Highlights:

- Bruce steps down as NFSD maintainer
 - Prepare for dynamic nfsd thread management
 - More work on supporting re-exporting NFS mounts
 - One fs/locks patch on behalf of Jeff Layton
 
 Notable bug fixes:
 - Fix zero-length NFSv3 WRITEs
 - Fix directory cinfo on FS's that do not support iversion
 - Fix WRITE verifiers for stable writes
 - Fix crash on COPY_NOTIFY with a special state ID
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEKLLlsBKG3yQ88j7+M2qzM29mf5cFAmHcWOMACgkQM2qzM29m
 f5dh0Q/+MjEL0IK551FdChx9Es1JqKRggv9KwJkLIoa1bw/PMSwP2pnKz6eL0Yun
 mdhE9AZQgyFH1IAGdqjeLZKIYRin6bvAdDrnlqQ9SvTviPLWniSUI6AuyUqK6Zyk
 wMcXpyOze0fhpxkYmz8/g7i66w967tmLh5MRvV1dkpOYAe99rYwGhvj+9ZeEWfNI
 TgmptntMG6YEb+xY0E73otXZHMr2DL67ZYvOUYWemJA1uxcX4joaWBg8sx74dB6k
 DUB4BFuoURk6viDD1QYh3qPU3dz9RCJNMz/cWd8+2t7BdaujTSXRIcaFslrQnKfL
 Rm+O7pi5W+XohFDjeuMZ1g0c1ot/aoZSaAz00LoCVhejJ/sK9NiPAN1+LyY91Lja
 cUBMVPNfW7ClIpiZcORP/chNmVn2qlaL2nxzSY/Uegnd5pIIeVD0pFVgx4+NlEat
 mbrrQBcMpBRM0B+RzHS6AusqHrGdSEcwqWoVXWdxsBigJQT/AxWmii3U88k0Z54i
 ooMWLaQ9EBBmygV01JN/OBySW2M/dvbfz3eFROvAVqsIP9JWP3FlUOlRDl8GcjXA
 azi9fTysBom7WtL6NPcxDJbJ2t9hYr2YaztTpdo9YCHOuQbSQT6IWR5PAa3zvwMu
 Bfz6Y8Hoo/KZHCqmkPGYM+x1ENCyDPv788E+erdnw1PFP5F3Pbo=
 =/kX3
 -----END PGP SIGNATURE-----

Merge tag 'nfsd-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "Bruce has announced he is leaving Red Hat at the end of the month and
  is stepping back from his role as NFSD co-maintainer. As a result,
  this includes a patch removing him from the MAINTAINERS file.

  There is one patch in here that Jeff Layton was carrying in the locks
  tree. Since he had only one for this cycle, he asked us to send it to
  you via the nfsd tree.

  There continues to be 0-day reports from Robert Morris @MIT. This time
  we include a fix for a crash in the COPY_NOTIFY operation.

  Highlights:
   - Bruce steps down as NFSD maintainer
   - Prepare for dynamic nfsd thread management
   - More work on supporting re-exporting NFS mounts
   - One fs/locks patch on behalf of Jeff Layton

  Notable bug fixes:
   - Fix zero-length NFSv3 WRITEs
   - Fix directory cinfo on FS's that do not support iversion
   - Fix WRITE verifiers for stable writes
   - Fix crash on COPY_NOTIFY with a special state ID"

