Merge tag 'ext4_for_linus-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "New features and improvements for the ext4 file system:
   - Optimize online defragmentation by using folios instead of
     individual buffer heads
   - Improve error codes stored in the superblock when the journal
     aborts
   - Minor cleanups and clarifications in ext4_map_blocks()
   - Add documentation of the casefold and encrypt flags
   - Add support for file systems with a blocksize greater than the
     pagesize
   - Improve performance by enabling the caching the fact that an inode
     does not have a Posix ACL

  Various Bug Fixes:
   - Fix false positive complaints from smatch
   - Fix error code which is returned by ext4fs_dirhash() when Siphash
     is used without the encryption key
   - Fix races when writing to inline data files which could trigger a
     BUG
   - Fix potential NULL dereference when there is an corrupt file system
     with an extended attribute value stored in a inode
   - Fix false positive lockdep report when syzbot uses ext4 and ocfs2
     together
   - Fix false positive reported by DEPT by adjusting lock annotation
   - Avoid a potential BUG_ON in jbd2 when a file system is massively
     corrupted
   - Fix a WARN_ON when superblock is corrupted with a non-NULL
     terminated mount options field
   - Add check if the userspace passes in a non-NULL terminated mount
     options field to EXT4_IOC_SET_TUNE_SB_PARAM
   - Fix a potential journal checksum failure whena file system is
     copied while it is mounted read-only
   - Fix a potential potential orphan file tracking error which only
     showed on 32-bit systems
   - Fix assertion checks in mballoc (which have to be explicitly enbled
     by manually enabling AGGRESSIVE_CHECKS and recompiling)
   - Avoid complaining about overly large orphan files created by mke2fs
     with with file systems with a 64k block size"

* tag 'ext4_for_linus-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (58 commits)
  ext4: mark inodes without acls in __ext4_iget()
  ext4: enable block size larger than page size
  ext4: add checks for large folio incompatibilities when BS > PS
  ext4: support verifying data from large folios with fs-verity
  ext4: make data=journal support large block size
  ext4: support large block size in __ext4_block_zero_page_range()
  ext4: support large block size in mpage_prepare_extent_to_map()
  ext4: support large block size in mpage_map_and_submit_buffers()
  ext4: support large block size in ext4_block_write_begin()
  ext4: support large block size in ext4_mpage_readpages()
  ext4: rename 'page' references to 'folio' in multi-block allocator
  ext4: prepare buddy cache inode for BS > PS with large folios
  ext4: support large block size in ext4_mb_init_cache()
  ext4: support large block size in ext4_mb_get_buddy_page_lock()
  ext4: support large block size in ext4_mb_load_buddy_gfp()
  ext4: add EXT4_LBLK_TO_PG and EXT4_PG_TO_LBLK for block/page conversion
  ext4: add EXT4_LBLK_TO_B macro for logical block to bytes conversion
  ext4: support large block size in ext4_readdir()
  ext4: support large block size in ext4_calculate_overhead()
  ext4: introduce s_min_folio_order for future BS > PS support
  ...

21 files changed, 725 insertions, 684 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index c9329ed5c094..8040c731b3e4 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -752,7 +752,7 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 		*count = ar.len;
 	/*
 	 * Account for the allocated meta blocks.  We will never
-	 * fail EDQUOT for metdata, but we do account for it.
+	 * fail EDQUOT for metadata, but we do account for it.
 	 */
 	if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) {
 		dquot_alloc_block_nofail(inode,
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index d4164c507a90..256fe2c1d4c1 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -192,13 +192,13 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 			continue;
 		}
 		if (err > 0) {
-			pgoff_t index = map.m_pblk >>
-					(PAGE_SHIFT - inode->i_blkbits);
+			pgoff_t index = map.m_pblk << inode->i_blkbits >>
+					PAGE_SHIFT;
 			if (!ra_has_index(&file->f_ra, index))
 				page_cache_sync_readahead(
 					sb->s_bdev->bd_mapping,
-					&file->f_ra, file,
-					index, 1);
+					&file->f_ra, file, index,
+					1 << EXT4_SB(sb)->s_min_folio_order);
 			file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT;
 			bh = ext4_bread(NULL, inode, map.m_lblk, 0);
 			if (IS_ERR(bh)) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 57087da6c7be..56112f201cac 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -260,6 +260,7 @@ struct ext4_map_blocks {
 	ext4_lblk_t m_lblk;
 	unsigned int m_len;
 	unsigned int m_flags;
+	u64 m_seq;
 };
 
