[PATCH v2 0/4] exfat: fix VDL tracking bugs

[PATCH v2 0/4] exfat: fix VDL tracking bugs

[Chi Zhiling]

From: Chi Zhiling <chizhiling@kylinos.cn>

exFAT tracks a valid data length (VDL) as exfat_inode_info.valid_size:
below it is valid data, at or above it is a hole that the read paths
zero-fill.  It is read without the inode lock (->iomap_begin and the
buffered-read bio completion) and updated from the write, mmap and
truncate paths, so it must only move forward, and only once the data has
actually been copied and the folio dirtied.  This series fixes the bugs
around that invariant:

 - An O_APPEND write uses the caller's offset instead of the position
   recalculated by generic_write_checks(), so valid_size may not be
   advanced to EOF.

 - Truncate does not hold mapping->invalidate_lock, so it can race with
   an mmap write faulting a page back in for the same range.

 - exfat_zero_new_range() does not dirty non-uptodate pages, so some of
   the zeroed blocks are never written back.

Patch 4 converts valid_size and zeroed_size to monotonic atomic counters
as a prerequisite for updating valid_size from contexts that do not hold
i_rwsem.

This series was split from:
https://lore.kernel.org/exfat/20261003033032.1775311-1-chizhiling@163.com/T/#t
The other patches still need some improvement.

Changes in v2:
Rebase onto the latest dev branch.

Chi Zhiling (4):
  exfat: advance valid_size to EOF for append writes
  exfat: hold the invalidate lock while truncating
  exfat: dirty all new pages when extending valid_size
  exfat: make valid_size and zeroed_size atomic

 fs/exfat/exfat_fs.h |  60 +++++++++++++++++-
 fs/exfat/file.c     | 144 ++++++++++++++------------------------------
 fs/exfat/inode.c    |  16 ++---
 fs/exfat/iomap.c    |  27 ++++-----
 fs/exfat/namei.c    |   4 +-
 5 files changed, 127 insertions(+), 124 deletions(-)

-- 
2.53.0

[PATCH v2 1/4] exfat: advance valid_size to EOF for append writes

[Chi Zhiling]

From: Chi Zhiling <chizhiling@kylinos.cn>

For an append write, the write position is recalculated by
generic_write_checks(). Therefore, the write position must be obtained
after generic_write_checks() returns.

Using the original write position to advance valid_size may cause the
valid_size update to be skipped, potentially exposing stale data.

Also move the truncate_pagecache() check below the recalculated
position, so that pos is never read before it is assigned.

Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
---
 fs/exfat/file.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index a2a9ee1a2004..b30aec858da6 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -854,8 +854,7 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct exfat_inode_info *ei = EXFAT_I(inode);
-	loff_t pos = iocb->ki_pos;
-	loff_t valid_size;
+	loff_t pos, valid_size;
 	int err;
 
 	if (unlikely(exfat_forced_shutdown(inode->i_sb)))
@@ -863,11 +862,6 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 	inode_lock(inode);
 
-	if (pos > i_size_read(inode))
-		truncate_pagecache(inode, i_size_read(inode));
-
-	valid_size = ei->valid_size;
-
 	ret = generic_write_checks(iocb, iter);
 	if (ret <= 0)
 		goto unlock;
@@ -878,6 +872,11 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 		goto unlock;
 	}
 
+	pos = iocb->ki_pos;
+	if (pos > i_size_read(inode))
+		truncate_pagecache(inode, i_size_read(inode));
+
+	valid_size = ei->valid_size;
 	if (pos > valid_size) {
 		ret = exfat_extend_valid_size(inode, pos);
 		if (ret < 0 && ret != -ENOSPC) {
@@ -887,6 +886,8 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 		}
 		if (ret < 0)
 			goto unlock;
+
+		pos = valid_size;
 	}
 
 	if (iocb->ki_flags & IOCB_DIRECT)
@@ -899,9 +900,6 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 	inode_unlock(inode);
 
-	if (pos > valid_size)
-		pos = valid_size;
-
 	if (iocb->ki_pos > pos) {
 		ssize_t err = generic_write_sync(iocb, iocb->ki_pos - pos);
 
-- 
2.53.0

[PATCH v2 2/4] exfat: hold the invalidate lock while truncating

[Chi Zhiling]

From: Chi Zhiling <chizhiling@kylinos.cn>

truncate_setsize() ends in truncate_inode_pages(), which is documented
as being "Called under (and serialised by) inode->i_rwsem and
mapping->invalidate_lock".

