1 files changed, 173 insertions, 45 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c5d199d7e6b4..198d7abf34e4 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -160,6 +160,13 @@ static bool is_client_expired(struct nfs4_client *clp)
 	return clp->cl_time == 0;
 }
 
+static void nfsd4_dec_courtesy_client_count(struct nfsd_net *nn,
+					struct nfs4_client *clp)
+{
+	if (clp->cl_state != NFSD4_ACTIVE)
+		atomic_add_unless(&nn->nfsd_courtesy_clients, -1, 0);
+}
+
 static __be32 get_client_locked(struct nfs4_client *clp)
 {
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
@@ -169,6 +176,7 @@ static __be32 get_client_locked(struct nfs4_client *clp)
 	if (is_client_expired(clp))
 		return nfserr_expired;
 	atomic_inc(&clp->cl_rpc_users);
+	nfsd4_dec_courtesy_client_count(nn, clp);
 	clp->cl_state = NFSD4_ACTIVE;
 	return nfs_ok;
 }
@@ -190,6 +198,7 @@ renew_client_locked(struct nfs4_client *clp)
 
 	list_move_tail(&clp->cl_lru, &nn->client_lru);
 	clp->cl_time = ktime_get_boottime_seconds();
+	nfsd4_dec_courtesy_client_count(nn, clp);
 	clp->cl_state = NFSD4_ACTIVE;
 }
 
@@ -357,6 +366,8 @@ nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb)
 static int
 nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task)
 {
+	trace_nfsd_cb_notify_lock_done(&zero_stateid, task);
+
 	/*
 	 * Since this is just an optimization, we don't try very hard if it
 	 * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and
@@ -963,19 +974,19 @@ out_free:
  * Create a unique stateid_t to represent each COPY.
  */
 static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
-			      unsigned char sc_type)
+			      unsigned char cs_type)
 {
 	int new_id;
 
-	stid->stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
-	stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
-	stid->sc_type = sc_type;
+	stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
+	stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
+	stid->cs_type = cs_type;
 
 	idr_preload(GFP_KERNEL);
 	spin_lock(&nn->s2s_cp_lock);
 	new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT);
-	stid->stid.si_opaque.so_id = new_id;
-	stid->stid.si_generation = 1;
+	stid->cs_stid.si_opaque.so_id = new_id;
+	stid->cs_stid.si_generation = 1;
 	spin_unlock(&nn->s2s_cp_lock);
 	idr_preload_end();
 	if (new_id < 0)
@@ -997,7 +1008,7 @@ struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
 	if (!cps)
 		return NULL;
 	cps->cpntf_time = ktime_get_boottime_seconds();
-	refcount_set(&cps->cp_stateid.sc_count, 1);
+	refcount_set(&cps->cp_stateid.cs_count, 1);
 	if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID))
 		goto out_free;
 	spin_lock(&nn->s2s_cp_lock);
@@ -1013,11 +1024,11 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy)
 {
 	struct nfsd_net *nn;
 
-	WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID);
+	WARN_ON_ONCE(copy->cp_stateid.cs_type != NFS4_COPY_STID);
 	nn = net_generic(copy->cp_clp->net, nfsd_net_id);
 	spin_lock(&nn->s2s_cp_lock);
 	idr_remove(&nn->s2s_cp_stateids,
-		   copy->cp_stateid.stid.si_opaque.so_id);
+		   copy->cp_stateid.cs_stid.si_opaque.so_id);
 	spin_unlock(&nn->s2s_cp_lock);
 }
 
@@ -1049,6 +1060,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
 
 static void nfs4_free_deleg(struct nfs4_stid *stid)
 {
+	struct nfs4_delegation *dp = delegstateid(stid);
+
+	WARN_ON_ONCE(!list_empty(&stid->sc_cp_list));
+	WARN_ON_ONCE(!list_empty(&dp->dl_perfile));
+	WARN_ON_ONCE(!list_empty(&dp->dl_perclnt));
+	WARN_ON_ONCE(!list_empty(&dp->dl_recall_lru));
 	kmem_cache_free(deleg_slab, stid);
 	atomic_long_dec(&num_delegations);
 }
@@ -1462,6 +1479,7 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid)
 	release_all_access(stp);
 	if (stp->st_stateowner)
 		nfs4_put_stateowner(stp->st_stateowner);
+	WARN_ON(!list_empty(&stid->sc_cp_list));
 	kmem_cache_free(stateid_slab, stid);
 }
 
