Merge tag 'nfsd-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
"This is a light release containing mostly optimizations, code clean-
ups, and minor bug fixes. This development cycle has focused on non-
upstream kernel work:

1. Continuing to build upstream CI for NFSD, based on kdevops

2. Backporting NFSD filecache-related fixes to selected LTS kernels

One notable new feature in v6.10 NFSD is the addition of a new netlink
protocol dedicated to configuring NFSD. A new user space tool,
nfsdctl, is to be added to nfs-utils. Lots more to come here.

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

* tag 'nfsd-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (29 commits)
NFSD: Force all NFSv4.2 COPY requests to be synchronous
SUNRPC: Fix gss_free_in_token_pages()
NFS/knfsd: Remove the invalid NFS error 'NFSERR_OPNOTSUPP'
knfsd: LOOKUP can return an illegal error value
nfsd: set security label during create operations
NFSD: Add COPY status code to OFFLOAD_STATUS response
NFSD: Record status of async copy operation in struct nfsd4_copy
SUNRPC: Remove comment for sp_lock
NFSD: add listener-{set,get} netlink command
SUNRPC: add a new svc_find_listener helper
SUNRPC: introduce svc_xprt_create_from_sa utility routine
NFSD: add write_version to netlink command
NFSD: convert write_threads to netlink command
NFSD: allow callers to pass in scope string to nfsd_svc
NFSD: move nfsd_mutex handling into nfsd_svc callers
lockd: host: Remove unnecessary statements＇host = NULL;＇
nfsd: don't create nfsv4recoverydir in nfsdfs when not used.
nfsd: optimise recalculate_deny_mode() for a common case
nfsd: add tracepoint in mark_client_expired_locked
nfsd: new tracepoint for check_slot_seqid
...

Documentation/netlink/specs/nfsd.yaml

···
         name: compound-ops
         type: u32
         multi-attr: true
+  -
+    name: server
+    attributes:
+      -
+        name: threads
+        type: u32
+        multi-attr: true
+      -
+        name: gracetime
+        type: u32
+      -
+        name: leasetime
+        type: u32
+      -
+        name: scope
+        type: string
+  -
+    name: version
+    attributes:
+      -
+        name: major
+        type: u32
+      -
+        name: minor
+        type: u32
+      -
+        name: enabled
+        type: flag
+  -
+    name: server-proto
+    attributes:
+      -
+        name: version
+        type: nest
+        nested-attributes: version
+        multi-attr: true
+  -
+    name: sock
+    attributes:
+      -
+        name: addr
+        type: binary
+      -
+        name: transport-name
+        type: string
+  -
+    name: server-sock
+    attributes:
+      -
+        name: addr
+        type: nest
+        nested-attributes: sock
+        multi-attr: true
 
 operations:
   list:
···
             - sport
             - dport
             - compound-ops
+    -
+      name: threads-set
+      doc: set the number of running threads
+      attribute-set: server
+      flags: [ admin-perm ]
+      do:
+        request:
+          attributes:
+            - threads
+            - gracetime
+            - leasetime
+            - scope
+    -
+      name: threads-get
+      doc: get the number of running threads
+      attribute-set: server
+      do:
+        reply:
+          attributes:
+            - threads
+            - gracetime
+            - leasetime
+            - scope
+    -
+      name: version-set
+      doc: set nfs enabled versions
+      attribute-set: server-proto
+      flags: [ admin-perm ]
+      do:
+        request:
+          attributes:
+            - version
+    -
+      name: version-get
+      doc: get nfs enabled versions
+      attribute-set: server-proto
+      do:
+        reply:
+          attributes:
+            - version
+    -
+      name: listener-set
+      doc: set nfs running sockets
+      attribute-set: server-sock
+      flags: [ admin-perm ]
+      do:
+        request:
+          attributes:
+            - addr
+    -
+      name: listener-get
+      doc: get nfs running listeners
+      attribute-set: server-sock
+      do:
+        reply:
+          attributes:
+            - addr

fs/lockd/host.c

···
 	if (nsm != NULL)
 		refcount_inc(&nsm->sm_count);
 	else {
-		host = NULL;
 		nsm = nsm_get_handle(ni->net, ni->sap, ni->salen,
 					ni->hostname, ni->hostname_len);
 		if (unlikely(nsm == NULL)) {

fs/nfsd/export.c

···
 static int export_stats_init(struct export_stats *stats)
 {
 	stats->start_time = ktime_get_seconds();
-	return nfsd_percpu_counters_init(stats->counter, EXP_STATS_COUNTERS_NUM);
+	return percpu_counter_init_many(stats->counter, 0, GFP_KERNEL,
+					EXP_STATS_COUNTERS_NUM);
 }
 
 static void export_stats_reset(struct export_stats *stats)
 {
-	if (stats)
-		nfsd_percpu_counters_reset(stats->counter,
-					   EXP_STATS_COUNTERS_NUM);
+	if (stats) {
+		int i;
+
+		for (i = 0; i < EXP_STATS_COUNTERS_NUM; i++)
+			percpu_counter_set(&stats->counter[i], 0);
+	}
 }
 
 static void export_stats_destroy(struct export_stats *stats)
 {
 	if (stats)
-		nfsd_percpu_counters_destroy(stats->counter,
-					     EXP_STATS_COUNTERS_NUM);
+		percpu_counter_destroy_many(stats->counter,
+					    EXP_STATS_COUNTERS_NUM);
 }
 
 static void svc_export_put(struct kref *ref)

fs/nfsd/netlink.c

···
 
 #include <uapi/linux/nfsd_netlink.h>
 
+/* Common nested types */
+const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1] = {
+	[NFSD_A_SOCK_ADDR] = { .type = NLA_BINARY, },
+	[NFSD_A_SOCK_TRANSPORT_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1] = {
+	[NFSD_A_VERSION_MAJOR] = { .type = NLA_U32, },
+	[NFSD_A_VERSION_MINOR] = { .type = NLA_U32, },
+	[NFSD_A_VERSION_ENABLED] = { .type = NLA_FLAG, },
+};
+
+/* NFSD_CMD_THREADS_SET - do */
+static const struct nla_policy nfsd_threads_set_nl_policy[NFSD_A_SERVER_SCOPE + 1] = {
+	[NFSD_A_SERVER_THREADS] = { .type = NLA_U32, },
+	[NFSD_A_SERVER_GRACETIME] = { .type = NLA_U32, },
+	[NFSD_A_SERVER_LEASETIME] = { .type = NLA_U32, },
+	[NFSD_A_SERVER_SCOPE] = { .type = NLA_NUL_STRING, },
+};
+
+/* NFSD_CMD_VERSION_SET - do */
+static const struct nla_policy nfsd_version_set_nl_policy[NFSD_A_SERVER_PROTO_VERSION + 1] = {
+	[NFSD_A_SERVER_PROTO_VERSION] = NLA_POLICY_NESTED(nfsd_version_nl_policy),
+};
+
+/* NFSD_CMD_LISTENER_SET - do */
+static const struct nla_policy nfsd_listener_set_nl_policy[NFSD_A_SERVER_SOCK_ADDR + 1] = {
+	[NFSD_A_SERVER_SOCK_ADDR] = NLA_POLICY_NESTED(nfsd_sock_nl_policy),
+};
+
 /* Ops table for nfsd */
 static const struct genl_split_ops nfsd_nl_ops[] = {
 	{
···
 		.dumpit	= nfsd_nl_rpc_status_get_dumpit,
 		.done	= nfsd_nl_rpc_status_get_done,
 		.flags	= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= NFSD_CMD_THREADS_SET,
+		.doit		= nfsd_nl_threads_set_doit,
+		.policy		= nfsd_threads_set_nl_policy,
+		.maxattr	= NFSD_A_SERVER_SCOPE,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_THREADS_GET,
+		.doit	= nfsd_nl_threads_get_doit,
+		.flags	= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_VERSION_SET,
+		.doit		= nfsd_nl_version_set_doit,
+		.policy		= nfsd_version_set_nl_policy,
+		.maxattr	= NFSD_A_SERVER_PROTO_VERSION,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_VERSION_GET,
+		.doit	= nfsd_nl_version_get_doit,
+		.flags	= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_LISTENER_SET,
+		.doit		= nfsd_nl_listener_set_doit,
+		.policy		= nfsd_listener_set_nl_policy,
+		.maxattr	= NFSD_A_SERVER_SOCK_ADDR,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_LISTENER_GET,
+		.doit	= nfsd_nl_listener_get_doit,
+		.flags	= GENL_CMD_CAP_DO,
 	},
 };
 

fs/nfsd/netlink.h

···
 
 #include <uapi/linux/nfsd_netlink.h>
 
+/* Common nested types */
+extern const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1];
+extern const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1];
+
 int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb);
 int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb);
 
 int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
 				  struct netlink_callback *cb);
+int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info);
 
 extern struct genl_family nfsd_nl_family;
 

fs/nfsd/netns.h

···
 /* Simple check to find out if a given net was properly initialized */
 #define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl)
 
+extern bool nfsd_support_version(int vers);
 extern void nfsd_netns_free_versions(struct nfsd_net *nn);
 
 extern unsigned int nfsd_net_id;

fs/nfsd/nfs4callback.c

···
 	return max(((u32)nn->nfsd4_lease)/10, 1u) * HZ;
 }
 
-static struct workqueue_struct *callback_wq;
-
 static bool nfsd4_queue_cb(struct nfsd4_callback *cb)
 {
-	trace_nfsd_cb_queue(cb->cb_clp, cb);
-	return queue_work(callback_wq, &cb->cb_work);
+	struct nfs4_client *clp = cb->cb_clp;
+
+	trace_nfsd_cb_queue(clp, cb);
+	return queue_work(clp->cl_callback_wq, &cb->cb_work);
 }
 
 static void nfsd41_cb_inflight_begin(struct nfs4_client *clp)
···
 void nfsd4_probe_callback_sync(struct nfs4_client *clp)
 {
 	nfsd4_probe_callback(clp);
-	flush_workqueue(callback_wq);
+	flush_workqueue(clp->cl_callback_wq);
 }
 
 void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
···
 	.rpc_release = nfsd4_cb_release,
 };
 
