1 files changed, 282 insertions, 122 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0c04f81aa63b..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.
@@ -359,7 +368,7 @@ put_nfs4_file(struct nfs4_file *fi)
 {
 	might_lock(&state_lock);
 
-	if (atomic_dec_and_lock(&fi->fi_ref, &state_lock)) {
+	if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) {
 		hlist_del_rcu(&fi->fi_hash);
 		spin_unlock(&state_lock);
 		WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate));
@@ -568,7 +577,7 @@ alloc_clnt_odstate(struct nfs4_client *clp)
 	co = kmem_cache_zalloc(odstate_slab, GFP_KERNEL);
 	if (co) {
 		co->co_client = clp;
-		atomic_set(&co->co_odcount, 1);
+		refcount_set(&co->co_odcount, 1);
 	}
 	return co;
 }
@@ -586,7 +595,7 @@ static inline void
 get_clnt_odstate(struct nfs4_clnt_odstate *co)
 {
 	if (co)
-		atomic_inc(&co->co_odcount);
+		refcount_inc(&co->co_odcount);
 }
 
 static void
@@ -598,7 +607,7 @@ put_clnt_odstate(struct nfs4_clnt_odstate *co)
 		return;
 
 	fp = co->co_file;
-	if (atomic_dec_and_lock(&co->co_odcount, &fp->fi_lock)) {
+	if (refcount_dec_and_lock(&co->co_odcount, &fp->fi_lock)) {
 		list_del(&co->co_perfile);
 		spin_unlock(&fp->fi_lock);
 
@@ -656,7 +665,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla
 	stid->sc_stateid.si_opaque.so_id = new_id;
 	stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
 	/* Will be incremented before return to client: */
-	atomic_set(&stid->sc_count, 1);
+	refcount_set(&stid->sc_count, 1);
 	spin_lock_init(&stid->sc_lock);
 
 	/*
@@ -813,7 +822,7 @@ nfs4_put_stid(struct nfs4_stid *s)
 
 	might_lock(&clp->cl_lock);
 
-	if (!atomic_dec_and_lock(&s->sc_count, &clp->cl_lock)) {
+	if (!refcount_dec_and_lock(&s->sc_count, &clp->cl_lock)) {
 		wake_up_all(&close_wq);
 		return;
 	}
@@ -913,7 +922,7 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
 	if (status)
 		return status;
 	++fp->fi_delegees;
-	atomic_inc(&dp->dl_stid.sc_count);
+	refcount_inc(&dp->dl_stid.sc_count);
 	dp->dl_stid.sc_type = NFS4_DELEG_STID;
 	list_add(&dp->dl_perfile, &fp->fi_delegations);
 	list_add(&dp->dl_perclnt, &clp->cl_delegations);
@@ -1214,7 +1223,7 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp,
 
 	WARN_ON_ONCE(!list_empty(&stp->st_locks));
 
-	if (!atomic_dec_and_test(&s->sc_count)) {
+	if (!refcount_dec_and_test(&s->sc_count)) {
 		wake_up_all(&close_wq);
 		return;
 	}
@@ -1439,8 +1448,10 @@ free_session_slots(struct nfsd4_session *ses)
 {
 	int i;
 
-	for (i = 0; i < ses->se_fchannel.maxreqs; i++)
+	for (i = 0; i < ses->se_fchannel.maxreqs; i++) {
+		free_svc_cred(&ses->se_slots[i]->sl_cred);
 		kfree(ses->se_slots[i]);
+	}
 }
 
 /*
@@ -1472,6 +1483,11 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca)
 	spin_lock(&nfsd_drc_lock);
 	avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION,
 		    nfsd_drc_max_mem - nfsd_drc_mem_used);
+	/*
+	 * Never use more than a third of the remaining memory,
+	 * unless it's the only way to give this client a slot:
+	 */
+	avail = clamp_t(int, avail, slotsize, avail/3);
 	num = min_t(int, num, avail / slotsize);
 	nfsd_drc_mem_used += num * slotsize;
 	spin_unlock(&nfsd_drc_lock);
@@ -2072,7 +2088,7 @@ find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
 	s = find_stateid_locked(cl, t);
 	if (s != NULL) {
 		if (typemask & s->sc_type)
-			atomic_inc(&s->sc_count);
+			refcount_inc(&s->sc_count);
 		else
 			s = NULL;
 	}
@@ -2287,14 +2303,18 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
 
 	dprintk("--> %s slot %p\n", __func__, slot);
 
