Merge tag 'nfsd-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "This is a light release containing optimizations, code clean-ups, and
  minor bug fixes.

  This development cycle focused on work outside of upstream kernel
  development:

   - Continuing to build upstream CI for NFSD based on kdevops

   - Continuing to focus on the quality of NFSD in LTS kernels

   - Participation in IETF nfsv4 WG discussions about NFSv4 ACLs,
     directory delegation, and NFSv4.2 COPY offload

  Notable features for v6.11 that do not come through the NFSD tree
  include NFS server-side support for the new pNFS NVMe layout type
  [RFC9561]. Functional testing for pNFS block layouts like this one has
  been introduced to our kdevops CI harness. Work on improving the
  resolution of file attribute time stamps in local filesystems is also
  ongoing tree-wide.

  As always I am grateful to NFSD contributors, reviewers, testers, and
  bug reporters who participated during this cycle"

* tag 'nfsd-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux:
  nfsd: nfsd_file_lease_notifier_call gets a file_lease as an argument
  gss_krb5: Fix the error handling path for crypto_sync_skcipher_setkey
  MAINTAINERS: Add a bugzilla link for NFSD
  nfsd: new netlink ops to get/set server pool_mode
  sunrpc: refactor pool_mode setting code
  nfsd: allow passing in array of thread counts via netlink
  nfsd: make nfsd_svc take an array of thread counts
  sunrpc: fix up the special handling of sv_nrpools == 1
  SUNRPC: Add a trace point in svc_xprt_deferred_close
  NFSD: Support write delegations in LAYOUTGET
  lockd: Use *-y instead of *-objs in Makefile
  NFSD: Fix nfsdcld warning
  svcrdma: Handle ADDR_CHANGE CM event properly
  svcrdma: Refactor the creation of listener CMA ID
  NFSD: remove unused structs 'nfsd3_voidargs'
  NFSD: harden svcxdr_dupstr() and svcxdr_tmpalloc() against integer overflows

4 files changed, 128 insertions, 69 deletions

diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c
index 06d8ee0db000..4eb19c3a54c7 100644
--- a/net/sunrpc/auth_gss/gss_krb5_keys.c
+++ b/net/sunrpc/auth_gss/gss_krb5_keys.c
@@ -168,7 +168,7 @@ static int krb5_DK(const struct gss_krb5_enctype *gk5e,
 		goto err_return;
 	blocksize = crypto_sync_skcipher_blocksize(cipher);
 	if (crypto_sync_skcipher_setkey(cipher, inkey->data, inkey->len))
-		goto err_return;
+		goto err_free_cipher;
 
 	ret = -ENOMEM;
 	inblockdata = kmalloc(blocksize, gfp_mask);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index d9cda1e53a01..e03f14024e47 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -72,57 +72,100 @@ static struct svc_pool_map svc_pool_map = {
 static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */
 
 static int
-param_set_pool_mode(const char *val, const struct kernel_param *kp)
+__param_set_pool_mode(const char *val, struct svc_pool_map *m)
 {
-	int *ip = (int *)kp->arg;
-	struct svc_pool_map *m = &svc_pool_map;
-	int err;
+	int err, mode;
 
 	mutex_lock(&svc_pool_map_mutex);
 
-	err = -EBUSY;
-	if (m->count)
-		goto out;
-
 	err = 0;
 	if (!strncmp(val, "auto", 4))
-		*ip = SVC_POOL_AUTO;
+		mode = SVC_POOL_AUTO;
 	else if (!strncmp(val, "global", 6))
-		*ip = SVC_POOL_GLOBAL;
+		mode = SVC_POOL_GLOBAL;
 	else if (!strncmp(val, "percpu", 6))
-		*ip = SVC_POOL_PERCPU;
+		mode = SVC_POOL_PERCPU;
 	else if (!strncmp(val, "pernode", 7))
-		*ip = SVC_POOL_PERNODE;
+		mode = SVC_POOL_PERNODE;
 	else
 		err = -EINVAL;
 
+	if (err)
+		goto out;
+
+	if (m->count == 0)
+		m->mode = mode;
+	else if (mode != m->mode)
+		err = -EBUSY;
 out:
 	mutex_unlock(&svc_pool_map_mutex);
 	return err;
 }
 
 static int
-param_get_pool_mode(char *buf, const struct kernel_param *kp)
+param_set_pool_mode(const char *val, const struct kernel_param *kp)
+{
+	struct svc_pool_map *m = kp->arg;
+
+	return __param_set_pool_mode(val, m);
+}
+
+int sunrpc_set_pool_mode(const char *val)
+{
+	return __param_set_pool_mode(val, &svc_pool_map);
+}
+EXPORT_SYMBOL(sunrpc_set_pool_mode);
+
+/**
+ * sunrpc_get_pool_mode - get the current pool_mode for the host
+ * @buf: where to write the current pool_mode
+ * @size: size of @buf
+ *
+ * Grab the current pool_mode from the svc_pool_map and write
+ * the resulting string to @buf. Returns the number of characters
+ * written to @buf (a'la snprintf()).
+ */
+int
+sunrpc_get_pool_mode(char *buf, size_t size)
 {
-	int *ip = (int *)kp->arg;
+	struct svc_pool_map *m = &svc_pool_map;
 
