Re: [PATCH] xfs: serialize unaligned dio writes against all other dio writes

[Christoph Hellwig <hch@infradead.org>]

>  	if (unaligned_io) {
> +		/* unaligned dio always waits, bail */
> +		if (iocb->ki_flags & IOCB_NOWAIT)
> +			return -EAGAIN;
> +		else
>  			inode_dio_wait(inode);

No need for the else here.

>  	} else if (iolock == XFS_IOLOCK_EXCL) {
>  		xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
>  		iolock = XFS_IOLOCK_SHARED;
> @@ -548,6 +549,8 @@ xfs_file_dio_aio_write(
>  
>  	trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
>  	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
> +	if (unaligned_io && !is_sync_kiocb(iocb))
> +		inode_dio_wait(inode);

Instead of explicittly waiting here I'd much rather just mark the
I/O as sync before submitting it.  The only thing needed for that
is to clear iocb->ki_complete.  To avoid too much low-level hacking
that is probably best done with a:

static inline void mark_kiocb_sync(struct kiocb *kiocb)
{
	kiocb->ki_complete = NULL;
}

helper in fs.h.