Hold invalidate_lock while executing truncate_setsize() to ensure that
truncate and mmap writes are mutually exclusive. This can simplify the
handling in exfat_page_mkwrite().

Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
---
 fs/exfat/file.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index b30aec858da6..81eeb76ef94b 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -413,6 +413,7 @@ int exfat_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 * about to be freed.
 		 */
 		inode_dio_wait(inode);
+		filemap_invalidate_lock(inode->i_mapping);
 		truncate_setsize(inode, attr->ia_size);
 
 		/*
@@ -420,6 +421,7 @@ int exfat_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 * is already written by it, so mark_inode_dirty() is unneeded.
 		 */
 		exfat_truncate(inode);
+		filemap_invalidate_unlock(inode->i_mapping);
 	} else
 		mark_inode_dirty(inode);
 
@@ -784,8 +786,10 @@ static int exfat_extend_valid_size(struct inode *inode, loff_t new_valid_size)
 		ret = exfat_zero_new_range(inode, gap_start, new_valid_size);
 		filemap_invalidate_unlock(inode->i_mapping);
 		if (ret) {
+			filemap_invalidate_lock(inode->i_mapping);
 			truncate_setsize(inode, old_valid_size);
 			exfat_truncate(inode);
+			filemap_invalidate_unlock(inode->i_mapping);
 			return ret;
 		}
 
-- 
2.53.0

[PATCH v2 3/4] exfat: dirty all new pages when extending valid_size

[Chi Zhiling]

From: Chi Zhiling <chizhiling@kylinos.cn>

In the current code, exfat_zero_new_range() does not mark non-uptodate
pages as dirty, which may cause some blocks within a page to not be
written back.

This commit no longer checks each block in a non-uptodate page
individually. Instead, it reads the entire page back into the cache and
then writes it back as a whole. This allows concurrent writes and zeroing
operations to be synchronized using the folio lock.

Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
---
 fs/exfat/file.c | 92 +++++++++----------------------------------------
 1 file changed, 16 insertions(+), 76 deletions(-)

diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 81eeb76ef94b..d729e881bff0 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -664,90 +664,30 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 static int exfat_zero_new_range(struct inode *inode, loff_t start, loff_t end)
 {
 	struct address_space *mapping = inode->i_mapping;
-	unsigned int blocksize = i_blocksize(inode);
-	loff_t pos = start;
-	int err;
-
-	while (pos < end) {
-		loff_t next = min_t(loff_t,
-				round_down(pos, PAGE_SIZE) + PAGE_SIZE, end);
-		struct folio *folio;
-		loff_t bpos;
-
-		folio = filemap_get_folio(mapping, pos >> PAGE_SHIFT);
-		if (IS_ERR(folio)) {
-			err = iomap_zero_range(inode, pos, next - pos, NULL,
-					       &exfat_iomap_ops, NULL, NULL);
-			if (err < 0)
-				return err;
-			pos = next;
-			continue;
-		}
+	loff_t next, pos = start;
+	struct folio *folio;
+	pgoff_t index;
 
-		if (folio_test_uptodate(folio)) {
-			folio_lock(folio);
-			if (folio->mapping == mapping)
-				folio_mark_dirty(folio);
-			folio_unlock(folio);
-			folio_put(folio);
-			pos = next;
-			continue;
-		}
-
-		/*
-		 * Zero not-uptodate block runs. iomap_zero_range() requires an
-		 * unlocked folio, so recheck ->mapping after each call.
-		 */
-		folio_lock(folio);
-		bpos = pos;
-		while (bpos < next) {
-			loff_t rstart, rend;
-
-			if (folio->mapping != mapping) {
-				folio_unlock(folio);
-				err = iomap_zero_range(inode, bpos, next - bpos,
-						NULL, &exfat_iomap_ops, NULL, NULL);
-				if (err < 0) {
-					folio_put(folio);
-					return err;
-				}
-				folio_lock(folio);
-				break;
-			}
+	if (pos >= end)
+		return 0;
 
