On 6/10/25 4:57 PM, Mike Snitzer wrote:
> Add 'enable-dontcache' to NFSD's debugfs interface so that: Any data
> read or written by NFSD will either not be cached (thanks to O_DIRECT)
> or will be removed from the page cache upon completion (DONTCACHE).
I thought we were going to do two switches: One for reads and one for
writes? I could be misremembering.
After all, you are describing two different facilities here: a form of
direct I/O for READs, and RWF_DONTCACHE for WRITEs (I think?).
> enable-dontcache is 0 by default. It may be enabled with:
> echo 1 > /sys/kernel/debug/nfsd/enable-dontcache
>
> FOP_DONTCACHE must be advertised as supported by the underlying
> filesystem (e.g. XFS), otherwise if/when 'enable-dontcache' is 1
> all IO flagged with RWF_DONTCACHE will fail with -EOPNOTSUPP.
> Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
> ---
> fs/nfsd/debugfs.c | 39 +++++++++++++++++++++++++++++++++++++++
> fs/nfsd/nfsd.h | 1 +
> fs/nfsd/vfs.c | 12 +++++++++++-
> 3 files changed, 51 insertions(+), 1 deletion(-)
>
> diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c
> index 84b0c8b559dc..8decdec60a8e 100644
> --- a/fs/nfsd/debugfs.c
> +++ b/fs/nfsd/debugfs.c
> @@ -32,6 +32,42 @@ static int nfsd_dsr_set(void *data, u64 val)
>
> DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set, "%llu\n");
>
> +/*
> + * /sys/kernel/debug/nfsd/enable-dontcache
> + *
> + * Contents:
> + * %0: NFS READ and WRITE are not allowed to use dontcache
> + * %1: NFS READ and WRITE are allowed to use dontcache
> + *
> + * NFSD's dontcache support reserves the right to use O_DIRECT
> + * if it chooses (instead of dontcache's usual pagecache-based
> + * dropbehind semantics).
> + *
> + * The default value of this setting is zero (dontcache is
> + * disabled). This setting takes immediate effect for all NFS
> + * versions, all exports, and in all NFSD net namespaces.
> + */
> +
> +static int nfsd_dontcache_get(void *data, u64 *val)
> +{
> + *val = nfsd_enable_dontcache ? 1 : 0;
> + return 0;
> +}
> +
> +static int nfsd_dontcache_set(void *data, u64 val)
> +{
> + if (val > 0) {
> + /* Must first also disable-splice-read */
> + nfsd_disable_splice_read = true;
> + nfsd_enable_dontcache = true;
> + } else
> + nfsd_enable_dontcache = false;
> + return 0;
> +}
> +
> +DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dontcache_fops, nfsd_dontcache_get,
> + nfsd_dontcache_set, "%llu\n");
> +
> void nfsd_debugfs_exit(void)
> {
> debugfs_remove_recursive(nfsd_top_dir);
> @@ -44,4 +80,7 @@ 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("enable-dontcache", S_IWUSR | S_IRUGO,
> + nfsd_top_dir, NULL, &nfsd_dontcache_fops);
> }
> diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
> index 1bfd0b4e9af7..00546547eae6 100644
> --- a/fs/nfsd/nfsd.h
> +++ b/fs/nfsd/nfsd.h
> @@ -155,6 +155,7 @@ static inline void nfsd_debugfs_exit(void) {}
> #endif
>
> extern bool nfsd_disable_splice_read __read_mostly;
> +extern bool nfsd_enable_dontcache __read_mostly;
>
> extern int nfsd_max_blksize;
>
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index 7d94fae1dee8..bba3e6f4f56b 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;
> +bool nfsd_enable_dontcache __read_mostly;
>
> /**
> * nfserrno - Map Linux errnos to NFS errnos
> @@ -1086,6 +1087,7 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
> unsigned long v, total;
> struct iov_iter iter;
> loff_t ppos = offset;
> + rwf_t flags = 0;
> ssize_t host_err;
> size_t len;
>
> @@ -1103,7 +1105,11 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
>
> trace_nfsd_read_vector(rqstp, fhp, offset, *count);
> iov_iter_bvec(&iter, ITER_DEST, rqstp->rq_bvec, v, *count);
> - host_err = vfs_iter_read(file, &iter, &ppos, 0);
> +
> + if (nfsd_enable_dontcache)
> + flags |= RWF_DONTCACHE;
Two things:
- Maybe NFSD should record whether the file system is DONTCACHE-enabled
in @fhp or in the export it is associated with, and then check that
setting here before asserting RWF_DONTCACHE
- I thought we were going with O_DIRECT for READs.
> +
> + host_err = vfs_iter_read(file, &iter, &ppos, flags);
> return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err);
> }
>
> @@ -1209,6 +1215,10 @@ 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);
> +
> + if (nfsd_enable_dontcache)
> + flags |= RWF_DONTCACHE;
> +
> since = READ_ONCE(file->f_wb_err);
> if (verf)
> nfsd_copy_write_verifier(verf, nn);
--
Chuck Lever