-int nfsd4_create_callback_queue(void)
-{
-	callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0);
-	if (!callback_wq)
-		return -ENOMEM;
-	return 0;
-}
-
-void nfsd4_destroy_callback_queue(void)
-{
-	destroy_workqueue(callback_wq);
-}
-
 /* must be called under the state lock */
 void nfsd4_shutdown_callback(struct nfs4_client *clp)
 {
···
 	 * client, destroy the rpc client, and stop:
 	 */
 	nfsd4_run_cb(&clp->cl_cb_null);
-	flush_workqueue(callback_wq);
+	flush_workqueue(clp->cl_callback_wq);
 	nfsd41_cb_inflight_wait_complete(clp);
 }
 
···
 
 /*
  * Note there isn't a lot of locking in this code; instead we depend on
- * the fact that it is run from the callback_wq, which won't run two
- * work items at once.  So, for example, callback_wq handles all access
- * of cl_cb_client and all calls to rpc_create or rpc_shutdown_client.
+ * the fact that it is run from clp->cl_callback_wq, which won't run two
+ * work items at once.  So, for example, clp->cl_callback_wq handles all
+ * access of cl_cb_client and all calls to rpc_create or rpc_shutdown_client.
  */
 static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 {

fs/nfsd/nfs4proc.c

···
 	nfs4_put_copy(copy);
 }
 
-static void nfsd4_send_cb_offload(struct nfsd4_copy *copy, __be32 nfserr)
+static void nfsd4_send_cb_offload(struct nfsd4_copy *copy)
 {
 	struct nfsd4_cb_offload *cbo;
 
···
 
 	memcpy(&cbo->co_res, &copy->cp_res, sizeof(copy->cp_res));
 	memcpy(&cbo->co_fh, &copy->fh, sizeof(copy->fh));
-	cbo->co_nfserr = nfserr;
+	cbo->co_nfserr = copy->nfserr;
 
 	nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops,
 		      NFSPROC4_CLNT_CB_OFFLOAD);
 	trace_nfsd_cb_offload(copy->cp_clp, &cbo->co_res.cb_stateid,
-			      &cbo->co_fh, copy->cp_count, nfserr);
+			      &cbo->co_fh, copy->cp_count, copy->nfserr);
 	nfsd4_run_cb(&cbo->co_cb);
 }
 
···
 static int nfsd4_do_async_copy(void *data)
 {
 	struct nfsd4_copy *copy = (struct nfsd4_copy *)data;
-	__be32 nfserr;
 
 	trace_nfsd_copy_do_async(copy);
 	if (nfsd4_ssc_is_inter(copy)) {
···
 		if (IS_ERR(filp)) {
 			switch (PTR_ERR(filp)) {
 			case -EBADF:
-				nfserr = nfserr_wrong_type;
+				copy->nfserr = nfserr_wrong_type;
 				break;
 			default:
-				nfserr = nfserr_offload_denied;
+				copy->nfserr = nfserr_offload_denied;
 			}
 			/* ss_mnt will be unmounted by the laundromat */
 			goto do_callback;
 		}
-		nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file,
-				       false);
+		copy->nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file,
+					     false);
 		nfsd4_cleanup_inter_ssc(copy->ss_nsui, filp, copy->nf_dst);
 	} else {
-		nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file,
-				       copy->nf_dst->nf_file, false);
+		copy->nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file,
+					     copy->nf_dst->nf_file, false);
 	}
 
 do_callback:
-	nfsd4_send_cb_offload(copy, nfserr);
+	set_bit(NFSD4_COPY_F_COMPLETED, &copy->cp_flags);
+	nfsd4_send_cb_offload(copy);
 	cleanup_async_copy(copy);
 	return 0;
 }
···
 	struct nfsd4_copy *copy = &u->copy;
 	__be32 status;
 	struct nfsd4_copy *async_copy = NULL;
+
+	/*
+	 * Currently, async COPY is not reliable. Force all COPY
+	 * requests to be synchronous to avoid client application
+	 * hangs waiting for COPY completion.
+	 */
+	nfsd4_copy_set_sync(copy, true);
 
 	copy->cp_clp = cstate->clp;
 	if (nfsd4_ssc_is_inter(copy)) {
···
 	struct nfsd4_copy *copy;
 	struct nfs4_client *clp = cstate->clp;
 
+	os->completed = false;
 	spin_lock(&clp->async_lock);
 	copy = find_async_copy_locked(clp, &os->stateid);
-	if (copy)
+	if (copy) {
 		os->count = copy->cp_res.wr_bytes_written;
-	else
+		if (test_bit(NFSD4_COPY_F_COMPLETED, &copy->cp_flags)) {
+			os->completed = true;
+			os->status = copy->nfserr;
+		}
+	} else
 		status = nfserr_bad_stateid;
 	spin_unlock(&clp->async_lock);
 
···
 
 	status = _nfsd4_verify(rqstp, cstate, &u->nverify);
 	return status == nfserr_same ? nfs_ok : status;
+}
+
+static __be32
+nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
+			 struct nfsd4_compound_state *cstate,
+			 union nfsd4_op_u *u)
+{
+	struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation;
+
+	/*
+	 * RFC 8881, section 18.39.3 says:
+	 *
+	 * "The server may refuse to grant the delegation. In that case, the
+	 *  server will return NFS4ERR_DIRDELEG_UNAVAIL."
+	 *
+	 * This is sub-optimal, since it means that the server would need to
+	 * abort compound processing just because the delegation wasn't
+	 * available. RFC8881bis should change this to allow the server to
+	 * return NFS4_OK with a non-fatal status of GDD4_UNAVAIL in this
+	 * situation.
+	 */
+	gdd->gddrnf_status = GDD4_UNAVAIL;
+	return nfs_ok;
 }
 
 #ifdef CONFIG_NFSD_PNFS
···
 		* sizeof(__be32);
 }
 
+static u32 nfsd4_get_dir_delegation_rsize(const struct svc_rqst *rqstp,
+					  const struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* gddr_status */ +
+		op_encode_verifier_maxsz +
+		op_encode_stateid_maxsz +
+		2 /* gddr_notification */ +
+		2 /* gddr_child_attributes */ +
+		2 /* gddr_dir_attributes */);
+}
+
 #ifdef CONFIG_NFSD_PNFS
 static u32 nfsd4_getdeviceinfo_rsize(const struct svc_rqst *rqstp,
 				     const struct nfsd4_op *op)
···
 		.op_name = "OP_FREE_STATEID",
 		.op_get_currentstateid = nfsd4_get_freestateid,
 		.op_rsize_bop = nfsd4_only_status_rsize,
+	},
+	[OP_GET_DIR_DELEGATION] = {
+		.op_func = nfsd4_get_dir_delegation,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_GET_DIR_DELEGATION",
+		.op_rsize_bop = nfsd4_get_dir_delegation_rsize,
 	},
 #ifdef CONFIG_NFSD_PNFS
 	[OP_GETDEVICEINFO] = {

fs/nfsd/nfs4state.c

···
 }
 
 static struct nfs4_openowner *
-find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
+find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
 			struct nfs4_client *clp)
 {
 	struct nfs4_stateowner *so;
···
 			return openowner(nfs4_get_stateowner(so));
 	}
 	return NULL;
-}
-
-static struct nfs4_openowner *
-find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
-			struct nfs4_client *clp)
-{
-	struct nfs4_openowner *oo;
-
-	spin_lock(&clp->cl_lock);
-	oo = find_openstateowner_str_locked(hashval, open, clp);
-	spin_unlock(&clp->cl_lock);
-	return oo;
 }
 
 static inline u32
···
 recalculate_deny_mode(struct nfs4_file *fp)
 {
 	struct nfs4_ol_stateid *stp;
+	u32 old_deny;
 
 	spin_lock(&fp->fi_lock);
+	old_deny = fp->fi_share_deny;
 	fp->fi_share_deny = 0;
-	list_for_each_entry(stp, &fp->fi_stateids, st_perfile)
+	list_for_each_entry(stp, &fp->fi_stateids, st_perfile) {
 		fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap);
+		if (fp->fi_share_deny == old_deny)
+			break;
+	}
 	spin_unlock(&fp->fi_lock);
 }
 
···
 						 GFP_KERNEL);
 	if (!clp->cl_ownerstr_hashtbl)
 		goto err_no_hashtbl;
+	clp->cl_callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0);
+	if (!clp->cl_callback_wq)
+		goto err_no_callback_wq;
+
 	for (i = 0; i < OWNER_HASH_SIZE; i++)
 		INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]);
 	INIT_LIST_HEAD(&clp->cl_sessions);
···
 	spin_lock_init(&clp->cl_lock);
 	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
+err_no_callback_wq:
+	kfree(clp->cl_ownerstr_hashtbl);
 err_no_hashtbl:
 	kfree(clp->cl_name.data);
 err_no_name:
···
 	struct nfs4_client *clp = container_of(c, struct nfs4_client, cl_nfsdfs);
 
 	free_svc_cred(&clp->cl_cred);
+	destroy_workqueue(clp->cl_callback_wq);
 	kfree(clp->cl_ownerstr_hashtbl);
 	kfree(clp->cl_name.data);
 	kfree(clp->cl_nii_domain.data);
···
 
 static __be32 mark_client_expired_locked(struct nfs4_client *clp)
 {
-	if (atomic_read(&clp->cl_rpc_users))
+	int users = atomic_read(&clp->cl_rpc_users);
+
+	trace_nfsd_mark_client_expired(clp, users);
+
+	if (users)
 		return nfserr_jukebox;
 	unhash_client_locked(clp);
 	return nfs_ok;
···
 	return status;
 }
 