+	slot->sl_flags |= NFSD4_SLOT_INITIALIZED;
 	slot->sl_opcnt = resp->opcnt;
 	slot->sl_status = resp->cstate.status;
+	free_svc_cred(&slot->sl_cred);
+	copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred);
 
-	slot->sl_flags |= NFSD4_SLOT_INITIALIZED;
-	if (nfsd4_not_cached(resp)) {
-		slot->sl_datalen = 0;
+	if (!nfsd4_cache_this(resp)) {
+		slot->sl_flags &= ~NFSD4_SLOT_CACHED;
 		return;
 	}
+	slot->sl_flags |= NFSD4_SLOT_CACHED;
+
 	base = resp->cstate.data_offset;
 	slot->sl_datalen = buf->len - base;
 	if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen))
@@ -2321,8 +2341,16 @@ nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args,
 	op = &args->ops[resp->opcnt - 1];
 	nfsd4_encode_operation(resp, op);
 
-	/* Return nfserr_retry_uncached_rep in next operation. */
-	if (args->opcnt > 1 && !(slot->sl_flags & NFSD4_SLOT_CACHETHIS)) {
+	if (slot->sl_flags & NFSD4_SLOT_CACHED)
+		return op->status;
+	if (args->opcnt == 1) {
+		/*
+		 * The original operation wasn't a solo sequence--we
+		 * always cache those--so this retry must not match the
+		 * original:
+		 */
+		op->status = nfserr_seq_false_retry;
+	} else {
 		op = &args->ops[resp->opcnt++];
 		op->status = nfserr_retry_uncached_rep;
 		nfsd4_encode_operation(resp, op);
@@ -2986,6 +3014,34 @@ static bool nfsd4_request_too_big(struct svc_rqst *rqstp,
 	return xb->len > session->se_fchannel.maxreq_sz;
 }
 
+static bool replay_matches_cache(struct svc_rqst *rqstp,
+		 struct nfsd4_sequence *seq, struct nfsd4_slot *slot)
+{
+	struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+
+	if ((bool)(slot->sl_flags & NFSD4_SLOT_CACHETHIS) !=
+	    (bool)seq->cachethis)
+		return false;
+	/*
+	 * If there's an error than the reply can have fewer ops than
+	 * the call.  But if we cached a reply with *more* ops than the
+	 * call you're sending us now, then this new call is clearly not
+	 * really a replay of the old one:
+	 */
+	if (slot->sl_opcnt < argp->opcnt)
+		return false;
+	/* This is the only check explicitly called by spec: */
+	if (!same_creds(&rqstp->rq_cred, &slot->sl_cred))
+		return false;
+	/*
+	 * There may be more comparisons we could actually do, but the
+	 * spec doesn't require us to catch every case where the calls
+	 * don't match (that would require caching the call as well as
+	 * the reply), so we don't bother.
+	 */
+	return true;
+}
+
 __be32
 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		union nfsd4_op_u *u)
@@ -3045,6 +3101,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_seq_misordered;
 		if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED))
 			goto out_put_session;
+		status = nfserr_seq_false_retry;
+		if (!replay_matches_cache(rqstp, seq, slot))
+			goto out_put_session;
 		cstate->slot = slot;
 		cstate->session = session;
 		cstate->clp = clp;
@@ -3351,7 +3410,7 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
 {
 	lockdep_assert_held(&state_lock);
 
-	atomic_set(&fp->fi_ref, 1);
+	refcount_set(&fp->fi_ref, 1);
 	spin_lock_init(&fp->fi_lock);
 	INIT_LIST_HEAD(&fp->fi_stateids);
 	INIT_LIST_HEAD(&fp->fi_delegations);
@@ -3512,15 +3571,63 @@ 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;
-			atomic_inc(&ret->st_stid.sc_count);
+			refcount_inc(&ret->st_stid.sc_count);
 			break;
 		}
 	}
 	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)
@@ -3563,8 +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);
 
