iomap: introduce IOMAP_F_ZERO_TAIL flag

In filesystems that maintain a separate Valid Data Length, such as exFAT
and NTFS, a partial write may start at or beyond the current valid_size and
extend it. In this case, the region after the previous valid_size but
within the same filesystem block is considered unwritten.

This patch introduces IOMAP_F_ZERO_TAIL. When this flag is set in iomap,
__iomap_write_begin() will zero only the tail portion while preserving any
valid data before it in the same block.

Without this tail zeroing, stale data in the unwritten portion of the block
can remain in the page cache. Subsequent reads can then return incorrect
contents from that region.

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Link: https://patch.msgid.link/20260518114705.9601-2-linkinjeon@kernel.org
Acked-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index c98cf19fbe08ad1c349d0918e87984397ac79735..d6451c4208d499586c993574fceb678f3f8c9394 100644 (file)
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -836,6 +836,7 @@ static int __iomap_write_begin(const struct iomap_iter *iter,
                                return -EIO;
                        folio_zero_segments(folio, poff, from, to, poff + plen);
                } else {
+                       const struct iomap *iomap = iomap_iter_srcmap(iter);
                        int status;
 
                        if (iter->flags & IOMAP_NOWAIT)
@@ -853,6 +854,9 @@ static int __iomap_write_begin(const struct iomap_iter *iter,
                                                  len, status, GFP_NOFS);
                        if (status)
                                return status;
+
+                       if (iomap->flags & IOMAP_F_ZERO_TAIL)
+                               folio_zero_segment(folio, to, poff + plen);
                }
                iomap_set_range_uptodate(folio, poff, plen);
        } while ((block_start += plen) < block_end);

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 52bfd6783417cb93faa4017c1f68cb2bdf1f4186..cea6bbc97b6ef886f4aa57acbd5da6f0ec2cbff0 100644 (file)
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -67,6 +67,9 @@ struct vm_fault;
  * bio, i.e. set REQ_ATOMIC.
  *
  * IOMAP_F_INTEGRITY indicates that the filesystems handles integrity metadata.
+ *
+ * IOMAP_F_ZERO_TAIL indicates the remainder of the block after the data
+ * written should be zeroed.
  */
 #define IOMAP_F_NEW            (1U << 0)
 #define IOMAP_F_DIRTY          (1U << 1)
@@ -86,6 +89,7 @@ struct vm_fault;
 #else
 #define IOMAP_F_INTEGRITY      0
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
+#define IOMAP_F_ZERO_TAIL      (1U << 10)
 
 /*
  * Flag reserved for file system specific usage