dax: provide an iomap based dax read/write path

This is a much simpler implementation of the DAX read/write path
that makes use of the iomap infrastructure.  It does not try to
mirror the direct I/O calling conventions and thus doesn't have to
deal with i_dio_count or the end_io handler, but instead leaves
locking and filesystem-specific I/O completion to the caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
This commit is contained in:
Christoph Hellwig 2016-09-19 11:24:49 +10:00 committed by Dave Chinner
parent b0d5e82fcf
commit a254e56812
2 changed files with 118 additions and 0 deletions

View file

@ -6,9 +6,13 @@
#include <linux/radix-tree.h>
#include <asm/pgtable.h>
struct iomap_ops;
/* We use lowest available exceptional entry bit for locking */
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
ssize_t iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
struct iomap_ops *ops);
ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
get_block_t, dio_iodone_t, int flags);
int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);