Merge tag 'nfsd-7.0-2' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd fixes from Chuck Lever:

 - Fix cache_request leak in cache_release()

 - Fix heap overflow in the NFSv4.0 LOCK replay cache

 - Hold net reference for the lifetime of /proc/fs/nfs/exports fd

 - Defer sub-object cleanup in export "put" callbacks

* tag 'nfsd-7.0-2' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux:
  nfsd: fix heap overflow in NFSv4.0 LOCK replay cache
  sunrpc: fix cache_request leak in cache_release
  NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd
  NFSD: Defer sub-object cleanup in export put callbacks

Author: torvalds

fs/nfsd/export.c

@@ -36,19 +36,30 @@
  * second map contains a reference to the entry in the first map.
  */
 
+static struct workqueue_struct *nfsd_export_wq;
+
 #define	EXPKEY_HASHBITS		8
 #define	EXPKEY_HASHMAX		(1 << EXPKEY_HASHBITS)
 #define	EXPKEY_HASHMASK		(EXPKEY_HASHMAX -1)
 
-static void expkey_put(struct kref *ref)
+static void expkey_release(struct work_struct *work)
 {
-	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
+	struct svc_expkey *key = container_of(to_rcu_work(work),
+					      struct svc_expkey, ek_rwork);
 
 	if (test_bit(CACHE_VALID, &key->h.flags) &&
 	    !test_bit(CACHE_NEGATIVE, &key->h.flags))
 		path_put(&key->ek_path);
 	auth_domain_put(key->ek_client);
-	kfree_rcu(key, ek_rcu);
+	kfree(key);
+}
+
+static void expkey_put(struct kref *ref)
+{
+	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
+
+	INIT_RCU_WORK(&key->ek_rwork, expkey_release);
+	queue_rcu_work(nfsd_export_wq, &key->ek_rwork);
 }
 
 static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
@@ -353,11 +364,13 @@ static void export_stats_destroy(struct export_stats *stats)
 					    EXP_STATS_COUNTERS_NUM);
 }
 
-static void svc_export_release(struct rcu_head *rcu_head)
+static void svc_export_release(struct work_struct *work)
 {
-	struct svc_export *exp = container_of(rcu_head, struct svc_export,
-			ex_rcu);
+	struct svc_export *exp = container_of(to_rcu_work(work),
+					      struct svc_export, ex_rwork);
 
+	path_put(&exp->ex_path);
+	auth_domain_put(exp->ex_client);
 	nfsd4_fslocs_free(&exp->ex_fslocs);
 	export_stats_destroy(exp->ex_stats);
 	kfree(exp->ex_stats);
@@ -369,9 +382,8 @@ static void svc_export_put(struct kref *ref)
 {
 	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
 
-	path_put(&exp->ex_path);
-	auth_domain_put(exp->ex_client);
-	call_rcu(&exp->ex_rcu, svc_export_release);
+	INIT_RCU_WORK(&exp->ex_rwork, svc_export_release);
+	queue_rcu_work(nfsd_export_wq, &exp->ex_rwork);
 }
 
 static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
@@ -1479,6 +1491,36 @@ const struct seq_operations nfs_exports_op = {
 	.show	= e_show,
 };
 
+/**
+ * nfsd_export_wq_init - allocate the export release workqueue
+ *
+ * Called once at module load. The workqueue runs deferred svc_export and
+ * svc_expkey release work scheduled by queue_rcu_work() in the cache put
+ * callbacks.
+ *
+ * Return values:
+ *   %0: workqueue allocated
+ *   %-ENOMEM: allocation failed
+ */
+int nfsd_export_wq_init(void)
+{
+	nfsd_export_wq = alloc_workqueue("nfsd_export", WQ_UNBOUND, 0);
+	if (!nfsd_export_wq)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * nfsd_export_wq_shutdown - drain and free the export release workqueue
+ *
+ * Called once at module unload. Per-namespace teardown in
+ * nfsd_export_shutdown() has already drained all deferred work.
+ */
+void nfsd_export_wq_shutdown(void)
+{
+	destroy_workqueue(nfsd_export_wq);
+}
+
 /*
  * Initialize the exports module.
  */
@@ -1540,6 +1582,9 @@ nfsd_export_shutdown(struct net *net)
 