-static __be32
-check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse)
+static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool slot_inuse)
 {
-	dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid,
-		slot_seqid);
-
 	/* The slot is in use, and no response has been sent. */
 	if (slot_inuse) {
 		if (seqid == slot_seqid)
···
 	}
 
 	/* RFC 8881 Section 18.36.4 Phase 2: Sequence ID processing. */
-	if (conf)
+	if (conf) {
 		cs_slot = &conf->cl_cs_slot;
-	else
+		trace_nfsd_slot_seqid_conf(conf, cr_ses);
+	} else {
 		cs_slot = &unconf->cl_cs_slot;
+		trace_nfsd_slot_seqid_unconf(unconf, cr_ses);
+	}
 	status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
 	switch (status) {
 	case nfs_ok:
···
 	 * sr_highest_slotid and the sr_target_slot id to maxslots */
 	seq->maxslots = session->se_fchannel.maxreqs;
 
+	trace_nfsd_slot_seqid_sequence(clp, seq, slot);
 	status = check_slot_seqid(seq->seqid, slot->sl_seqid,
 					slot->sl_flags & NFSD4_SLOT_INUSE);
 	if (status == nfserr_replay_cache) {
···
 	atomic_set(&nn->nfsd_courtesy_clients, 0);
 }
 
+enum rp_lock {
+	RP_UNLOCKED,
+	RP_LOCKED,
+	RP_UNHASHED,
+};
+
 static void init_nfs4_replay(struct nfs4_replay *rp)
 {
 	rp->rp_status = nfserr_serverfault;
 	rp->rp_buflen = 0;
 	rp->rp_buf = rp->rp_ibuf;
-	mutex_init(&rp->rp_mutex);
+	atomic_set(&rp->rp_locked, RP_UNLOCKED);
 }
 
-static void nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
-		struct nfs4_stateowner *so)
+static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
+				      struct nfs4_stateowner *so)
 {
 	if (!nfsd4_has_session(cstate)) {
-		mutex_lock(&so->so_replay.rp_mutex);
+		wait_var_event(&so->so_replay.rp_locked,
+			       atomic_cmpxchg(&so->so_replay.rp_locked,
+					      RP_UNLOCKED, RP_LOCKED) != RP_LOCKED);
+		if (atomic_read(&so->so_replay.rp_locked) == RP_UNHASHED)
+			return -EAGAIN;
 		cstate->replay_owner = nfs4_get_stateowner(so);
 	}
+	return 0;
 }
 
 void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate)
···
 
 	if (so != NULL) {
 		cstate->replay_owner = NULL;
-		mutex_unlock(&so->so_replay.rp_mutex);
+		atomic_set(&so->so_replay.rp_locked, RP_UNLOCKED);
+		wake_up_var(&so->so_replay.rp_locked);
 		nfs4_put_stateowner(so);
 	}
 }
···
 }
 
 static struct nfs4_openowner *
-alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
-			   struct nfsd4_compound_state *cstate)
+find_or_alloc_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
+			      struct nfsd4_compound_state *cstate)
 {
 	struct nfs4_client *clp = cstate->clp;
-	struct nfs4_openowner *oo, *ret;
+	struct nfs4_openowner *oo, *new = NULL;
 
-	oo = alloc_stateowner(openowner_slab, &open->op_owner, clp);
-	if (!oo)
-		return NULL;
-	oo->oo_owner.so_ops = &openowner_ops;
-	oo->oo_owner.so_is_open_owner = 1;
-	oo->oo_owner.so_seqid = open->op_seqid;
-	oo->oo_flags = 0;
-	if (nfsd4_has_session(cstate))
-		oo->oo_flags |= NFS4_OO_CONFIRMED;
-	oo->oo_time = 0;
-	oo->oo_last_closed_stid = NULL;
-	INIT_LIST_HEAD(&oo->oo_close_lru);
+retry:
 	spin_lock(&clp->cl_lock);
-	ret = find_openstateowner_str_locked(strhashval, open, clp);
-	if (ret == NULL) {
-		hash_openowner(oo, clp, strhashval);
-		ret = oo;
-	} else
-		nfs4_free_stateowner(&oo->oo_owner);
-
+	oo = find_openstateowner_str(strhashval, open, clp);
+	if (!oo && new) {
+		hash_openowner(new, clp, strhashval);
+		spin_unlock(&clp->cl_lock);
+		return new;
+	}
 	spin_unlock(&clp->cl_lock);
-	return ret;
+
+	if (oo && !(oo->oo_flags & NFS4_OO_CONFIRMED)) {
+		/* Replace unconfirmed owners without checking for replay. */
+		release_openowner(oo);
+		oo = NULL;
+	}
+	if (oo) {
+		if (new)
+			nfs4_free_stateowner(&new->oo_owner);
+		return oo;
+	}
+
+	new = alloc_stateowner(openowner_slab, &open->op_owner, clp);
+	if (!new)
+		return NULL;
+	new->oo_owner.so_ops = &openowner_ops;
+	new->oo_owner.so_is_open_owner = 1;
+	new->oo_owner.so_seqid = open->op_seqid;
+	new->oo_flags = 0;
+	if (nfsd4_has_session(cstate))
+		new->oo_flags |= NFS4_OO_CONFIRMED;
+	new->oo_time = 0;
+	new->oo_last_closed_stid = NULL;
+	INIT_LIST_HEAD(&new->oo_close_lru);
+	goto retry;
 }
 
 static struct nfs4_ol_stateid *
···
 	 * Wait for the refcount to drop to 2. Since it has been unhashed,
 	 * there should be no danger of the refcount going back up again at
 	 * this point.
+	 * Some threads with a reference might be waiting for rp_locked,
+	 * so tell them to stop waiting.
 	 */
+	atomic_set(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED);
+	wake_up_var(&oo->oo_owner.so_replay.rp_locked);
 	wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2);
 
 	release_all_access(s);
···
 	clp = cstate->clp;
 
 	strhashval = ownerstr_hashval(&open->op_owner);
-	oo = find_openstateowner_str(strhashval, open, clp);
+retry:
+	oo = find_or_alloc_open_stateowner(strhashval, open, cstate);
 	open->op_openowner = oo;
-	if (!oo) {
-		goto new_owner;
-	}
-	if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
-		/* Replace unconfirmed owners without checking for replay. */
-		release_openowner(oo);
-		open->op_openowner = NULL;
-		goto new_owner;
+	if (!oo)
+		return nfserr_jukebox;
+	if (nfsd4_cstate_assign_replay(cstate, &oo->oo_owner) == -EAGAIN) {
+		nfs4_put_stateowner(&oo->oo_owner);
+		goto retry;
 	}
 	status = nfsd4_check_seqid(cstate, &oo->oo_owner, open->op_seqid);
 	if (status)
 		return status;
-	goto alloc_stateid;
-new_owner:
-	oo = alloc_init_open_stateowner(strhashval, open, cstate);
-	if (oo == NULL)
-		return nfserr_jukebox;
-	open->op_openowner = oo;
-alloc_stateid:
+
 	open->op_stp = nfs4_alloc_open_stateid(clp);
 	if (!open->op_stp)
 		return nfserr_jukebox;
···
 void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
 			      struct nfsd4_open *open)
 {
-	if (open->op_openowner) {
-		struct nfs4_stateowner *so = &open->op_openowner->oo_owner;
-
-		nfsd4_cstate_assign_replay(cstate, so);
-		nfs4_put_stateowner(so);
-	}
+	if (open->op_openowner)
+		nfs4_put_stateowner(&open->op_openowner->oo_owner);
 	if (open->op_file)
 		kmem_cache_free(file_slab, open->op_file);
 	if (open->op_stp)
···
 	trace_nfsd_preprocess(seqid, stateid);
 
 	*stpp = NULL;
+retry:
 	status = nfsd4_lookup_stateid(cstate, stateid,
 				      typemask, statusmask, &s, nn);
 	if (status)
 		return status;
 	stp = openlockstateid(s);
-	nfsd4_cstate_assign_replay(cstate, stp->st_stateowner);
+	if (nfsd4_cstate_assign_replay(cstate, stp->st_stateowner) == -EAGAIN) {
+		nfs4_put_stateowner(stp->st_stateowner);
+		goto retry;
+	}
 
 	status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp);
 	if (!status)
···
 	return status;
 }
 
-static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
+static bool nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 {
 	struct nfs4_client *clp = s->st_stid.sc_client;
 	bool unhashed;
···
 		list_for_each_entry(stp, &reaplist, st_locks)
 			nfs4_free_cpntf_statelist(clp->net, &stp->st_stid);
 		free_ol_stateid_reaplist(&reaplist);
+		return false;
 	} else {
 		spin_unlock(&clp->cl_lock);
 		free_ol_stateid_reaplist(&reaplist);
-		if (unhashed)
-			move_to_close_lru(s, clp->net);
+		return unhashed;
 	}
 }
 
···
 	struct nfs4_ol_stateid *stp;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	bool need_move_to_close_list;
 
 	dprintk("NFSD: nfsd4_close on file %pd\n",
 			cstate->current_fh.fh_dentry);
···
 	 */
 	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
 
-	nfsd4_close_open_stateid(stp);
+	need_move_to_close_list = nfsd4_close_open_stateid(stp);
 	mutex_unlock(&stp->st_mutex);
+	if (need_move_to_close_list)
+		move_to_close_lru(stp, net);
 
 	/* v4.1+ suggests that we send a special stateid in here, since the
 	 * clients should just ignore this anyway. Since this is not useful
···
 	if (ret)
 		return ret;
 