* tag 'nfsd-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (51 commits)
  SUNRPC: Fix sockaddr handling in svcsock_accept_class trace points
  SUNRPC: Fix sockaddr handling in the svc_xprt_create_error trace point
  fs/locks: fix fcntl_getlk64/fcntl_setlk64 stub prototypes
  nfsd: fix crash on COPY_NOTIFY with special stateid
  MAINTAINERS: remove bfields
  NFSD: Move fill_pre_wcc() and fill_post_wcc()
  Revert "nfsd: skip some unnecessary stats in the v4 case"
  NFSD: Trace boot verifier resets
  NFSD: Rename boot verifier functions
  NFSD: Clean up the nfsd_net::nfssvc_boot field
  NFSD: Write verifier might go backwards
  nfsd: Add a tracepoint for errors in nfsd4_clone_file_range()
  NFSD: De-duplicate net_generic(nf->nf_net, nfsd_net_id)
  NFSD: De-duplicate net_generic(SVC_NET(rqstp), nfsd_net_id)
  NFSD: Clean up nfsd_vfs_write()
  nfsd: Replace use of rwsem with errseq_t
  NFSD: Fix verifier returned in stable WRITEs
  nfsd: Retry once in nfsd_open on an -EOPENSTALE return
  nfsd: Add errno mapping for EREMOTEIO
  nfsd: map EBADF
  ...

MAINTAINERS

@@ -7417,7 +7417,6 @@ F:	include/uapi/scsi/fc/
 
 FILE LOCKING (flock() and fcntl()/lockf())
 M:	Jeff Layton <jlayton@kernel.org>
-M:	"J. Bruce Fields" <bfields@fieldses.org>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	fs/fcntl.c
@@ -10428,12 +10427,11 @@ S:	Odd Fixes
 W:	http://kernelnewbies.org/KernelJanitors
 
 KERNEL NFSD, SUNRPC, AND LOCKD SERVERS
-M:	"J. Bruce Fields" <bfields@fieldses.org>
 M:	Chuck Lever <chuck.lever@oracle.com>
 L:	linux-nfs@vger.kernel.org
 S:	Supported
 W:	http://nfs.sourceforge.net/
-T:	git git://linux-nfs.org/~bfields/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux.git
 F:	fs/lockd/
 F:	fs/nfs_common/
 F:	fs/nfsd/

fs/lockd/svc.c

@@ -54,13 +54,9 @@ EXPORT_SYMBOL_GPL(nlmsvc_ops);
 
 static DEFINE_MUTEX(nlmsvc_mutex);
 static unsigned int		nlmsvc_users;
-static struct task_struct	*nlmsvc_task;
-static struct svc_rqst		*nlmsvc_rqst;
+static struct svc_serv		*nlmsvc_serv;
 unsigned long			nlmsvc_timeout;
 
-static atomic_t nlm_ntf_refcnt = ATOMIC_INIT(0);
-static DECLARE_WAIT_QUEUE_HEAD(nlm_ntf_wq);
-
 unsigned int lockd_net_id;
 
 /*
@@ -184,7 +180,12 @@ lockd(void *vrqstp)
 	nlm_shutdown_hosts();
 	cancel_delayed_work_sync(&ln->grace_period_end);
 	locks_end_grace(&ln->lockd_manager);
-	return 0;
+
+	dprintk("lockd_down: service stopped\n");
+
+	svc_exit_thread(rqstp);
+
+	module_put_and_exit(0);
 }
 
 static int create_lockd_listener(struct svc_serv *serv, const char *name,
@@ -290,8 +291,8 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
 				__func__, net->ns.inum);
 		}
 	} else {
-		pr_err("%s: no users! task=%p, net=%x\n",
-			__func__, nlmsvc_task, net->ns.inum);
+		pr_err("%s: no users! net=%x\n",
+			__func__, net->ns.inum);
 		BUG();
 	}
 }
@@ -302,20 +303,16 @@ 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) ||
-	    !atomic_inc_not_zero(&nlm_ntf_refcnt))
+	if (event != NETDEV_DOWN)
 		goto out;
 