-			if (iomap_is_partially_uptodate(folio,
-					offset_in_folio(folio, bpos), blocksize)) {
-				bpos += blocksize;
-				continue;
-			}
+	while (pos < end) {
+		index = pos >> PAGE_SHIFT;
+		next = min(((loff_t)index + 1) << PAGE_SHIFT, end);
 
-			rstart = bpos;
-			rend = min_t(loff_t, bpos + blocksize, next);
-			while (rend < next &&
-			       !iomap_is_partially_uptodate(folio,
-					offset_in_folio(folio, rend), blocksize))
-				rend = min_t(loff_t, rend + blocksize, next);
+		balance_dirty_pages_ratelimited(mapping);
 
-			folio_unlock(folio);
-			err = iomap_zero_range(inode, rstart, rend - rstart,
-					NULL, &exfat_iomap_ops, NULL, NULL);
-			if (err < 0) {
-				folio_put(folio);
-				return err;
-			}
-			folio_lock(folio);
-			bpos = rend;
-		}
+		folio = read_mapping_folio(mapping, index, NULL);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
 
-		/*
-		 * Dirty only a fully uptodate folio. Dirtying a partial folio could
-		 * write uninitialised cache contents over valid on-disk blocks.
-		 */
-		if (folio->mapping == mapping && folio_test_uptodate(folio))
+		folio_lock(folio);
+		if (folio->mapping == mapping) {
 			folio_mark_dirty(folio);
+			pos = next;
+		}
 		folio_unlock(folio);
 		folio_put(folio);
-		pos = next;
 	}
 
 	return 0;
-- 
2.53.0

Re: [PATCH v2 3/4] exfat: dirty all new pages when extending valid_size

[Namjae Jeon]

> @@ -664,90 +664,30 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
>  static int exfat_zero_new_range(struct inode *inode, loff_t start, loff_t end)
Function name and comments no longer seem to match. What do you think
about changing them like this?

/*
 * exfat_prepare_valid_range - populate and dirty folios covering [start, end)
 *
 * Populate missing blocks via the read path, which zero-fills data
 * beyond the current valid_size while preserving uptodate blocks.
 * Mark entire folios dirty so the newly valid range is written back.
 *
 * Call before advancing valid_size.
 */

And generic/538 test fails with this patch set. Please check if this
test failure is reproducible for you as well.
Thanks.

Re: [PATCH v2 3/4] exfat: dirty all new pages when extending valid_size

[Chi Zhiling]

On 10/5/26 5:08 PM, Namjae Jeon wrote:
>> @@ -664,90 +664,30 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
>>   static int exfat_zero_new_range(struct inode *inode, loff_t start, loff_t end)
> Function name and comments no longer seem to match. What do you think
> about changing them like this?
> 
> /*
>   * exfat_prepare_valid_range - populate and dirty folios covering [start, end)
>   *
>   * Populate missing blocks via the read path, which zero-fills data
>   * beyond the current valid_size while preserving uptodate blocks.
>   * Mark entire folios dirty so the newly valid range is written back.
>   *
>   * Call before advancing valid_size.
>   */

Okay, I'll add it to v3.

> 
> And generic/538 test fails with this patch set. Please check if this
> test failure is reproducible for you as well.

I ran the tests, but I wasn't able to reproduce the failure. Could you 
tell me the block size and cluster size used to reproduce it?

There is also a new failure in generic/551. This failure can be fixed by 
adding inode_dio_wait() to exfat_extend_valid_size(). Jiale's patch 
includes this fix:

https://lore.kernel.org/exfat/20261003093035.532916-4-yaojiale02@163.com/T/#u


Thanks.

[PATCH v2 4/4] exfat: make valid_size and zeroed_size atomic

[Chi Zhiling]

From: Chi Zhiling <chizhiling@kylinos.cn>

ei->valid_size and ei->zeroed_size are 64-bit fields read from bio
completion context (exfat_iomap_read_end_io()) and from ->iomap_begin
without i_rwsem, while writers update them under i_rwsem.  On 32-bit
these loads can tear, and the "if (x < new) x = new" read-modify-write
can lose an update or regress the value when two writers race.

