Merge tag 'nfsd-4.15-1' of git://linux-nfs.org/~bfields/linux

Pull nfsd fixes from Bruce Fields:
 "I screwed up my merge window pull request; I only sent half of what I
  meant to.

  There were no new features, just bugfixes of various importance and
  some very minor cleanup, so I think it's all still appropriate for
  -rc2.

  Highlights:

   - Fixes from Trond for some races in the NFSv4 state code.

   - Fix from Naofumi Honda for a typo in the blocked lock notificiation
     code

   - Fixes from Vasily Averin for some problems starting and stopping
     lockd especially in network namespaces"

* tag 'nfsd-4.15-1' of git://linux-nfs.org/~bfields/linux: (23 commits)
  lockd: fix "list_add double add" caused by legacy signal interface
  nlm_shutdown_hosts_net() cleanup
  race of nfsd inetaddr notifiers vs nn->nfsd_serv change
  race of lockd inetaddr notifiers vs nlmsvc_rqst change
  SUNRPC: make cache_detail structures const
  NFSD: make cache_detail structures const
  sunrpc: make the function arg as const
  nfsd: check for use of the closed special stateid
  nfsd: fix panic in posix_unblock_lock called from nfs4_laundromat
  lockd: lost rollback of set_grace_period() in lockd_down_net()
  lockd: added cleanup checks in exit_net hook
  grace: replace BUG_ON by WARN_ONCE in exit_net hook
  nfsd: fix locking validator warning on nfs4_ol_stateid->st_mutex class
  lockd: remove net pointer from messages
  nfsd: remove net pointer from debug messages
  nfsd: Fix races with check_stateid_generation()
  nfsd: Ensure we check stateid validity in the seqid operation checks
  nfsd: Fix race in lock stateid creation
  nfsd4: move find_lock_stateid
  nfsd: Ensure we don't recognise lock stateids after freeing them
  ...

11 files changed, 264 insertions, 126 deletions

diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 0d4e590e0549..826a89184f90 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -578,8 +578,10 @@ static void nlm_complain_hosts(struct net *net)
 
 		if (ln->nrhosts == 0)
 			return;
-		printk(KERN_WARNING "lockd: couldn't shutdown host module for net %p!\n", net);
-		dprintk("lockd: %lu hosts left in net %p:\n", ln->nrhosts, net);
+		pr_warn("lockd: couldn't shutdown host module for net %x!\n",
+			net->ns.inum);
+		dprintk("lockd: %lu hosts left in net %x:\n", ln->nrhosts,
+			net->ns.inum);
 	} else {
 		if (nrhosts == 0)
 			return;
@@ -590,9 +592,9 @@ static void nlm_complain_hosts(struct net *net)
 	for_each_host(host, chain, nlm_server_hosts) {
 		if (net && host->net != net)
 			continue;
-		dprintk("       %s (cnt %d use %d exp %ld net %p)\n",
+		dprintk("       %s (cnt %d use %d exp %ld net %x)\n",
 			host->h_name, atomic_read(&host->h_count),
-			host->h_inuse, host->h_expires, host->net);
+			host->h_inuse, host->h_expires, host->net->ns.inum);
 	}
 }
 
@@ -605,7 +607,8 @@ nlm_shutdown_hosts_net(struct net *net)
 	mutex_lock(&nlm_host_mutex);
 
 	/* First, make all hosts eligible for gc */
-	dprintk("lockd: nuking all hosts in net %p...\n", net);
+	dprintk("lockd: nuking all hosts in net %x...\n",
+		net ? net->ns.inum : 0);
 	for_each_host(host, chain, nlm_server_hosts) {
 		if (net && host->net != net)
 			continue;
@@ -618,9 +621,8 @@ nlm_shutdown_hosts_net(struct net *net)
 
 	/* Then, perform a garbage collection pass */
 	nlm_gc_hosts(net);
-	mutex_unlock(&nlm_host_mutex);
-
 	nlm_complain_hosts(net);
+	mutex_unlock(&nlm_host_mutex);
 }
 
 /*
@@ -646,7 +648,8 @@ nlm_gc_hosts(struct net *net)
 	struct hlist_node *next;
 	struct nlm_host	*host;
 