@@ -3573,7 +3681,7 @@ init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
 		goto out_unlock;
 
 	open->op_stp = NULL;
-	atomic_inc(&stp->st_stid.sc_count);
+	refcount_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_OPEN_STID;
 	INIT_LIST_HEAD(&stp->st_locks);
 	stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner);
@@ -3589,7 +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;
@@ -3621,7 +3733,7 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
 	 * there should be no danger of the refcount going back up again at
 	 * this point.
 	 */
-	wait_event(close_wq, atomic_read(&s->st_stid.sc_count) == 2);
+	wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2);
 
 	release_all_access(s);
 	if (s->st_stid.sc_file) {
@@ -3647,7 +3759,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 
 	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) {
 		if (fh_match(&fp->fi_fhandle, fh)) {
-			if (atomic_inc_not_zero(&fp->fi_ref))
+			if (refcount_inc_not_zero(&fp->fi_ref))
 				return fp;
 		}
 	}
@@ -3783,7 +3895,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 	 * lock) we know the server hasn't removed the lease yet, we know
 	 * it's safe to take a reference.
 	 */
-	atomic_inc(&dp->dl_stid.sc_count);
+	refcount_inc(&dp->dl_stid.sc_count);
 	nfsd4_run_cb(&dp->dl_recall);
 }
 
@@ -3966,7 +4078,8 @@ static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, statei
 {
 	struct nfs4_stid *ret;
 
-	ret = find_stateid_by_type(cl, s, NFS4_DELEG_STID);
+	ret = find_stateid_by_type(cl, s,
+				NFS4_DELEG_STID|NFS4_REVOKED_DELEG_STID);
 	if (!ret)
 		return NULL;
 	return delegstateid(ret);
@@ -3989,6 +4102,12 @@ nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open,
 	deleg = find_deleg_stateid(cl, &open->op_delegate_stateid);
 	if (deleg == NULL)
 		goto out;
+	if (deleg->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) {
+		nfs4_put_stid(&deleg->dl_stid);
+		if (cl->cl_minorversion)
+			status = nfserr_deleg_revoked;
+		goto out;
+	}
 	flags = share_access_to_flags(open->op_share_access);
 	status = nfs4_check_delegmode(deleg, flags);
 	if (status) {
@@ -4392,6 +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,
@@ -4403,9 +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;
@@ -4413,35 +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;
 		}
 
@@ -4450,7 +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);
 
@@ -4677,7 +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);
@@ -4798,6 +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 &&
@@ -4811,7 +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)) {
@@ -4826,7 +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) {
@@ -4858,8 +4985,19 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     struct nfs4_stid **s, struct nfsd_net *nn)
 {
 	__be32 status;
+	bool return_revoked = false;
 
-	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+	/*
+	 *  only return revoked delegations if explicitly asked.
+	 *  otherwise we report revoked or bad_stateid status.
+	 */
+	if (typemask & NFS4_REVOKED_DELEG_STID)
+		return_revoked = true;
+	else if (typemask & NFS4_DELEG_STID)
+		typemask |= NFS4_REVOKED_DELEG_STID;
+
+	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) {
@@ -4872,6 +5010,12 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 	*s = find_stateid_by_type(cstate->clp, stateid, typemask);
 	if (!*s)
 		return nfserr_bad_stateid;
+	if (((*s)->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
+		nfs4_put_stid(*s);
+		if (cstate->minorversion)
+			return nfserr_deleg_revoked;
+		return nfserr_bad_stateid;
+	}
 	return nfs_ok;
 }
 
@@ -4971,7 +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;
@@ -5025,7 +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)
@@ -5036,11 +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;
 }
@@ -5060,6 +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;
@@ -5071,11 +5220,13 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		ret = nfserr_locks_held;
 		break;
 	case NFS4_LOCK_STID:
-		atomic_inc(&s->sc_count);
+		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);
@@ -5084,6 +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:
@@ -5106,15 +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);
@@ -5294,7 +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);
 
@@ -5334,10 +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);
@@ -5363,7 +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;
 
@@ -5569,16 +5721,43 @@ 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;
 
-	atomic_inc(&stp->st_stid.sc_count);
+	refcount_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_LOCK_STID;
 	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
 	get_nfs4_file(fp);
@@ -5586,29 +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) {
-			atomic_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 *
@@ -5621,26 +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;
 }
 
@@ -5677,7 +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) {
@@ -5693,25 +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:
@@ -5917,14 +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);
 	}
@@ -6944,6 +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);
@@ -7001,13 +7164,10 @@ 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 %p)\n",
-	       nn->nfsd4_grace, net);
+	printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n",
+	       nn->nfsd4_grace, net->ns.inum);
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ);
 	return 0;
 }
@@ -7080,7 +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);