Convert both to atomic64_t and funnel updates through a cmpxchg-based
monotonic advance helper so the value only moves forward; plain reads use
exfat_get_*(), and the few shrink/init paths (truncate, inode fill,
create) use exfat_set_*().  This is a prerequisite for taking
exfat_page_mkwrite() out from under i_rwsem.

Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
---
 fs/exfat/exfat_fs.h | 60 +++++++++++++++++++++++++++++++++++++++++++--
 fs/exfat/file.c     | 32 +++++++++++++-----------
 fs/exfat/inode.c    | 16 ++++++------
 fs/exfat/iomap.c    | 27 ++++++++++----------
 fs/exfat/namei.c    |  4 +--
 5 files changed, 100 insertions(+), 39 deletions(-)

diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 41a2c7dfc479..43c034532ec5 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -7,6 +7,7 @@
 #define _EXFAT_FS_H
 
 #include <linux/fs.h>
+#include <linux/atomic.h>
 #include <linux/ratelimit.h>
 #include <linux/nls.h>
 #include <linux/blkdev.h>
@@ -294,9 +295,16 @@ struct exfat_inode_info {
 
 	/* on-disk position of directory entry or 0 */
 	loff_t i_pos;
-	loff_t valid_size;
+	/*
+	 * valid_size and zeroed_size are updated from multiple contexts that
+	 * are not serialised against each other (page_mkwrite runs without
+	 * i_rwsem, while buffered/DIO writes advance them under i_rwsem).  Keep
+	 * them atomic and only ever advance them with a cmpxchg loop so a
+	 * concurrent update can never regress the value or tear on 32-bit.
+	 */
+	atomic64_t valid_size;
 	/* block-aligned size zeroed in the page cache (>= valid_size) */
-	loff_t zeroed_size;
+	atomic64_t zeroed_size;
 	/* hash by i_location */
 	struct hlist_node i_hash_fat;
 	struct inode vfs_inode;
@@ -314,6 +322,54 @@ static inline struct exfat_inode_info *EXFAT_I(struct inode *inode)
 	return container_of(inode, struct exfat_inode_info, vfs_inode);
 }
 
+static inline loff_t exfat_get_valid_size(struct exfat_inode_info *ei)
+{
+	return atomic64_read(&ei->valid_size);
+}
+
+static inline loff_t exfat_get_zeroed_size(struct exfat_inode_info *ei)
+{
+	return atomic64_read(&ei->zeroed_size);
+}
+
+static inline void exfat_set_valid_size(struct exfat_inode_info *ei, loff_t v)
+{
+	atomic64_set(&ei->valid_size, v);
+}
+
+static inline void exfat_set_zeroed_size(struct exfat_inode_info *ei, loff_t v)
+{
+	atomic64_set(&ei->zeroed_size, v);
+}
+
+/*
+ * Monotonically advance @v to at least @new. Returns true if the value was
+ * actually raised, so callers can decide whether to mark the inode dirty.
+ */
+static inline bool exfat_size_advance(atomic64_t *v, loff_t new)
+{
+	loff_t old = atomic64_read(v);
+
+	do {
+		if (old >= new)
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &old, new));
+
+	return true;
+}
+
+static inline bool exfat_advance_valid_size(struct exfat_inode_info *ei,
+		loff_t new)
+{
+	return exfat_size_advance(&ei->valid_size, new);
+}
+
+static inline bool exfat_advance_zeroed_size(struct exfat_inode_info *ei,
+		loff_t new)
+{
+	return exfat_size_advance(&ei->zeroed_size, new);
+}
+
 static inline int exfat_forced_shutdown(struct super_block *sb)
 {
 	return test_bit(EXFAT_FLAGS_SHUTDOWN, &EXFAT_SB(sb)->s_exfat_flags);
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index d729e881bff0..a7c3d0aa7546 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -247,8 +247,10 @@ int __exfat_truncate(struct inode *inode)
 		ei->start_clu = EXFAT_EOF_CLUSTER;
 	}
 