-	dprintk("lockd: host garbage collection for net %p\n", net);
+	dprintk("lockd: host garbage collection for net %x\n",
+		net ? net->ns.inum : 0);
 	for_each_host(host, chain, nlm_server_hosts) {
 		if (net && host->net != net)
 			continue;
@@ -662,9 +665,10 @@ nlm_gc_hosts(struct net *net)
 		if (atomic_read(&host->h_count) || host->h_inuse
 		 || time_before(jiffies, host->h_expires)) {
 			dprintk("nlm_gc_hosts skipping %s "
-				"(cnt %d use %d exp %ld net %p)\n",
+				"(cnt %d use %d exp %ld net %x)\n",
 				host->h_name, atomic_read(&host->h_count),
-				host->h_inuse, host->h_expires, host->net);
+				host->h_inuse, host->h_expires,
+				host->net->ns.inum);
 			continue;
 		}
 		nlm_destroy_host_locked(host);
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 9fbbd11f9ecb..96cfb2967ac7 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -110,7 +110,8 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
 	clnt = nsm_create(host->net, host->nodename);
 	if (IS_ERR(clnt)) {
 		dprintk("lockd: failed to create NSM upcall transport, "
-			"status=%ld, net=%p\n", PTR_ERR(clnt), host->net);
+			"status=%ld, net=%x\n", PTR_ERR(clnt),
+			host->net->ns.inum);
 		return PTR_ERR(clnt);
 	}
 
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index a8e3777c94dc..9c36d614bf89 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -57,6 +57,9 @@ static struct task_struct	*nlmsvc_task;
 static struct svc_rqst		*nlmsvc_rqst;
 unsigned long			nlmsvc_timeout;
 
+atomic_t nlm_ntf_refcnt = ATOMIC_INIT(0);
+DECLARE_WAIT_QUEUE_HEAD(nlm_ntf_wq);
+
 unsigned int lockd_net_id;
 
 /*
@@ -259,7 +262,7 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net)
 	if (error < 0)
 		goto err_bind;
 	set_grace_period(net);
-	dprintk("lockd_up_net: per-net data created; net=%p\n", net);
+	dprintk("%s: per-net data created; net=%x\n", __func__, net->ns.inum);
 	return 0;
 
 err_bind:
@@ -274,12 +277,15 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
 	if (ln->nlmsvc_users) {
 		if (--ln->nlmsvc_users == 0) {
 			nlm_shutdown_hosts_net(net);
+			cancel_delayed_work_sync(&ln->grace_period_end);
+			locks_end_grace(&ln->lockd_manager);
 			svc_shutdown_net(serv, net);
-			dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net);
+			dprintk("%s: per-net data destroyed; net=%x\n",
+				__func__, net->ns.inum);
 		}
 	} else {
-		printk(KERN_ERR "lockd_down_net: no users! task=%p, net=%p\n",
-				nlmsvc_task, net);
+		pr_err("%s: no users! task=%p, net=%x\n",
+			__func__, nlmsvc_task, net->ns.inum);
 		BUG();
 	}
 }
@@ -290,7 +296,8 @@ static int lockd_inetaddr_event(struct notifier_block *this,
 	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
 	struct sockaddr_in sin;
 
-	if (event != NETDEV_DOWN)
+	if ((event != NETDEV_DOWN) ||
+	    !atomic_inc_not_zero(&nlm_ntf_refcnt))
 		goto out;
 
 	if (nlmsvc_rqst) {
@@ -301,6 +308,8 @@ static int lockd_inetaddr_event(struct notifier_block *this,
 		svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
 			(struct sockaddr *)&sin);
 	}
+	atomic_dec(&nlm_ntf_refcnt);
+	wake_up(&nlm_ntf_wq);
 
 out:
 	return NOTIFY_DONE;
@@ -317,7 +326,8 @@ static int lockd_inet6addr_event(struct notifier_block *this,
 	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
 	struct sockaddr_in6 sin6;
 
-	if (event != NETDEV_DOWN)
+	if ((event != NETDEV_DOWN) ||
+	    !atomic_inc_not_zero(&nlm_ntf_refcnt))
 		goto out;
 
 	if (nlmsvc_rqst) {
@@ -329,6 +339,8 @@ static int lockd_inet6addr_event(struct notifier_block *this,
 		svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
 			(struct sockaddr *)&sin6);
 	}
+	atomic_dec(&nlm_ntf_refcnt);
+	wake_up(&nlm_ntf_wq);
 
 out:
 	return NOTIFY_DONE;
@@ -345,10 +357,12 @@ static void lockd_unregister_notifiers(void)
 #if IS_ENABLED(CONFIG_IPV6)
 	unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
 #endif
+	wait_event(nlm_ntf_wq, atomic_read(&nlm_ntf_refcnt) == 0);
 }
 
 static void lockd_svc_exit_thread(void)
 {
+	atomic_dec(&nlm_ntf_refcnt);
 	lockd_unregister_notifiers();
 	svc_exit_thread(nlmsvc_rqst);
 }
@@ -373,6 +387,7 @@ static int lockd_start_svc(struct svc_serv *serv)
 		goto out_rqst;
 	}
 
+	atomic_inc(&nlm_ntf_refcnt);
 	svc_sock_update_bufs(serv);
 	serv->sv_maxconn = nlm_max_connections;
 