-	if (nlmsvc_rqst) {
+	if (nlmsvc_serv) {
 		dprintk("lockd_inetaddr_event: removed %pI4\n",
 			&ifa->ifa_local);
 		sin.sin_family = AF_INET;
 		sin.sin_addr.s_addr = ifa->ifa_local;
-		svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
-			(struct sockaddr *)&sin);
+		svc_age_temp_xprts_now(nlmsvc_serv, (struct sockaddr *)&sin);
 	}
-	atomic_dec(&nlm_ntf_refcnt);
-	wake_up(&nlm_ntf_wq);
 
 out:
 	return NOTIFY_DONE;
@@ -332,21 +329,17 @@ 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) ||
-	    !atomic_inc_not_zero(&nlm_ntf_refcnt))
+	if (event != NETDEV_DOWN)
 		goto out;
 
-	if (nlmsvc_rqst) {
+	if (nlmsvc_serv) {
 		dprintk("lockd_inet6addr_event: removed %pI6\n", &ifa->addr);
 		sin6.sin6_family = AF_INET6;
 		sin6.sin6_addr = ifa->addr;
 		if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
 			sin6.sin6_scope_id = ifa->idev->dev->ifindex;
-		svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
-			(struct sockaddr *)&sin6);
+		svc_age_temp_xprts_now(nlmsvc_serv, (struct sockaddr *)&sin6);
 	}
-	atomic_dec(&nlm_ntf_refcnt);
-	wake_up(&nlm_ntf_wq);
 
 out:
 	return NOTIFY_DONE;
@@ -357,86 +350,22 @@ static struct notifier_block lockd_inet6addr_notifier = {
 };
 #endif
 
-static void lockd_unregister_notifiers(void)
-{
-	unregister_inetaddr_notifier(&lockd_inetaddr_notifier);
-#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);
-}
-
-static int lockd_start_svc(struct svc_serv *serv)
-{
-	int error;
-
-	if (nlmsvc_rqst)
-		return 0;
-
-	/*
-	 * Create the kernel thread and wait for it to start.
-	 */
-	nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
-	if (IS_ERR(nlmsvc_rqst)) {
-		error = PTR_ERR(nlmsvc_rqst);
-		printk(KERN_WARNING
-			"lockd_up: svc_rqst allocation failed, error=%d\n",
-			error);
-		lockd_unregister_notifiers();
-		goto out_rqst;
-	}
-
-	atomic_inc(&nlm_ntf_refcnt);
-	svc_sock_update_bufs(serv);
-	serv->sv_maxconn = nlm_max_connections;
-
-	nlmsvc_task = kthread_create(lockd, nlmsvc_rqst, "%s", serv->sv_name);
-	if (IS_ERR(nlmsvc_task)) {
-		error = PTR_ERR(nlmsvc_task);
-		printk(KERN_WARNING
-			"lockd_up: kthread_run failed, error=%d\n", error);
-		goto out_task;
-	}
-	nlmsvc_rqst->rq_task = nlmsvc_task;
-	wake_up_process(nlmsvc_task);
-
-	dprintk("lockd_up: service started\n");
-	return 0;
-
-out_task:
-	lockd_svc_exit_thread();
-	nlmsvc_task = NULL;
-out_rqst:
-	nlmsvc_rqst = NULL;
-	return error;
-}
-
 static const struct svc_serv_ops lockd_sv_ops = {
 	.svo_shutdown		= svc_rpcb_cleanup,
+	.svo_function		= lockd,
 	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
+	.svo_module		= THIS_MODULE,
 };
 
-static struct svc_serv *lockd_create_svc(void)
+static int lockd_get(void)
 {
 	struct svc_serv *serv;
+	int error;
 
-	/*
-	 * Check whether we're already up and running.
-	 */
-	if (nlmsvc_rqst) {
-		/*
-		 * Note: increase service usage, because later in case of error
-		 * svc_destroy() will be called.
-		 */
-		svc_get(nlmsvc_rqst->rq_server);
-		return nlmsvc_rqst->rq_server;
+	if (nlmsvc_serv) {
+		svc_get(nlmsvc_serv);
+		nlmsvc_users++;
+		return 0;
 	}
 