-	if (i_size_read(inode) < ei->valid_size)
-		ei->valid_size = ei->zeroed_size = i_size_read(inode);
+	if (i_size_read(inode) < exfat_get_valid_size(ei)) {
+		exfat_set_valid_size(ei, i_size_read(inode));
+		exfat_set_zeroed_size(ei, i_size_read(inode));
+	}
 
 	if (ei->type == TYPE_FILE)
 		ei->attr |= EXFAT_ATTR_ARCHIVE;
@@ -696,12 +698,12 @@ static int exfat_zero_new_range(struct inode *inode, loff_t start, loff_t end)
 static int exfat_extend_valid_size(struct inode *inode, loff_t new_valid_size)
 {
 	struct exfat_inode_info *ei = EXFAT_I(inode);
-	loff_t old_valid_size = ei->valid_size;
+	loff_t old_valid_size = exfat_get_valid_size(ei);
 	int ret = 0;
 
 	if (old_valid_size < new_valid_size) {
 		/* Do not re-zero blocks already covered by zeroed_size. */
-		loff_t gap_start = max(old_valid_size, ei->zeroed_size);
+		loff_t gap_start = max(old_valid_size, exfat_get_zeroed_size(ei));
 
 		if (i_size_read(inode) < new_valid_size) {
 			/*
@@ -733,9 +735,9 @@ static int exfat_extend_valid_size(struct inode *inode, loff_t new_valid_size)
 			return ret;
 		}
 
-		ei->valid_size = new_valid_size;
-		if (ei->zeroed_size < round_up(new_valid_size, i_blocksize(inode)))
-			ei->zeroed_size = round_up(new_valid_size, i_blocksize(inode));
+		exfat_set_valid_size(ei, new_valid_size);
+		exfat_advance_zeroed_size(ei,
+				round_up(new_valid_size, i_blocksize(inode)));
 		mark_inode_dirty(inode);
 	}
 
@@ -820,7 +822,7 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	if (pos > i_size_read(inode))
 		truncate_pagecache(inode, i_size_read(inode));
 
-	valid_size = ei->valid_size;
+	valid_size = exfat_get_valid_size(ei);
 	if (pos > valid_size) {
 		ret = exfat_extend_valid_size(inode, pos);
 		if (ret < 0 && ret != -ENOSPC) {
@@ -896,8 +898,10 @@ static vm_fault_t exfat_page_mkwrite(struct vm_fault *vmf)
 	fault_page_start = ((loff_t)vmf->pgoff) << PAGE_SHIFT;
 	new_valid_size = min(mmap_valid_size, i_size_read(inode));
 
-	if (ei->valid_size < new_valid_size) {
-		if (ei->zeroed_size < fault_page_start) {
+	if (exfat_get_valid_size(ei) < new_valid_size) {
+		loff_t zeroed_size = exfat_get_zeroed_size(ei);
+
+		if (zeroed_size < fault_page_start) {
 			int err;
 
 			/*
@@ -905,7 +909,7 @@ static vm_fault_t exfat_page_mkwrite(struct vm_fault *vmf)
 			 * fault populated its folio and iomap_page_mkwrite()
 			 * will dirty it.
 			 */
-			err = exfat_zero_new_range(inode, ei->zeroed_size,
+			err = exfat_zero_new_range(inode, zeroed_size,
 					fault_page_start);
 			if (err < 0) {
 				inode_unlock(inode);
@@ -918,9 +922,9 @@ static vm_fault_t exfat_page_mkwrite(struct vm_fault *vmf)
 		 * at i_size recording blocks wholly beyond it could skip a
 		 * later required zeroing.
 		 */
-		if (ei->zeroed_size < round_up(new_valid_size, i_blocksize(inode)))
-			ei->zeroed_size = round_up(new_valid_size, i_blocksize(inode));
-		ei->valid_size = new_valid_size;
+		exfat_advance_zeroed_size(ei,
+				round_up(new_valid_size, i_blocksize(inode)));
+		exfat_set_valid_size(ei, new_valid_size);
 		mark_inode_dirty(inode);
 	}
 