 /*
@@ -367,7 +368,14 @@ struct ext4_io_submit {
 								  blkbits))
 #define EXT4_B_TO_LBLK(inode, offset) \
 	(round_up((offset), i_blocksize(inode)) >> (inode)->i_blkbits)
-
+#define EXT4_LBLK_TO_B(inode, lblk) ((loff_t)(lblk) << (inode)->i_blkbits)
+
+/* Translate a block number to a page index */
+#define EXT4_LBLK_TO_PG(inode, lblk)	(EXT4_LBLK_TO_B((inode), (lblk)) >> \
+					 PAGE_SHIFT)
+/* Translate a page index to a block number */
+#define EXT4_PG_TO_LBLK(inode, pnum)	(((loff_t)(pnum) << PAGE_SHIFT) >> \
+					 (inode)->i_blkbits)
 /* Translate a block number to a cluster number */
 #define EXT4_B2C(sbi, blk)	((blk) >> (sbi)->s_cluster_bits)
 /* Translate a cluster number to a block number */
@@ -694,13 +702,22 @@ enum {
 	/* Caller is from the delayed allocation writeout path
 	 * finally doing the actual allocation of delayed blocks */
 #define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
-	/* caller is from the direct IO path, request to creation of an
-	unwritten extents if not allocated, split the unwritten
-	extent if blocks has been preallocated already*/
-#define EXT4_GET_BLOCKS_PRE_IO			0x0008
-#define EXT4_GET_BLOCKS_CONVERT			0x0010
-#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
+	/*
+	 * This means that we cannot merge newly allocated extents, and if we
+	 * found an unwritten extent, we need to split it.
+	 */
+#define EXT4_GET_BLOCKS_SPLIT_NOMERGE		0x0008
+	/*
+	 * Caller is from the dio or dioread_nolock buffered IO, reqest to
+	 * create an unwritten extent if it does not exist or split the
+	 * found unwritten extent. Also do not merge the newly created
+	 * unwritten extent, io end will convert unwritten to written,
+	 * and try to merge the written extent.
+	 */
+#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_SPLIT_NOMERGE|\
 					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
+	/* Convert unwritten extent to initialized. */
+#define EXT4_GET_BLOCKS_CONVERT			0x0010
 	/* Eventual metadata allocation (due to growing extent tree)
 	 * should not fail, so try to use reserved blocks for that.*/
 #define EXT4_GET_BLOCKS_METADATA_NOFAIL		0x0020
@@ -1138,6 +1155,8 @@ struct ext4_inode_info {
 	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
 					   extents to shrink. Protected by
 					   i_es_lock  */
+	u64 i_es_seq;			/* Change counter for extents.
+					   Protected by i_es_lock */
 
 	/* ialloc */
 	ext4_group_t	i_last_alloc_group;
@@ -1685,6 +1704,11 @@ struct ext4_sb_info {
 	/* record the last minlen when FITRIM is called. */
 	unsigned long s_last_trim_minblks;
 
+	/* minimum folio order of a page cache allocation */
+	u16 s_min_folio_order;
+	/* supported maximum folio order, 0 means not supported */
+	u16 s_max_folio_order;
+
 	/* Precomputed FS UUID checksum for seeding other checksums */
 	__u32 s_csum_seed;
 
@@ -2472,28 +2496,19 @@ static inline unsigned int ext4_dir_rec_len(__u8 name_len,
 	return (rec_len & ~EXT4_DIR_ROUND);
 }
 
-/*
- * If we ever get support for fs block sizes > page_size, we'll need
- * to remove the #if statements in the next two functions...
- */
 static inline unsigned int
 ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
 {
 	unsigned len = le16_to_cpu(dlen);
 
-#if (PAGE_SIZE >= 65536)
 	if (len == EXT4_MAX_REC_LEN || len == 0)
 		return blocksize;
 	return (len & 65532) | ((len & 3) << 16);
-#else
-	return len;
-#endif
 }
 
 static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
 {
 	BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3));
-#if (PAGE_SIZE >= 65536)
 	if (len < 65536)
 		return cpu_to_le16(len);
 	if (len == blocksize) {
@@ -2503,9 +2518,6 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
 			return cpu_to_le16(0);
 	}
 	return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
-#else
-	return cpu_to_le16(len);
-#endif
 }
 
