On 8/7/25 12:25 PM, Mike Snitzer wrote:
> Add 'io_cache_write' to NFSD's debugfs interface so that: Any data
> written 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_write may be set by writing to:
> /sys/kernel/debug/nfsd/io_cache_write
>
> 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 WRITE payload must be aligned relative
> to the underlying block device's dma_alignment.
>
> Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
> ---
> fs/nfsd/debugfs.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
> fs/nfsd/nfsd.h | 1 +
> fs/nfsd/vfs.c | 16 ++++++++++++++++
> 3 files changed, 61 insertions(+)
>
> diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c
> index c07f71d4e84f4..872de65f0e9ac 100644
> --- a/fs/nfsd/debugfs.c
> +++ b/fs/nfsd/debugfs.c
> @@ -87,6 +87,47 @@ static int nfsd_io_cache_read_set(void *data, u64 val)
> DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_read_fops, nfsd_io_cache_read_get,
> nfsd_io_cache_read_set, "%llu\n");
>
> +/*
> + * /sys/kernel/debug/nfsd/io_cache_write
> + *
> + * Contents:
> + * %1: NFS WRITE will use buffered IO
> + * %2: NFS WRITE will use dontcache (buffered IO w/ dropbehind)
> + * %3: NFS WRITE 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_write_get(void *data, u64 *val)
> +{
> + *val = nfsd_io_cache_write;
> + return 0;
> +}
> +
> +static int nfsd_io_cache_write_set(void *data, u64 val)
> +{
> + int ret = 0;
> +
> + switch (val) {
> + case NFSD_IO_BUFFERED:
> + case NFSD_IO_DONTCACHE:
> + case NFSD_IO_DIRECT:
> + nfsd_io_cache_write = val;
> + break;
> + default:
> + nfsd_io_cache_write = NFSD_IO_UNSPECIFIED;
> + ret = -EINVAL;
I might be wrong, but an error return should leave the setting
untouched, IMO. Likewise for the read setting.
> + break;
> + }
> +
> + return ret;
> +}
> +
> +DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_write_fops, nfsd_io_cache_write_get,
> + nfsd_io_cache_write_set, "%llu\n");
> +
> void nfsd_debugfs_exit(void)
> {
> debugfs_remove_recursive(nfsd_top_dir);
> @@ -102,4 +143,7 @@ void nfsd_debugfs_init(void)
>
> debugfs_create_file("io_cache_read", S_IWUSR | S_IRUGO,
> nfsd_top_dir, NULL, &nfsd_io_cache_read_fops);
> +
> + debugfs_create_file("io_cache_write", S_IWUSR | S_IRUGO,
> + nfsd_top_dir, NULL, &nfsd_io_cache_write_fops);
> }
> diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
> index 6ef799405145f..fe935b4cda538 100644
> --- a/fs/nfsd/nfsd.h
> +++ b/fs/nfsd/nfsd.h
> @@ -161,6 +161,7 @@ enum {
> };
>
> extern u64 nfsd_io_cache_read __read_mostly;
> +extern u64 nfsd_io_cache_write __read_mostly;
>
> extern int nfsd_max_blksize;
>
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index 26b6d96258711..5768244c7a3c3 100644
> --- a/fs/nfsd/vfs.c
> +++ b/fs/nfsd/vfs.c
> @@ -50,6 +50,7 @@
>
> bool nfsd_disable_splice_read __read_mostly;
> u64 nfsd_io_cache_read __read_mostly;
> +u64 nfsd_io_cache_write __read_mostly;
>
> /**
> * nfserrno - Map Linux errnos to NFS errnos
> @@ -1234,6 +1235,21 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
>
> nvecs = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, payload);
> iov_iter_bvec(&iter, ITER_SOURCE, rqstp->rq_bvec, nvecs, *cnt);
> +
> + switch (nfsd_io_cache_write) {
> + case NFSD_IO_DIRECT:
> + /* direct I/O must be aligned to device logical sector size */
> + if (nf->nf_dio_mem_align && nf->nf_dio_offset_align &&
> + (((offset | *cnt) & (nf->nf_dio_offset_align-1)) == 0))
> + kiocb.ki_flags |= IOCB_DIRECT;
> + break;
> + case NFSD_IO_DONTCACHE:
> + kiocb.ki_flags |= IOCB_DONTCACHE;
> + break;
> + case NFSD_IO_BUFFERED:
> + break;
> + }
> +
> since = READ_ONCE(file->f_wb_err);
> if (verf)
> nfsd_copy_write_verifier(verf, nn);
--
Chuck Lever
