fs: introduce iomap infrastructure
Add infrastructure for multipage buffered writes. This is implemented
using an main iterator that applies an actor function to a range that
can be written.
This infrastucture is used to implement a buffered write helper, one
to zero file ranges and one to implement the ->page_mkwrite VM
operations. All of them borrow a fair amount of code from fs/buffers.
for now by using an internal version of __block_write_begin that
gets passed an iomap and builds the corresponding buffer head.
The file system is gets a set of paired ->iomap_begin and ->iomap_end
calls which allow it to map/reserve a range and get a notification
once the write code is finished with it.
Based on earlier code from Dave Chinner.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 1b22197..d2f469a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -3,19 +3,65 @@
#include <linux/types.h>
-/* types of block ranges for multipage write mappings. */
+struct inode;
+struct iov_iter;
+struct kiocb;
+struct vm_area_struct;
+struct vm_fault;
+
+/*
+ * Types of block ranges for iomap mappings:
+ */
#define IOMAP_HOLE 0x01 /* no blocks allocated, need allocation */
#define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */
#define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */
#define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */
+/*
+ * Magic value for blkno:
+ */
#define IOMAP_NULL_BLOCK -1LL /* blkno is not valid */
struct iomap {
- sector_t blkno; /* first sector of mapping */
- loff_t offset; /* file offset of mapping, bytes */
- u64 length; /* length of mapping, bytes */
- int type; /* type of mapping */
+ sector_t blkno; /* 1st sector of mapping, 512b units */
+ loff_t offset; /* file offset of mapping, bytes */
+ u64 length; /* length of mapping, bytes */
+ int type; /* type of mapping */
+ struct block_device *bdev; /* block device for I/O */
};
+/*
+ * Flags for iomap_begin / iomap_end. No flag implies a read.
+ */
+#define IOMAP_WRITE (1 << 0)
+#define IOMAP_ZERO (1 << 1)
+
+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);
+
+ /*
+ * 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);
+};
+
+ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
+ struct iomap_ops *ops);
+int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
+ bool *did_zero, struct iomap_ops *ops);
+int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+ struct iomap_ops *ops);
+int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+ struct iomap_ops *ops);
+
#endif /* LINUX_IOMAP_H */