-	switch (*ip)
+	switch (m->mode)
 	{
 	case SVC_POOL_AUTO:
-		return sysfs_emit(buf, "auto\n");
+		return snprintf(buf, size, "auto");
 	case SVC_POOL_GLOBAL:
-		return sysfs_emit(buf, "global\n");
+		return snprintf(buf, size, "global");
 	case SVC_POOL_PERCPU:
-		return sysfs_emit(buf, "percpu\n");
+		return snprintf(buf, size, "percpu");
 	case SVC_POOL_PERNODE:
-		return sysfs_emit(buf, "pernode\n");
+		return snprintf(buf, size, "pernode");
 	default:
-		return sysfs_emit(buf, "%d\n", *ip);
+		return snprintf(buf, size, "%d", m->mode);
 	}
 }
+EXPORT_SYMBOL(sunrpc_get_pool_mode);
+
+static int
+param_get_pool_mode(char *buf, const struct kernel_param *kp)
+{
+	char str[16];
+	int len;
+
+	len = sunrpc_get_pool_mode(str, ARRAY_SIZE(str));
+
+	/* Ensure we have room for newline and NUL */
+	len = min_t(int, len, ARRAY_SIZE(str) - 2);
+
+	/* tack on the newline */
+	str[len] = '\n';
+	str[len + 1] = '\0';
+
+	return sysfs_emit(buf, str);
+}
 
 module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode,
-		 &svc_pool_map.mode, 0644);
+		  &svc_pool_map, 0644);
 
 /*
  * Detect best pool mapping mode heuristically,
@@ -250,10 +293,8 @@ svc_pool_map_get(void)
 	int npools = -1;
 
 	mutex_lock(&svc_pool_map_mutex);
-
 	if (m->count++) {
 		mutex_unlock(&svc_pool_map_mutex);
-		WARN_ON_ONCE(m->npools <= 1);
 		return m->npools;
 	}
 
@@ -275,32 +316,21 @@ svc_pool_map_get(void)
 		m->mode = SVC_POOL_GLOBAL;
 	}
 	m->npools = npools;
-
-	if (npools == 1)
-		/* service is unpooled, so doesn't hold a reference */
-		m->count--;
-
 	mutex_unlock(&svc_pool_map_mutex);
 	return npools;
 }
 
 /*
- * Drop a reference to the global map of cpus to pools, if
- * pools were in use, i.e. if npools > 1.
+ * Drop a reference to the global map of cpus to pools.
  * When the last reference is dropped, the map data is
- * freed; this allows the sysadmin to change the pool
- * mode using the pool_mode module option without
- * rebooting or re-loading sunrpc.ko.
+ * freed; this allows the sysadmin to change the pool.
  */
 static void
-svc_pool_map_put(int npools)
+svc_pool_map_put(void)
 {
 	struct svc_pool_map *m = &svc_pool_map;
 
-	if (npools <= 1)
-		return;
 	mutex_lock(&svc_pool_map_mutex);
-
 	if (!--m->count) {
 		kfree(m->to_pool);
 		m->to_pool = NULL;
@@ -308,7 +338,6 @@ svc_pool_map_put(int npools)
 		m->pool_to = NULL;
 		m->npools = 0;
 	}
-
 	mutex_unlock(&svc_pool_map_mutex);
 }
 
@@ -553,9 +582,10 @@ struct svc_serv *svc_create_pooled(struct svc_program *prog,
 	serv = __svc_create(prog, stats, bufsize, npools, threadfn);
 	if (!serv)
 		goto out_err;
+	serv->sv_is_pooled = true;
 	return serv;
 out_err:
-	svc_pool_map_put(npools);
+	svc_pool_map_put();
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(svc_create_pooled);
@@ -585,7 +615,8 @@ svc_destroy(struct svc_serv **servp)
 
 	cache_clean_deferred(serv);
 