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index ccd13630187e..5129df1e79b4 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -29,6 +29,7 @@ int __exfat_write_inode(struct inode *inode, int sync)
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	bool is_dir = (ei->type == TYPE_DIR);
+	loff_t valid_size = exfat_get_valid_size(ei);
 	struct timespec64 ts;
 
 	if (inode->i_ino == EXFAT_ROOT_INO)
@@ -81,7 +82,7 @@ int __exfat_write_inode(struct inode *inode, int sync)
 	 * preventing fsck from reporting "more clusters are allocated".
 	 */
 	on_disk_size = max_t(unsigned long long, i_size_read(inode),
-			ei->valid_size);
+			valid_size);
 
 	if (ei->start_clu == EXFAT_EOF_CLUSTER)
 		on_disk_size = 0;
@@ -89,7 +90,7 @@ int __exfat_write_inode(struct inode *inode, int sync)
 	 * valid_size on disk must reflect only confirmed data (up to i_size)
 	 * and must not exceed on_disk_size.
 	 */
-	on_disk_valid_size = min_t(unsigned long long, ei->valid_size,
+	on_disk_valid_size = min_t(unsigned long long, valid_size,
 			i_size_read(inode));
 	if (ei->start_clu == EXFAT_EOF_CLUSTER)
 		on_disk_valid_size = 0;
@@ -258,15 +259,16 @@ static void exfat_readahead(struct readahead_control *rac)
 	struct inode *inode = mapping->host;
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	loff_t pos = readahead_pos(rac);
+	loff_t valid_size = exfat_get_valid_size(ei);
 	struct iomap_read_folio_ctx ctx = {
 		.ops = &exfat_iomap_bio_read_ops,
 		.rac = rac,
 	};
 
 	/* Range cross valid_size, read it page by page. */
-	if (ei->valid_size < i_size_read(inode) &&
-	    pos <= ei->valid_size &&
-	    ei->valid_size < pos + readahead_length(rac))
+	if (valid_size < i_size_read(inode) &&
+	    pos <= valid_size &&
+	    valid_size < pos + readahead_length(rac))
 		return;
 
 	iomap_readahead(&exfat_iomap_ops, &ctx, NULL);
@@ -371,8 +373,8 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info)
 	ei->start_clu = info->start_clu;
 	ei->flags = info->flags;
 	ei->type = info->type;
-	ei->valid_size = info->valid_size;
-	ei->zeroed_size = info->valid_size;
+	exfat_set_valid_size(ei, info->valid_size);
+	exfat_set_zeroed_size(ei, info->valid_size);
 
 	ei->version = 0;
 	ei->hint_stat.eidx = 0;
diff --git a/fs/exfat/iomap.c b/fs/exfat/iomap.c
index 6253a9c63130..bec0b35b9420 100644
--- a/fs/exfat/iomap.c
+++ b/fs/exfat/iomap.c
@@ -46,6 +46,7 @@ static int __exfat_iomap_begin(struct inode *inode, loff_t offset, loff_t length
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	unsigned int cluster, num_clusters;
 	loff_t cluster_offset, cluster_length;
+	loff_t valid_size = exfat_get_valid_size(ei);
 	int err;
 	bool balloc = false;
 