@@ -676,6 +691,17 @@ static int lockd_init_net(struct net *net)
 
 static void lockd_exit_net(struct net *net)
 {
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+	WARN_ONCE(!list_empty(&ln->lockd_manager.list),
+		  "net %x %s: lockd_manager.list is not empty\n",
+		  net->ns.inum, __func__);
+	WARN_ONCE(!list_empty(&ln->nsm_handles),
+		  "net %x %s: nsm_handles list is not empty\n",
+		  net->ns.inum, __func__);
+	WARN_ONCE(delayed_work_pending(&ln->grace_period_end),
+		  "net %x %s: grace_period_end was not cancelled\n",
+		  net->ns.inum, __func__);
 }
 
 static struct pernet_operations lockd_net_ops = {
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index a563ddbc19e6..4ec3d6e03e76 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -370,7 +370,7 @@ nlmsvc_mark_resources(struct net *net)
 {
 	struct nlm_host hint;
 
-	dprintk("lockd: nlmsvc_mark_resources for net %p\n", net);
+	dprintk("lockd: %s for net %x\n", __func__, net ? net->ns.inum : 0);
 	hint.net = net;
 	nlm_traverse_files(&hint, nlmsvc_mark_host, NULL);
 }
diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c
index 897b299db55e..5be08f02a76b 100644
--- a/fs/nfs_common/grace.c
+++ b/fs/nfs_common/grace.c
@@ -30,7 +30,11 @@ locks_start_grace(struct net *net, struct lock_manager *lm)
 	struct list_head *grace_list = net_generic(net, grace_net_id);
 
 	spin_lock(&grace_lock);
-	list_add(&lm->list, grace_list);
+	if (list_empty(&lm->list))
+		list_add(&lm->list, grace_list);
+	else
+		WARN(1, "double list_add attempt detected in net %x %s\n",
+		     net->ns.inum, (net == &init_net) ? "(init_net)" : "");
 	spin_unlock(&grace_lock);
 }
 EXPORT_SYMBOL_GPL(locks_start_grace);
@@ -104,7 +108,9 @@ grace_exit_net(struct net *net)
 {
 	struct list_head *grace_list = net_generic(net, grace_net_id);
 
-	BUG_ON(!list_empty(grace_list));
+	WARN_ONCE(!list_empty(grace_list),
+		  "net %x %s: grace_list is not empty\n",
+		  net->ns.inum, __func__);
 }
 
 static struct pernet_operations grace_net_ops = {
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 46b48dbbdd32..8ceb25a10ea0 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -232,7 +232,7 @@ static struct cache_head *expkey_alloc(void)
 		return NULL;
 }
 
-static struct cache_detail svc_expkey_cache_template = {
+static const struct cache_detail svc_expkey_cache_template = {
 	.owner		= THIS_MODULE,
 	.hash_size	= EXPKEY_HASHMAX,
 	.name		= "nfsd.fh",
@@ -748,7 +748,7 @@ static struct cache_head *svc_export_alloc(void)
 		return NULL;
 }
 
-static struct cache_detail svc_export_cache_template = {
+static const struct cache_detail svc_export_cache_template = {
 	.owner		= THIS_MODULE,
 	.hash_size	= EXPORT_HASHMAX,
 	.name		= "nfsd.export",
@@ -1230,7 +1230,7 @@ nfsd_export_init(struct net *net)
 	int rv;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	dprintk("nfsd: initializing export module (net: %p).\n", net);
+	dprintk("nfsd: initializing export module (net: %x).\n", net->ns.inum);
 
 	nn->svc_export_cache = cache_create_net(&svc_export_cache_template, net);
 	if (IS_ERR(nn->svc_export_cache))
@@ -1278,7 +1278,7 @@ nfsd_export_shutdown(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	dprintk("nfsd: shutting down export module (net: %p).\n", net);
+	dprintk("nfsd: shutting down export module (net: %x).\n", net->ns.inum);
 
 	cache_unregister_net(nn->svc_expkey_cache, net);
 	cache_unregister_net(nn->svc_export_cache, net);
@@ -1286,5 +1286,5 @@ nfsd_export_shutdown(struct net *net)
 	cache_destroy_net(nn->svc_export_cache, net);
 	svcauth_unix_purge(net);
 
-	dprintk("nfsd: export shutdown complete (net: %p).\n", net);
+	dprintk("nfsd: export shutdown complete (net: %x).\n", net->ns.inum);
 }
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 1c91391f4805..36358d435cb0 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -119,6 +119,9 @@ struct nfsd_net {
 	u32 clverifier_counter;
 
 	struct svc_serv *nfsd_serv;
+
+	wait_queue_head_t ntf_wq;
+	atomic_t ntf_refcnt;
 };
 