-	ret = nfsd4_create_callback_queue();
-	if (ret) {
-		rhltable_destroy(&nfs4_file_rhltable);
-		return ret;
-	}
-
 	set_max_delegations();
 	return 0;
 }
···
 void
 nfs4_state_shutdown(void)
 {
-	nfsd4_destroy_callback_queue();
 	rhltable_destroy(&nfs4_file_rhltable);
 }
 

fs/nfsd/nfs4xdr.c

···
 	return nfsd4_decode_stateid4(argp, &free_stateid->fr_stateid);
 }
 
+static __be32
+nfsd4_decode_get_dir_delegation(struct nfsd4_compoundargs *argp,
+		union nfsd4_op_u *u)
+{
+	struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation;
+	__be32 status;
+
+	memset(gdd, 0, sizeof(*gdd));
+
+	if (xdr_stream_decode_bool(argp->xdr, &gdd->gdda_signal_deleg_avail) < 0)
+		return nfserr_bad_xdr;
+	status = nfsd4_decode_bitmap4(argp, gdd->gdda_notification_types,
+				      ARRAY_SIZE(gdd->gdda_notification_types));
+	if (status)
+		return status;
+	status = nfsd4_decode_nfstime4(argp, &gdd->gdda_child_attr_delay);
+	if (status)
+		return status;
+	status = nfsd4_decode_nfstime4(argp, &gdd->gdda_dir_attr_delay);
+	if (status)
+		return status;
+	status = nfsd4_decode_bitmap4(argp, gdd->gdda_child_attributes,
+					ARRAY_SIZE(gdd->gdda_child_attributes));
+	if (status)
+		return status;
+	return nfsd4_decode_bitmap4(argp, gdd->gdda_dir_attributes,
+					ARRAY_SIZE(gdd->gdda_dir_attributes));
+}
+
 #ifdef CONFIG_NFSD_PNFS
 static __be32
 nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
···
 	[OP_CREATE_SESSION]	= nfsd4_decode_create_session,
 	[OP_DESTROY_SESSION]	= nfsd4_decode_destroy_session,
 	[OP_FREE_STATEID]	= nfsd4_decode_free_stateid,
-	[OP_GET_DIR_DELEGATION]	= nfsd4_decode_notsupp,
+	[OP_GET_DIR_DELEGATION]	= nfsd4_decode_get_dir_delegation,
 #ifdef CONFIG_NFSD_PNFS
 	[OP_GETDEVICEINFO]	= nfsd4_decode_getdeviceinfo,
 	[OP_GETDEVICELIST]	= nfsd4_decode_notsupp,
···
 	return nfs_ok;
 }
 
+static __be32
+nfsd4_encode_get_dir_delegation(struct nfsd4_compoundres *resp, __be32 nfserr,
+				union nfsd4_op_u *u)
+{
+	struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation;
+	struct xdr_stream *xdr = resp->xdr;
+	__be32 status = nfserr_resource;
+
+	switch(gdd->gddrnf_status) {
+	case GDD4_OK:
+		if (xdr_stream_encode_u32(xdr, GDD4_OK) != XDR_UNIT)
+			break;
+		status = nfsd4_encode_verifier4(xdr, &gdd->gddr_cookieverf);
+		if (status)
+			break;
+		status = nfsd4_encode_stateid4(xdr, &gdd->gddr_stateid);
+		if (status)
+			break;
+		status = nfsd4_encode_bitmap4(xdr, gdd->gddr_notification[0], 0, 0);
+		if (status)
+			break;
+		status = nfsd4_encode_bitmap4(xdr, gdd->gddr_child_attributes[0],
+						   gdd->gddr_child_attributes[1],
+						   gdd->gddr_child_attributes[2]);
+		if (status)
+			break;
+		status = nfsd4_encode_bitmap4(xdr, gdd->gddr_dir_attributes[0],
+						   gdd->gddr_dir_attributes[1],
+						   gdd->gddr_dir_attributes[2]);
+		break;
+	default:
+		pr_warn("nfsd: bad gddrnf_status (%u)\n", gdd->gddrnf_status);
+		gdd->gddrnf_will_signal_deleg_avail = 0;
+		fallthrough;
+	case GDD4_UNAVAIL:
+		if (xdr_stream_encode_u32(xdr, GDD4_UNAVAIL) != XDR_UNIT)
+			break;
+		status = nfsd4_encode_bool(xdr, gdd->gddrnf_will_signal_deleg_avail);
+		break;
+	}
+	return status;
+}
+
 #ifdef CONFIG_NFSD_PNFS
 static __be32
 nfsd4_encode_device_addr4(struct xdr_stream *xdr,
···
 	if (nfserr != nfs_ok)
 		return nfserr;
 	/* osr_complete<1> */
-	if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT)
+	if (os->completed) {
+		if (xdr_stream_encode_u32(xdr, 1) != XDR_UNIT)
+			return nfserr_resource;
+		if (xdr_stream_encode_be32(xdr, os->status) != XDR_UNIT)
+			return nfserr_resource;
+	} else if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT)
 		return nfserr_resource;
 	return nfs_ok;
 }
···
 	[OP_CREATE_SESSION]	= nfsd4_encode_create_session,
 	[OP_DESTROY_SESSION]	= nfsd4_encode_noop,
 	[OP_FREE_STATEID]	= nfsd4_encode_noop,
-	[OP_GET_DIR_DELEGATION]	= nfsd4_encode_noop,
+	[OP_GET_DIR_DELEGATION]	= nfsd4_encode_get_dir_delegation,
 #ifdef CONFIG_NFSD_PNFS
 	[OP_GETDEVICEINFO]	= nfsd4_encode_getdeviceinfo,
 	[OP_GETDEVICELIST]	= nfsd4_encode_noop,

fs/nfsd/nfsctl.c

···
 #include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/gss_api.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
+#include <linux/sunrpc/svc.h>
 #include <linux/module.h>
 #include <linux/fsnotify.h>
 
···
 	NFSD_MaxBlkSize,
 	NFSD_MaxConnections,
 	NFSD_Filecache,
-#ifdef CONFIG_NFSD_V4
 	NFSD_Leasetime,
 	NFSD_Gracetime,
 	NFSD_RecoveryDir,
 	NFSD_V4EndGrace,
-#endif
 	NFSD_MaxReserved
 };
 
···
 		if (newthreads < 0)
 			return -EINVAL;
 		trace_nfsd_ctl_threads(net, newthreads);
-		rv = nfsd_svc(newthreads, net, file->f_cred);
+		mutex_lock(&nfsd_mutex);
+		rv = nfsd_svc(newthreads, net, file->f_cred, NULL);
+		mutex_unlock(&nfsd_mutex);
 		if (rv < 0)
 			return rv;
 	} else
···
 #ifdef CONFIG_NFSD_V4
 		[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR},
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 		[NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR},
+#endif
 		[NFSD_V4EndGrace] = {"v4_end_grace", &transaction_ops, S_IWUSR|S_IRUGO},
 #endif
 		/* last one */ {""}
···
 }
 
