Merge branch 'work.preadv2' of git://git.kernel.org/pub/scm/linux/ker…

…nel/git/viro/vfs

Pull vfs cleanups from Al Viro:
 "More cleanups from Christoph"

* 'work.preadv2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  nfsd: use RWF_SYNC
  fs: add RWF_DSYNC aand RWF_SYNC
  ceph: use generic_write_sync
  fs: simplify the generic_write_sync prototype
  fs: add IOCB_SYNC and IOCB_DSYNC
  direct-io: remove the offset argument to dio_complete
  direct-io: eliminate the offset argument to ->direct_IO
  xfs: eliminate the pos variable in xfs_file_dio_aio_write
  filemap: remove the pos argument to generic_file_direct_write
  filemap: remove pos variables in generic_file_read_iter

Documentation/filesystems/Locking

@@ -194,7 +194,7 @@ prototypes:
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
-	int (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset);
+	int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
 	int (*launder_page)(struct page *);
 	int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);

Documentation/filesystems/vfs.txt

@@ -591,7 +591,7 @@ struct address_space_operations {
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
-	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset);
+	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);

drivers/staging/lustre/lustre/llite/rw26.c

@@ -358,14 +358,14 @@ static ssize_t ll_direct_IO_26_seg(const struct lu_env *env, struct cl_io *io,
  */
 #define MAX_DIO_SIZE ((KMALLOC_MAX_SIZE / sizeof(struct brw_page) *	  \
 		       PAGE_SIZE) & ~(DT_MAX_BRW_SIZE - 1))
-static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter,
-			       loff_t file_offset)
+static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct lu_env *env;
 	struct cl_io *io;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct ccc_object *obj = cl_inode2ccc(inode);
+	loff_t file_offset = iocb->ki_pos;
 	ssize_t count = iov_iter_count(iter);
 	ssize_t tot_bytes = 0, result = 0;
 	struct ll_inode_info *lli = ll_i2info(inode);

fs/9p/vfs_addr.c

@@ -245,9 +245,10 @@ static int v9fs_launder_page(struct page *page)
  *
  */
 static ssize_t
-v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
+	loff_t pos = iocb->ki_pos;
 	ssize_t n;
 	int err = 0;
 	if (iov_iter_rw(iter) == WRITE) {

fs/affs/file.c

@@ -389,12 +389,13 @@ static void affs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static ssize_t
-affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
+affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	size_t count = iov_iter_count(iter);
+	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
 
 	if (iov_iter_rw(iter) == WRITE) {
@@ -404,7 +405,7 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 			return 0;
 	}
 
-	ret = blockdev_direct_IO(iocb, inode, iter, offset, affs_get_block);
+	ret = blockdev_direct_IO(iocb, inode, iter, affs_get_block);
 	if (ret < 0 && iov_iter_rw(iter) == WRITE)
 		affs_write_failed(mapping, offset + count);
 	return ret;

fs/block_dev.c

@@ -162,15 +162,15 @@ static struct inode *bdev_file_inode(struct file *file)
 }
 
 static ssize_t
-blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
+blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = bdev_file_inode(file);
 
 	if (IS_DAX(inode))
-		return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
+		return dax_do_io(iocb, inode, iter, blkdev_get_block,
 				NULL, DIO_SKIP_DIO_COUNT);
-	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
+	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter,
 				    blkdev_get_block, NULL, NULL,
 				    DIO_SKIP_DIO_COUNT);
 }
@@ -1660,12 +1660,8 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	blk_start_plug(&plug);
 	ret = __generic_file_write_iter(iocb, from);
-	if (ret > 0) {
-		ssize_t err;
-		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
-		if (err < 0)
-			ret = err;
-	}
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
 	blk_finish_plug(&plug);
 	return ret;
 }

fs/btrfs/file.c

@@ -1703,18 +1703,17 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	return num_written ? num_written : ret;
 }
 
-static ssize_t __btrfs_direct_write(struct kiocb *iocb,
-				    struct iov_iter *from,
-				    loff_t pos)
+static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	loff_t pos = iocb->ki_pos;
 	ssize_t written;
 	ssize_t written_buffered;
 	loff_t endbyte;
 	int err;
 