 /* Simple check to find out if a given net was properly initialized */
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index 6b9b6cca469f..a5bb76593ce7 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -178,7 +178,7 @@ static struct ent *idtoname_lookup(struct cache_detail *, struct ent *);
 static struct ent *idtoname_update(struct cache_detail *, struct ent *,
 				   struct ent *);
 
-static struct cache_detail idtoname_cache_template = {
+static const struct cache_detail idtoname_cache_template = {
 	.owner		= THIS_MODULE,
 	.hash_size	= ENT_HASHMAX,
 	.name		= "nfs4.idtoname",
@@ -341,7 +341,7 @@ static struct ent *nametoid_update(struct cache_detail *, struct ent *,
 				   struct ent *);
 static int         nametoid_parse(struct cache_detail *, char *, int);
 
-static struct cache_detail nametoid_cache_template = {
+static const struct cache_detail nametoid_cache_template = {
 	.owner		= THIS_MODULE,
 	.hash_size	= ENT_HASHMAX,
 	.name		= "nfs4.nametoid",
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b82817767b9d..b29b5a185a2c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -63,12 +63,16 @@ static const stateid_t zero_stateid = {
 static const stateid_t currentstateid = {
 	.si_generation = 1,
 };
+static const stateid_t close_stateid = {
+	.si_generation = 0xffffffffU,
+};
 
 static u64 current_sessionid = 1;
 
 #define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t)))
 #define ONE_STATEID(stateid)  (!memcmp((stateid), &one_stateid, sizeof(stateid_t)))
 #define CURRENT_STATEID(stateid) (!memcmp((stateid), &currentstateid, sizeof(stateid_t)))
+#define CLOSE_STATEID(stateid)  (!memcmp((stateid), &close_stateid, sizeof(stateid_t)))
 
 /* forward declarations */
 static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner);
@@ -83,6 +87,11 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid);
  */
 static DEFINE_SPINLOCK(state_lock);
 
+enum nfsd4_st_mutex_lock_subclass {
+	OPEN_STATEID_MUTEX = 0,
+	LOCK_STATEID_MUTEX = 1,
+};
+
 /*
  * A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for
  * the refcount on the open stateid to drop.
@@ -3562,7 +3571,9 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
 		/* ignore lock owners */
 		if (local->st_stateowner->so_is_open_owner == 0)
 			continue;
-		if (local->st_stateowner == &oo->oo_owner) {
+		if (local->st_stateowner != &oo->oo_owner)
+			continue;
+		if (local->st_stid.sc_type == NFS4_OPEN_STID) {
 			ret = local;
 			refcount_inc(&ret->st_stid.sc_count);
 			break;
@@ -3571,6 +3582,52 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
 	return ret;
 }
 
+static __be32
+nfsd4_verify_open_stid(struct nfs4_stid *s)
+{
+	__be32 ret = nfs_ok;
+
+	switch (s->sc_type) {
+	default:
+		break;
+	case NFS4_CLOSED_STID:
+	case NFS4_CLOSED_DELEG_STID:
+		ret = nfserr_bad_stateid;
+		break;
+	case NFS4_REVOKED_DELEG_STID:
+		ret = nfserr_deleg_revoked;
+	}
+	return ret;
+}
+
+/* Lock the stateid st_mutex, and deal with races with CLOSE */
+static __be32
+nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp)
+{
+	__be32 ret;
+
+	mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX);
+	ret = nfsd4_verify_open_stid(&stp->st_stid);
+	if (ret != nfs_ok)
+		mutex_unlock(&stp->st_mutex);
+	return ret;
+}
+
+static struct nfs4_ol_stateid *
+nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
+{
+	struct nfs4_ol_stateid *stp;
+	for (;;) {
+		spin_lock(&fp->fi_lock);
+		stp = nfsd4_find_existing_open(fp, open);
+		spin_unlock(&fp->fi_lock);
+		if (!stp || nfsd4_lock_ol_stateid(stp) == nfs_ok)
+			break;
+		nfs4_put_stid(&stp->st_stid);
+	}
+	return stp;
+}
+
 static struct nfs4_openowner *
 alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
 			   struct nfsd4_compound_state *cstate)
@@ -3613,8 +3670,9 @@ init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
 	stp = open->op_stp;
 	/* We are moving these outside of the spinlocks to avoid the warnings */
 	mutex_init(&stp->st_mutex);
-	mutex_lock(&stp->st_mutex);
+	mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);
 
+retry:
 	spin_lock(&oo->oo_owner.so_client->cl_lock);
 	spin_lock(&fp->fi_lock);
 
