Merge patch series "fsdax/xfs: unshare range fixes for 6.12"

Darrick J. Wong <[email protected]> says:

This patchset fixes multiple data corruption bugs in the fallocate
unshare range implementation for fsdax.

* patches from https://lore.kernel.org/r/172796813251.1131942.12184885574609980777.stgit@frogsfrogsfrogs:
  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

Link: https://lore.kernel.org/r/172796813251.1131942.12184885574609980777.stgit@frogsfrogsfrogs
Signed-off-by: Christian Brauner <[email protected]>

4 files changed, 46 insertions, 32 deletions

diff --git a/fs/dax.c b/fs/dax.c
index c62acd2812f8..21b47402b3dc 100644
--- a/fs/dax.c
+++ b/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;
 
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 78ebd265f425..3899169b2cf7 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1309,19 +1309,12 @@ void iomap_file_buffered_write_punch_delalloc(struct inode *inode,
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc);
 
-static loff_t iomap_unshare_iter(struct iomap_iter *iter)
+bool iomap_want_unshare_iter(const struct iomap_iter *iter)
 {
-	struct iomap *iomap = &iter->iomap;
-	loff_t pos = iter->pos;
-	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.
+	 * 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
@@ -1329,9 +1322,18 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 	 * 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)
+	return (iter->iomap.flags & IOMAP_F_SHARED) &&
+		iter->srcmap.type == IOMAP_MAPPED;
+}
+
+static loff_t iomap_unshare_iter(struct iomap_iter *iter)
+{
+	struct iomap *iomap = &iter->iomap;
+	loff_t pos = iter->pos;
+	loff_t length = iomap_length(iter);
+	loff_t written = 0;
+
+	if (!iomap_want_unshare_iter(iter))
 		return length;
 
 	do {
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 1e11f48814c0..dc0443848485 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/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)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 4ad12a3c8bae..d8a7fc84348c 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -267,6 +267,7 @@ void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
 bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
+bool iomap_want_unshare_iter(const struct iomap_iter *iter);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
 		bool *did_zero, const struct iomap_ops *ops);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,