iomap: split iomap_iter() logic into iomap_iter_next()

In preparation for changing iomap to use an in-iter (->iomap_next())
model, move the iomap_iter() logic out into the new iomap_iter_next()
helper function.

iomap_iter_next() is added as an inlined helper so it can be called
directly by ->iomap_next() implementations where the begin()/end()
callbacks can be direct calls.

The DEFINE_IOMAP_ITER_NEXT() and DEFINE_IOMAP_ITER_NEXT_END() macros are
also provided to generate the boilerplate ->iomap_next() wrapper
functions that simply forward to iomap_iter_next() with the appropriate
begin/end callbacks. DEFINE_IOMAP_ITER_NEXT() is for the common case
where there is no end() callback. DEFINE_IOMAP_ITER_NEXT_END() is for
the case where there is an explicit end() callback.

No functional change intended. The one would-be behavioral difference is
that on the iomap_end() error path (ret < 0 && !advanced), the old code
returned with iter.status left as the caller's last value whereas the
new code zeroes it, but this is not observable in practice as there are
no in-tree callers that read iter.status after the iteration loop.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Fengnan Chang <changfengnan@bytedance.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://patch.msgid.link/20260729192737.3190206-3-joannelkoong@gmail.com
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

fs/iomap/iter.c

@@ -10,11 +10,12 @@
  * Release the iter folio batch. Note that the iomap flag is meant to control
  * the I/O path for the mapping and may not be set in error situations.
  */
-static inline void iomap_iter_clean_fbatch(struct iomap_iter *iter)
+static inline void iomap_iter_clean_fbatch(const struct iomap_iter *iter,
+		struct iomap *iomap)
 {
 	if (!iter->fbatch)
 		return;
-	iter->iomap.flags &= ~IOMAP_F_FOLIO_BATCH;
+	iomap->flags &= ~IOMAP_F_FOLIO_BATCH;
 	if (folio_batch_count(iter->fbatch)) {
 		folio_batch_release(iter->fbatch);
 		folio_batch_reinit(iter->fbatch);
@@ -46,9 +47,60 @@ static inline void iomap_iter_done(struct iomap_iter *iter)
 }
 
 /**
- * iomap_iter - iterate over a ranges in a file
- * @iter: iteration structue
- * @ops: iomap ops provided by the file system
+ * iomap_iter_continue - decide whether iteration should continue
+ * @iter: iteration structure
+ * @iomap: the mapping that was just processed
+ * @srcmap: the source mapping that was just processed
+ *
+ * Helper normally called via iomap_iter_next(). Called after the previous
+ * mapping has been finished to determine whether there is more of the file
+ * range left to process.
+ *
+ * Returns 1 if there is more work to do, in which case @iomap and @srcmap are
+ * cleared so the caller can produce the next mapping; zero if the range is
+ * fully consumed; or a negative errno on error.
+ */
+int iomap_iter_continue(const struct iomap_iter *iter, struct iomap *iomap,
+		struct iomap *srcmap, int ret)
+{
+	const bool stale = iomap->flags & IOMAP_F_STALE;
+	const ssize_t advanced = iter->pos - iter->iter_start_pos;
+
+	if (ret < 0 && !advanced)
+		return ret;
+
+	/*
+	 * Use iter->len to determine whether to continue onto the next mapping.
+	 * Explicitly terminate on error status or if the current iter has not
+	 * advanced at all (i.e. no work was done for some reason) unless the
+	 * mapping has been marked stale and needs to be reprocessed.
+	 */
+	if (WARN_ON_ONCE(iter->status > 0))
+		/* detect old return semantics where this would advance */
+		ret = -EIO;
+	else if (iter->status < 0)
+		ret = iter->status;
+	else if (iter->len == 0 || (!advanced && !stale))
+		ret = 0;
+	else
+		ret = 1;
+
+	iomap_iter_clean_fbatch(iter, iomap);
+
+	if (ret <= 0)
+		return ret;
+
+	memset(iomap, 0, sizeof(*iomap));
+	memset(srcmap, 0, sizeof(*srcmap));
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_iter_continue);
+
+/**
+ * iomap_iter - iterate over ranges in a file
+ * @iter: iteration structure
+ * @ops: iomap ops provided by the filesystem
  *
  * Iterate over filesystem-provided space mappings for the provided file range.
  *
@@ -62,65 +114,17 @@ static inline void iomap_iter_done(struct iomap_iter *iter)
  */
 int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops)
 {
-	bool stale = iter->iomap.flags & IOMAP_F_STALE;
-	ssize_t advanced;
-	u64 olen;
 	int ret;
 
 	trace_iomap_iter(iter, ops, _RET_IP_);
 
-	if (!iter->iomap.length)
-		goto begin;
-
-	/*
-	 * Calculate how far the iter was advanced and the original length bytes
-	 * for ->iomap_end().
-	 */
-	advanced = iter->pos - iter->iter_start_pos;
-	olen = iter->len + advanced;
-
-	if (ops->iomap_end) {
-		ret = ops->iomap_end(iter->inode, iter->iter_start_pos,
-				iomap_length_trim(iter, iter->iter_start_pos,
-						  olen),
-				advanced, iter->flags, &iter->iomap);
-		if (ret < 0 && !advanced)
-			goto error;
-	}
-
-	/* detect old return semantics where this would advance */
-	if (WARN_ON_ONCE(iter->status > 0))
-		iter->status = -EIO;
-
-	/*
-	 * Use iter->len to determine whether to continue onto the next mapping.
-	 * Explicitly terminate on error status or if the current iter has not
-	 * advanced at all (i.e. no work was done for some reason) unless the
-	 * mapping has been marked stale and needs to be reprocessed.
-	 */
-	if (iter->status < 0)
-		ret = iter->status;
-	else if (iter->len == 0 || (!advanced && !stale))
-		ret = 0;
-	else
-		ret = 1;
-	iomap_iter_clean_fbatch(iter);
+	ret = iomap_iter_next(iter, &iter->iomap, &iter->srcmap,
+			ops->iomap_begin, ops->iomap_end);
 	iter->status = 0;
-	if (ret <= 0)
-		return ret;
+	if (ret > 0)
+		iomap_iter_done(iter);
+	else if (ret < 0)
+		iomap_iter_clean_fbatch(iter, &iter->iomap);
 
