Received-SPF: pass (google.com: domain of linux-nfs+bounces-2929-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk
MIME-Version: 1.0
From: "NeilBrown" <neilb@suse.de>
To: Chuck Lever <chuck.lever@oracle.com>, Jeff Layton <jlayton@kernel.org>,
 Olga Kornievskaia <kolga@netapp.com>, Dai Ngo <Dai.Ngo@oracle.com>,
 Tom Talpey <tom@talpey.com>
Cc: Petr Vorel <pvorel@suse.cz>, linux-nfs@vger.kernel.org
Subject: [PATCH v2] nfsd: return hard failure for OP_SETCLIENTID when there
 are too many clients.
Date: Tue, 23 Apr 2024 17:28:46 +1000
Message-id: <171385732687.7600.2864936377155228614@noble.neil.brown.name>


If there are more non-courteous clients than the calculated limit, we
should fail the request rather than report a soft failure and
encouraging the client to retry indefinitely.

If there a courteous clients which push us over the limit, then expedite
their removal.

This is not known to have caused a problem is production use, but
testing of lots of clients reports repeated NFS4ERR_DELAY responses
which doesn't seem helpful.

Also remove an outdated comment - we do use a slab cache.

Signed-off-by: NeilBrown <neilb@suse.de>
---
 fs/nfsd/nfs4state.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index daf83823ba48..dfc19a5d1780 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2212,21 +2212,20 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
 	return 1;
 }
=20
-/*=20
- * XXX Should we use a slab cache ?
- * This type of memory management is somewhat inefficient, but we use it
- * anyway since SETCLIENTID is not a common operation.
- */
 static struct nfs4_client *alloc_client(struct xdr_netobj name,
 				struct nfsd_net *nn)
 {
 	struct nfs4_client *clp;
 	int i;
=20
-	if (atomic_read(&nn->nfs4_client_count) >=3D nn->nfs4_max_clients) {
+	if (atomic_read(&nn->nfs4_client_count) -
+	    atomic_read(&nn->nfsd_courtesy_clients) >=3D nn->nfs4_max_clients)
+		return ERR_PTR(-EREMOTEIO);
+
+	if (atomic_read(&nn->nfs4_client_count) >=3D nn->nfs4_max_clients &&
+	    atomic_read(&nn->nfsd_courtesy_clients) > 0)
 		mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
-		return NULL;
-	}
+
 	clp =3D kmem_cache_zalloc(client_slab, GFP_KERNEL);
 	if (clp =3D=3D NULL)
 		return NULL;
@@ -3118,8 +3117,8 @@ static struct nfs4_client *create_client(struct xdr_net=
obj name,
 	struct dentry *dentries[ARRAY_SIZE(client_files)];
=20
 	clp =3D alloc_client(name, nn);
-	if (clp =3D=3D NULL)
-		return NULL;
+	if (IS_ERR_OR_NULL(clp))
+		return clp;
=20
 	ret =3D copy_cred(&clp->cl_cred, &rqstp->rq_cred);
 	if (ret) {
@@ -3501,6 +3500,8 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_=
compound_state *cstate,
 	new =3D create_client(exid->clname, rqstp, &verf);
 	if (new =3D=3D NULL)
 		return nfserr_jukebox;
+	if (IS_ERR(new))
+		return nfserr_resource;
 	status =3D copy_impl_id(new, exid);
 	if (status)
 		goto out_nolock;
@@ -4421,6 +4422,8 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_=
compound_state *cstate,
 	new =3D create_client(clname, rqstp, &clverifier);
 	if (new =3D=3D NULL)
 		return nfserr_jukebox;
+	if (IS_ERR(new))
+		return nfserr_resource;
 	spin_lock(&nn->client_lock);
 	conf =3D find_confirmed_client_by_name(&clname, nn);
 	if (conf && client_has_state(conf)) {
--=20
2.44.0