 	/*
@@ -454,14 +383,41 @@ static struct svc_serv *lockd_create_svc(void)
 	serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, &lockd_sv_ops);
 	if (!serv) {
 		printk(KERN_WARNING "lockd_up: create service failed\n");
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	}
+
+	serv->sv_maxconn = nlm_max_connections;
+	error = svc_set_num_threads(serv, NULL, 1);
+	/* The thread now holds the only reference */
+	svc_put(serv);
+	if (error < 0)
+		return error;
+
+	nlmsvc_serv = serv;
 	register_inetaddr_notifier(&lockd_inetaddr_notifier);
 #if IS_ENABLED(CONFIG_IPV6)
 	register_inet6addr_notifier(&lockd_inet6addr_notifier);
 #endif
 	dprintk("lockd_up: service created\n");
-	return serv;
+	nlmsvc_users++;
+	return 0;
+}
+
+static void lockd_put(void)
+{
+	if (WARN(nlmsvc_users <= 0, "lockd_down: no users!\n"))
+		return;
+	if (--nlmsvc_users)
+		return;
+
+	unregister_inetaddr_notifier(&lockd_inetaddr_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
+	unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
+#endif
+
+	svc_set_num_threads(nlmsvc_serv, NULL, 0);
+	nlmsvc_serv = NULL;
+	dprintk("lockd_down: service destroyed\n");
 }
 
 /*
@@ -469,36 +425,21 @@ static struct svc_serv *lockd_create_svc(void)
  */
 int lockd_up(struct net *net, const struct cred *cred)
 {
-	struct svc_serv *serv;
 	int error;
 
 	mutex_lock(&nlmsvc_mutex);
 
-	serv = lockd_create_svc();
-	if (IS_ERR(serv)) {
-		error = PTR_ERR(serv);
-		goto err_create;
+	error = lockd_get();
+	if (error)
+		goto err;
+
+	error = lockd_up_net(nlmsvc_serv, net, cred);
+	if (error < 0) {
+		lockd_put();
+		goto err;
 	}
 
-	error = lockd_up_net(serv, net, cred);
-	if (error < 0) {
-		lockd_unregister_notifiers();
-		goto err_put;
-	}
-
-	error = lockd_start_svc(serv);
-	if (error < 0) {
-		lockd_down_net(serv, net);
-		goto err_put;
-	}
-	nlmsvc_users++;
-	/*
-	 * Note: svc_serv structures have an initial use count of 1,
-	 * so we exit through here on both success and failure.
-	 */
-err_put:
-	svc_destroy(serv);
-err_create:
+err:
 	mutex_unlock(&nlmsvc_mutex);
 	return error;
 }
@@ -511,27 +452,8 @@ void
 lockd_down(struct net *net)
 {
 	mutex_lock(&nlmsvc_mutex);
-	lockd_down_net(nlmsvc_rqst->rq_server, net);
-	if (nlmsvc_users) {
-		if (--nlmsvc_users)
-			goto out;
-	} else {
-		printk(KERN_ERR "lockd_down: no users! task=%p\n",
-			nlmsvc_task);
-		BUG();
-	}
-
-	if (!nlmsvc_task) {
-		printk(KERN_ERR "lockd_down: no lockd running.\n");
-		BUG();
-	}
-	kthread_stop(nlmsvc_task);
-	dprintk("lockd_down: service stopped\n");
-	lockd_svc_exit_thread();
-	dprintk("lockd_down: service destroyed\n");
-	nlmsvc_task = NULL;
-	nlmsvc_rqst = NULL;
-out:
+	lockd_down_net(nlmsvc_serv, net);
+	lockd_put();
 	mutex_unlock(&nlmsvc_mutex);
 }
 EXPORT_SYMBOL_GPL(lockd_down);

fs/lockd/svclock.c

@@ -470,8 +470,10 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 	    struct nlm_host *host, struct nlm_lock *lock, int wait,
 	    struct nlm_cookie *cookie, int reclaim)
 {
-	struct nlm_block	*block = NULL;
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct inode		*inode = nlmsvc_file_inode(file);
+#endif
+	struct nlm_block	*block = NULL;
 	int			error;
 	int			mode;
 	int			async_block = 0;
@@ -484,7 +486,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 				(long long)lock->fl.fl_end,
 				wait);
 