 /*
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index a0e66bc10093..05e5946ed9b3 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -16,8 +16,7 @@ int ext4_inode_journal_mode(struct inode *inode)
 	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
 	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
 	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
-	    !test_opt(inode->i_sb, DELALLOC) &&
-	    !mapping_large_folio_support(inode->i_mapping))) {
+	    !test_opt(inode->i_sb, DELALLOC))) {
 		/* We do not support data journalling for encrypted data */
 		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
 			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index ca5499e9412b..2cf5759ba689 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -333,7 +333,7 @@ ext4_force_split_extent_at(handle_t *handle, struct inode *inode,
 			   int nofail)
 {
 	int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext);
-	int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO;
+	int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_SPLIT_NOMERGE;
 
 	if (nofail)
 		flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL;
@@ -2002,7 +2002,7 @@ ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	}
 
 	/* try to insert block into found extent and return */
-	if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) {
+	if (ex && !(gb_flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE)) {
 
 		/*
 		 * Try to see whether we should rather test the extent on
@@ -2181,7 +2181,7 @@ has_space:
 
 merge:
 	/* try to merge extents */
-	if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO))
+	if (!(gb_flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE))
 		ext4_ext_try_to_merge(handle, inode, path, nearex);
 
 	/* time to correct all indexes above */
@@ -2213,7 +2213,7 @@ static int ext4_fill_es_cache_info(struct inode *inode,
 	while (block <= end) {
 		next = 0;
 		flags = 0;
-		if (!ext4_es_lookup_extent(inode, block, &next, &es))
+		if (!ext4_es_lookup_extent(inode, block, &next, &es, NULL))
 			break;
 		if (ext4_es_is_unwritten(&es))
 			flags |= FIEMAP_EXTENT_UNWRITTEN;
@@ -3224,7 +3224,7 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle,
 		else
 			ext4_ext_mark_initialized(ex);
 
-		if (!(flags & EXT4_GET_BLOCKS_PRE_IO))
+		if (!(flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE))
 			ext4_ext_try_to_merge(handle, inode, path, ex);
 
 		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
@@ -3368,7 +3368,7 @@ static struct ext4_ext_path *ext4_split_extent(handle_t *handle,
 
 	if (map->m_lblk + map->m_len < ee_block + ee_len) {
 		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
-		flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
+		flags1 = flags | EXT4_GET_BLOCKS_SPLIT_NOMERGE;
 		if (unwritten)
 			split_flag1 |= EXT4_EXT_MARK_UNWRIT1 |
 				       EXT4_EXT_MARK_UNWRIT2;
@@ -3721,10 +3721,6 @@ static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle,
 			>> inode->i_sb->s_blocksize_bits;
 	if (eof_block < map->m_lblk + map->m_len)
 		eof_block = map->m_lblk + map->m_len;
-	/*
-	 * It is safe to convert extent to initialized via explicit
-	 * zeroout only if extent is fully inside i_size or new_size.
-	 */
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
@@ -3735,11 +3731,15 @@ static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle,
 		split_flag |= EXT4_EXT_DATA_VALID1;
 	/* Convert to initialized */
 	} else if (flags & EXT4_GET_BLOCKS_CONVERT) {
+		/*
+		 * It is safe to convert extent to initialized via explicit
+		 * zeroout only if extent is fully inside i_size or new_size.
+		 */
 		split_flag |= ee_block + ee_len <= eof_block ?
 			      EXT4_EXT_MAY_ZEROOUT : 0;
 		split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
 	}
-	flags |= EXT4_GET_BLOCKS_PRE_IO;
+	flags |= EXT4_GET_BLOCKS_SPLIT_NOMERGE;
 	return ext4_split_extent(handle, inode, path, map, split_flag, flags,
 				 allocated);
 }
@@ -3911,7 +3911,7 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 						*allocated, newblock);
 
