Re: [PATCH v5 3/7] NFSD: add io_cache_read controls to debugfs interface

[Chuck Lever <chuck.lever@oracle.com>]

On 8/7/25 12:25 PM, Mike Snitzer wrote:
> Add 'io_cache_read' to NFSD's debugfs interface so that: Any data
> read by NFSD will either be:
> - cached using page cache (NFSD_IO_BUFFERED=1)
> - cached but removed from the page cache upon completion
>   (NFSD_IO_DONTCACHE=2).
> - not cached (NFSD_IO_DIRECT=3)
> 
> io_cache_read may be set by writing to:
>   /sys/kernel/debug/nfsd/io_cache_read
> 
> If NFSD_IO_DONTCACHE is specified using 2, FOP_DONTCACHE must be
> advertised as supported by the underlying filesystem (e.g. XFS),
> otherwise all IO flagged with RWF_DONTCACHE will fail with
> -EOPNOTSUPP.
> 
> If NFSD_IO_DIRECT is specified using 3, the IO must be aligned
> relative to the underlying block device's logical_block_size. Also the
> memory buffer used to store the read must be aligned relative to the
> underlying block device's dma_alignment.
> 
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> ---
>  fs/nfsd/debugfs.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++
>  fs/nfsd/nfsd.h    |  9 ++++++++
>  fs/nfsd/vfs.c     | 19 +++++++++++++---
>  3 files changed, 83 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c
> index 84b0c8b559dc9..c07f71d4e84f4 100644
> --- a/fs/nfsd/debugfs.c
> +++ b/fs/nfsd/debugfs.c
> @@ -27,11 +27,66 @@ static int nfsd_dsr_get(void *data, u64 *val)
>  static int nfsd_dsr_set(void *data, u64 val)
>  {
>  	nfsd_disable_splice_read = (val > 0) ? true : false;
> +	if (!nfsd_disable_splice_read) {
> +		/*
> +		 * Cannot use NFSD_IO_DONTCACHE or NFSD_IO_DIRECT
> +		 * if splice_read is enabled.
> +		 */
> +		nfsd_io_cache_read = NFSD_IO_BUFFERED;
> +	}
>  	return 0;
>  }
>  
>  DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set, "%llu\n");
>  
> +/*
> + * /sys/kernel/debug/nfsd/io_cache_read
> + *
> + * Contents:
> + *   %1: NFS READ will use buffered IO
> + *   %2: NFS READ will use dontcache (buffered IO w/ dropbehind)
> + *   %3: NFS READ will use direct IO
> + *
> + * The default value of this setting is zero (UNSPECIFIED).
> + * This setting takes immediate effect for all NFS versions,
> + * all exports, and in all NFSD net namespaces.
> + */
> +
> +static int nfsd_io_cache_read_get(void *data, u64 *val)
> +{
> +	*val = nfsd_io_cache_read;
> +	return 0;
> +}
> +
> +static int nfsd_io_cache_read_set(void *data, u64 val)
> +{
> +	int ret = 0;
> +
> +	switch (val) {
> +	case NFSD_IO_BUFFERED:
> +		nfsd_io_cache_read = NFSD_IO_BUFFERED;
> +		break;
> +	case NFSD_IO_DONTCACHE:
> +	case NFSD_IO_DIRECT:
> +		/*
> +		 * Must disable splice_read when enabling
> +		 * NFSD_IO_DONTCACHE or NFSD_IO_DIRECT.
> +		 */
> +		nfsd_disable_splice_read = true;
> +		nfsd_io_cache_read = val;
> +		break;
> +	default:
> +		nfsd_io_cache_read = NFSD_IO_UNSPECIFIED;
> +		ret = -EINVAL;
> +		break;
> +	}
> +
> +	return ret;
> +}
> +
> +DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_read_fops, nfsd_io_cache_read_get,
> +			 nfsd_io_cache_read_set, "%llu\n");
> +
>  void nfsd_debugfs_exit(void)
>  {
>  	debugfs_remove_recursive(nfsd_top_dir);
> @@ -44,4 +99,7 @@ void nfsd_debugfs_init(void)
>  
>  	debugfs_create_file("disable-splice-read", S_IWUSR | S_IRUGO,
>  			    nfsd_top_dir, NULL, &nfsd_dsr_fops);
> +
> +	debugfs_create_file("io_cache_read", S_IWUSR | S_IRUGO,
> +			    nfsd_top_dir, NULL, &nfsd_io_cache_read_fops);
>  }
> diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
> index 1cd0bed57bc2f..6ef799405145f 100644
> --- a/fs/nfsd/nfsd.h
> +++ b/fs/nfsd/nfsd.h
> @@ -153,6 +153,15 @@ static inline void nfsd_debugfs_exit(void) {}
>  
>  extern bool nfsd_disable_splice_read __read_mostly;
>  
> +enum {
> +	NFSD_IO_UNSPECIFIED = 0,
> +	NFSD_IO_BUFFERED,
> +	NFSD_IO_DONTCACHE,
> +	NFSD_IO_DIRECT,
> +};
> +
> +extern u64 nfsd_io_cache_read __read_mostly;
> +
>  extern int nfsd_max_blksize;
>  
>  static inline int nfsd_v4client(struct svc_rqst *rq)
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index 79439ad93880a..26b6d96258711 100644
> --- a/fs/nfsd/vfs.c
> +++ b/fs/nfsd/vfs.c
> @@ -49,6 +49,7 @@
>  #define NFSDDBG_FACILITY		NFSDDBG_FILEOP
>  
>  bool nfsd_disable_splice_read __read_mostly;
> +u64 nfsd_io_cache_read __read_mostly;
>  
>  /**
>   * nfserrno - Map Linux errnos to NFS errnos
> @@ -1099,17 +1100,29 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
>  	size_t len;
>  
>  	init_sync_kiocb(&kiocb, file);
> +
> +	if (nfsd_io_cache_read == NFSD_IO_DIRECT) {
> +		/* Verify ondisk DIO alignment, memory addrs checked below */
> +		if (nf->nf_dio_mem_align && nf->nf_dio_read_offset_align &&
> +		    (((offset | *count) & (nf->nf_dio_read_offset_align - 1)) == 0))
> +			kiocb.ki_flags = IOCB_DIRECT;
> +	} else if (nfsd_io_cache_read == NFSD_IO_DONTCACHE)
> +		kiocb.ki_flags = IOCB_DONTCACHE;
> +

Personal style: let's make this a switch statement like it will be for
the write path.


>  	kiocb.ki_pos = offset;
>  
>  	v = 0;
>  	total = *count;
>  	while (total) {
>  		len = min_t(size_t, total, PAGE_SIZE - base);
> -		bvec_set_page(&rqstp->rq_bvec[v], *(rqstp->rq_next_page++),
> -			      len, base);
> +		bvec_set_page(&rqstp->rq_bvec[v], *(rqstp->rq_next_page++), len, base);

Nit: changing this line does not appear to be necessary.


> +		/* No need to verify memory is DIO-aligned since bv_offset is 0 */
> +		if (unlikely((kiocb.ki_flags & IOCB_DIRECT) && base &&
> +			     (base & (nf->nf_dio_mem_align - 1))))
> +			kiocb.ki_flags &= ~IOCB_DIRECT;
>  		total -= len;
> -		++v;
>  		base = 0;
> +		v++;

Nit: I've actually measured pre-incrementing to be slightly faster than
post-incrementing, so I'd like to keep "++v;" here.


>  	}
>  	WARN_ON_ONCE(v > rqstp->rq_maxpages);
>  


-- 
Chuck Lever