() paths not allocating blocks update i_disksize.
-	 *
-	 * Note that we defer inode dirtying to generic_write_end() /
-	 * ext4_da_write_inline_data_end().
-	 */
-	new_i_size = pos + copied;
-	if (copied && new_i_size > inode->i_size &&
-	    ext4_da_should_update_i_disksize(folio, end))
-		ext4_update_i_disksize(inode, new_i_size);
-
-	return generic_write_end(file, mapping, pos, len, copied, &folio->page,
-				 fsdata);
+	return ext4_da_do_write_end(mapping, pos, len, copied, &folio->page);
 }
 
 /*
@@ -4940,9 +4974,12 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 				 "iget: bogus i_mode (%o)", inode->i_mode);
 		goto bad_inode;
 	}
-	if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb))
+	if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) {
 		ext4_error_inode(inode, function, line, 0,
 				 "casefold flag without casefold feature");
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	if ((err_str = check_igot_inode(inode, flags)) != NULL) {
 		ext4_error_inode(inode, function, line, 0, err_str);
 		ret = -EFSCORRUPTED;
@@ -5131,11 +5168,10 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	int err;
 
-	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC) ||
-	    sb_rdonly(inode->i_sb))
+	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
 		return 0;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	if (EXT4_SB(inode->i_sb)->s_journal) {
@@ -5255,7 +5291,7 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	const unsigned int ia_valid = attr->ia_valid;
 	bool inc_ivers = true;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	if (unlikely(IS_IMMUTABLE(inode)))
@@ -5674,7 +5710,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 {
 	int err = 0;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
+	if (unlikely(ext4_forced_shutdown(inode->i_sb))) {
 		put_bh(iloc->bh);
 		return -EIO;
 	}
@@ -5700,7 +5736,7 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 {
 	int err;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	err = ext4_get_inode_loc(inode, iloc);

fs/ext4/ioctl.c

@@ -802,7 +802,7 @@ int ext4_force_shutdown(struct super_block *sb, u32 flags)
 	if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
 		return -EINVAL;
 
-	if (ext4_forced_shutdown(sbi))
+	if (ext4_forced_shutdown(sb))
 		return 0;
 
 	ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags);

fs/ext4/mballoc.h

@@ -233,6 +233,20 @@ static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
 		(fex->fe_start << EXT4_SB(sb)->s_cluster_bits);
 }
 
+static inline loff_t extent_logical_end(struct ext4_sb_info *sbi,
+					struct ext4_free_extent *fex)
+{
+	/* Use loff_t to avoid end exceeding ext4_lblk_t max. */
+	return (loff_t)fex->fe_logical + EXT4_C2B(sbi, fex->fe_len);
+}
+
+static inline loff_t pa_logical_end(struct ext4_sb_info *sbi,
+				    struct ext4_prealloc_space *pa)
+{
+	/* Use loff_t to avoid end exceeding ext4_lblk_t max. */
+	return (loff_t)pa->pa_lstart + EXT4_C2B(sbi, pa->pa_len);
+}
+
 typedef int (*ext4_mballoc_query_range_fn)(
 	struct super_block		*sb,
 	ext4_group_t			agno,

fs/ext4/mmp.c

@@ -162,7 +162,7 @@ static int kmmpd(void *data)
 	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
 	       sizeof(mmp->mmp_nodename));
 
-	while (!kthread_should_stop() && !sb_rdonly(sb)) {
+	while (!kthread_should_stop() && !ext4_forced_shutdown(sb)) {
 		if (!ext4_has_feature_mmp(sb)) {
 			ext4_warning(sb, "kmmpd being stopped since MMP feature"
 				     " has been disabled.");

fs/ext4/namei.c

@@ -1445,7 +1445,7 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
 	struct dx_hash_info *hinfo = &name->hinfo;
 	int len;
 
-	if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding ||
+	if (!IS_CASEFOLDED(dir) ||
 	    (IS_ENCRYPTED(dir) && !fscrypt_has_encryption_key(dir))) {
 		cf_name->name = NULL;
 		return 0;
@@ -1496,7 +1496,7 @@ static bool ext4_match(struct inode *parent,
 #endif
 
 #if IS_ENABLED(CONFIG_UNICODE)
-	if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) &&
+	if (IS_CASEFOLDED(parent) &&
 	    (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) {
 		if (fname->cf_name.name) {
 			struct qstr cf = {.name = fname->cf_name.name,
@@ -2393,7 +2393,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 
 #if IS_ENABLED(CONFIG_UNICODE)
 	if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
-	    sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name))
+	    utf8_validate(sb->s_encoding, &dentry->d_name))
 		return -EINVAL;
 #endif
 
@@ -2799,6 +2799,7 @@ static int ext4_add_nondir(handle_t *handle,
 		return err;
 	}
 	drop_nlink(inode);
+	ext4_mark_inode_dirty(handle, inode);
 	ext4_orphan_add(handle, inode);
 	unlock_new_inode(inode);
 	return err;
@@ -3142,7 +3143,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 	struct ext4_dir_entry_2 *de;
 	handle_t *handle = NULL;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+	if (unlikely(ext4_forced_shutdown(dir->i_sb)))
 		return -EIO;
 
 	/* Initialize quotas before so that eventual writes go in
@@ -3302,7 +3303,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int retval;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+	if (unlikely(ext4_forced_shutdown(dir->i_sb)))
 		return -EIO;
 
 	trace_ext4_unlink_enter(dir, dentry);
@@ -3370,7 +3371,7 @@ static int ext4_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	struct fscrypt_str disk_link;
 	int retries = 0;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+	if (unlikely(ext4_forced_shutdown(dir->i_sb)))
 		return -EIO;
 
 	err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize,
@@ -3437,6 +3438,7 @@ retry:
 
 err_drop_inode:
 	clear_nlink(inode);
+	ext4_mark_inode_dirty(handle, inode);
 	ext4_orphan_add(handle, inode);
 	unlock_new_inode(inode);
 	if (handle)
@@ -4021,6 +4023,7 @@ end_rename:
 			ext4_resetent(handle, &old,
 				      old.inode->i_ino, old_file_type);
 			drop_nlink(whiteout);
+			ext4_mark_inode_dirty(handle, whiteout);
 			ext4_orphan_add(handle, whiteout);
 		}
 		unlock_new_inode(whiteout);
@@ -4187,7 +4190,7 @@ static int ext4_rename2(struct mnt_idmap *idmap,
 {
 	int err;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(old_dir->i_sb))))
+	if (unlikely(ext4_forced_shutdown(old_dir->i_sb)))
 		return -EIO;
 
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))

fs/ext4/page-io.c

@@ -184,7 +184,7 @@ static int ext4_end_io_end(ext4_io_end_t *io_end)
 
 	io_end->handle = NULL;	/* Following call will use up the handle */
 	ret = ext4_convert_unwritten_io_end_vec(handle, io_end);
-	if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) {
+	if (ret < 0 && !ext4_forced_shutdown(inode->i_sb)) {
 		ext4_msg(inode->i_sb, KERN_EMERG,
 			 "failed to convert unwritten extents to written "
 			 "extents -- potential data loss!  "

fs/ext4/xattr.c

@@ -701,7 +701,7 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
 {
 	int error;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
 	if (strlen(name) > 255)