 	cache_unregister_net(nn->svc_expkey_cache, net);
 	cache_unregister_net(nn->svc_export_cache, net);
+	/* Drain deferred export and expkey release work. */
+	rcu_barrier();
+	flush_workqueue(nfsd_export_wq);
 	cache_destroy_net(nn->svc_expkey_cache, net);
 	cache_destroy_net(nn->svc_export_cache, net);
 	svcauth_unix_purge(net);

fs/nfsd/export.h

@@ -7,6 +7,7 @@
 
 #include <linux/sunrpc/cache.h>
 #include <linux/percpu_counter.h>
+#include <linux/workqueue.h>
 #include <uapi/linux/nfsd/export.h>
 #include <linux/nfs4.h>
 
@@ -75,7 +76,7 @@ struct svc_export {
 	u32			ex_layout_types;
 	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
-	struct rcu_head		ex_rcu;
+	struct rcu_work		ex_rwork;
 	unsigned long		ex_xprtsec_modes;
 	struct export_stats	*ex_stats;
 };
@@ -92,7 +93,7 @@ struct svc_expkey {
 	u32			ek_fsid[6];
 
 	struct path		ek_path;
-	struct rcu_head		ek_rcu;
+	struct rcu_work		ek_rwork;
 };
 
 #define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))
@@ -110,6 +111,8 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
 /*
  * Function declarations
  */
+int			nfsd_export_wq_init(void);
+void			nfsd_export_wq_shutdown(void);
 int			nfsd_export_init(struct net *);
 void			nfsd_export_shutdown(struct net *);
 void			nfsd_export_flush(struct net *);

fs/nfsd/nfs4xdr.c

@@ -6281,9 +6281,14 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
 		int len = xdr->buf->len - (op_status_offset + XDR_UNIT);
 
 		so->so_replay.rp_status = op->status;
-		so->so_replay.rp_buflen = len;
-		read_bytes_from_xdr_buf(xdr->buf, op_status_offset + XDR_UNIT,
+		if (len <= NFSD4_REPLAY_ISIZE) {
+			so->so_replay.rp_buflen = len;
+			read_bytes_from_xdr_buf(xdr->buf,
+						op_status_offset + XDR_UNIT,
 						so->so_replay.rp_buf, len);
+		} else {
+			so->so_replay.rp_buflen = 0;
+		}
 	}
 status:
 	op->status = nfsd4_map_status(op->status,

fs/nfsd/nfsctl.c

@@ -149,9 +149,19 @@ static int exports_net_open(struct net *net, struct file *file)
 
 	seq = file->private_data;
 	seq->private = nn->svc_export_cache;
+	get_net(net);
 	return 0;
 }
 
+static int exports_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct cache_detail *cd = seq->private;
+
+	put_net(cd->net);
+	return seq_release(inode, file);
+}
+
 static int exports_nfsd_open(struct inode *inode, struct file *file)
 {
 	return exports_net_open(inode->i_sb->s_fs_info, file);
@@ -161,7 +171,7 @@ static const struct file_operations exports_nfsd_operations = {
 	.open		= exports_nfsd_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release	= exports_release,
 };
 
 static int export_features_show(struct seq_file *m, void *v)
@@ -1376,7 +1386,7 @@ static const struct proc_ops exports_proc_ops = {
 	.proc_open	= exports_proc_open,
 	.proc_read	= seq_read,
 	.proc_lseek	= seq_lseek,
-	.proc_release	= seq_release,
+	.proc_release	= exports_release,
 };
 