@@ -3639,7 +3697,11 @@ out_unlock:
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&oo->oo_owner.so_client->cl_lock);
 	if (retstp) {
-		mutex_lock(&retstp->st_mutex);
+		/* Handle races with CLOSE */
+		if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+			nfs4_put_stid(&retstp->st_stid);
+			goto retry;
+		}
 		/* To keep mutex tracking happy */
 		mutex_unlock(&stp->st_mutex);
 		stp = retstp;
@@ -4449,6 +4511,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	struct nfs4_ol_stateid *stp = NULL;
 	struct nfs4_delegation *dp = NULL;
 	__be32 status;
+	bool new_stp = false;
 
 	/*
 	 * Lookup file; if found, lookup stateid and check open request,
@@ -4460,9 +4523,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		status = nfs4_check_deleg(cl, open, &dp);
 		if (status)
 			goto out;
-		spin_lock(&fp->fi_lock);
-		stp = nfsd4_find_existing_open(fp, open);
-		spin_unlock(&fp->fi_lock);
+		stp = nfsd4_find_and_lock_existing_open(fp, open);
 	} else {
 		open->op_file = NULL;
 		status = nfserr_bad_stateid;
@@ -4470,35 +4531,31 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 			goto out;
 	}
 
+	if (!stp) {
+		stp = init_open_stateid(fp, open);
+		if (!open->op_stp)
+			new_stp = true;
+	}
+
 	/*
 	 * OPEN the file, or upgrade an existing OPEN.
 	 * If truncate fails, the OPEN fails.
+	 *
+	 * stp is already locked.
 	 */
-	if (stp) {
+	if (!new_stp) {
 		/* Stateid was found, this is an OPEN upgrade */
-		mutex_lock(&stp->st_mutex);
 		status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
 		if (status) {
 			mutex_unlock(&stp->st_mutex);
 			goto out;
 		}
 	} else {
-		/* stp is returned locked. */
-		stp = init_open_stateid(fp, open);
-		/* See if we lost the race to some other thread */
-		if (stp->st_access_bmap != 0) {
-			status = nfs4_upgrade_open(rqstp, fp, current_fh,
-						stp, open);
-			if (status) {
-				mutex_unlock(&stp->st_mutex);
-				goto out;
-			}
-			goto upgrade_out;
-		}
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
 		if (status) {
-			mutex_unlock(&stp->st_mutex);
+			stp->st_stid.sc_type = NFS4_CLOSED_STID;
 			release_open_stateid(stp);
+			mutex_unlock(&stp->st_mutex);
 			goto out;
 		}
 
@@ -4507,7 +4564,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		if (stp->st_clnt_odstate == open->op_odstate)
 			open->op_odstate = NULL;
 	}
-upgrade_out:
+
 	nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
 	mutex_unlock(&stp->st_mutex);
 
@@ -4734,7 +4791,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 	spin_unlock(&nn->blocked_locks_lock);
 
 	while (!list_empty(&reaplist)) {
-		nbl = list_first_entry(&nn->blocked_locks_lru,
+		nbl = list_first_entry(&reaplist,
 					struct nfsd4_blocked_lock, nbl_lru);
 		list_del_init(&nbl->nbl_lru);
 		posix_unblock_lock(&nbl->nbl_lock);
@@ -4855,6 +4912,18 @@ static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_s
 	return nfserr_old_stateid;
 }
 
+static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_stid *s, bool has_session)
+{
+	__be32 ret;
+
+	spin_lock(&s->sc_lock);
+	ret = nfsd4_verify_open_stid(s);
+	if (ret == nfs_ok)
+		ret = check_stateid_generation(in, &s->sc_stateid, has_session);
+	spin_unlock(&s->sc_lock);
+	return ret;
+}
+
 static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols)
 {
 	if (ols->st_stateowner->so_is_open_owner &&
@@ -4868,7 +4937,8 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	struct nfs4_stid *s;
 	__be32 status = nfserr_bad_stateid;
 
-	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
+		CLOSE_STATEID(stateid))
 		return status;
 	/* Client debugging aid. */
 	if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) {
@@ -4883,7 +4953,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	s = find_stateid_locked(cl, stateid);
 	if (!s)
 		goto out_unlock;
-	status = check_stateid_generation(stateid, &s->sc_stateid, 1);
+	status = nfsd4_stid_check_stateid_generation(stateid, s, 1);
 	if (status)
 		goto out_unlock;
 	switch (s->sc_type) {
@@ -4926,7 +4996,8 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 	else if (typemask & NFS4_DELEG_STID)
 		typemask |= NFS4_REVOKED_DELEG_STID;
 
-	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
+		CLOSE_STATEID(stateid))
 		return nfserr_bad_stateid;
 	status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
 	if (status == nfserr_stale_clientid) {
@@ -5044,7 +5115,7 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 				&s, nn);
 	if (status)
 		return status;
-	status = check_stateid_generation(stateid, &s->sc_stateid,
+	status = nfsd4_stid_check_stateid_generation(stateid, s,
 			nfsd4_has_session(cstate));
 	if (status)
 		goto out;
@@ -5098,7 +5169,9 @@ nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
 	struct nfs4_ol_stateid *stp = openlockstateid(s);
 	__be32 ret;
 
