1 files changed, 138 insertions, 38 deletions

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 8b09463dae0d..238a03087e17 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -13,6 +13,7 @@
 struct address_space;
 struct fiemap_extent_info;
 struct inode;
+struct iomap_dio;
 struct iomap_writepage_ctx;
 struct iov_iter;
 struct kiocb;
@@ -54,6 +55,7 @@ struct vm_fault;
 #define IOMAP_F_SHARED		0x04
 #define IOMAP_F_MERGED		0x08
 #define IOMAP_F_BUFFER_HEAD	0x10
+#define IOMAP_F_ZONE_APPEND	0x20
 
 /*
  * Flags set by the core iomap code during operations:
@@ -89,13 +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
@@ -106,10 +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);
 };
 
 /*
@@ -121,6 +139,13 @@ struct iomap_page_ops {
 #define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
 #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 */
+#ifdef CONFIG_FS_DAX
+#define IOMAP_DAX		(1 << 8) /* DAX mapping */
+#else
+#define IOMAP_DAX		0
+#endif /* CONFIG_FS_DAX */
 
 struct iomap_ops {
 	/*
@@ -142,33 +167,70 @@ 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
+ */
+struct iomap_iter {
+	struct inode *inode;
+	loff_t pos;
+	u64 len;
+	s64 processed;
+	unsigned flags;
+	struct iomap iomap;
+	struct iomap srcmap;
+	void *private;
+};
+
+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.
  */
-typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len,
-		void *data, struct iomap *iomap, struct iomap *srcmap);
+static inline u64 iomap_length(const struct iomap_iter *iter)
+{
+	u64 end = iter->iomap.offset + iter->iomap.length;
 
-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);
+	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);
-int iomap_readpage(struct page *page, const struct iomap_ops *ops);
-int iomap_readpages(struct address_space *mapping, struct list_head *pages,
-		unsigned nr_pages, const struct iomap_ops *ops);
-int iomap_set_page_dirty(struct page *page);
-int iomap_is_partially_uptodate(struct page *page, unsigned long from,
-		unsigned long count);
-int iomap_releasepage(struct page *page, gfp_t gfp_mask);
-void iomap_invalidatepage(struct page *page, unsigned int offset,
-		unsigned int len);
-#ifdef CONFIG_MIGRATION
-int iomap_migrate_page(struct address_space *mapping, struct page *newpage,
-		struct page *page, enum migrate_mode mode);
-#else
-#define iomap_migrate_page NULL
-#endif
+int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
+void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
+bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
+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);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
@@ -178,7 +240,7 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
 			const struct iomap_ops *ops);
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
-		loff_t start, loff_t len, const struct iomap_ops *ops);
+		u64 start, u64 len, const struct iomap_ops *ops);
 loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
 		const struct iomap_ops *ops);
 loff_t iomap_seek_data(struct inode *inode, loff_t offset,
@@ -193,10 +255,11 @@ struct iomap_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
 	u16			io_type;
 	u16			io_flags;	/* IOMAP_F_* */
+	u32			io_folios;	/* folios added to ioend */
 	struct inode		*io_inode;	/* file being written to */
 	size_t			io_size;	/* size of the extent */
 	loff_t			io_offset;	/* offset in the file */
-	void			*io_private;	/* file system private data */
+	sector_t		io_sector;	/* start sector of ioend */
 	struct bio		*io_bio;	/* bio being built */
 	struct bio		io_inline_bio;	/* MUST BE LAST! */
 };
@@ -221,7 +284,7 @@ struct iomap_writeback_ops {
 	 * Optional, allows the file system to discard state on a page where
 	 * we failed to submit any I/O.
 	 */
-	void (*discard_page)(struct page *page);
+	void (*discard_folio)(struct folio *folio, loff_t pos);
 };
 
 struct iomap_writepage_ctx {
@@ -232,13 +295,8 @@ struct iomap_writepage_ctx {
 
 void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
 void iomap_ioend_try_merge(struct iomap_ioend *ioend,
-		struct list_head *more_ioends,
-		void (*merge_private)(struct iomap_ioend *ioend,
-				struct iomap_ioend *next));
+		struct list_head *more_ioends);
 void iomap_sort_ioends(struct list_head *ioend_list);
-int iomap_writepage(struct page *page, struct writeback_control *wbc,
-		struct iomap_writepage_ctx *wpc,
-		const struct iomap_writeback_ops *ops);
 int iomap_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, struct iomap_writepage_ctx *wpc,
 		const struct iomap_writeback_ops *ops);
@@ -252,12 +310,54 @@ int iomap_writepages(struct address_space *mapping,
 struct iomap_dio_ops {
 	int (*end_io)(struct kiocb *iocb, ssize_t size, int error,
 		      unsigned flags);
+	void (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
+		          loff_t file_offset);
+
+	/*
+	 * Filesystems wishing to attach private information to a direct io bio
+	 * must provide a ->submit_io method that attaches the additional
+	 * information to the bio and changes the ->bi_end_io callback to a
+	 * custom function.  This function should, at a minimum, perform any
+	 * relevant post-processing of the bio and end with a call to
+	 * iomap_dio_bio_end_io.
+	 */
+	struct bio_set *bio_set;
 };
 
+/*
+ * Wait for the I/O to complete in iomap_dio_rw even if the kiocb is not
+ * synchronous.
+ */
+#define IOMAP_DIO_FORCE_WAIT	(1 << 0)
+
+/*
+ * Do not allocate blocks or zero partial blocks, but instead fall back to
+ * the caller by returning -EAGAIN.  Used to optimize direct I/O writes that
+ * are not aligned to the file system block size.
+  */
+#define IOMAP_DIO_OVERWRITE_ONLY	(1 << 1)
+
+/*
+ * When a page fault occurs, return a partial synchronous result and allow
+ * the caller to retry the rest of the operation after dealing with the page
+ * fault.
+ */
+#define IOMAP_DIO_PARTIAL		(1 << 2)
+
+/*
+ * The caller will sync the write if needed; do not sync it within
+ * iomap_dio_rw.  Overrides IOMAP_DIO_FORCE_WAIT.
+ */
+#define IOMAP_DIO_NOSYNC		(1 << 3)
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		bool wait_for_completion);
-int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
+		unsigned int dio_flags, void *private, size_t done_before);
+struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		unsigned int dio_flags, void *private, size_t done_before);
+ssize_t iomap_dio_complete(struct iomap_dio *dio);
+void iomap_dio_bio_end_io(struct bio *bio);
 
 #ifdef CONFIG_SWAP
 struct file;