 	/* get_block() before submitting IO, split the extent */
-	if (flags & EXT4_GET_BLOCKS_PRE_IO) {
+	if (flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE) {
 		path = ext4_split_convert_extents(handle, inode, map, path,
 				flags | EXT4_GET_BLOCKS_CONVERT, allocated);
 		if (IS_ERR(path))
@@ -4562,7 +4562,7 @@ retry:
 		 * allow a full retry cycle for any remaining allocations
 		 */
 		retries = 0;
-		epos = (loff_t)(map.m_lblk + ret) << blkbits;
+		epos = EXT4_LBLK_TO_B(inode, map.m_lblk + ret);
 		inode_set_ctime_current(inode);
 		if (new_size) {
 			if (epos > new_size)
@@ -5618,7 +5618,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
 			path = ext4_split_extent_at(handle, inode, path,
 					start_lblk, split_flag,
 					EXT4_EX_NOCACHE |
-					EXT4_GET_BLOCKS_PRE_IO |
+					EXT4_GET_BLOCKS_SPLIT_NOMERGE |
 					EXT4_GET_BLOCKS_METADATA_NOFAIL);
 		}
 
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 31dc0496f8d0..e04fbf10fe4f 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -235,6 +235,13 @@ static inline ext4_lblk_t ext4_es_end(struct extent_status *es)
 	return es->es_lblk + es->es_len - 1;
 }
 
+static inline void ext4_es_inc_seq(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	WRITE_ONCE(ei->i_es_seq, ei->i_es_seq + 1);
+}
+
 /*
  * search through the tree for an delayed extent with a given offset.  If
  * it can't be found, try to find next extent.
@@ -906,7 +913,6 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, pblk, status);
-	trace_ext4_es_insert_extent(inode, &newes);
 
 	ext4_es_insert_extent_check(inode, &newes);
 
@@ -955,6 +961,11 @@ retry:
 		}
 		pending = err3;
 	}
+	/*
+	 * TODO: For cache on-disk extents, there is no need to increment
+	 * the sequence counter, this requires future optimization.
+	 */
+	ext4_es_inc_seq(inode);
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	/*
@@ -981,6 +992,7 @@ error:
 	if (err1 || err2 || err3 < 0)
 		goto retry;
 
+	trace_ext4_es_insert_extent(inode, &newes);
 	ext4_es_print_tree(inode);
 	return;
 }
@@ -1027,8 +1039,8 @@ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
  * Return: 1 on found, 0 on not
  */
 int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
-			  ext4_lblk_t *next_lblk,
-			  struct extent_status *es)
+			  ext4_lblk_t *next_lblk, struct extent_status *es,
+			  u64 *pseq)
 {
 	struct ext4_es_tree *tree;
 	struct ext4_es_stats *stats;
@@ -1087,6 +1099,8 @@ out:
 			} else
 				*next_lblk = 0;
 		}
+		if (pseq)
+			*pseq = EXT4_I(inode)->i_es_seq;
 	} else {
 		percpu_counter_inc(&stats->es_stats_cache_misses);
 	}
@@ -1550,7 +1564,6 @@ void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
 
-	trace_ext4_es_remove_extent(inode, lblk, len);
 	es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
 		 lblk, len, inode->i_ino);
 
@@ -1570,16 +1583,21 @@ retry:
 	 */
 	write_lock(&EXT4_I(inode)->i_es_lock);
 	err = __es_remove_extent(inode, lblk, end, &reserved, es);
+	if (err)
+		goto error;
 	/* Free preallocated extent if it didn't get used. */
 	if (es) {
 		if (!es->es_len)
 			__es_free_extent(es);
 		es = NULL;
 	}
+	ext4_es_inc_seq(inode);
+error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	if (err)
 		goto retry;
 
+	trace_ext4_es_remove_extent(inode, lblk, len);
 	ext4_es_print_tree(inode);
 	ext4_da_release_space(inode, reserved);
 }
@@ -2140,8 +2158,6 @@ void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED);
-	trace_ext4_es_insert_delayed_extent(inode, &newes, lclu_allocated,
-					    end_allocated);
 
 	ext4_es_insert_extent_check(inode, &newes);
 
@@ -2196,11 +2212,14 @@ retry:
 			pr2 = NULL;
 		}
 	}
+	ext4_es_inc_seq(inode);
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	if (err1 || err2 || err3 < 0)
 		goto retry;
 