-	written = generic_file_direct_write(iocb, from, pos);
+	written = generic_file_direct_write(iocb, from);
 
 	if (written < 0 || !iov_iter_count(from))
 		return written;
@@ -1832,7 +1831,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 		atomic_inc(&BTRFS_I(inode)->sync_writers);
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
-		num_written = __btrfs_direct_write(iocb, from, pos);
+		num_written = __btrfs_direct_write(iocb, from);
 	} else {
 		num_written = __btrfs_buffered_write(file, from, pos);
 		if (num_written > 0)
@@ -1852,11 +1851,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
 	spin_unlock(&BTRFS_I(inode)->lock);
-	if (num_written > 0) {
-		err = generic_write_sync(file, pos, num_written);
-		if (err < 0)
-			num_written = err;
-	}
+	if (num_written > 0)
+		num_written = generic_write_sync(iocb, num_written);
 
 	if (sync)
 		atomic_dec(&BTRFS_I(inode)->sync_writers);

fs/btrfs/inode.c

@@ -8541,13 +8541,13 @@ static ssize_t check_direct_IO(struct btrfs_root *root, struct kiocb *iocb,
 	return retval;
 }
 
-static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-			       loff_t offset)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_dio_data dio_data = { 0 };
+	loff_t offset = iocb->ki_pos;
 	size_t count = 0;
 	int flags = 0;
 	bool wakeup = true;
@@ -8607,7 +8607,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 	ret = __blockdev_direct_IO(iocb, inode,
 				   BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
-				   iter, offset, btrfs_get_blocks_direct, NULL,
+				   iter, btrfs_get_blocks_direct, NULL,
 				   btrfs_submit_direct, flags);
 	if (iov_iter_rw(iter) == WRITE) {
 		current->journal_info = NULL;

fs/ceph/addr.c

@@ -1292,8 +1292,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
  * intercept O_DIRECT reads and writes early, this function should
  * never get called.
  */
-static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter,
-			      loff_t pos)
+static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter)
 {
 	WARN_ON(1);
 	return -EINVAL;

fs/ceph/file.c

@@ -1382,12 +1382,11 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	     ceph_cap_string(got));
 	ceph_put_cap_refs(ci, got);
 
-	if (written >= 0 &&
-	    ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host) ||
-	     ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
-		err = vfs_fsync_range(file, pos, pos + written - 1, 1);
-		if (err < 0)
-			written = err;
+	if (written >= 0) {
+		if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))
+			iocb->ki_flags |= IOCB_DSYNC;
+
+		written = generic_write_sync(iocb, written);
 	}
 
 	goto out_unlocked;

fs/cifs/file.c

@@ -2687,11 +2687,8 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 out:
 	inode_unlock(inode);
 
-	if (rc > 0) {
-		ssize_t err = generic_write_sync(file, iocb->ki_pos - rc, rc);
-		if (err < 0)
-			rc = err;
-	}
+	if (rc > 0)
+		rc = generic_write_sync(iocb, rc);
 	up_read(&cinode->lock_sem);
 	return rc;
 }
@@ -3854,7 +3851,7 @@ void cifs_oplock_break(struct work_struct *work)
  * Direct IO is not yet supported in the cached mode. 
  */
 static ssize_t
-cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter)
 {
         /*
          * FIXME

fs/dax.c

@@ -244,7 +244,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
  * @iocb: The control block for this I/O
  * @inode: The file which the I/O is directed at
  * @iter: The addresses to do I/O from or to
- * @pos: The file offset where the I/O starts
  * @get_block: The filesystem method used to translate file offsets to blocks
  * @end_io: A filesystem callback for I/O completion
  * @flags: See below
@@ -257,11 +256,12 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
  * is in progress.
  */
 ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
-		  struct iov_iter *iter, loff_t pos, get_block_t get_block,
+		  struct iov_iter *iter, get_block_t get_block,
 		  dio_iodone_t end_io, int flags)
 {
 	struct buffer_head bh;
 	ssize_t retval = -EINVAL;
+	loff_t pos = iocb->ki_pos;
 	loff_t end = pos + iov_iter_count(iter);
 
 	memset(&bh, 0, sizeof(bh));

fs/direct-io.c

@@ -224,9 +224,9 @@ static inline struct page *dio_get_page(struct dio *dio,
  * filesystems can use it to hold additional state between get_block calls and
  * dio_complete.
  */
-static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
-		bool is_async)
+static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
 {
+	loff_t offset = dio->iocb->ki_pos;
 	ssize_t transferred = 0;
 
 	/*
@@ -256,6 +256,7 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
 	if (dio->end_io) {
 		int err;
 
