1 files changed, 26 insertions, 16 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index ae8673ce08b1..2bc0aa23fde3 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -640,11 +640,13 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 	size_t poff, plen;
 
 	/*
-	 * If the write completely overlaps the current folio, then
+	 * If the write or zeroing completely overlaps the current folio, then
 	 * entire folio will be dirtied so there is no need for
 	 * per-block state tracking structures to be attached to this folio.
+	 * For the unshare case, we must read in the ondisk contents because we
+	 * are not changing pagecache contents.
 	 */
-	if (pos <= folio_pos(folio) &&
+	if (!(iter->flags & IOMAP_UNSHARE) && pos <= folio_pos(folio) &&
 	    pos + len >= folio_pos(folio) + folio_size(folio))
 		return 0;
 
@@ -879,8 +881,10 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		size_t bytes;		/* Bytes to write to folio */
 		size_t copied;		/* Bytes copied from user */
 
+		bytes = iov_iter_count(i);
+retry:
 		offset = pos & (chunk - 1);
-		bytes = min(chunk - offset, iov_iter_count(i));
+		bytes = min(chunk - offset, bytes);
 		status = balance_dirty_pages_ratelimited_flags(mapping,
 							       bdp_flags);
 		if (unlikely(status))
@@ -931,10 +935,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 			 * halfway through, might be a race with munmap,
 			 * might be severe memory pressure.
 			 */
-			if (copied)
-				bytes = copied;
 			if (chunk > PAGE_SIZE)
 				chunk /= 2;
+			if (copied) {
+				bytes = copied;
+				goto retry;
+			}
 		} else {
 			pos += status;
 			written += status;
@@ -1047,7 +1053,7 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio,
 
 /*
  * Scan the data range passed to us for dirty page cache folios. If we find a
- * dirty folio, punch out the preceeding range and update the offset from which
+ * dirty folio, punch out the preceding range and update the offset from which
  * the next punch will start from.
  *
  * We can punch out storage reservations under clean pages because they either
@@ -1261,7 +1267,6 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 	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 */
@@ -1272,28 +1277,33 @@ static loff_t iomap_unshare_iter(struct iomap_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;
-		if (iter->iomap.flags & IOMAP_F_STALE)
+		if (iomap->flags & IOMAP_F_STALE)
 			break;
 
-		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;
 }