-	mutex_lock(&stp->st_mutex);
+	ret = nfsd4_lock_ol_stateid(stp);
+	if (ret)
+		goto out_put_stid;
 
 	ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
 	if (ret)
@@ -5109,11 +5182,13 @@ nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
 			    lockowner(stp->st_stateowner)))
 		goto out;
 
+	stp->st_stid.sc_type = NFS4_CLOSED_STID;
 	release_lock_stateid(stp);
 	ret = nfs_ok;
 
 out:
 	mutex_unlock(&stp->st_mutex);
+out_put_stid:
 	nfs4_put_stid(s);
 	return ret;
 }
@@ -5133,6 +5208,7 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	s = find_stateid_locked(cl, stateid);
 	if (!s)
 		goto out_unlock;
+	spin_lock(&s->sc_lock);
 	switch (s->sc_type) {
 	case NFS4_DELEG_STID:
 		ret = nfserr_locks_held;
@@ -5144,11 +5220,13 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		ret = nfserr_locks_held;
 		break;
 	case NFS4_LOCK_STID:
+		spin_unlock(&s->sc_lock);
 		refcount_inc(&s->sc_count);
 		spin_unlock(&cl->cl_lock);
 		ret = nfsd4_free_lock_stateid(stateid, s);
 		goto out;
 	case NFS4_REVOKED_DELEG_STID:
+		spin_unlock(&s->sc_lock);
 		dp = delegstateid(s);
 		list_del_init(&dp->dl_recall_lru);
 		spin_unlock(&cl->cl_lock);
@@ -5157,6 +5235,7 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 	/* Default falls through and returns nfserr_bad_stateid */
 	}
+	spin_unlock(&s->sc_lock);
 out_unlock:
 	spin_unlock(&cl->cl_lock);
 out:
@@ -5179,15 +5258,9 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
 	status = nfsd4_check_seqid(cstate, sop, seqid);
 	if (status)
 		return status;
-	if (stp->st_stid.sc_type == NFS4_CLOSED_STID
-		|| stp->st_stid.sc_type == NFS4_REVOKED_DELEG_STID)
-		/*
-		 * "Closed" stateid's exist *only* to return
-		 * nfserr_replay_me from the previous step, and
-		 * revoked delegations are kept only for free_stateid.
-		 */
-		return nfserr_bad_stateid;
-	mutex_lock(&stp->st_mutex);
+	status = nfsd4_lock_ol_stateid(stp);
+	if (status != nfs_ok)
+		return status;
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
 	if (status == nfs_ok)
 		status = nfs4_check_fh(current_fh, &stp->st_stid);
@@ -5367,7 +5440,6 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 	bool unhashed;
 	LIST_HEAD(reaplist);
 
-	s->st_stid.sc_type = NFS4_CLOSED_STID;
 	spin_lock(&clp->cl_lock);
 	unhashed = unhash_open_stateid(s, &reaplist);
 
@@ -5407,10 +5479,17 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	nfsd4_bump_seqid(cstate, status);
 	if (status)
 		goto out; 
+
+	stp->st_stid.sc_type = NFS4_CLOSED_STID;
 	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
-	mutex_unlock(&stp->st_mutex);
 
 	nfsd4_close_open_stateid(stp);
+	mutex_unlock(&stp->st_mutex);
+
+	/* See RFC5661 sectionm 18.2.4 */
+	if (stp->st_stid.sc_client->cl_minorversion)
+		memcpy(&close->cl_stateid, &close_stateid,
+				sizeof(close->cl_stateid));
 
 	/* put reference from nfs4_preprocess_seqid_op */
 	nfs4_put_stid(&stp->st_stid);
@@ -5436,7 +5515,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out;
 	dp = delegstateid(s);
-	status = check_stateid_generation(stateid, &dp->dl_stid.sc_stateid, nfsd4_has_session(cstate));
+	status = nfsd4_stid_check_stateid_generation(stateid, &dp->dl_stid, nfsd4_has_session(cstate));
 	if (status)
 		goto put_stateid;
 
@@ -5642,14 +5721,41 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
 	return ret;
 }
 