 /**
+ * nfsd_nl_threads_set_doit - set the number of running threads
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	int nthreads = 0, count = 0, nrpools, ret = -EOPNOTSUPP, rem;
+	struct net *net = genl_info_net(info);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	const struct nlattr *attr;
+	const char *scope = NULL;
+
+	if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_THREADS))
+		return -EINVAL;
+
+	/* count number of SERVER_THREADS values */
+	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+		if (nla_type(attr) == NFSD_A_SERVER_THREADS)
+			count++;
+	}
+
+	mutex_lock(&nfsd_mutex);
+
+	nrpools = nfsd_nrpools(net);
+	if (nrpools && count > nrpools)
+		count = nrpools;
+
+	/* XXX: make this handle non-global pool-modes */
+	if (count > 1)
+		goto out_unlock;
+
+	nthreads = nla_get_u32(info->attrs[NFSD_A_SERVER_THREADS]);
+	if (info->attrs[NFSD_A_SERVER_GRACETIME] ||
+	    info->attrs[NFSD_A_SERVER_LEASETIME] ||
+	    info->attrs[NFSD_A_SERVER_SCOPE]) {
+		ret = -EBUSY;
+		if (nn->nfsd_serv && nn->nfsd_serv->sv_nrthreads)
+			goto out_unlock;
+
+		ret = -EINVAL;
+		attr = info->attrs[NFSD_A_SERVER_GRACETIME];
+		if (attr) {
+			u32 gracetime = nla_get_u32(attr);
+
+			if (gracetime < 10 || gracetime > 3600)
+				goto out_unlock;
+
+			nn->nfsd4_grace = gracetime;
+		}
+
+		attr = info->attrs[NFSD_A_SERVER_LEASETIME];
+		if (attr) {
+			u32 leasetime = nla_get_u32(attr);
+
+			if (leasetime < 10 || leasetime > 3600)
+				goto out_unlock;
+
+			nn->nfsd4_lease = leasetime;
+		}
+
+		attr = info->attrs[NFSD_A_SERVER_SCOPE];
+		if (attr)
+			scope = nla_data(attr);
+	}
+
+	ret = nfsd_svc(nthreads, net, get_current_cred(), scope);
+
+out_unlock:
+	mutex_unlock(&nfsd_mutex);
+
+	return ret == nthreads ? 0 : ret;
+}
+
+/**
+ * nfsd_nl_threads_get_doit - get the number of running threads
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	void *hdr;
+	int err;
+
+	skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(skb, info);
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto err_free_msg;
+	}
+
+	mutex_lock(&nfsd_mutex);
+
+	err = nla_put_u32(skb, NFSD_A_SERVER_GRACETIME,
+			  nn->nfsd4_grace) ||
+	      nla_put_u32(skb, NFSD_A_SERVER_LEASETIME,
+			  nn->nfsd4_lease) ||
+	      nla_put_string(skb, NFSD_A_SERVER_SCOPE,
+			  nn->nfsd_name);
+	if (err)
+		goto err_unlock;
+
+	if (nn->nfsd_serv) {
+		int i;
+
+		for (i = 0; i < nfsd_nrpools(net); ++i) {
+			struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i];
+
+			err = nla_put_u32(skb, NFSD_A_SERVER_THREADS,
+					  atomic_read(&sp->sp_nrthreads));
+			if (err)
+				goto err_unlock;
+		}
+	} else {
+		err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, 0);
+		if (err)
+			goto err_unlock;
+	}
+
+	mutex_unlock(&nfsd_mutex);
+
+	genlmsg_end(skb, hdr);
+
+	return genlmsg_reply(skb, info);
+
+err_unlock:
+	mutex_unlock(&nfsd_mutex);
+err_free_msg:
+	nlmsg_free(skb);
+
+	return err;
+}
+
+/**
+ * nfsd_nl_version_set_doit - set the nfs enabled versions
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	const struct nlattr *attr;
+	struct nfsd_net *nn;
+	int i, rem;
+
+	if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_PROTO_VERSION))
+		return -EINVAL;
+
+	mutex_lock(&nfsd_mutex);
+
+	nn = net_generic(genl_info_net(info), nfsd_net_id);
+	if (nn->nfsd_serv) {
+		mutex_unlock(&nfsd_mutex);
+		return -EBUSY;
+	}
+
+	/* clear current supported versions. */
+	nfsd_vers(nn, 2, NFSD_CLEAR);
+	nfsd_vers(nn, 3, NFSD_CLEAR);
+	for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++)
+		nfsd_minorversion(nn, i, NFSD_CLEAR);
+
+	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+		struct nlattr *tb[NFSD_A_VERSION_MAX + 1];
+		u32 major, minor = 0;
+		bool enabled;
+
+		if (nla_type(attr) != NFSD_A_SERVER_PROTO_VERSION)
+			continue;
+
+		if (nla_parse_nested(tb, NFSD_A_VERSION_MAX, attr,
+				     nfsd_version_nl_policy, info->extack) < 0)
+			continue;
+
+		if (!tb[NFSD_A_VERSION_MAJOR])
+			continue;
+
+		major = nla_get_u32(tb[NFSD_A_VERSION_MAJOR]);
+		if (tb[NFSD_A_VERSION_MINOR])
+			minor = nla_get_u32(tb[NFSD_A_VERSION_MINOR]);
+
+		enabled = nla_get_flag(tb[NFSD_A_VERSION_ENABLED]);
+
+		switch (major) {
+		case 4:
+			nfsd_minorversion(nn, minor, enabled ? NFSD_SET : NFSD_CLEAR);
+			break;
+		case 3:
+		case 2:
+			if (!minor)
+				nfsd_vers(nn, major, enabled ? NFSD_SET : NFSD_CLEAR);
+			break;
+		default:
+			break;
+		}
+	}
+
+	mutex_unlock(&nfsd_mutex);
+
+	return 0;
+}
+
+/**
+ * nfsd_nl_version_get_doit - get the enabled status for all supported nfs versions
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nfsd_net *nn;
+	int i, err;
+	void *hdr;
+
+	skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(skb, info);
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto err_free_msg;
+	}
+
+	mutex_lock(&nfsd_mutex);
+	nn = net_generic(genl_info_net(info), nfsd_net_id);
+
+	for (i = 2; i <= 4; i++) {
+		int j;
+
+		for (j = 0; j <= NFSD_SUPPORTED_MINOR_VERSION; j++) {
+			struct nlattr *attr;
+
+			/* Don't record any versions the kernel doesn't have
+			 * compiled in
+			 */
+			if (!nfsd_support_version(i))
+				continue;
+
+			/* NFSv{2,3} does not support minor numbers */
+			if (i < 4 && j)
+				continue;
+
+			attr = nla_nest_start(skb,
+					      NFSD_A_SERVER_PROTO_VERSION);
+			if (!attr) {
+				err = -EINVAL;
+				goto err_nfsd_unlock;
+			}
+
+			if (nla_put_u32(skb, NFSD_A_VERSION_MAJOR, i) ||
+			    nla_put_u32(skb, NFSD_A_VERSION_MINOR, j)) {
+				err = -EINVAL;
+				goto err_nfsd_unlock;
+			}
+
+			/* Set the enabled flag if the version is enabled */
+			if (nfsd_vers(nn, i, NFSD_TEST) &&
+			    (i < 4 || nfsd_minorversion(nn, j, NFSD_TEST)) &&
+			    nla_put_flag(skb, NFSD_A_VERSION_ENABLED)) {
+				err = -EINVAL;
+				goto err_nfsd_unlock;
+			}
+
+			nla_nest_end(skb, attr);
+		}
+	}
+
+	mutex_unlock(&nfsd_mutex);
+	genlmsg_end(skb, hdr);
+
+	return genlmsg_reply(skb, info);
+
+err_nfsd_unlock:
+	mutex_unlock(&nfsd_mutex);
+err_free_msg:
+	nlmsg_free(skb);
+
+	return err;
+}
+
+/**
+ * nfsd_nl_listener_set_doit - set the nfs running sockets
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct svc_xprt *xprt, *tmp;
+	const struct nlattr *attr;
+	struct svc_serv *serv;
+	LIST_HEAD(permsocks);
+	struct nfsd_net *nn;
+	int err, rem;
+
+	mutex_lock(&nfsd_mutex);
+
+	err = nfsd_create_serv(net);
+	if (err) {
+		mutex_unlock(&nfsd_mutex);
+		return err;
+	}
+
+	nn = net_generic(net, nfsd_net_id);
+	serv = nn->nfsd_serv;
+
+	spin_lock_bh(&serv->sv_lock);
+
+	/* Move all of the old listener sockets to a temp list */
+	list_splice_init(&serv->sv_permsocks, &permsocks);
+
+	/*
+	 * Walk the list of server_socks from userland and move any that match
+	 * back to sv_permsocks
+	 */
+	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+		struct nlattr *tb[NFSD_A_SOCK_MAX + 1];
+		const char *xcl_name;
+		struct sockaddr *sa;
+
+		if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR)
+			continue;
+
+		if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr,
+				     nfsd_sock_nl_policy, info->extack) < 0)
+			continue;
+
+		if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME])
+			continue;
+
+		if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa))
+			continue;
+
+		xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]);
+		sa = nla_data(tb[NFSD_A_SOCK_ADDR]);
+
+		/* Put back any matching sockets */
+		list_for_each_entry_safe(xprt, tmp, &permsocks, xpt_list) {
+			/* This shouldn't be possible */
+			if (WARN_ON_ONCE(xprt->xpt_net != net)) {
+				list_move(&xprt->xpt_list, &serv->sv_permsocks);
+				continue;
+			}
+
+			/* If everything matches, put it back */
+			if (!strcmp(xprt->xpt_class->xcl_name, xcl_name) &&
+			    rpc_cmp_addr_port(sa, (struct sockaddr *)&xprt->xpt_local)) {
+				list_move(&xprt->xpt_list, &serv->sv_permsocks);
+				break;
+			}
+		}
+	}
+
+	/* For now, no removing old sockets while server is running */
+	if (serv->sv_nrthreads && !list_empty(&permsocks)) {
+		list_splice_init(&permsocks, &serv->sv_permsocks);
+		spin_unlock_bh(&serv->sv_lock);
+		err = -EBUSY;
+		goto out_unlock_mtx;
+	}
+
+	/* Close the remaining sockets on the permsocks list */
+	while (!list_empty(&permsocks)) {
+		xprt = list_first_entry(&permsocks, struct svc_xprt, xpt_list);
+		list_move(&xprt->xpt_list, &serv->sv_permsocks);
+
+		/*
+		 * Newly-created sockets are born with the BUSY bit set. Clear
+		 * it if there are no threads, since nothing can pick it up
+		 * in that case.
+		 */
+		if (!serv->sv_nrthreads)
+			clear_bit(XPT_BUSY, &xprt->xpt_flags);
+
+		set_bit(XPT_CLOSE, &xprt->xpt_flags);
+		spin_unlock_bh(&serv->sv_lock);
+		svc_xprt_close(xprt);
+		spin_lock_bh(&serv->sv_lock);
+	}
+
+	spin_unlock_bh(&serv->sv_lock);
+
+	/* walk list of addrs again, open any that still don't exist */
+	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+		struct nlattr *tb[NFSD_A_SOCK_MAX + 1];
+		const char *xcl_name;
+		struct sockaddr *sa;
+		int ret;
+
+		if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR)
+			continue;
+
+		if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr,
+				     nfsd_sock_nl_policy, info->extack) < 0)
+			continue;
+
+		if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME])
+			continue;
+
+		if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa))
+			continue;
+
+		xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]);
+		sa = nla_data(tb[NFSD_A_SOCK_ADDR]);
+
+		xprt = svc_find_listener(serv, xcl_name, net, sa);
+		if (xprt) {
+			svc_xprt_put(xprt);
+			continue;
+		}
+
+		ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa,
+					      SVC_SOCK_ANONYMOUS,
+					      get_current_cred());
+		/* always save the latest error */
+		if (ret < 0)
+			err = ret;
+	}
+
+	if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+		nfsd_destroy_serv(net);
+
+out_unlock_mtx:
+	mutex_unlock(&nfsd_mutex);
+
+	return err;
+}
+
+/**
+ * nfsd_nl_listener_get_doit - get the nfs running listeners
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct svc_xprt *xprt;
+	struct svc_serv *serv;
+	struct nfsd_net *nn;
+	void *hdr;
+	int err;
+
+	skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(skb, info);
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto err_free_msg;
+	}
+
+	mutex_lock(&nfsd_mutex);
+	nn = net_generic(genl_info_net(info), nfsd_net_id);
+
+	/* no nfs server? Just send empty socket list */
+	if (!nn->nfsd_serv)
+		goto out_unlock_mtx;
+
+	serv = nn->nfsd_serv;
+	spin_lock_bh(&serv->sv_lock);
+	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
+		struct nlattr *attr;
+
+		attr = nla_nest_start(skb, NFSD_A_SERVER_SOCK_ADDR);
+		if (!attr) {
+			err = -EINVAL;
+			goto err_serv_unlock;
+		}
+
+		if (nla_put_string(skb, NFSD_A_SOCK_TRANSPORT_NAME,
+				   xprt->xpt_class->xcl_name) ||
+		    nla_put(skb, NFSD_A_SOCK_ADDR,
+			    sizeof(struct sockaddr_storage),
+			    &xprt->xpt_local)) {
+			err = -EINVAL;
+			goto err_serv_unlock;
+		}
+
+		nla_nest_end(skb, attr);
+	}
+	spin_unlock_bh(&serv->sv_lock);
+out_unlock_mtx:
+	mutex_unlock(&nfsd_mutex);
+	genlmsg_end(skb, hdr);
+
+	return genlmsg_reply(skb, info);
+
+err_serv_unlock:
+	spin_unlock_bh(&serv->sv_lock);
+	mutex_unlock(&nfsd_mutex);
+err_free_msg:
+	nlmsg_free(skb);
+
+	return err;
+}
+
+/**
  * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace
  * @net: a freshly-created network namespace
  *
···
 	retval = nfsd_idmap_init(net);
 	if (retval)
 		goto out_idmap_error;
-	retval = nfsd_stat_counters_init(nn);
+	retval = percpu_counter_init_many(nn->counter, 0, GFP_KERNEL,
+					  NFSD_STATS_COUNTERS_NUM);
 	if (retval)
 		goto out_repcache_error;
 	memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats));
···
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	nfsd_proc_stat_shutdown(net);
-	nfsd_stat_counters_destroy(nn);
+	percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM);
 	nfsd_idmap_shutdown(net);
 	nfsd_export_shutdown(net);
 	nfsd_netns_free_versions(nn);

