1 files changed, 42 insertions, 91 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 11ea747228ae..ef0b68bccbb6 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1145,10 +1145,36 @@ static void iomap_write_delalloc_scan(struct inode *inode,
 }
 
 /*
+ * When a short write occurs, the filesystem might need to use ->iomap_end
+ * to remove space reservations created in ->iomap_begin.
+ *
+ * For filesystems that use delayed allocation, there can be dirty pages over
+ * the delalloc extent outside the range of a short write but still within the
+ * delalloc extent allocated for this iomap if the write raced with page
+ * faults.
+ *
  * Punch out all the delalloc blocks in the range given except for those that
  * have dirty data still pending in the page cache - those are going to be
  * written and so must still retain the delalloc backing for writeback.
  *
+ * The punch() callback *must* only punch delalloc extents in the range passed
+ * to it. It must skip over all other types of extents in the range and leave
+ * them completely unchanged. It must do this punch atomically with respect to
+ * other extent modifications.
+ *
+ * The punch() callback may be called with a folio locked to prevent writeback
+ * extent allocation racing at the edge of the range we are currently punching.
+ * The locked folio may or may not cover the range being punched, so it is not
+ * safe for the punch() callback to lock folios itself.
+ *
+ * Lock order is:
+ *
+ * inode->i_rwsem (shared or exclusive)
+ *   inode->i_mapping->invalidate_lock (exclusive)
+ *     folio_lock()
+ *       ->punch
+ *         internal filesystem allocation lock
+ *
  * As we are scanning the page cache for data, we don't need to reimplement the
  * wheel - mapping_seek_hole_data() does exactly what we need to identify the
  * start and end of data ranges correctly even for sub-folio block sizes. This
@@ -1177,7 +1203,7 @@ static void iomap_write_delalloc_scan(struct inode *inode,
  * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose
  * the code to subtle off-by-one bugs....
  */
-static void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
+void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
 		loff_t end_byte, unsigned flags, struct iomap *iomap,
 		iomap_punch_t punch)
 {
@@ -1185,12 +1211,13 @@ static void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
 	loff_t scan_end_byte = min(i_size_read(inode), end_byte);
 
 	/*
-	 * Lock the mapping to avoid races with page faults re-instantiating
-	 * folios and dirtying them via ->page_mkwrite whilst we walk the
-	 * cache and perform delalloc extent removal. Failing to do this can
-	 * leave dirty pages with no space reservation in the cache.
+	 * The caller must hold invalidate_lock to avoid races with page faults
+	 * re-instantiating folios and dirtying them via ->page_mkwrite whilst
+	 * we walk the cache and perform delalloc extent removal.  Failing to do
+	 * this can leave dirty pages with no space reservation in the cache.
 	 */
-	filemap_invalidate_lock(inode->i_mapping);
+	lockdep_assert_held_write(&inode->i_mapping->invalidate_lock);
+
 	while (start_byte < scan_end_byte) {
 		loff_t		data_end;
 
@@ -1207,7 +1234,7 @@ static void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
 		if (start_byte == -ENXIO || start_byte == scan_end_byte)
 			break;
 		if (WARN_ON_ONCE(start_byte < 0))
-			goto out_unlock;
+			return;
 		WARN_ON_ONCE(start_byte < punch_start_byte);
 		WARN_ON_ONCE(start_byte > scan_end_byte);
 
@@ -1218,7 +1245,7 @@ static void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
 		data_end = mapping_seek_hole_data(inode->i_mapping, start_byte,
 				scan_end_byte, SEEK_HOLE);
 		if (WARN_ON_ONCE(data_end < 0))
-			goto out_unlock;
+			return;
 
 		/*
 		 * If we race with post-direct I/O invalidation of the page cache,
@@ -1240,74 +1267,8 @@ static void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
 	if (punch_start_byte < end_byte)
 		punch(inode, punch_start_byte, end_byte - punch_start_byte,
 				iomap);
-out_unlock:
-	filemap_invalidate_unlock(inode->i_mapping);
-}
-
-/*
- * When a short write occurs, the filesystem may need to remove reserved space
- * that was allocated in ->iomap_begin from it's ->iomap_end method. For
- * filesystems that use delayed allocation, we need to punch out delalloc
- * extents from the range that are not dirty in the page cache. As the write can
- * race with page faults, there can be dirty pages over the delalloc extent
- * outside the range of a short write but still within the delalloc extent
- * allocated for this iomap.
- *
- * This function uses [start_byte, end_byte) intervals (i.e. open ended) to
- * simplify range iterations.
- *
- * The punch() callback *must* only punch delalloc extents in the range passed
- * to it. It must skip over all other types of extents in the range and leave
- * them completely unchanged. It must do this punch atomically with respect to
- * other extent modifications.
- *
- * The punch() callback may be called with a folio locked to prevent writeback
- * extent allocation racing at the edge of the range we are currently punching.
- * The locked folio may or may not cover the range being punched, so it is not
- * safe for the punch() callback to lock folios itself.
- *
- * Lock order is:
- *
- * inode->i_rwsem (shared or exclusive)
- *   inode->i_mapping->invalidate_lock (exclusive)
- *     folio_lock()
- *       ->punch
- *         internal filesystem allocation lock
- */
-void iomap_file_buffered_write_punch_delalloc(struct inode *inode,
-		loff_t pos, loff_t length, ssize_t written, unsigned flags,
-		struct iomap *iomap, iomap_punch_t punch)
-{
-	loff_t			start_byte;
-	loff_t			end_byte;
-	unsigned int		blocksize = i_blocksize(inode);
-
-	if (iomap->type != IOMAP_DELALLOC)
-		return;
-
-	/* If we didn't reserve the blocks, we're not allowed to punch them. */
-	if (!(iomap->flags & IOMAP_F_NEW))
-		return;
-
-	/*
-	 * start_byte refers to the first unused block after a short write. If
-	 * nothing was written, round offset down to point at the first block in
-	 * the range.
-	 */
-	if (unlikely(!written))
-		start_byte = round_down(pos, blocksize);
-	else
-		start_byte = round_up(pos + written, blocksize);
-	end_byte = round_up(pos + length, blocksize);
-
-	/* Nothing to do if we've written the entire delalloc extent */
-	if (start_byte >= end_byte)
-		return;
-
-	iomap_write_delalloc_release(inode, start_byte, end_byte, flags, iomap,
-			punch);
 }
-EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc);
+EXPORT_SYMBOL_GPL(iomap_write_delalloc_release);
 
 static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 {
@@ -1316,21 +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 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_UNWRITTEN)
+	if (!iomap_want_unshare_iter(iter))
 		return length;
 
 	do {
@@ -1374,11 +1321,15 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 	struct iomap_iter iter = {
 		.inode		= inode,
 		.pos		= pos,
-		.len		= len,
 		.flags		= IOMAP_WRITE | IOMAP_UNSHARE,
 	};
+	loff_t size = i_size_read(inode);
 	int ret;
 
+	if (pos < 0 || pos >= size)
+		return 0;
+
+	iter.len = min(len, size - pos);
 	while ((ret = iomap_iter(&iter, ops)) > 0)
 		iter.processed = iomap_unshare_iter(&iter);
 	return ret;