+		// XXX: ki_pos??
 		err = dio->end_io(dio->iocb, offset, ret, dio->private);
 		if (err)
 			ret = err;
@@ -265,15 +266,15 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
 		inode_dio_end(dio->inode);
 
 	if (is_async) {
-		if (dio->rw & WRITE) {
-			int err;
-
-			err = generic_write_sync(dio->iocb->ki_filp, offset,
-						 transferred);
-			if (err < 0 && ret > 0)
-				ret = err;
-		}
+		/*
+		 * generic_write_sync expects ki_pos to have been updated
+		 * already, but the submission path only does this for
+		 * synchronous I/O.
+		 */
+		dio->iocb->ki_pos += transferred;
 
+		if (dio->rw & WRITE)
+			ret = generic_write_sync(dio->iocb,  transferred);
 		dio->iocb->ki_complete(dio->iocb, ret, 0);
 	}
 
@@ -285,7 +286,7 @@ static void dio_aio_complete_work(struct work_struct *work)
 {
 	struct dio *dio = container_of(work, struct dio, complete_work);
 
-	dio_complete(dio, dio->iocb->ki_pos, 0, true);
+	dio_complete(dio, 0, true);
 }
 
 static int dio_bio_complete(struct dio *dio, struct bio *bio);
@@ -314,7 +315,7 @@ static void dio_bio_end_aio(struct bio *bio)
 			queue_work(dio->inode->i_sb->s_dio_done_wq,
 				   &dio->complete_work);
 		} else {
-			dio_complete(dio, dio->iocb->ki_pos, 0, true);
+			dio_complete(dio, 0, true);
 		}
 	}
 }
@@ -1113,14 +1114,15 @@ static inline int drop_refcount(struct dio *dio)
 static inline ssize_t
 do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 		      struct block_device *bdev, struct iov_iter *iter,
-		      loff_t offset, get_block_t get_block, dio_iodone_t end_io,
+		      get_block_t get_block, dio_iodone_t end_io,
 		      dio_submit_t submit_io, int flags)
 {
 	unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits);
 	unsigned blkbits = i_blkbits;
 	unsigned blocksize_mask = (1 << blkbits) - 1;
 	ssize_t retval = -EINVAL;
 	size_t count = iov_iter_count(iter);
+	loff_t offset = iocb->ki_pos;
 	loff_t end = offset + count;
 	struct dio *dio;
 	struct dio_submit sdio = { 0, };
@@ -1318,7 +1320,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 		dio_await_completion(dio);
 
 	if (drop_refcount(dio) == 0) {
-		retval = dio_complete(dio, offset, retval, false);
+		retval = dio_complete(dio, retval, false);
 	} else
 		BUG_ON(retval != -EIOCBQUEUED);
 
@@ -1328,7 +1330,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 			     struct block_device *bdev, struct iov_iter *iter,
-			     loff_t offset, get_block_t get_block,
+			     get_block_t get_block,
 			     dio_iodone_t end_io, dio_submit_t submit_io,
 			     int flags)
 {
@@ -1344,7 +1346,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	prefetch(bdev->bd_queue);
 	prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
 
-	return do_blockdev_direct_IO(iocb, inode, bdev, iter, offset, get_block,
+	return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block,
 				     end_io, submit_io, flags);
 }
 

fs/exofs/inode.c

@@ -960,8 +960,7 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset,
 
 
  /* TODO: Should be easy enough to do proprly */
-static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-			       loff_t offset)
+static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	return 0;
 }

fs/ext2/inode.c

@@ -854,20 +854,20 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
 }
 
 static ssize_t
-ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
+ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	size_t count = iov_iter_count(iter);
+	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
 
 	if (IS_DAX(inode))
-		ret = dax_do_io(iocb, inode, iter, offset, ext2_get_block, NULL,
+		ret = dax_do_io(iocb, inode, iter, ext2_get_block, NULL,
 				DIO_LOCKING);
 	else
-		ret = blockdev_direct_IO(iocb, inode, iter, offset,
-					 ext2_get_block);
+		ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
 	if (ret < 0 && iov_iter_rw(iter) == WRITE)
 		ext2_write_failed(mapping, offset + count);
 	return ret;

fs/ext4/ext4.h

@@ -2581,8 +2581,7 @@ extern int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
 /* indirect.c */
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 				struct ext4_map_blocks *map, int flags);
-extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-				  loff_t offset);
+extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
 extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
 extern void ext4_ind_truncate(handle_t *, struct inode *inode);