 static int create_proc_exports_entry(void)
@@ -2259,9 +2269,12 @@ static int __init init_nfsd(void)
 	if (retval)
 		goto out_free_pnfs;
 	nfsd_lockd_init();	/* lockd->nfsd callbacks */
+	retval = nfsd_export_wq_init();
+	if (retval)
+		goto out_free_lockd;
 	retval = register_pernet_subsys(&nfsd_net_ops);
 	if (retval < 0)
-		goto out_free_lockd;
+		goto out_free_export_wq;
 	retval = register_cld_notifier();
 	if (retval)
 		goto out_free_subsys;
@@ -2290,6 +2303,8 @@ static int __init init_nfsd(void)
 	unregister_cld_notifier();
 out_free_subsys:
 	unregister_pernet_subsys(&nfsd_net_ops);
+out_free_export_wq:
+	nfsd_export_wq_shutdown();
 out_free_lockd:
 	nfsd_lockd_shutdown();
 	nfsd_drc_slab_free();
@@ -2310,6 +2325,7 @@ static void __exit exit_nfsd(void)
 	nfsd4_destroy_laundry_wq();
 	unregister_cld_notifier();
 	unregister_pernet_subsys(&nfsd_net_ops);
+	nfsd_export_wq_shutdown();
 	nfsd_drc_slab_free();
 	nfsd_lockd_shutdown();
 	nfsd4_free_slabs();

fs/nfsd/state.h

@@ -541,11 +541,18 @@ struct nfs4_client_reclaim {
 	struct xdr_netobj	cr_princhash;
 };
 
-/* A reasonable value for REPLAY_ISIZE was estimated as follows:  
- * The OPEN response, typically the largest, requires 
- *   4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) +  8(verifier) + 
- *   4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) + 
- *   20(deleg. space limit) + ~32(deleg. ace) = 112 bytes 
+/*
+ * REPLAY_ISIZE is sized for an OPEN response with delegation:
+ *   4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) +
+ *   8(verifier) + 4(deleg. type) + 8(deleg. stateid) +
+ *   4(deleg. recall flag) + 20(deleg. space limit) +
+ *   ~32(deleg. ace) = 112 bytes
+ *
+ * Some responses can exceed this. A LOCK denial includes the conflicting
+ * lock owner, which can be up to 1024 bytes (NFS4_OPAQUE_LIMIT). Responses
+ * larger than REPLAY_ISIZE are not cached in rp_ibuf; only rp_status is
+ * saved. Enlarging this constant increases the size of every
+ * nfs4_stateowner.
  */
 
 #define NFSD4_REPLAY_ISIZE       112 

net/sunrpc/cache.c

@@ -1062,24 +1062,40 @@ static int cache_release(struct inode *inode, struct file *filp,
 	struct cache_reader *rp = filp->private_data;
 
 	if (rp) {
+		struct cache_request *rq = NULL;
+
 		spin_lock(&queue_lock);
 		if (rp->offset) {
 			struct cache_queue *cq;
-			for (cq= &rp->q; &cq->list != &cd->queue;
-			     cq = list_entry(cq->list.next, struct cache_queue, list))
+			for (cq = &rp->q; &cq->list != &cd->queue;
+			     cq = list_entry(cq->list.next,
+					     struct cache_queue, list))
 				if (!cq->reader) {
-					container_of(cq, struct cache_request, q)
-						->readers--;
+					struct cache_request *cr =
+						container_of(cq,
+						struct cache_request, q);
+					cr->readers--;
+					if (cr->readers == 0 &&
+					    !test_bit(CACHE_PENDING,
+						      &cr->item->flags)) {
+						list_del(&cr->q.list);
+						rq = cr;
+					}
 					break;
 				}
 			rp->offset = 0;
 		}
 		list_del(&rp->q.list);
 		spin_unlock(&queue_lock);
 
+		if (rq) {
+			cache_put(rq->item, cd);
+			kfree(rq->buf);
+			kfree(rq);
+		}
+
 		filp->private_data = NULL;
 		kfree(rp);
-
 	}
 	if (filp->f_mode & FMODE_WRITE) {
 		atomic_dec(&cd->writers);