diff --git a/fs/dax.c b/fs/dax.c
index 72a437892b4a..ca7138bb1d54 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1225,35 +1225,46 @@ 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);
 
-	id = dax_read_lock();
-	ret = dax_iomap_direct_access(iomap, pos, length, &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;
+	/*
+	 * 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;
 	}
 
-	ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL);
+	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, copy_pos, copy_len, &daddr, NULL);
 	if (ret < 0)
 		goto out_unlock;
 
-	if (copy_mc_to_kernel(daddr, saddr, length) == 0)
-		ret = length;
+	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, 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 919a56d0b985..f83f993ca84b 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1061,43 +1061,58 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc);
 
+bool iomap_want_unshare_iter(const struct iomap_iter *iter)
+{
+	/*
+	 * 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.
+	 */
+	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;
-	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	loff_t pos = iter->pos;
 	loff_t length = iomap_length(iter);
-	long status = 0;
 	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 holes or unwritten extents */
-	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
+	if (!iomap_want_unshare_iter(iter))
 		return length;
 
 	do {
-		unsigned long offset = offset_in_page(pos);
-		unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length);
 		struct folio *folio;
+		int status;
+		size_t offset;
+		size_t bytes = min_t(u64, SIZE_MAX, length);
 
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (unlikely(status))
 			return status;
 
-		status = iomap_write_end(iter, pos, bytes, bytes, folio);
-		if (WARN_ON_ONCE(status == 0))
+		offset = offset_in_folio(folio, pos);
+		if (bytes > folio_size(folio) - offset)
+			bytes = folio_size(folio) - offset;
+
+		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
+		if (WARN_ON_ONCE(bytes == 0))
 			return -EIO;
 
 		cond_resched();
 
-		pos += status;
-		written += status;
-		length -= status;
+		pos += bytes;
+		written += bytes;
+		length -= bytes;
 
 		balance_dirty_pages_ratelimited(iter->inode->i_mapping);
-	} while (length);
+	} while (length > 0);
 
 	return written;
 }
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 9005ad2343ac..8f29942a54b3 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -243,6 +243,7 @@ bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
 void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
 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,