-	if (inode->i_sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS) {
+	if (nlmsvc_file_file(file)->f_op->lock) {
 		async_block = wait;
 		wait = 0;
 	}

fs/nfs/callback.c

@@ -169,12 +169,12 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt,
 	if (nrservs < NFS4_MIN_NR_CALLBACK_THREADS)
 		nrservs = NFS4_MIN_NR_CALLBACK_THREADS;
 
-	if (serv->sv_nrthreads-1 == nrservs)
+	if (serv->sv_nrthreads == nrservs)
 		return 0;
 
-	ret = serv->sv_ops->svo_setup(serv, NULL, nrservs);
+	ret = svc_set_num_threads(serv, NULL, nrservs);
 	if (ret) {
-		serv->sv_ops->svo_setup(serv, NULL, 0);
+		svc_set_num_threads(serv, NULL, 0);
 		return ret;
 	}
 	dprintk("nfs_callback_up: service started\n");
@@ -235,14 +235,12 @@ err_bind:
 static const struct svc_serv_ops nfs40_cb_sv_ops = {
 	.svo_function		= nfs4_callback_svc,
 	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
-	.svo_setup		= svc_set_num_threads_sync,
 	.svo_module		= THIS_MODULE,
 };
 #if defined(CONFIG_NFS_V4_1)
 static const struct svc_serv_ops nfs41_cb_sv_ops = {
 	.svo_function		= nfs41_callback_svc,
 	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
-	.svo_setup		= svc_set_num_threads_sync,
 	.svo_module		= THIS_MODULE,
 };
 
@@ -266,14 +264,8 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 	/*
 	 * Check whether we're already up and running.
 	 */
-	if (cb_info->serv) {
-		/*
-		 * Note: increase service usage, because later in case of error
-		 * svc_destroy() will be called.
-		 */
-		svc_get(cb_info->serv);
-		return cb_info->serv;
-	}
+	if (cb_info->serv)
+		return svc_get(cb_info->serv);
 
 	switch (minorversion) {
 	case 0:
@@ -294,7 +286,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 		printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n",
 			cb_info->users);
 
-	serv = svc_create_pooled(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops);
+	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops);
 	if (!serv) {
 		printk(KERN_ERR "nfs_callback_create_svc: create service failed\n");
 		return ERR_PTR(-ENOMEM);
@@ -335,16 +327,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 		goto err_start;
 
 	cb_info->users++;
-	/*
-	 * svc_create creates the svc_serv with sv_nrthreads == 1, and then
-	 * svc_prepare_thread increments that. So we need to call svc_destroy
-	 * on both success and failure so that the refcount is 1 when the
-	 * thread exits.
-	 */
 err_net:
 	if (!cb_info->users)
 		cb_info->serv = NULL;
-	svc_destroy(serv);
+	svc_put(serv);
 err_create:
 	mutex_unlock(&nfs_callback_mutex);
 	return ret;
@@ -369,8 +355,8 @@ void nfs_callback_down(int minorversion, struct net *net)
 	cb_info->users--;
 	if (cb_info->users == 0) {
 		svc_get(serv);
-		serv->sv_ops->svo_setup(serv, NULL, 0);
-		svc_destroy(serv);
+		svc_set_num_threads(serv, NULL, 0);
+		svc_put(serv);
 		dprintk("nfs_callback_down: service destroyed\n");
 		cb_info->serv = NULL;
 	}

fs/nfs/export.c

@@ -158,5 +158,5 @@ const struct export_operations nfs_export_ops = {
 	.fetch_iversion = nfs_fetch_iversion,
 	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK|
 		EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS|
-		EXPORT_OP_NOATOMIC_ATTR|EXPORT_OP_SYNC_LOCKS,
+		EXPORT_OP_NOATOMIC_ATTR,
 };