fs/nfsd/nfsd.h

···
 /*
  * Function prototypes.
  */
-int		nfsd_svc(int nrservs, struct net *net, const struct cred *cred);
+int		nfsd_svc(int nrservs, struct net *net, const struct cred *cred, const char *scope);
 int		nfsd_dispatch(struct svc_rqst *rqstp);
 
 int		nfsd_nrthreads(struct net *);
···
 #define	nfserr_nospc		cpu_to_be32(NFSERR_NOSPC)
 #define	nfserr_rofs		cpu_to_be32(NFSERR_ROFS)
 #define	nfserr_mlink		cpu_to_be32(NFSERR_MLINK)
-#define	nfserr_opnotsupp	cpu_to_be32(NFSERR_OPNOTSUPP)
 #define	nfserr_nametoolong	cpu_to_be32(NFSERR_NAMETOOLONG)
 #define	nfserr_notempty		cpu_to_be32(NFSERR_NOTEMPTY)
 #define	nfserr_dquot		cpu_to_be32(NFSERR_DQUOT)

fs/nfsd/nfsfh.c

···
 		_fh_update(fhp, exp, dentry);
 	if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
 		fh_put(fhp);
-		return nfserr_opnotsupp;
+		return nfserr_stale;
 	}
 
 	return 0;
···
 
 	_fh_update(fhp, fhp->fh_export, dentry);
 	if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
-		return nfserr_opnotsupp;
+		return nfserr_stale;
 	return 0;
 out_bad:
 	printk(KERN_ERR "fh_update: fh not verified!\n");

fs/nfsd/nfssvc.c

···
 	.pg_rpcbind_set		= nfsd_rpcbind_set,
 };
 
-static bool
-nfsd_support_version(int vers)
+bool nfsd_support_version(int vers)
 {
 	if (vers >= NFSD_MINVERS && vers < NFSD_NRVERS)
 		return nfsd_version[vers] != NULL;
···
  * this is the first time nrservs is nonzero.
  */
 int
-nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
+nfsd_svc(int nrservs, struct net *net, const struct cred *cred, const char *scope)
 {
 	int	error;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct svc_serv *serv;
 
-	mutex_lock(&nfsd_mutex);
+	lockdep_assert_held(&nfsd_mutex);
+
 	dprintk("nfsd: creating service\n");
 
 	nrservs = max(nrservs, 0);
···
 	if (nrservs == 0 && nn->nfsd_serv == NULL)
 		goto out;
 
-	strscpy(nn->nfsd_name, utsname()->nodename,
+	strscpy(nn->nfsd_name, scope ? scope : utsname()->nodename,
 		sizeof(nn->nfsd_name));
 
 	error = nfsd_create_serv(net);
···
 	if (serv->sv_nrthreads == 0)
 		nfsd_destroy_serv(net);
 out:
-	mutex_unlock(&nfsd_mutex);
 	return error;
 }
 

fs/nfsd/state.h

···
 					 1 << NFSD4_CLIENT_CB_KILL)
 #define NFSD4_CLIENT_CB_RECALL_ANY	(6)
 	unsigned long		cl_flags;
+
+	struct workqueue_struct *cl_callback_wq;
 	const struct cred	*cl_cb_cred;
 	struct rpc_clnt		*cl_cb_client;
 	u32			cl_cb_ident;
···
 	unsigned int		rp_buflen;
 	char			*rp_buf;
 	struct knfsd_fh		rp_openfh;
-	struct mutex		rp_mutex;
+	atomic_t		rp_locked;
 	char			rp_ibuf[NFSD4_REPLAY_ISIZE];
 };
 
···
 extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 		const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
 extern bool nfsd4_run_cb(struct nfsd4_callback *cb);
-extern int nfsd4_create_callback_queue(void);
-extern void nfsd4_destroy_callback_queue(void);
 extern void nfsd4_shutdown_callback(struct nfs4_client *);
 extern void nfsd4_shutdown_copy(struct nfs4_client *clp);
 extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name,

fs/nfsd/stats.c

···
 
 DEFINE_PROC_SHOW_ATTRIBUTE(nfsd);
 
-int nfsd_percpu_counters_init(struct percpu_counter *counters, int num)
-{
-	int i, err = 0;
-
-	for (i = 0; !err && i < num; i++)
-		err = percpu_counter_init(&counters[i], 0, GFP_KERNEL);
-
-	if (!err)
-		return 0;
-
-	for (; i > 0; i--)
-		percpu_counter_destroy(&counters[i-1]);
-
-	return err;
-}
-
-void nfsd_percpu_counters_reset(struct percpu_counter counters[], int num)
-{
-	int i;
-
-	for (i = 0; i < num; i++)
-		percpu_counter_set(&counters[i], 0);
-}
-
-void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num)
-{
-	int i;
-
-	for (i = 0; i < num; i++)
-		percpu_counter_destroy(&counters[i]);
-}
-
-int nfsd_stat_counters_init(struct nfsd_net *nn)
-{
-	return nfsd_percpu_counters_init(nn->counter, NFSD_STATS_COUNTERS_NUM);
-}
-
-void nfsd_stat_counters_destroy(struct nfsd_net *nn)
-{
-	nfsd_percpu_counters_destroy(nn->counter, NFSD_STATS_COUNTERS_NUM);
-}
-
 void nfsd_proc_stat_init(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

fs/nfsd/stats.h

···
 #include <uapi/linux/nfsd/stats.h>
 #include <linux/percpu_counter.h>
 
-int nfsd_percpu_counters_init(struct percpu_counter *counters, int num);
-void nfsd_percpu_counters_reset(struct percpu_counter *counters, int num);
-void nfsd_percpu_counters_destroy(struct percpu_counter *counters, int num);
-int nfsd_stat_counters_init(struct nfsd_net *nn);
-void nfsd_stat_counters_destroy(struct nfsd_net *nn);
 void nfsd_proc_stat_init(struct net *net);
 void nfsd_proc_stat_shutdown(struct net *net);
 

fs/nfsd/trace.h

···
 	)
 );
 