-static void
+static struct nfs4_ol_stateid *
+find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
+{
+	struct nfs4_ol_stateid *lst;
+	struct nfs4_client *clp = lo->lo_owner.so_client;
+
+	lockdep_assert_held(&clp->cl_lock);
+
+	list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
+		if (lst->st_stid.sc_type != NFS4_LOCK_STID)
+			continue;
+		if (lst->st_stid.sc_file == fp) {
+			refcount_inc(&lst->st_stid.sc_count);
+			return lst;
+		}
+	}
+	return NULL;
+}
+
+static struct nfs4_ol_stateid *
 init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 		  struct nfs4_file *fp, struct inode *inode,
 		  struct nfs4_ol_stateid *open_stp)
 {
 	struct nfs4_client *clp = lo->lo_owner.so_client;
+	struct nfs4_ol_stateid *retstp;
 
-	lockdep_assert_held(&clp->cl_lock);
+	mutex_init(&stp->st_mutex);
+	mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);
+retry:
+	spin_lock(&clp->cl_lock);
+	spin_lock(&fp->fi_lock);
+	retstp = find_lock_stateid(lo, fp);
+	if (retstp)
+		goto out_unlock;
 
 	refcount_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_LOCK_STID;
@@ -5659,29 +5765,22 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
-	mutex_init(&stp->st_mutex);
 	list_add(&stp->st_locks, &open_stp->st_locks);
 	list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
-	spin_lock(&fp->fi_lock);
 	list_add(&stp->st_perfile, &fp->fi_stateids);
+out_unlock:
 	spin_unlock(&fp->fi_lock);
-}
-
-static struct nfs4_ol_stateid *
-find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
-{
-	struct nfs4_ol_stateid *lst;
-	struct nfs4_client *clp = lo->lo_owner.so_client;
-
-	lockdep_assert_held(&clp->cl_lock);
-
-	list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
-		if (lst->st_stid.sc_file == fp) {
-			refcount_inc(&lst->st_stid.sc_count);
-			return lst;
+	spin_unlock(&clp->cl_lock);
+	if (retstp) {
+		if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+			nfs4_put_stid(&retstp->st_stid);
+			goto retry;
 		}
+		/* To keep mutex tracking happy */
+		mutex_unlock(&stp->st_mutex);
+		stp = retstp;
 	}
-	return NULL;
+	return stp;
 }
 
 static struct nfs4_ol_stateid *
@@ -5694,26 +5793,25 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,
 	struct nfs4_openowner *oo = openowner(ost->st_stateowner);
 	struct nfs4_client *clp = oo->oo_owner.so_client;
 
+	*new = false;
 	spin_lock(&clp->cl_lock);
 	lst = find_lock_stateid(lo, fi);
-	if (lst == NULL) {
-		spin_unlock(&clp->cl_lock);
-		ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
-		if (ns == NULL)
-			return NULL;
-
-		spin_lock(&clp->cl_lock);
-		lst = find_lock_stateid(lo, fi);
-		if (likely(!lst)) {
-			lst = openlockstateid(ns);
-			init_lock_stateid(lst, lo, fi, inode, ost);
-			ns = NULL;
-			*new = true;
-		}
-	}
 	spin_unlock(&clp->cl_lock);
-	if (ns)
+	if (lst != NULL) {
+		if (nfsd4_lock_ol_stateid(lst) == nfs_ok)
+			goto out;
+		nfs4_put_stid(&lst->st_stid);
+	}
+	ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
+	if (ns == NULL)
+		return NULL;
+
+	lst = init_lock_stateid(openlockstateid(ns), lo, fi, inode, ost);
+	if (lst == openlockstateid(ns))
+		*new = true;
+	else
 		nfs4_put_stid(ns);
+out:
 	return lst;
 }
 
@@ -5750,7 +5848,6 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
 	struct nfs4_lockowner *lo;
 	struct nfs4_ol_stateid *lst;
 	unsigned int strhashval;
-	bool hashed;
 
 	lo = find_lockowner_str(cl, &lock->lk_new_owner);
 	if (!lo) {
@@ -5766,25 +5863,12 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
 			goto out;
 	}
 
-retry:
 	lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
 	if (lst == NULL) {
 		status = nfserr_jukebox;
 		goto out;
 	}
 
-	mutex_lock(&lst->st_mutex);
-
-	/* See if it's still hashed to avoid race with FREE_STATEID */
-	spin_lock(&cl->cl_lock);
-	hashed = !list_empty(&lst->st_perfile);
-	spin_unlock(&cl->cl_lock);
-
-	if (!hashed) {
-		mutex_unlock(&lst->st_mutex);
-		nfs4_put_stid(&lst->st_stid);
-		goto retry;
-	}
 	status = nfs_ok;
 	*plst = lst;
 out:
@@ -5990,14 +6074,16 @@ out:
 		    seqid_mutating_err(ntohl(status)))
 			lock_sop->lo_owner.so_seqid++;
 