@@ -2233,6 +2251,7 @@ __destroy_client(struct nfs4_client *clp)
 	if (clp->cl_cb_conn.cb_xprt)
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
 	atomic_add_unless(&nn->nfs4_client_count, -1, 0);
+	nfsd4_dec_courtesy_client_count(nn, clp);
 	free_client(clp);
 	wake_up_all(&expiry_wq);
 }
@@ -2478,7 +2497,7 @@ static const char *cb_state2str(int state)
 
 static int client_info_show(struct seq_file *m, void *v)
 {
-	struct inode *inode = m->private;
+	struct inode *inode = file_inode(m->file);
 	struct nfs4_client *clp;
 	u64 clid;
 
@@ -2518,17 +2537,7 @@ static int client_info_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int client_info_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, client_info_show, inode);
-}
-
-static const struct file_operations client_info_fops = {
-	.open		= client_info_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(client_info);
 
 static void *states_start(struct seq_file *s, loff_t *pos)
 	__acquires(&clp->cl_lock)
@@ -4337,7 +4346,27 @@ out:
 	return -ENOMEM;
 }
 
-void nfsd4_init_leases_net(struct nfsd_net *nn)
+static unsigned long
+nfsd_courtesy_client_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cnt;
+	struct nfsd_net *nn = container_of(shrink,
+			struct nfsd_net, nfsd_client_shrinker);
+
+	cnt = atomic_read(&nn->nfsd_courtesy_clients);
+	if (cnt > 0)
+		mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
+	return (unsigned long)cnt;
+}
+
+static unsigned long
+nfsd_courtesy_client_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	return SHRINK_STOP;
+}
+
+int
+nfsd4_init_leases_net(struct nfsd_net *nn)
 {
 	struct sysinfo si;
 	u64 max_clients;
@@ -4356,6 +4385,18 @@ void nfsd4_init_leases_net(struct nfsd_net *nn)
 	max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024);
 	max_clients *= NFS4_CLIENTS_PER_GB;
 	nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
+
+	atomic_set(&nn->nfsd_courtesy_clients, 0);
+	nn->nfsd_client_shrinker.scan_objects = nfsd_courtesy_client_scan;
+	nn->nfsd_client_shrinker.count_objects = nfsd_courtesy_client_count;
+	nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
+	return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
+}
+
+void
+nfsd4_leases_net_shutdown(struct nfsd_net *nn)
+{
+	unregister_shrinker(&nn->nfsd_client_shrinker);
 }
 
 static void init_nfs4_replay(struct nfs4_replay *rp)
@@ -4715,6 +4756,35 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
 	return ret;
 }
 
+static bool nfsd4_deleg_present(const struct inode *inode)
+{
+	struct file_lock_context *ctx = smp_load_acquire(&inode->i_flctx);
+
+	return ctx && !list_empty_careful(&ctx->flc_lease);
+}
+
+/**
+ * nfsd_wait_for_delegreturn - wait for delegations to be returned
+ * @rqstp: the RPC transaction being executed
+ * @inode: in-core inode of the file being waited for
+ *
+ * The timeout prevents deadlock if all nfsd threads happen to be
+ * tied up waiting for returning delegations.
+ *
+ * Return values:
+ *   %true: delegation was returned
+ *   %false: timed out waiting for delegreturn
+ */
+bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode)
+{
+	long __maybe_unused timeo;
+
+	timeo = wait_var_event_timeout(inode, !nfsd4_deleg_present(inode),
+				       NFSD_DELEGRETURN_TIMEOUT);
+	trace_nfsd_delegret_wakeup(rqstp, inode, timeo);
+	return timeo > 0;
+}
+
 static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
 {
 	struct nfs4_delegation *dp = cb_to_delegation(cb);
@@ -4743,6 +4813,8 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
 {
 	struct nfs4_delegation *dp = cb_to_delegation(cb);
 
