Re: [PATCH v5 4/7] vfs: RWF_NONBLOCK flag for preadv2

[Sage Weil]

On Wed, 5 Nov 2014, Milosz Tanski wrote:
> generic_file_read_iter() supports a new flag RWF_NONBLOCK which says that we
> only want to read the data if it's already in the page cache.
> 
> Additionally, there are a few filesystems that we have to specifically
> bail early if RWF_NONBLOCK because the op would block. Christoph Hellwig
> contributed this code.
> 
> Signed-off-by: Milosz Tanski <milosz@xxxxxxxxx>
> Reviewed-by: Christoph Hellwig <hch@xxxxxx>
> Reviewed-by: Jeff Moyer <jmoyer@xxxxxxxxxx>

Ceph bits

Acked-by: Sage Weil <sage@xxxxxxxxxx>


> ---
>  fs/ceph/file.c     |  2 ++
>  fs/cifs/file.c     |  6 ++++++
>  fs/nfs/file.c      |  5 ++++-
>  fs/ocfs2/file.c    |  6 ++++++
>  fs/pipe.c          |  3 ++-
>  fs/read_write.c    | 38 +++++++++++++++++++++++++-------------
>  fs/xfs/xfs_file.c  |  4 ++++
>  include/linux/fs.h |  3 +++
>  mm/filemap.c       | 18 ++++++++++++++++++
>  mm/shmem.c         |  4 ++++
>  10 files changed, 74 insertions(+), 15 deletions(-)
> 
> diff --git a/fs/ceph/file.c b/fs/ceph/file.c
> index d7e0da8..b798b5c 100644
> --- a/fs/ceph/file.c
> +++ b/fs/ceph/file.c
> @@ -822,6 +822,8 @@ again:
>  	if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
>  	    (iocb->ki_filp->f_flags & O_DIRECT) ||
>  	    (fi->flags & CEPH_F_SYNC)) {
> +		if (iocb->ki_rwflags & O_NONBLOCK)
> +			return -EAGAIN;
>  
>  		dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
>  		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
> diff --git a/fs/cifs/file.c b/fs/cifs/file.c
> index 3e4d00a..c485afa 100644
> --- a/fs/cifs/file.c
> +++ b/fs/cifs/file.c
> @@ -3005,6 +3005,9 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
>  	struct cifs_readdata *rdata, *tmp;
>  	struct list_head rdata_list;
>  
> +	if (iocb->ki_rwflags & RWF_NONBLOCK)
> +		return -EAGAIN;
> +
>  	len = iov_iter_count(to);
>  	if (!len)
>  		return 0;
> @@ -3123,6 +3126,9 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
>  	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
>  		return generic_file_read_iter(iocb, to);
>  
> +	if (iocb->ki_rwflags & RWF_NONBLOCK)
> +		return -EAGAIN;
> +
>  	/*
>  	 * We need to hold the sem to be sure nobody modifies lock list
>  	 * with a brlock that prevents reading.
> diff --git a/fs/nfs/file.c b/fs/nfs/file.c
> index 2ab6f00..aa9046f 100644
> --- a/fs/nfs/file.c
> +++ b/fs/nfs/file.c
> @@ -171,8 +171,11 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
>  	struct inode *inode = file_inode(iocb->ki_filp);
>  	ssize_t result;
>  
> -	if (iocb->ki_filp->f_flags & O_DIRECT)
> +	if (iocb->ki_filp->f_flags & O_DIRECT) {
> +		if (iocb->ki_rwflags & O_NONBLOCK)
> +			return -EAGAIN;
>  		return nfs_file_direct_read(iocb, to, iocb->ki_pos);
> +	}
>  
>  	dprintk("NFS: read(%pD2, %zu@%lu)\n",
>  		iocb->ki_filp,
> diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
> index 324dc93..bb66ca4 100644
> --- a/fs/ocfs2/file.c
> +++ b/fs/ocfs2/file.c
> @@ -2472,6 +2472,12 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
>  			filp->f_path.dentry->d_name.name,
>  			to->nr_segs);	/* GRRRRR */
>  
> +	/*
> +	 * No non-blocking reads for ocfs2 for now.  Might be doable with
> +	 * non-blocking cluster lock helpers.
> +	 */
> +	if (iocb->ki_rwflags & RWF_NONBLOCK)
> +		return -EAGAIN;
>  
>  	if (!inode) {
>  		ret = -EINVAL;
> diff --git a/fs/pipe.c b/fs/pipe.c
> index 21981e5..212bf68 100644
> --- a/fs/pipe.c
> +++ b/fs/pipe.c
> @@ -302,7 +302,8 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
>  			 */
>  			if (ret)
>  				break;
> -			if (filp->f_flags & O_NONBLOCK) {
> +			if ((filp->f_flags & O_NONBLOCK) ||
> +			    (iocb->ki_rwflags & RWF_NONBLOCK)) {
>  				ret = -EAGAIN;
>  				break;
>  			}
> diff --git a/fs/read_write.c b/fs/read_write.c
> index 907735c..cba7d4c 100644
> --- a/fs/read_write.c
> +++ b/fs/read_write.c
> @@ -835,14 +835,19 @@ static ssize_t do_readv_writev(int type, struct file *file,
>  		file_start_write(file);
>  	}
>  
> -	if (iter_fn)
> +	if (iter_fn) {
>  		ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len,
>  						pos, iter_fn, flags);
> -	else if (fnv)
> -		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
> -						pos, fnv);
> -	else
> -		ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
> +	} else {