+DECLARE_EVENT_CLASS(nfsd_cs_slot_class,
+	TP_PROTO(
+		const struct nfs4_client *clp,
+		const struct nfsd4_create_session *cs
+	),
+	TP_ARGS(clp, cs),
+	TP_STRUCT__entry(
+		__field(u32, seqid)
+		__field(u32, slot_seqid)
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__sockaddr(addr, clp->cl_cb_conn.cb_addrlen)
+	),
+	TP_fast_assign(
+		const struct nfsd4_clid_slot *slot = &clp->cl_cs_slot;
+
+		__entry->cl_boot = clp->cl_clientid.cl_boot;
+		__entry->cl_id = clp->cl_clientid.cl_id;
+		__assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr,
+				  clp->cl_cb_conn.cb_addrlen);
+		__entry->seqid = cs->seqid;
+		__entry->slot_seqid = slot->sl_seqid;
+	),
+	TP_printk("addr=%pISpc client %08x:%08x seqid=%u slot_seqid=%u",
+		__get_sockaddr(addr), __entry->cl_boot, __entry->cl_id,
+		__entry->seqid, __entry->slot_seqid
+	)
+);
+
+#define DEFINE_CS_SLOT_EVENT(name) \
+DEFINE_EVENT(nfsd_cs_slot_class, nfsd_##name, \
+	TP_PROTO( \
+		const struct nfs4_client *clp, \
+		const struct nfsd4_create_session *cs \
+	), \
+	TP_ARGS(clp, cs))
+
+DEFINE_CS_SLOT_EVENT(slot_seqid_conf);
+DEFINE_CS_SLOT_EVENT(slot_seqid_unconf);
+
+TRACE_EVENT(nfsd_slot_seqid_sequence,
+	TP_PROTO(
+		const struct nfs4_client *clp,
+		const struct nfsd4_sequence *seq,
+		const struct nfsd4_slot *slot
+	),
+	TP_ARGS(clp, seq, slot),
+	TP_STRUCT__entry(
+		__field(u32, seqid)
+		__field(u32, slot_seqid)
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__sockaddr(addr, clp->cl_cb_conn.cb_addrlen)
+		__field(bool, in_use)
+	),
+	TP_fast_assign(
+		__entry->cl_boot = clp->cl_clientid.cl_boot;
+		__entry->cl_id = clp->cl_clientid.cl_id;
+		__assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr,
+				  clp->cl_cb_conn.cb_addrlen);
+		__entry->seqid = seq->seqid;
+		__entry->slot_seqid = slot->sl_seqid;
+	),
+	TP_printk("addr=%pISpc client %08x:%08x seqid=%u slot_seqid=%u (%sin use)",
+		__get_sockaddr(addr), __entry->cl_boot, __entry->cl_id,
+		__entry->seqid, __entry->slot_seqid,
+		__entry->in_use ? "" : "not "
+	)
+);
+
 DECLARE_EVENT_CLASS(nfsd_clientid_class,
 	TP_PROTO(const clientid_t *clid),
 	TP_ARGS(clid),
···
 DEFINE_CLIENTID_EVENT(purged);
 DEFINE_CLIENTID_EVENT(renew);
 DEFINE_CLIENTID_EVENT(stale);
+
+TRACE_EVENT(nfsd_mark_client_expired,
+	TP_PROTO(
+		const struct nfs4_client *clp,
+		int cl_rpc_users
+	),
+	TP_ARGS(clp, cl_rpc_users),
+	TP_STRUCT__entry(
+		__field(int, cl_rpc_users)
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__sockaddr(addr, clp->cl_cb_conn.cb_addrlen)
+	),
+	TP_fast_assign(
+		__entry->cl_rpc_users = cl_rpc_users;
+		__entry->cl_boot = clp->cl_clientid.cl_boot;
+		__entry->cl_id = clp->cl_clientid.cl_id;
+		__assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr,
+				  clp->cl_cb_conn.cb_addrlen)
+	),
+	TP_printk("addr=%pISpc client %08x:%08x cl_rpc_users=%d",
+		__get_sockaddr(addr), __entry->cl_boot, __entry->cl_id,
+		__entry->cl_rpc_users)
+);
 
 DECLARE_EVENT_CLASS(nfsd_net_class,
 	TP_PROTO(const struct nfsd_net *nn),
···
 		__entry->seq_status = cb->cb_seq_status;
 	),
 	TP_printk(SUNRPC_TRACE_TASK_SPECIFIER
-		" sessionid=%08x:%08x:%08x:%08x tk_status=%d seq_status=%d\n",
+		" sessionid=%08x:%08x:%08x:%08x tk_status=%d seq_status=%d",
 		__entry->task_id, __entry->client_id,
 		__entry->cl_boot, __entry->cl_id,
 		__entry->seqno, __entry->reserved,
···
 		__entry->slot_seqno = session->se_cb_seq_nr;
 	),
 	TP_printk(SUNRPC_TRACE_TASK_SPECIFIER
-		" sessionid=%08x:%08x:%08x:%08x new slot seqno=%u\n",
+		" sessionid=%08x:%08x:%08x:%08x new slot seqno=%u",
 		__entry->task_id, __entry->client_id,
 		__entry->cl_boot, __entry->cl_id,
 		__entry->seqno, __entry->reserved,
···
 		__entry->time = time;
 		__assign_str(name, name);
 	),
-	TP_printk("file=%s time=%d\n",
+	TP_printk("file=%s time=%d",
 		__get_str(name), __entry->time
 	)
 );

fs/nfsd/vfs.c

···
 	 * Callers expect new file metadata to be committed even
 	 * if the attributes have not changed.
 	 */
-	if (iap->ia_valid)
+	if (nfsd_attrs_valid(attrs))
 		status = nfsd_setattr(rqstp, resfhp, attrs, NULL);
 	else
 		status = nfserrno(commit_metadata(resfhp));

fs/nfsd/vfs.h

···
 	posix_acl_release(attrs->na_dpacl);
 }
 
+static inline bool nfsd_attrs_valid(struct nfsd_attrs *attrs)
+{
+	struct iattr *iap = attrs->na_iattr;
+
+	return (iap->ia_valid || (attrs->na_seclabel &&
+		attrs->na_seclabel->len));
+}
+
 __be32		nfserrno (int errno);
 int		nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 		                struct svc_export **expp);

fs/nfsd/xdr4.h

···
 	stateid_t	fr_stateid;         /* request */
 };
 
+struct nfsd4_get_dir_delegation {
+	/* request */
+	u32			gdda_signal_deleg_avail;
+	u32			gdda_notification_types[1];
+	struct timespec64	gdda_child_attr_delay;
+	struct timespec64	gdda_dir_attr_delay;
+	u32			gdda_child_attributes[3];
+	u32			gdda_dir_attributes[3];
+	/* response */
+	u32			gddrnf_status;
+	nfs4_verifier		gddr_cookieverf;
+	stateid_t		gddr_stateid;
+	u32			gddr_notification[1];
+	u32			gddr_child_attributes[3];
+	u32			gddr_dir_attributes[3];
+	bool			gddrnf_will_signal_deleg_avail;
+};
+
 /* also used for NVERIFY */
 struct nfsd4_verify {
 	u32		ve_bmval[3];        /* request */
···
 #define NFSD4_COPY_F_INTRA		(1)
 #define NFSD4_COPY_F_SYNCHRONOUS	(2)
 #define NFSD4_COPY_F_COMMITTED		(3)
+#define NFSD4_COPY_F_COMPLETED		(4)
 
 	/* response */
+	__be32			nfserr;
 	struct nfsd42_write_res	cp_res;
 	struct knfsd_fh		fh;
 
···
 
 	/* response */
 	u64		count;
-	u32		status;
+	__be32		status;
+	bool		completed;
 };
 
 struct nfsd4_copy_notify {
···
 		struct nfsd4_reclaim_complete	reclaim_complete;
 		struct nfsd4_test_stateid	test_stateid;
 		struct nfsd4_free_stateid	free_stateid;
+		struct nfsd4_get_dir_delegation	get_dir_delegation;
 		struct nfsd4_getdeviceinfo	getdeviceinfo;
 		struct nfsd4_layoutget		layoutget;
 		struct nfsd4_layoutcommit	layoutcommit;

include/linux/nfs4.h

···
 	SP4_SSV		= 2
 };
 
+/* GET_DIR_DELEGATION non-fatal status codes */
+enum gddrnf4_status {
+	GDD4_OK		= 0,
+	GDD4_UNAVAIL	= 1
+};
+
 enum pnfs_layouttype {
 	LAYOUT_NFSV4_1_FILES  = 1,
 	LAYOUT_OSD2_OBJECTS = 2,

include/linux/sunrpc/svc_xprt.h

···
 void	svc_unreg_xprt_class(struct svc_xprt_class *);
 void	svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *,
 		      struct svc_serv *);
+int	svc_xprt_create_from_sa(struct svc_serv *serv, const char *xprt_name,
+				struct net *net, struct sockaddr *sap,
+				int flags, const struct cred *cred);
 int	svc_xprt_create(struct svc_serv *serv, const char *xprt_name,
 			struct net *net, const int family,
 			const unsigned short port, int flags,
···
 void	svc_xprt_close(struct svc_xprt *xprt);
 int	svc_port_is_privileged(struct sockaddr *sin);
 int	svc_print_xprts(char *buf, int maxlen);
+struct svc_xprt *svc_find_listener(struct svc_serv *serv, const char *xcl_name,
+				   struct net *net, const struct sockaddr *sa);
 struct	svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name,
 			struct net *net, const sa_family_t af,
 			const unsigned short port);

include/trace/misc/nfs.h

···
 TRACE_DEFINE_ENUM(NFSERR_NOSPC);
 TRACE_DEFINE_ENUM(NFSERR_ROFS);
 TRACE_DEFINE_ENUM(NFSERR_MLINK);
-TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP);
 TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG);
 TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY);
 TRACE_DEFINE_ENUM(NFSERR_DQUOT);
···
 		{ NFSERR_NOSPC,			"NOSPC" }, \
 		{ NFSERR_ROFS,			"ROFS" }, \
 		{ NFSERR_MLINK,			"MLINK" }, \
-		{ NFSERR_OPNOTSUPP,		"OPNOTSUPP" }, \
 		{ NFSERR_NAMETOOLONG,		"NAMETOOLONG" }, \
 		{ NFSERR_NOTEMPTY,		"NOTEMPTY" }, \
 		{ NFSERR_DQUOT,			"DQUOT" }, \

include/uapi/linux/nfs.h

···
 	NFSERR_NOSPC = 28,		/* v2 v3 v4 */
 	NFSERR_ROFS = 30,		/* v2 v3 v4 */
 	NFSERR_MLINK = 31,		/*    v3 v4 */
-	NFSERR_OPNOTSUPP = 45,		/* v2 v3 */
 	NFSERR_NAMETOOLONG = 63,	/* v2 v3 v4 */
 	NFSERR_NOTEMPTY = 66,		/* v2 v3 v4 */
 	NFSERR_DQUOT = 69,		/* v2 v3 v4 */

include/uapi/linux/nfsd_netlink.h

···
 };
 