+	trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task);
+
 	if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID ||
 	    dp->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID)
 	        return 1;
@@ -4788,18 +4860,17 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 	 * We're assuming the state code never drops its reference
 	 * without first removing the lease.  Since we're in this lease
 	 * callback (and since the lease code is serialized by the
-	 * i_lock) we know the server hasn't removed the lease yet, and
+	 * flc_lock) we know the server hasn't removed the lease yet, and
 	 * we know it's safe to take a reference.
 	 */
 	refcount_inc(&dp->dl_stid.sc_count);
-	nfsd4_run_cb(&dp->dl_recall);
+	WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall));
 }
 
-/* Called from break_lease() with i_lock held. */
+/* Called from break_lease() with flc_lock held. */
 static bool
 nfsd_break_deleg_cb(struct file_lock *fl)
 {
-	bool ret = false;
 	struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
 	struct nfs4_client *clp = dp->dl_stid.sc_client;
@@ -4825,7 +4896,7 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 	fp->fi_had_conflict = true;
 	nfsd_break_one_deleg(dp);
 	spin_unlock(&fp->fi_lock);
-	return ret;
+	return false;
 }
 
 /**
@@ -5878,8 +5949,11 @@ nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist,
 			goto exp_client;
 		if (!state_expired(lt, clp->cl_time))
 			break;
-		if (!atomic_read(&clp->cl_rpc_users))
+		if (!atomic_read(&clp->cl_rpc_users)) {
+			if (clp->cl_state == NFSD4_ACTIVE)
+				atomic_inc(&nn->nfsd_courtesy_clients);
 			clp->cl_state = NFSD4_COURTESY;
+		}
 		if (!client_has_state(clp))
 			goto exp_client;
 		if (!nfs4_anylock_blockers(clp))
@@ -5894,10 +5968,49 @@ exp_client:
 	spin_unlock(&nn->client_lock);
 }
 
+static void
+nfs4_get_courtesy_client_reaplist(struct nfsd_net *nn,
+				struct list_head *reaplist)
+{
+	unsigned int maxreap = 0, reapcnt = 0;
+	struct list_head *pos, *next;
+	struct nfs4_client *clp;
+
+	maxreap = NFSD_CLIENT_MAX_TRIM_PER_RUN;
+	INIT_LIST_HEAD(reaplist);
+
+	spin_lock(&nn->client_lock);
+	list_for_each_safe(pos, next, &nn->client_lru) {
+		clp = list_entry(pos, struct nfs4_client, cl_lru);
+		if (clp->cl_state == NFSD4_ACTIVE)
+			break;
+		if (reapcnt >= maxreap)
+			break;
+		if (!mark_client_expired_locked(clp)) {
+			list_add(&clp->cl_lru, reaplist);
+			reapcnt++;
+		}
+	}
+	spin_unlock(&nn->client_lock);
+}
+
+static void
+nfs4_process_client_reaplist(struct list_head *reaplist)
+{
+	struct list_head *pos, *next;
+	struct nfs4_client *clp;
+
+	list_for_each_safe(pos, next, reaplist) {
+		clp = list_entry(pos, struct nfs4_client, cl_lru);
+		trace_nfsd_clid_purged(&clp->cl_clientid);
+		list_del_init(&clp->cl_lru);
+		expire_client(clp);
+	}
+}
+
 static time64_t
 nfs4_laundromat(struct nfsd_net *nn)
 {
-	struct nfs4_client *clp;
 	struct nfs4_openowner *oo;
 	struct nfs4_delegation *dp;
 	struct nfs4_ol_stateid *stp;
@@ -5920,18 +6033,14 @@ nfs4_laundromat(struct nfsd_net *nn)
 	spin_lock(&nn->s2s_cp_lock);
 	idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
 		cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
-		if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
+		if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID &&
 				state_expired(&lt, cps->cpntf_time))
 			_free_cpntf_state_locked(nn, cps);
 	}
 	spin_unlock(&nn->s2s_cp_lock);
 	nfs4_get_client_reaplist(nn, &reaplist, &lt);
-	list_for_each_safe(pos, next, &reaplist) {
-		clp = list_entry(pos, struct nfs4_client, cl_lru);
-		trace_nfsd_clid_purged(&clp->cl_clientid);
-		list_del_init(&clp->cl_lru);
-		expire_client(clp);
-	}
+	nfs4_process_client_reaplist(&reaplist);
+
 	spin_lock(&state_lock);
 	list_for_each_safe(pos, next, &nn->del_recall_lru) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
@@ -6014,6 +6123,18 @@ laundromat_main(struct work_struct *laundry)
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
 }
 
