1 files changed, 131 insertions, 100 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 1a93c7fcf76c..a20c2c9d7d45 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -541,7 +541,7 @@ same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner)
 }
 
 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;
@@ -558,18 +558,6 @@ find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
 	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
 opaque_hashval(const void *ptr, int nbytes)
 {
@@ -1409,11 +1397,16 @@ static void
 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);
 }
 
@@ -2245,6 +2238,10 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name,
 						 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);
@@ -2267,6 +2264,8 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name,
 	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:
@@ -2280,6 +2279,7 @@ static void __free_client(struct kref *k)
 	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);
@@ -2352,7 +2352,11 @@ unhash_client(struct nfs4_client *clp)
 
 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;
@@ -3042,12 +3046,9 @@ static void
 nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
 {
 	struct nfs4_client *clp = cb->cb_clp;
-	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
 
-	spin_lock(&nn->client_lock);
 	clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
-	put_client_renew_locked(clp);
-	spin_unlock(&nn->client_lock);
+	drop_client(clp);
 }
 
 static int
@@ -3644,12 +3645,8 @@ out_nolock:
 	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)
@@ -3826,20 +3823,28 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	}
 
 	/* 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);
-	if (status) {
-		if (status == nfserr_replay_cache) {
-			status = nfsd4_replay_create_session(cr_ses, cs_slot);
-			goto out_free_conn;
-		}
+	switch (status) {
+	case nfs_ok:
+		cs_slot->sl_seqid++;
+		cr_ses->seqid = cs_slot->sl_seqid;
+		break;
+	case nfserr_replay_cache:
+		status = nfsd4_replay_create_session(cr_ses, cs_slot);
+		fallthrough;
+	case nfserr_jukebox:
+		/* The server MUST NOT cache NFS4ERR_DELAY */
+		goto out_free_conn;
+	default:
 		goto out_cache_error;
 	}
-	cs_slot->sl_seqid++;
-	cr_ses->seqid = cs_slot->sl_seqid;
 
 	/* RFC 8881 Section 18.36.4 Phase 3: Client ID confirmation. */
 	if (conf) {
@@ -3859,10 +3864,8 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 		old = find_confirmed_client_by_name(&unconf->cl_name, nn);
 		if (old) {
 			status = mark_client_expired_locked(old);
-			if (status) {
-				old = NULL;
-				goto out_cache_error;
-			}
+			if (status)
+				goto out_expired_error;
 			trace_nfsd_clid_replaced(&old->cl_clientid);
 		}
 		move_to_confirmed(unconf);
@@ -3894,6 +3897,17 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 		expire_client(old);
 	return status;
 
+out_expired_error:
+	old = NULL;
+	/*
+	 * Revert the slot seq_nr change so the server will process
+	 * the client's resend instead of returning a cached response.
+	 */
+	if (status == nfserr_jukebox) {
+		cs_slot->sl_seqid--;
+		cr_ses->seqid = cs_slot->sl_seqid;
+		goto out_free_conn;
+	}
 out_cache_error:
 	nfsd4_cache_create_session(cr_ses, cs_slot, status);
 out_free_conn:
@@ -4210,6 +4224,7 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * 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) {
@@ -4651,21 +4666,32 @@ nfsd4_init_leases_net(struct nfsd_net *nn)
 	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)
@@ -4674,7 +4700,8 @@ 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);
 	}
 }
@@ -4855,34 +4882,46 @@ nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
 }
 
 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 *
@@ -4958,7 +4997,11 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
 	 * 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);
@@ -5331,27 +5374,19 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
 	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;
@@ -6122,12 +6157,8 @@ out:
 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)
@@ -6602,7 +6633,7 @@ deleg_reaper(struct nfsd_net *nn)
 		list_add(&clp->cl_ra_cblist, &cblist);
 
 		/* release in nfsd4_cb_recall_any_release */
-		atomic_inc(&clp->cl_rpc_users);
+		kref_get(&clp->cl_nfsdfs.cl_ref);
 		set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
 		clp->cl_ra_time = ktime_get_boottime_seconds();
 	}
@@ -7191,12 +7222,16 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
 	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)
@@ -7338,7 +7373,7 @@ out:
 	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;
@@ -7355,11 +7390,11 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 		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;
 	}
 }
 
@@ -7375,6 +7410,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	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);
@@ -7399,8 +7435,10 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 */
 	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
@@ -8614,12 +8652,6 @@ nfs4_state_start(void)
 	if (ret)
 		return ret;
 
-	ret = nfsd4_create_callback_queue();
-	if (ret) {
-		rhltable_destroy(&nfs4_file_rhltable);
-		return ret;
-	}
-
 	set_max_delegations();
 	return 0;
 }
@@ -8660,7 +8692,6 @@ nfs4_state_shutdown_net(struct net *net)
 void
 nfs4_state_shutdown(void)
 {
-	nfsd4_destroy_callback_queue();
 	rhltable_destroy(&nfs4_file_rhltable);
 }