-	memset(&iter->iomap, 0, sizeof(iter->iomap));
-	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
-
-begin:
-	ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags,
-			       &iter->iomap, &iter->srcmap);
-	if (ret < 0)
-		goto error;
-	iomap_iter_done(iter);
-	return 1;
-
-error:
-	iomap_iter_clean_fbatch(iter);
 	return ret;
 }

include/linux/iomap.h

@@ -212,24 +212,27 @@ struct iomap_write_ops {
 #define IOMAP_ATOMIC		(1 << 9) /* torn-write protection */
 #define IOMAP_DONTCACHE		(1 << 10)
 
-struct iomap_ops {
-	/*
-	 * Return the existing mapping at pos, or reserve space starting at
-	 * pos for up to length, as long as we can do it as a single mapping.
-	 * The actual length is returned in iomap->length.
-	 */
-	int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length,
-			unsigned flags, struct iomap *iomap,
-			struct iomap *srcmap);
+/*
+ * Return the existing mapping at pos, or reserve space starting at pos for up
+ * to length, as long as we can do it as a single mapping.
+ * The actual length is returned in iomap->length.
+ */
+typedef int (*iomap_iter_begin_fn)(struct inode *inode, loff_t pos,
+		loff_t length, unsigned flags, struct iomap *iomap,
+		struct iomap *srcmap);
 
-	/*
-	 * Commit and/or unreserve space previous allocated using iomap_begin.
-	 * Written indicates the length of the successful write operation which
-	 * needs to be commited, while the rest needs to be unreserved.
-	 * Written might be zero if no data was written.
-	 */
-	int (*iomap_end)(struct inode *inode, loff_t pos, loff_t length,
-			ssize_t written, unsigned flags, struct iomap *iomap);
+/*
+ * Commit and/or unreserve space previously allocated by iomap_iter_begin_fn.
+ * Written indicates the length of the successful write operation which needs
+ * to be committed, while the rest needs to be unreserved.
+ * Written might be zero if no data was written.
+ */
+typedef int (*iomap_iter_end_fn)(struct inode *inode, loff_t pos, loff_t length,
+		ssize_t written, unsigned flags, struct iomap *iomap);
+
+struct iomap_ops {
+	iomap_iter_begin_fn iomap_begin;
+	iomap_iter_end_fn iomap_end;
 };
 
 /**
@@ -317,6 +320,71 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i)
 	return &i->iomap;
 }
 
+int iomap_iter_continue(const struct iomap_iter *iter, struct iomap *iomap,
+		struct iomap *srcmap, int ret);
+
+/**
+ * iomap_iter_next - finish the previous mapping and produce the next one
+ * @iter: iteration structure
+ * @iomap: mapping to finish and then repopulate
+ * @srcmap: source mapping to finish and then repopulate
+ * @begin: callback that produces a mapping for the current position
+ * @end: optional callback that finishes the previous mapping, or NULL
+ *
+ * Inline helper that implements the common body of an ->iomap_next()
+ * callback: it finishes the previous mapping via @end (if present), decides
+ * via iomap_iter_continue() whether to keep going, and obtains the next
+ * mapping via @begin.
+ *
+ * This helper is marked __always_inline so that when a caller passes
+ * compile-time-constant @begin and @end callbacks, the compiler can call them
+ * directly, avoiding the indirect-call overhead.
+ *
+ * Returns 1 to continue iterating, 0 once the range is fully consumed, or a
+ * negative errno on error.
+ */
+static __always_inline int iomap_iter_next(const struct iomap_iter *iter,
+		struct iomap *iomap, struct iomap *srcmap,
+		iomap_iter_begin_fn begin, iomap_iter_end_fn end)
+{
+	int ret = 0;
+
+	if (iomap->length) {
+		if (end) {
+			/*
+			 * Calculate how far the iter was advanced and the
+			 * original length bytes for end().
+			 */
+			ssize_t advanced = iter->pos - iter->iter_start_pos;
+			loff_t len;
+
+			len = iomap_length_trim(iter, iter->iter_start_pos,
+					iter->len + advanced);
+
+			ret = end(iter->inode, iter->iter_start_pos, len,
+					advanced, iter->flags, iomap);
+		}
+		ret = iomap_iter_continue(iter, iomap, srcmap, ret);
+		if (ret <= 0)
+			return ret;
+	}
+
+	ret = begin(iter->inode, iter->pos, iter->len, iter->flags, iomap,
+			srcmap);
+
+	return ret < 0 ? ret : 1;
+}
+
+#define DEFINE_IOMAP_ITER_NEXT_END(name, begin_fn, end_fn)		\
+int name(const struct iomap_iter *iter, struct iomap *iomap,		\
+		struct iomap *srcmap)					\
+{									\
+	return iomap_iter_next(iter, iomap, srcmap, begin_fn, end_fn);	\
+}
+
+#define DEFINE_IOMAP_ITER_NEXT(name, begin_fn)				\
+	DEFINE_IOMAP_ITER_NEXT_END(name, begin_fn, NULL)
+
 /*
  * Return the file offset for the first unchanged block after a short write.
  *