+static void
+courtesy_client_reaper(struct work_struct *reaper)
+{
+	struct list_head reaplist;
+	struct delayed_work *dwork = to_delayed_work(reaper);
+	struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+					nfsd_shrinker_work);
+
+	nfs4_get_courtesy_client_reaplist(nn, &reaplist);
+	nfs4_process_client_reaplist(&reaplist);
+}
+
 static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
 {
 	if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
@@ -6149,6 +6270,7 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     struct nfs4_stid **s, struct nfsd_net *nn)
 {
 	__be32 status;
+	struct nfs4_stid *stid;
 	bool return_revoked = false;
 
 	/*
@@ -6171,15 +6293,16 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 	}
 	if (status)
 		return status;
-	*s = find_stateid_by_type(cstate->clp, stateid, typemask);
-	if (!*s)
+	stid = find_stateid_by_type(cstate->clp, stateid, typemask);
+	if (!stid)
 		return nfserr_bad_stateid;
-	if (((*s)->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
-		nfs4_put_stid(*s);
+	if ((stid->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
+		nfs4_put_stid(stid);
 		if (cstate->minorversion)
 			return nfserr_deleg_revoked;
 		return nfserr_bad_stateid;
 	}
+	*s = stid;
 	return nfs_ok;
 }
 
@@ -6244,12 +6367,12 @@ out:
 static void
 _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
 {
-	WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID);
-	if (!refcount_dec_and_test(&cps->cp_stateid.sc_count))
+	WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID);
+	if (!refcount_dec_and_test(&cps->cp_stateid.cs_count))
 		return;
 	list_del(&cps->cp_list);
 	idr_remove(&nn->s2s_cp_stateids,
-		   cps->cp_stateid.stid.si_opaque.so_id);
+		   cps->cp_stateid.cs_stid.si_opaque.so_id);
 	kfree(cps);
 }
 /*
@@ -6271,12 +6394,12 @@ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
 	if (cps_t) {
 		state = container_of(cps_t, struct nfs4_cpntf_state,
 				     cp_stateid);
-		if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID) {
+		if (state->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID) {
 			state = NULL;
 			goto unlock;
 		}
 		if (!clp)
-			refcount_inc(&state->cp_stateid.sc_count);
+			refcount_inc(&state->cp_stateid.cs_count);
 		else
 			_free_cpntf_state_locked(nn, state);
 	}
@@ -6684,6 +6807,7 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 	struct nfs4_client *clp = s->st_stid.sc_client;
 	bool unhashed;
 	LIST_HEAD(reaplist);
+	struct nfs4_ol_stateid *stp;
 
 	spin_lock(&clp->cl_lock);
 	unhashed = unhash_open_stateid(s, &reaplist);
@@ -6692,6 +6816,8 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 		if (unhashed)
 			put_ol_stateid_locked(s, &reaplist);
 		spin_unlock(&clp->cl_lock);
+		list_for_each_entry(stp, &reaplist, st_locks)
+			nfs4_free_cpntf_statelist(clp->net, &stp->st_stid);
 		free_ol_stateid_reaplist(&reaplist);
 	} else {
 		spin_unlock(&clp->cl_lock);
@@ -6775,6 +6901,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto put_stateid;
 
+	wake_up_var(d_inode(cstate->current_fh.fh_dentry));
 	destroy_delegation(dp);
 put_stateid:
 	nfs4_put_stid(&dp->dl_stid);
@@ -7830,6 +7957,7 @@ static int nfs4_state_create_net(struct net *net)
 	INIT_LIST_HEAD(&nn->blocked_locks_lru);
 
 	INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
+	INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, courtesy_client_reaper);
 	get_net(net);
 
 	return 0;