> +		if (type == READ && (flags & RWF_NONBLOCK))
> +			return -EAGAIN;
> +
> +		if (fnv)
> +			ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
> +							pos, fnv);
> +		else
> +			ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
> +	}
>  
>  	if (type != READ)
>  		file_end_write(file);
> @@ -866,8 +871,10 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
>  		return -EBADF;
>  	if (!(file->f_mode & FMODE_CAN_READ))
>  		return -EINVAL;
> -	if (flags & ~0)
> +	if (flags & ~RWF_NONBLOCK)
>  		return -EINVAL;
> +	if ((file->f_flags & O_DIRECT) && (flags & RWF_NONBLOCK))
> +		return -EAGAIN;
>  
>  	return do_readv_writev(READ, file, vec, vlen, pos, flags);
>  }
> @@ -1069,14 +1076,19 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
>  		file_start_write(file);
>  	}
>  
> -	if (iter_fn)
> +	if (iter_fn) {
>  		ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len,
>  						pos, iter_fn, flags);
> -	else if (fnv)
> -		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
> -						pos, fnv);
> -	else
> -		ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
> +	} else {
> +		if (type == READ && (flags & RWF_NONBLOCK))
> +			return -EAGAIN;
> +
> +		if (fnv)
> +			ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
> +							pos, fnv);
> +		else
> +			ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
> +	}
>  
>  	if (type != READ)
>  		file_end_write(file);
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index eb596b4..b1f6334 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -246,6 +246,10 @@ xfs_file_read_iter(
>  
>  	XFS_STATS_INC(xs_read_calls);
>  
> +	/* XXX: need a non-blocking iolock helper, shouldn't be too hard */
> +	if (iocb->ki_rwflags & RWF_NONBLOCK)
> +		return -EAGAIN;
> +
>  	if (unlikely(file->f_flags & O_DIRECT))
>  		ioflags |= XFS_IO_ISDIRECT;
>  	if (file->f_mode & FMODE_NOCMTIME)
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 9ed5711..eaebd99 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1459,6 +1459,9 @@ struct block_device_operations;
>  #define HAVE_COMPAT_IOCTL 1
>  #define HAVE_UNLOCKED_IOCTL 1
>  
> +/* These flags are used for the readv/writev syscalls with flags. */
> +#define RWF_NONBLOCK 0x00000001
> +
>  struct iov_iter;
>  
>  struct file_operations {
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 530c263..09d3af3 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -1494,6 +1494,8 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
>  find_page:
>  		page = find_get_page(mapping, index);
>  		if (!page) {
> +			if (flags & RWF_NONBLOCK)
> +				goto would_block;
>  			page_cache_sync_readahead(mapping,
>  					ra, filp,
>  					index, last_index - index);
> @@ -1585,6 +1587,11 @@ page_ok:
>  		continue;
>  
>  page_not_up_to_date:
> +		if (flags & RWF_NONBLOCK) {
> +			page_cache_release(page);
> +			goto would_block;
> +		}
> +
>  		/* Get exclusive access to the page ... */
>  		error = lock_page_killable(page);
>  		if (unlikely(error))
> @@ -1604,6 +1611,12 @@ page_not_up_to_date_locked:
>  			goto page_ok;
>  		}
>  
> +		if (flags & RWF_NONBLOCK) {
> +			unlock_page(page);
> +			page_cache_release(page);
> +			goto would_block;
> +		}
> +
>  readpage:
>  		/*
>  		 * A previous I/O error may have been due to temporary
> @@ -1674,6 +1687,8 @@ no_cached_page:
>  		goto readpage;
>  	}
>  
> +would_block:
> +	error = -EAGAIN;
>  out:
>  	ra->prev_pos = prev_index;
>  	ra->prev_pos <<= PAGE_CACHE_SHIFT;
> @@ -1707,6 +1722,9 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
>  		size_t count = iov_iter_count(iter);
>  		loff_t size;
>  
> +		if (iocb->ki_rwflags & RWF_NONBLOCK)
> +			return -EAGAIN;
> +
>  		if (!count)
>  			goto out; /* skip atime */
>  		size = i_size_read(inode);
> diff --git a/mm/shmem.c b/mm/shmem.c
> index cd6fc75..5c30f04 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1531,6 +1531,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  	ssize_t retval = 0;
>  	loff_t *ppos = &iocb->ki_pos;
>  
> +	/* XXX: should be easily supportable */
> +	if (iocb->ki_rwflags & RWF_NONBLOCK)
> +		return -EAGAIN;
> +
>  	/*
>  	 * Might this read be for a stacking filesystem?  Then when reading
>  	 * holes of a sparse file, we actually need to allocate those pages,
> -- 
> 1.9.1
> 
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/