+	trace_ext4_es_insert_delayed_extent(inode, &newes, lclu_allocated,
+					    end_allocated);
 	ext4_es_print_tree(inode);
 	ext4_print_pending_tree(inode);
 	return;
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 8f9c008d11e8..f3396cf32b44 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -148,7 +148,7 @@ extern void ext4_es_find_extent_range(struct inode *inode,
 				      struct extent_status *es);
 extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 				 ext4_lblk_t *next_lblk,
-				 struct extent_status *es);
+				 struct extent_status *es, u64 *pseq);
 extern bool ext4_es_scan_range(struct inode *inode,
 			       int (*matching_fn)(struct extent_status *es),
 			       ext4_lblk_t lblk, ext4_lblk_t end);
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 33cd5b6b02d5..48483cd015d3 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -268,7 +268,7 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len,
 			combined_hash = fscrypt_fname_siphash(dir, &qname);
 		} else {
 			ext4_warning_inode(dir, "Siphash requires key");
-			return -1;
+			return -EINVAL;
 		}
 
 		hash = (__u32)(combined_hash >> 32);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index ba4fd9aba1c1..b20a1bf866ab 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1293,7 +1293,6 @@ got:
 		ei->i_csum_seed = ext4_chksum(csum, (__u8 *)&gen, sizeof(gen));
 	}
 
-	ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
 	ext4_set_inode_state(inode, EXT4_STATE_NEW);
 
 	ei->i_extra_isize = sbi->s_want_extra_isize;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 1b094a4f3866..1f6bc05593df 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -418,7 +418,12 @@ static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
 		return -ENOSPC;
 
 	ext4_write_lock_xattr(inode, &no_expand);
-
+	/*
+	 * ei->i_inline_size may have changed since the initial check
+	 * if other xattrs were added. Recalculate to ensure
+	 * ext4_update_inline_data() validates against current capacity.
+	 */
+	(void) ext4_find_inline_data_nolock(inode);
 	if (ei->i_inline_off)
 		ret = ext4_update_inline_data(handle, inode, len);
 	else
@@ -446,9 +451,13 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
 	if (!ei->i_inline_off)
 		return 0;
 
+	down_write(&ei->i_data_sem);
+
 	error = ext4_get_inode_loc(inode, &is.iloc);
-	if (error)
+	if (error) {
+		up_write(&ei->i_data_sem);
 		return error;
+	}
 
 	error = ext4_xattr_ibody_find(inode, &i, &is);
 	if (error)
@@ -487,6 +496,7 @@ out:
 	brelse(is.iloc.bh);
 	if (error == -ENODATA)
 		error = 0;
+	up_write(&ei->i_data_sem);
 	return error;
 }
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 78ea864fa8cd..0c466ccbed69 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -549,10 +549,13 @@ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
 		retval = ext4_ext_map_blocks(handle, inode, map, flags);
 	else
 		retval = ext4_ind_map_blocks(handle, inode, map, flags);
-
-	if (retval <= 0)
+	if (retval < 0)
 		return retval;
 
+	/* A hole? */
+	if (retval == 0)
+		goto out;
+
 	if (unlikely(retval != map->m_len)) {
 		ext4_warning(inode->i_sb,
 			     "ES len assertion failed for inode "
@@ -572,11 +575,13 @@ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
 				      map->m_pblk, status, false);
-		return retval;
+	} else {
+		retval = ext4_map_query_blocks_next_in_leaf(handle, inode, map,
+							    orig_mlen);
 	}
-
-	return ext4_map_query_blocks_next_in_leaf(handle, inode, map,
-						  orig_mlen);
+out:
+	map->m_seq = READ_ONCE(EXT4_I(inode)->i_es_seq);
+	return retval;
 }
 
 static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
@@ -647,8 +652,8 @@ static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
 	 * If the extent has been zeroed out, we don't need to update
 	 * extent status tree.
 	 */
-	if (flags & EXT4_GET_BLOCKS_PRE_IO &&
-	    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE &&
+	    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, &map->m_seq)) {
 		if (ext4_es_is_written(&es))
 			return retval;
 	}
@@ -657,6 +662,7 @@ static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
 			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 	ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk,
 			      status, flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+	map->m_seq = READ_ONCE(EXT4_I(inode)->i_es_seq);
 