-		mutex_unlock(&lock_stp->st_mutex);
-
 		/*
 		 * If this is a new, never-before-used stateid, and we are
 		 * returning an error, then just go ahead and release it.
 		 */
-		if (status && new)
+		if (status && new) {
+			lock_stp->st_stid.sc_type = NFS4_CLOSED_STID;
 			release_lock_stateid(lock_stp);
+		}
+
+		mutex_unlock(&lock_stp->st_mutex);
 
 		nfs4_put_stid(&lock_stp->st_stid);
 	}
@@ -7017,6 +7103,10 @@ static int nfs4_state_create_net(struct net *net)
 		INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]);
 	nn->conf_name_tree = RB_ROOT;
 	nn->unconf_name_tree = RB_ROOT;
+	nn->boot_time = get_seconds();
+	nn->grace_ended = false;
+	nn->nfsd4_manager.block_opens = true;
+	INIT_LIST_HEAD(&nn->nfsd4_manager.list);
 	INIT_LIST_HEAD(&nn->client_lru);
 	INIT_LIST_HEAD(&nn->close_lru);
 	INIT_LIST_HEAD(&nn->del_recall_lru);
@@ -7074,9 +7164,6 @@ nfs4_state_start_net(struct net *net)
 	ret = nfs4_state_create_net(net);
 	if (ret)
 		return ret;
-	nn->boot_time = get_seconds();
-	nn->grace_ended = false;
-	nn->nfsd4_manager.block_opens = true;
 	locks_start_grace(net, &nn->nfsd4_manager);
 	nfsd4_client_tracking_init(net);
 	printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n",
@@ -7153,7 +7240,7 @@ nfs4_state_shutdown_net(struct net *net)
 	spin_unlock(&nn->blocked_locks_lock);
 
 	while (!list_empty(&reaplist)) {
-		nbl = list_first_entry(&nn->blocked_locks_lru,
+		nbl = list_first_entry(&reaplist,
 					struct nfsd4_blocked_lock, nbl_lru);
 		list_del_init(&nbl->nbl_lru);
 		posix_unblock_lock(&nbl->nbl_lock);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 6493df6b1bd5..d107b4426f7e 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1241,6 +1241,9 @@ static __net_init int nfsd_init_net(struct net *net)
 	nn->nfsd4_grace = 90;
 	nn->clverifier_counter = prandom_u32();
 	nn->clientid_counter = prandom_u32();
+
+	atomic_set(&nn->ntf_refcnt, 0);
+	init_waitqueue_head(&nn->ntf_wq);
 	return 0;
 
 out_idmap_error:
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 33117d4ffce0..89cb484f1cfb 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -335,7 +335,8 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct sockaddr_in sin;
 
-	if (event != NETDEV_DOWN)
+	if ((event != NETDEV_DOWN) ||
+	    !atomic_inc_not_zero(&nn->ntf_refcnt))
 		goto out;
 
 	if (nn->nfsd_serv) {
@@ -344,6 +345,8 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
 		sin.sin_addr.s_addr = ifa->ifa_local;
 		svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin);
 	}
+	atomic_dec(&nn->ntf_refcnt);
+	wake_up(&nn->ntf_wq);
 
 out:
 	return NOTIFY_DONE;
@@ -363,7 +366,8 @@ static int nfsd_inet6addr_event(struct notifier_block *this,
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct sockaddr_in6 sin6;
 
-	if (event != NETDEV_DOWN)
+	if ((event != NETDEV_DOWN) ||
+	    !atomic_inc_not_zero(&nn->ntf_refcnt))
 		goto out;
 
 	if (nn->nfsd_serv) {
@@ -374,7 +378,8 @@ static int nfsd_inet6addr_event(struct notifier_block *this,
 			sin6.sin6_scope_id = ifa->idev->dev->ifindex;
 		svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6);
 	}
-
+	atomic_dec(&nn->ntf_refcnt);
+	wake_up(&nn->ntf_wq);
 out:
 	return NOTIFY_DONE;
 }
@@ -391,6 +396,7 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
+	atomic_dec(&nn->ntf_refcnt);
 	/* check if the notifier still has clients */
 	if (atomic_dec_return(&nfsd_notifier_refcount) == 0) {
 		unregister_inetaddr_notifier(&nfsd_inetaddr_notifier);
@@ -398,6 +404,7 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
 		unregister_inet6addr_notifier(&nfsd_inet6addr_notifier);
 #endif
 	}
+	wait_event(nn->ntf_wq, atomic_read(&nn->ntf_refcnt) == 0);
 
 	/*
 	 * write_ports can create the server without actually starting
@@ -517,6 +524,7 @@ int nfsd_create_serv(struct net *net)
 		register_inet6addr_notifier(&nfsd_inet6addr_notifier);
 #endif
 	}
+	atomic_inc(&nn->ntf_refcnt);
 	ktime_get_real_ts64(&nn->nfssvc_boot); /* record boot time */
 	return 0;
 }