-	svc_pool_map_put(serv->sv_nrpools);
+	if (serv->sv_is_pooled)
+		svc_pool_map_put();
 
 	for (i = 0; i < serv->sv_nrpools; i++) {
 		struct svc_pool *pool = &serv->sv_pools[i];
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index dd86d7f1e97e..d3735ab3e6d1 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -157,6 +157,7 @@ int svc_print_xprts(char *buf, int maxlen)
  */
 void svc_xprt_deferred_close(struct svc_xprt *xprt)
 {
+	trace_svc_xprt_close(xprt);
 	if (!test_and_set_bit(XPT_CLOSE, &xprt->xpt_flags))
 		svc_xprt_enqueue(xprt);
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 2b1c16b9547d..f15750cacacf 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -65,6 +65,8 @@
 
 static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv,
 						 struct net *net, int node);
+static int svc_rdma_listen_handler(struct rdma_cm_id *cma_id,
+				   struct rdma_cm_event *event);
 static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 					struct net *net,
 					struct sockaddr *sa, int salen,
@@ -122,6 +124,41 @@ static void qp_event_handler(struct ib_event *event, void *context)
 	}
 }
 
+static struct rdma_cm_id *
+svc_rdma_create_listen_id(struct net *net, struct sockaddr *sap,
+			  void *context)
+{
+	struct rdma_cm_id *listen_id;
+	int ret;
+
+	listen_id = rdma_create_id(net, svc_rdma_listen_handler, context,
+				   RDMA_PS_TCP, IB_QPT_RC);
+	if (IS_ERR(listen_id))
+		return listen_id;
+
+	/* Allow both IPv4 and IPv6 sockets to bind a single port
+	 * at the same time.
+	 */
+#if IS_ENABLED(CONFIG_IPV6)
+	ret = rdma_set_afonly(listen_id, 1);
+	if (ret)
+		goto out_destroy;
+#endif
+	ret = rdma_bind_addr(listen_id, sap);
+	if (ret)
+		goto out_destroy;
+
+	ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG);
+	if (ret)
+		goto out_destroy;
+
+	return listen_id;
+
+out_destroy:
+	rdma_destroy_id(listen_id);
+	return ERR_PTR(ret);
+}
+
 static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv,
 						 struct net *net, int node)
 {
@@ -247,17 +284,31 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id,
  *
  * Return values:
  *     %0: Do not destroy @cma_id
- *     %1: Destroy @cma_id (never returned here)
+ *     %1: Destroy @cma_id
  *
  * NB: There is never a DEVICE_REMOVAL event for INADDR_ANY listeners.
  */
 static int svc_rdma_listen_handler(struct rdma_cm_id *cma_id,
 				   struct rdma_cm_event *event)
 {
+	struct sockaddr *sap = (struct sockaddr *)&cma_id->route.addr.src_addr;
+	struct svcxprt_rdma *cma_xprt = cma_id->context;
+	struct svc_xprt *cma_rdma = &cma_xprt->sc_xprt;
+	struct rdma_cm_id *listen_id;
+
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
 		handle_connect_req(cma_id, &event->param.conn);
 		break;
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+		listen_id = svc_rdma_create_listen_id(cma_rdma->xpt_net,
+						      sap, cma_xprt);
+		if (IS_ERR(listen_id)) {
+			pr_err("Listener dead, address change failed for device %s\n",
+				cma_id->device->name);
+		} else
+			cma_xprt->sc_cm_id = listen_id;
+		return 1;
 	default:
 		break;
 	}
@@ -307,7 +358,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 {
 	struct rdma_cm_id *listen_id;
 	struct svcxprt_rdma *cma_xprt;
-	int ret;
 
 	if (sa->sa_family != AF_INET && sa->sa_family != AF_INET6)
 		return ERR_PTR(-EAFNOSUPPORT);
@@ -317,30 +367,13 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 	set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags);
 	strcpy(cma_xprt->sc_xprt.xpt_remotebuf, "listener");
 
-	listen_id = rdma_create_id(net, svc_rdma_listen_handler, cma_xprt,
-				   RDMA_PS_TCP, IB_QPT_RC);
+	listen_id = svc_rdma_create_listen_id(net, sa, cma_xprt);
 	if (IS_ERR(listen_id)) {
-		ret = PTR_ERR(listen_id);
-		goto err0;
+		kfree(cma_xprt);
+		return (struct svc_xprt *)listen_id;
 	}
-
-	/* Allow both IPv4 and IPv6 sockets to bind a single port
-	 * at the same time.
-	 */
-#if IS_ENABLED(CONFIG_IPV6)
-	ret = rdma_set_afonly(listen_id, 1);
-	if (ret)
-		goto err1;
-#endif
-	ret = rdma_bind_addr(listen_id, sa);
-	if (ret)
-		goto err1;
 	cma_xprt->sc_cm_id = listen_id;
 
-	ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG);
-	if (ret)
-		goto err1;
-
 	/*
 	 * We need to use the address from the cm_id in case the
 	 * caller specified 0 for the port number.
@@ -349,12 +382,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 	svc_xprt_set_local(&cma_xprt->sc_xprt, sa, salen);
 
 	return &cma_xprt->sc_xprt;
-
- err1:
-	rdma_destroy_id(listen_id);
- err0:
-	kfree(cma_xprt);
-	return ERR_PTR(ret);
 }
 
 /*