 	return retval;
 }
@@ -722,7 +728,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		ext4_check_map_extents_env(inode);
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, &map->m_seq)) {
 		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
 			map->m_pblk = ext4_es_pblock(&es) +
 					map->m_lblk - es.es_lblk;
@@ -809,7 +815,13 @@ found:
 	down_write(&EXT4_I(inode)->i_data_sem);
 	retval = ext4_map_create_blocks(handle, inode, map, flags);
 	up_write((&EXT4_I(inode)->i_data_sem));
-	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+
+	if (retval < 0)
+		ext_debug(inode, "failed with err %d\n", retval);
+	if (retval <= 0)
+		return retval;
+
+	if (map->m_flags & EXT4_MAP_MAPPED) {
 		ret = check_block_validity(inode, map);
 		if (ret != 0)
 			return ret;
@@ -824,9 +836,8 @@ found:
 		    !(flags & EXT4_GET_BLOCKS_ZERO) &&
 		    !ext4_is_quota_file(inode) &&
 		    ext4_should_order_data(inode)) {
-			loff_t start_byte =
-				(loff_t)map->m_lblk << inode->i_blkbits;
-			loff_t length = (loff_t)map->m_len << inode->i_blkbits;
+			loff_t start_byte = EXT4_LBLK_TO_B(inode, map->m_lblk);
+			loff_t length = EXT4_LBLK_TO_B(inode, map->m_len);
 
 			if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
 				ret = ext4_jbd2_inode_add_wait(handle, inode,
@@ -838,12 +849,8 @@ found:
 				return ret;
 		}
 	}
-	if (retval > 0 && (map->m_flags & EXT4_MAP_UNWRITTEN ||
-				map->m_flags & EXT4_MAP_MAPPED))
-		ext4_fc_track_range(handle, inode, map->m_lblk,
-					map->m_lblk + map->m_len - 1);
-	if (retval < 0)
-		ext_debug(inode, "failed with err %d\n", retval);
+	ext4_fc_track_range(handle, inode, map->m_lblk, map->m_lblk +
+			    map->m_len - 1);
 	return retval;
 }
 
@@ -1162,8 +1169,7 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
 	unsigned block_start, block_end;
 	sector_t block;
 	int err = 0;
-	unsigned blocksize = inode->i_sb->s_blocksize;
-	unsigned bbits;
+	unsigned int blocksize = i_blocksize(inode);
 	struct buffer_head *bh, *head, *wait[2];
 	int nr_wait = 0;
 	int i;
@@ -1172,12 +1178,12 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
 	BUG_ON(!folio_test_locked(folio));
 	BUG_ON(to > folio_size(folio));
 	BUG_ON(from > to);
+	WARN_ON_ONCE(blocksize > folio_size(folio));
 
 	head = folio_buffers(folio);
 	if (!head)
 		head = create_empty_buffers(folio, blocksize, 0);
-	bbits = ilog2(blocksize);
-	block = (sector_t)folio->index << (PAGE_SHIFT - bbits);
+	block = EXT4_PG_TO_LBLK(inode, folio->index);
 
 	for (bh = head, block_start = 0; bh != head || !block_start;
 	    block++, block_start = block_end, bh = bh->b_this_page) {
@@ -1907,7 +1913,7 @@ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map)
 	ext4_check_map_extents_env(inode);
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, NULL)) {
 		map->m_len = min_t(unsigned int, map->m_len,
 				   es.es_len - (map->m_lblk - es.es_lblk));
 
@@ -1960,7 +1966,7 @@ add_delayed:
 	 * is held in write mode, before inserting a new da entry in
 	 * the extent status tree.
 	 */
-	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, NULL)) {
 		map->m_len = min_t(unsigned int, map->m_len,
 				   es.es_len - (map->m_lblk - es.es_lblk));
 
@@ -1978,6 +1984,8 @@ add_delayed:
 
 	map->m_flags |= EXT4_MAP_DELAYED;
 	retval = ext4_insert_delayed_blocks(inode, map->m_lblk, map->m_len);
+	if (!retval)
+		map->m_seq = READ_ONCE(EXT4_I(inode)->i_es_seq);
 	up_write(&EXT4_I(inode)->i_data_sem);
 
 	return retval;
@@ -2224,7 +2232,6 @@ static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio,
 	ext4_lblk_t lblk = *m_lblk;
 	ext4_fsblk_t pblock = *m_pblk;
 	int err = 0;
-	int blkbits = mpd->inode->i_blkbits;
 	ssize_t io_end_size = 0;
 	struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end);
 