@@ -88,7 +89,7 @@ static int __exfat_iomap_begin(struct inode *inode, loff_t offset, loff_t length
 	if (may_alloc || flags & IOMAP_ZERO) {
 		if (balloc)
 			iomap->flags |= IOMAP_F_NEW;
-		else if (iomap->offset + iomap->length >= ei->valid_size) {
+		else if (iomap->offset + iomap->length >= valid_size) {
 			/*
 			 * This is a write that starts at or extends beyond
 			 * the current valid_size. The region between the old
@@ -114,10 +115,10 @@ static int __exfat_iomap_begin(struct inode *inode, loff_t offset, loff_t length
 		 * return IOMAP_UNWRITTEN so the write path can
 		 * distinguish it from a real hole.
 		 */
-		if (offset >= ei->valid_size) {
+		if (offset >= valid_size) {
 			iomap->type = flags & IOMAP_REPORT ?
 				IOMAP_HOLE : IOMAP_UNWRITTEN;
-		} else if (offset + iomap->length > ei->valid_size) {
+		} else if (offset + iomap->length > valid_size) {
 			if (flags & IOMAP_REPORT) {
 				/*
 				 * For SEEK_HOLE/SEEK_DATA, clip the length
@@ -125,9 +126,9 @@ static int __exfat_iomap_begin(struct inode *inode, loff_t offset, loff_t length
 				 * This ensures the caller gets the precise
 				 * hole position in byte units.
 				 */
-				iomap->length = ei->valid_size - iomap->offset;
+				iomap->length = valid_size - iomap->offset;
 			} else
-				iomap->length = round_up(ei->valid_size,
+				iomap->length = round_up(valid_size,
 							 i_blocksize(inode)) -
 								iomap->offset;
 		}
@@ -149,6 +150,7 @@ static int exfat_write_iomap_begin(struct inode *inode, loff_t offset, loff_t le
 		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
 {
 	struct exfat_inode_info *ei = EXFAT_I(inode);
+	loff_t valid_size = exfat_get_valid_size(ei);
 	loff_t end;
 	int err;
 
@@ -158,15 +160,15 @@ static int exfat_write_iomap_begin(struct inode *inode, loff_t offset, loff_t le
 		return err;
 
 	end = iomap->offset + iomap->length;
-	if (end >= ei->valid_size ||
-	    round_up(end, i_blocksize(inode)) <= ei->valid_size)
+	if (end >= valid_size ||
+	    round_up(end, i_blocksize(inode)) <= valid_size)
 		return 0;
 
 	/*
 	 * Zero the invalid bytes from valid_size to the end of the block
 	 * to prevent stale data from being exposed through the page cache.
 	 */
-	return iomap_truncate_page(inode, ei->valid_size, NULL, &exfat_iomap_ops,
+	return iomap_truncate_page(inode, valid_size, NULL, &exfat_iomap_ops,
 				   NULL, NULL);
 }
 
@@ -215,10 +217,8 @@ static int exfat_write_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 
 	end = pos + written;
 
-	if (ei->valid_size < end) {
-		ei->valid_size = end;
+	if (exfat_advance_valid_size(ei, end))
 		dirtied = true;
-	}
 
 	/*
 	 * IOMAP_F_ZERO_TAIL zeroes the remainder of the last block. Track that
@@ -226,8 +226,7 @@ static int exfat_write_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	 */
 	if (iomap->flags & IOMAP_F_ZERO_TAIL)
 		end = round_up(end, i_blocksize(inode));
-	if (ei->zeroed_size < end)
-		ei->zeroed_size = end;
+	exfat_advance_zeroed_size(ei, end);
 
 	if (dirtied || iomap->flags & IOMAP_F_SIZE_CHANGED)
 		mark_inode_dirty(inode);
@@ -290,7 +289,7 @@ static void exfat_iomap_read_end_io(struct bio *bio)
 		s64 valid_size;
 		loff_t pos = folio_pos(folio);
 
-		valid_size = ei->valid_size;
+		valid_size = exfat_get_valid_size(ei);
 		if (pos + iter.offset < valid_size &&
 		    pos + iter.offset + iter.length > valid_size)
 			folio_zero_segment(folio, offset_in_folio(folio, valid_size),
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 3c5746fc57d9..86c8c18d363f 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -380,7 +380,7 @@ int exfat_find_empty_entry(struct inode *inode,
 
 		/* directory inode should be updated in here */
 		i_size_write(inode, size);
-		ei->valid_size += sbi->cluster_size;
+		atomic64_add(sbi->cluster_size, &ei->valid_size);
 		ei->flags = p_dir->flags;
 		inode->i_blocks += sbi->cluster_size >> 9;
 	}
@@ -1249,7 +1249,7 @@ static int __exfat_rename(struct inode *old_parent_inode,
 			}
 
 			i_size_write(new_inode, 0);
-			new_ei->valid_size = 0;
+			exfat_set_valid_size(new_ei, 0);
 			new_ei->start_clu = EXFAT_EOF_CLUSTER;
 			new_ei->flags = ALLOC_NO_FAT_CHAIN;
 		}
-- 
2.53.0