Merge tag 'vfs-6.12-rc6.iomap' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs

Pull iomap fixes from Christian Brauner:
 "Fixes for iomap to prevent data corruption bugs in the fallocate
  unshare range implementation of fsdax and a small cleanup to turn
  iomap_want_unshare_iter() into an inline function"

* tag 'vfs-6.12-rc6.iomap' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs:
  iomap: turn iomap_want_unshare_iter into an inline function
  fsdax: dax_unshare_iter needs to copy entire blocks
  fsdax: remove zeroing code from dax_unshare_iter
  iomap: share iomap_unshare_iter predicate code with fsdax
  xfs: don't allocate COW extents when unsharing a hole

Author: torvalds

fs/dax.c

@@ -1262,35 +1262,46 @@ static s64 dax_unshare_iter(struct iomap_iter *iter)
 {
 	struct iomap *iomap = &iter->iomap;
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
-	loff_t pos = iter->pos;
-	loff_t length = iomap_length(iter);
+	loff_t copy_pos = iter->pos;
+	u64 copy_len = iomap_length(iter);
+	u32 mod;
 	int id = 0;
 	s64 ret = 0;
 	void *daddr = NULL, *saddr = NULL;
 
-	/* don't bother with blocks that are not shared to start with */
-	if (!(iomap->flags & IOMAP_F_SHARED))
-		return length;
+	if (!iomap_want_unshare_iter(iter))
+		return iomap_length(iter);
+
+	/*
+	 * Extend the file range to be aligned to fsblock/pagesize, because
+	 * we need to copy entire blocks, not just the byte range specified.
+	 * Invalidate the mapping because we're about to CoW.
+	 */
+	mod = offset_in_page(copy_pos);
+	if (mod) {
+		copy_len += mod;
+		copy_pos -= mod;
+	}
+
+	mod = offset_in_page(copy_pos + copy_len);
+	if (mod)
+		copy_len += PAGE_SIZE - mod;
+
+	invalidate_inode_pages2_range(iter->inode->i_mapping,
+				      copy_pos >> PAGE_SHIFT,
+				      (copy_pos + copy_len - 1) >> PAGE_SHIFT);
 
 	id = dax_read_lock();
-	ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL);
+	ret = dax_iomap_direct_access(iomap, copy_pos, copy_len, &daddr, NULL);
 	if (ret < 0)
 		goto out_unlock;
 
-	/* zero the distance if srcmap is HOLE or UNWRITTEN */
-	if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) {
-		memset(daddr, 0, length);
-		dax_flush(iomap->dax_dev, daddr, length);
-		ret = length;
-		goto out_unlock;
-	}
-
-	ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL);
+	ret = dax_iomap_direct_access(srcmap, copy_pos, copy_len, &saddr, NULL);
 	if (ret < 0)
 		goto out_unlock;
 
-	if (copy_mc_to_kernel(daddr, saddr, length) == 0)
-		ret = length;
+	if (copy_mc_to_kernel(daddr, saddr, copy_len) == 0)
+		ret = iomap_length(iter);
 	else
 		ret = -EIO;
 

fs/iomap/buffered-io.c

@@ -1277,22 +1277,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 	loff_t length = iomap_length(iter);
 	loff_t written = 0;
 
-	/* Don't bother with blocks that are not shared to start with. */
-	if (!(iomap->flags & IOMAP_F_SHARED))
-		return length;
-
-	/*
-	 * Don't bother with delalloc reservations, holes or unwritten extents.
-	 *
-	 * Note that we use srcmap directly instead of iomap_iter_srcmap as
-	 * unsharing requires providing a separate source map, and the presence
-	 * of one is a good indicator that unsharing is needed, unlike
-	 * IOMAP_F_SHARED which can be set for any data that goes into the COW
-	 * fork for XFS.
-	 */
-	if (iter->srcmap.type == IOMAP_HOLE ||
-	    iter->srcmap.type == IOMAP_DELALLOC ||
-	    iter->srcmap.type == IOMAP_UNWRITTEN)
+	if (!iomap_want_unshare_iter(iter))
 		return length;
 
 	do {

fs/xfs/xfs_iomap.c

@@ -707,7 +707,7 @@ imap_needs_cow(
 		return false;
 
 	/* when zeroing we don't have to COW holes or unwritten extents */
-	if (flags & IOMAP_ZERO) {
+	if (flags & (IOMAP_UNSHARE | IOMAP_ZERO)) {
 		if (!nimaps ||
 		    imap->br_startblock == HOLESTARTBLOCK ||
 		    imap->br_state == XFS_EXT_UNWRITTEN)

include/linux/iomap.h

@@ -270,6 +270,25 @@ static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos,
 	return round_up(pos + written, i_blocksize(inode));
 }
 
+/*
+ * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE
+ * operation.
+ *
+ * Don't bother with blocks that are not shared to start with; or mappings that
+ * cannot be shared, such as inline data, delalloc reservations, holes or
+ * unwritten extents.
+ *
+ * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing
+ * requires providing a separate source map, and the presence of one is a good
+ * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set
+ * for any data that goes into the COW fork for XFS.
+ */
+static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
+{
+	return (iter->iomap.flags & IOMAP_F_SHARED) &&
+		iter->srcmap.type == IOMAP_MAPPED;
+}
+
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops, void *private);
 int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);