@@ -2250,7 +2257,8 @@ static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio,
 					err = PTR_ERR(io_end_vec);
 					goto out;
 				}
-				io_end_vec->offset = (loff_t)mpd->map.m_lblk << blkbits;
+				io_end_vec->offset = EXT4_LBLK_TO_B(mpd->inode,
+								mpd->map.m_lblk);
 			}
 			*map_bh = true;
 			goto out;
@@ -2260,7 +2268,7 @@ static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio,
 			bh->b_blocknr = pblock++;
 		}
 		clear_buffer_unwritten(bh);
-		io_end_size += (1 << blkbits);
+		io_end_size += i_blocksize(mpd->inode);
 	} while (lblk++, (bh = bh->b_this_page) != head);
 
 	io_end_vec->size += io_end_size;
@@ -2290,15 +2298,14 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 	struct folio_batch fbatch;
 	unsigned nr, i;
 	struct inode *inode = mpd->inode;
-	int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
 	pgoff_t start, end;
 	ext4_lblk_t lblk;
 	ext4_fsblk_t pblock;
 	int err;
 	bool map_bh = false;
 
-	start = mpd->map.m_lblk >> bpp_bits;
-	end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
+	start = EXT4_LBLK_TO_PG(inode, mpd->map.m_lblk);
+	end = EXT4_LBLK_TO_PG(inode, mpd->map.m_lblk + mpd->map.m_len - 1);
 	pblock = mpd->map.m_pblk;
 
 	folio_batch_init(&fbatch);
@@ -2309,7 +2316,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 		for (i = 0; i < nr; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			lblk = folio->index << bpp_bits;
+			lblk = EXT4_PG_TO_LBLK(inode, folio->index);
 			err = mpage_process_folio(mpd, folio, &lblk, &pblock,
 						 &map_bh);
 			/*
@@ -2462,7 +2469,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 	io_end_vec = ext4_alloc_io_end_vec(io_end);
 	if (IS_ERR(io_end_vec))
 		return PTR_ERR(io_end_vec);
-	io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits;
+	io_end_vec->offset = EXT4_LBLK_TO_B(inode, map->m_lblk);
 	do {
 		err = mpage_map_one_extent(handle, mpd);
 		if (err < 0) {
@@ -2612,7 +2619,6 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 	pgoff_t end = mpd->end_pos >> PAGE_SHIFT;
 	xa_mark_t tag;
 	int i, err = 0;
-	int blkbits = mpd->inode->i_blkbits;
 	ext4_lblk_t lblk;
 	struct buffer_head *head;
 	handle_t *handle = NULL;
@@ -2648,7 +2654,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			 */
 			if (mpd->wbc->sync_mode == WB_SYNC_NONE &&
 			    mpd->wbc->nr_to_write <=
-			    mpd->map.m_len >> (PAGE_SHIFT - blkbits))
+			    EXT4_LBLK_TO_PG(mpd->inode, mpd->map.m_len))
 				goto out;
 
 			/* If we can't merge this page, we are done. */
@@ -2726,8 +2732,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 				mpage_folio_done(mpd, folio);
 			} else {
 				/* Add all dirty buffers to mpd */
-				lblk = ((ext4_lblk_t)folio->index) <<
-					(PAGE_SHIFT - blkbits);
+				lblk = EXT4_PG_TO_LBLK(mpd->inode, folio->index);
 				head = folio_buffers(folio);
 				err = mpage_process_page_bufs(mpd, head, head,
 						lblk);
@@ -3499,8 +3504,8 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 		iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
 	else
 		iomap->bdev = inode->i_sb->s_bdev;
-	iomap->offset = (u64) map->m_lblk << blkbits;
-	iomap->length = (u64) map->m_len << blkbits;
+	iomap->offset = EXT4_LBLK_TO_B(inode, map->m_lblk);
+	iomap->length = EXT4_LBLK_TO_B(inode, map->m_len);
 
 	if ((map->m_flags & EXT4_MAP_MAPPED) &&