 enum {
+	NFSD_A_SERVER_THREADS = 1,
+	NFSD_A_SERVER_GRACETIME,
+	NFSD_A_SERVER_LEASETIME,
+	NFSD_A_SERVER_SCOPE,
+
+	__NFSD_A_SERVER_MAX,
+	NFSD_A_SERVER_MAX = (__NFSD_A_SERVER_MAX - 1)
+};
+
+enum {
+	NFSD_A_VERSION_MAJOR = 1,
+	NFSD_A_VERSION_MINOR,
+	NFSD_A_VERSION_ENABLED,
+
+	__NFSD_A_VERSION_MAX,
+	NFSD_A_VERSION_MAX = (__NFSD_A_VERSION_MAX - 1)
+};
+
+enum {
+	NFSD_A_SERVER_PROTO_VERSION = 1,
+
+	__NFSD_A_SERVER_PROTO_MAX,
+	NFSD_A_SERVER_PROTO_MAX = (__NFSD_A_SERVER_PROTO_MAX - 1)
+};
+
+enum {
+	NFSD_A_SOCK_ADDR = 1,
+	NFSD_A_SOCK_TRANSPORT_NAME,
+
+	__NFSD_A_SOCK_MAX,
+	NFSD_A_SOCK_MAX = (__NFSD_A_SOCK_MAX - 1)
+};
+
+enum {
+	NFSD_A_SERVER_SOCK_ADDR = 1,
+
+	__NFSD_A_SERVER_SOCK_MAX,
+	NFSD_A_SERVER_SOCK_MAX = (__NFSD_A_SERVER_SOCK_MAX - 1)
+};
+
+enum {
 	NFSD_CMD_RPC_STATUS_GET = 1,
+	NFSD_CMD_THREADS_SET,
+	NFSD_CMD_THREADS_GET,
+	NFSD_CMD_VERSION_SET,
+	NFSD_CMD_VERSION_GET,
+	NFSD_CMD_LISTENER_SET,
+	NFSD_CMD_LISTENER_GET,
 
 	__NFSD_CMD_MAX,
 	NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1)

net/sunrpc/auth_gss/svcauth_gss.c

···
 
 static void gss_free_in_token_pages(struct gssp_in_token *in_token)
 {
-	u32 inlen;
 	int i;
 
 	i = 0;
-	inlen = in_token->page_len;
-	while (inlen) {
-		if (in_token->pages[i])
-			put_page(in_token->pages[i]);
-		inlen -= inlen > PAGE_SIZE ? PAGE_SIZE : inlen;
-	}
-
+	while (in_token->pages[i])
+		put_page(in_token->pages[i++]);
 	kfree(in_token->pages);
 	in_token->pages = NULL;
 }

net/sunrpc/svc.c

···
 	if (rqstp->rq_proc >= versp->vs_nproc)
 		goto err_bad_proc;
 	rqstp->rq_procinfo = procp = &versp->vs_proc[rqstp->rq_proc];
-	if (!procp)
-		goto err_bad_proc;
 
 	/* Initialize storage for argp and resp */
 	memset(rqstp->rq_argp, 0, procp->pc_argzero);

net/sunrpc/svc_xprt.c

···
 
 /* SMP locking strategy:
  *
- *	svc_pool->sp_lock protects most of the fields of that pool.
  *	svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
  *	when both need to be taken (rare), svc_serv->sv_lock is first.
  *	The "service mutex" protects svc_serv->sv_nrthread.
···
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
-static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
-					 struct svc_serv *serv,
-					 struct net *net,
-					 const int family,
-					 const unsigned short port,
-					 int flags)
-{
-	struct sockaddr_in sin = {
-		.sin_family		= AF_INET,
-		.sin_addr.s_addr	= htonl(INADDR_ANY),
-		.sin_port		= htons(port),
-	};
-#if IS_ENABLED(CONFIG_IPV6)
-	struct sockaddr_in6 sin6 = {
-		.sin6_family		= AF_INET6,
-		.sin6_addr		= IN6ADDR_ANY_INIT,
-		.sin6_port		= htons(port),
-	};
-#endif
-	struct svc_xprt *xprt;
-	struct sockaddr *sap;
-	size_t len;
-
-	switch (family) {
-	case PF_INET:
-		sap = (struct sockaddr *)&sin;
-		len = sizeof(sin);
-		break;
-#if IS_ENABLED(CONFIG_IPV6)
-	case PF_INET6:
-		sap = (struct sockaddr *)&sin6;
-		len = sizeof(sin6);
-		break;
-#endif
-	default:
-		return ERR_PTR(-EAFNOSUPPORT);
-	}
-
-	xprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
-	if (IS_ERR(xprt))
-		trace_svc_xprt_create_err(serv->sv_program->pg_name,
-					  xcl->xcl_name, sap, len, xprt);
-	return xprt;
-}
-
 /**
  * svc_xprt_received - start next receiver thread
  * @xprt: controlling transport
···
 }
 
 static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name,
-			    struct net *net, const int family,
-			    const unsigned short port, int flags,
-			    const struct cred *cred)
+			    struct net *net, struct sockaddr *sap,
+			    size_t len, int flags, const struct cred *cred)
 {
 	struct svc_xprt_class *xcl;
 
···
 			goto err;
 
 		spin_unlock(&svc_xprt_class_lock);
-		newxprt = __svc_xpo_create(xcl, serv, net, family, port, flags);
+		newxprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
 		if (IS_ERR(newxprt)) {
+			trace_svc_xprt_create_err(serv->sv_program->pg_name,
+						  xcl->xcl_name, sap, len,
+						  newxprt);
 			module_put(xcl->xcl_owner);
 			return PTR_ERR(newxprt);
 		}
···
 }
 
 /**
+ * svc_xprt_create_from_sa - Add a new listener to @serv from socket address
+ * @serv: target RPC service
+ * @xprt_name: transport class name
+ * @net: network namespace
+ * @sap: socket address pointer
+ * @flags: SVC_SOCK flags
+ * @cred: credential to bind to this transport
+ *
+ * Return local xprt port on success or %-EPROTONOSUPPORT on failure
+ */
+int svc_xprt_create_from_sa(struct svc_serv *serv, const char *xprt_name,
+			    struct net *net, struct sockaddr *sap,
+			    int flags, const struct cred *cred)
+{
+	size_t len;
+	int err;
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		len = sizeof(struct sockaddr_in);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		len = sizeof(struct sockaddr_in6);
+		break;
+#endif
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	err = _svc_xprt_create(serv, xprt_name, net, sap, len, flags, cred);
+	if (err == -EPROTONOSUPPORT) {
+		request_module("svc%s", xprt_name);
+		err = _svc_xprt_create(serv, xprt_name, net, sap, len, flags,
+				       cred);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(svc_xprt_create_from_sa);
+
+/**
  * svc_xprt_create - Add a new listener to @serv
  * @serv: target RPC service
  * @xprt_name: transport class name
···
  * @flags: SVC_SOCK flags
  * @cred: credential to bind to this transport
  *
- * Return values:
- *   %0: New listener added successfully
- *   %-EPROTONOSUPPORT: Requested transport type not supported
+ * Return local xprt port on success or %-EPROTONOSUPPORT on failure
  */
 int svc_xprt_create(struct svc_serv *serv, const char *xprt_name,
 		    struct net *net, const int family,
 		    const unsigned short port, int flags,
 		    const struct cred *cred)
 {
-	int err;
+	struct sockaddr_in sin = {
+		.sin_family		= AF_INET,
+		.sin_addr.s_addr	= htonl(INADDR_ANY),
+		.sin_port		= htons(port),
+	};
+#if IS_ENABLED(CONFIG_IPV6)
+	struct sockaddr_in6 sin6 = {
+		.sin6_family		= AF_INET6,
+		.sin6_addr		= IN6ADDR_ANY_INIT,
+		.sin6_port		= htons(port),
+	};
+#endif
+	struct sockaddr *sap;
 
-	err = _svc_xprt_create(serv, xprt_name, net, family, port, flags, cred);
-	if (err == -EPROTONOSUPPORT) {
-		request_module("svc%s", xprt_name);
-		err = _svc_xprt_create(serv, xprt_name, net, family, port, flags, cred);
+	switch (family) {
+	case PF_INET:
+		sap = (struct sockaddr *)&sin;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case PF_INET6:
+		sap = (struct sockaddr *)&sin6;
+		break;
+#endif
+	default:
+		return -EAFNOSUPPORT;
 	}
-	return err;
+
+	return svc_xprt_create_from_sa(serv, xprt_name, net, sap, flags, cred);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_create);
 
···
 	spin_unlock(&xprt->xpt_lock);
 	return dr;
 }
+
+/**
+ * svc_find_listener - find an RPC transport instance
+ * @serv: pointer to svc_serv to search
+ * @xcl_name: C string containing transport's class name
+ * @net: owner net pointer
+ * @sa: sockaddr containing address
+ *
+ * Return the transport instance pointer for the endpoint accepting
+ * connections/peer traffic from the specified transport class,
+ * and matching sockaddr.
+ */
+struct svc_xprt *svc_find_listener(struct svc_serv *serv, const char *xcl_name,
+				   struct net *net, const struct sockaddr *sa)
+{
+	struct svc_xprt *xprt;
+	struct svc_xprt *found = NULL;
+
+	spin_lock_bh(&serv->sv_lock);
+	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
+		if (xprt->xpt_net != net)
+			continue;
+		if (strcmp(xprt->xpt_class->xcl_name, xcl_name))
+			continue;
+		if (!rpc_cmp_addr_port(sa, (struct sockaddr *)&xprt->xpt_local))
+			continue;
+		found = xprt;
+		svc_xprt_get(xprt);
+		break;
+	}
+	spin_unlock_bh(&serv->sv_lock);
+	return found;
+}
+EXPORT_SYMBOL_GPL(svc_find_listener);
 
 /**
  * svc_find_xprt - find an RPC transport instance