Merge tag 'iomap-5.15-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull iomap updates from Darrick Wong:
 "The most notable externally visible change for this cycle is the
  addition of support for reads to inline tail fragments of files, which
  was requested by the erofs developers; and a correction for a kernel
  memory corruption bug if the sysadmin tries to activate a swapfile
  with more pages than the swapfile header suggests.

  We also now report writeback completion errors to the file mapping
  correctly, instead of munging all errors into EIO.

  Internally, the bulk of the changes are Christoph's patchset to reduce
  the indirect function call count by a third to a half by converting
  iomap iteration from a loop pattern to a generator/consumer pattern.
  As an added bonus, fsdax no longer open-codes iomap apply loops.

  Summary:

   - Simplify the bio_end_page usage in the buffered IO code.

   - Support reading inline data at nonzero offsets for erofs.

   - Fix some typos and bad grammar.

   - Convert kmap_atomic usage in the inline data read path.

   - Add some extra inline data input checking.

   - Fix a memory corruption bug stemming from iomap_swapfile_activate
     trying to activate more pages than mm was expecting.

   - Pass errnos through the page writeback code so that writeback
     errors are reported correctly instead of being munged to EIO.

   - Replace iomap_apply with a open-coded iterator loops to reduce the
     number of indirect calls by a third to a half.

   - Refactor the fsdax code to use iomap iterators instead of the
     open-coded iomap_apply code that it had before.

   - Format file range iomap tracepoint data in hexadecimal and
     standardize the names used in the pretty-print string"

* tag 'iomap-5.15-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (41 commits)
  iomap: standardize tracepoint formatting and storage
  mm/swap: consider max pages in iomap_swapfile_add_extent
  iomap: move loop control code to iter.c
  iomap: constify iomap_iter_srcmap
  fsdax: switch the fault handlers to use iomap_iter
  fsdax: factor out a dax_fault_actor() helper
  fsdax: factor out helpers to simplify the dax fault code
  iomap: rework unshare flag
  iomap: pass an iomap_iter to various buffered I/O helpers
  iomap: remove iomap_apply
  fsdax: switch dax_iomap_rw to use iomap_iter
  iomap: switch iomap_swapfile_activate to use iomap_iter
  iomap: switch iomap_seek_data to use iomap_iter
  iomap: switch iomap_seek_hole to use iomap_iter
  iomap: switch iomap_bmap to use iomap_iter
  iomap: switch iomap_fiemap to use iomap_iter
  iomap: switch __iomap_dio_rw to use iomap_iter
  iomap: switch iomap_page_mkwrite to use iomap_iter
  iomap: switch iomap_zero_range to use iomap_iter
  iomap: switch iomap_file_unshare to use iomap_iter
  ...

1 files changed, 77 insertions, 14 deletions

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 479c1da3e221..24f8489583ca 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -91,13 +91,30 @@ struct iomap {
 	const struct iomap_page_ops *page_ops;
 };
 
-static inline sector_t
-iomap_sector(struct iomap *iomap, loff_t pos)
+static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos)
 {
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
 /*
+ * Returns the inline data pointer for logical offset @pos.
+ */
+static inline void *iomap_inline_data(const struct iomap *iomap, loff_t pos)
+{
+	return iomap->inline_data + pos - iomap->offset;
+}
+
+/*
+ * Check if the mapping's length is within the valid range for inline data.
+ * This is used to guard against accessing data beyond the page inline_data
+ * points at.
+ */
+static inline bool iomap_inline_data_valid(const struct iomap *iomap)
+{
+	return iomap->length <= PAGE_SIZE - offset_in_page(iomap->inline_data);
+}
+
+/*
  * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare
  * and page_done will be called for each page written to.  This only applies to
  * buffered writes as unbuffered writes will not typically have pages
@@ -108,10 +125,9 @@ iomap_sector(struct iomap *iomap, loff_t pos)
  * associated page could not be obtained.
  */
 struct iomap_page_ops {
-	int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len,
-			struct iomap *iomap);
+	int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len);
 	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
-			struct page *page, struct iomap *iomap);
+			struct page *page);
 };
 
 /*
@@ -124,6 +140,7 @@ struct iomap_page_ops {
 #define IOMAP_DIRECT		(1 << 4) /* direct I/O */
 #define IOMAP_NOWAIT		(1 << 5) /* do not block */
 #define IOMAP_OVERWRITE_ONLY	(1 << 6) /* only pure overwrites allowed */
+#define IOMAP_UNSHARE		(1 << 7) /* unshare_file_range */
 
 struct iomap_ops {
 	/*
@@ -145,15 +162,61 @@ struct iomap_ops {
 			ssize_t written, unsigned flags, struct iomap *iomap);
 };
 
-/*
- * Main iomap iterator function.
+/**
+ * struct iomap_iter - Iterate through a range of a file
+ * @inode: Set at the start of the iteration and should not change.
+ * @pos: The current file position we are operating on.  It is updated by
+ *	calls to iomap_iter().  Treat as read-only in the body.
+ * @len: The remaining length of the file segment we're operating on.
+ *	It is updated at the same time as @pos.
+ * @processed: The number of bytes processed by the body in the most recent
+ *	iteration, or a negative errno. 0 causes the iteration to stop.
+ * @flags: Zero or more of the iomap_begin flags above.
+ * @iomap: Map describing the I/O iteration
+ * @srcmap: Source map for COW operations
  */
-typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len,
-		void *data, struct iomap *iomap, struct iomap *srcmap);
+struct iomap_iter {
+	struct inode *inode;
+	loff_t pos;
+	u64 len;
+	s64 processed;
+	unsigned flags;
+	struct iomap iomap;
+	struct iomap srcmap;
+};
 
-loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length,
-		unsigned flags, const struct iomap_ops *ops, void *data,
-		iomap_actor_t actor);
+int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops);
+
+/**
+ * iomap_length - length of the current iomap iteration
+ * @iter: iteration structure
+ *
+ * Returns the length that the operation applies to for the current iteration.
+ */
+static inline u64 iomap_length(const struct iomap_iter *iter)
+{
+	u64 end = iter->iomap.offset + iter->iomap.length;
+
+	if (iter->srcmap.type != IOMAP_HOLE)
+		end = min(end, iter->srcmap.offset + iter->srcmap.length);
+	return min(iter->len, end - iter->pos);
+}
+
+/**
+ * iomap_iter_srcmap - return the source map for the current iomap iteration
+ * @i: iteration structure
+ *
+ * Write operations on file systems with reflink support might require a
+ * source and a destination map.  This function retourns the source map
+ * for a given operation, which may or may no be identical to the destination
+ * map in &i->iomap.
+ */
+static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i)
+{
+	if (i->srcmap.type != IOMAP_HOLE)
+		return &i->srcmap;
+	return &i->iomap;
+}
 
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
@@ -250,8 +313,8 @@ int iomap_writepages(struct address_space *mapping,
 struct iomap_dio_ops {
 	int (*end_io)(struct kiocb *iocb, ssize_t size, int error,
 		      unsigned flags);
-	blk_qc_t (*submit_io)(struct inode *inode, struct iomap *iomap,
-			struct bio *bio, loff_t file_offset);
+	blk_qc_t (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
+			      loff_t file_offset);
 };
 
 /*