fs/nfsd/filecache.c

@@ -44,12 +44,9 @@ struct nfsd_fcache_bucket {
 static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
 
 struct nfsd_fcache_disposal {
-	struct list_head list;
 	struct work_struct work;
-	struct net *net;
 	spinlock_t lock;
 	struct list_head freeme;
-	struct rcu_head rcu;
 };
 
 static struct workqueue_struct *nfsd_filecache_wq __read_mostly;
@@ -62,8 +59,6 @@ static long				nfsd_file_lru_flags;
 static struct fsnotify_group		*nfsd_file_fsnotify_group;
 static atomic_long_t			nfsd_filecache_count;
 static struct delayed_work		nfsd_filecache_laundrette;
-static DEFINE_SPINLOCK(laundrette_lock);
-static LIST_HEAD(laundrettes);
 
 static void nfsd_file_gc(void);
 
@@ -194,7 +189,6 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval,
 				__set_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags);
 		}
 		nf->nf_mark = NULL;
-		init_rwsem(&nf->nf_rwsem);
 		trace_nfsd_file_alloc(nf);
 	}
 	return nf;
@@ -249,7 +243,7 @@ nfsd_file_do_unhash(struct nfsd_file *nf)
 	trace_nfsd_file_unhash(nf);
 
 	if (nfsd_file_check_write_error(nf))
-		nfsd_reset_boot_verifier(net_generic(nf->nf_net, nfsd_net_id));
+		nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id));
 	--nfsd_file_hashtbl[nf->nf_hashval].nfb_count;
 	hlist_del_rcu(&nf->nf_node);
 	atomic_long_dec(&nfsd_filecache_count);
@@ -367,19 +361,13 @@ nfsd_file_list_remove_disposal(struct list_head *dst,
 static void
 nfsd_file_list_add_disposal(struct list_head *files, struct net *net)
 {
-	struct nfsd_fcache_disposal *l;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct nfsd_fcache_disposal *l = nn->fcache_disposal;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(l, &laundrettes, list) {
-		if (l->net == net) {
-			spin_lock(&l->lock);
-			list_splice_tail_init(files, &l->freeme);
-			spin_unlock(&l->lock);
-			queue_work(nfsd_filecache_wq, &l->work);
-			break;
-		}
-	}
-	rcu_read_unlock();
+	spin_lock(&l->lock);
+	list_splice_tail_init(files, &l->freeme);
+	spin_unlock(&l->lock);
+	queue_work(nfsd_filecache_wq, &l->work);
 }
 
 static void
@@ -755,7 +743,7 @@ nfsd_file_cache_purge(struct net *net)
 }
 
 static struct nfsd_fcache_disposal *
-nfsd_alloc_fcache_disposal(struct net *net)
+nfsd_alloc_fcache_disposal(void)
 {
 	struct nfsd_fcache_disposal *l;
 
@@ -763,7 +751,6 @@ nfsd_alloc_fcache_disposal(struct net *net)
 	if (!l)
 		return NULL;
 	INIT_WORK(&l->work, nfsd_file_delayed_close);
-	l->net = net;
 	spin_lock_init(&l->lock);
 	INIT_LIST_HEAD(&l->freeme);
 	return l;
@@ -772,61 +759,27 @@ nfsd_alloc_fcache_disposal(struct net *net)
 static void
 nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l)
 {
-	rcu_assign_pointer(l->net, NULL);
 	cancel_work_sync(&l->work);
 	nfsd_file_dispose_list(&l->freeme);
-	kfree_rcu(l, rcu);
-}
-
-static void
-nfsd_add_fcache_disposal(struct nfsd_fcache_disposal *l)
-{
-	spin_lock(&laundrette_lock);
-	list_add_tail_rcu(&l->list, &laundrettes);
-	spin_unlock(&laundrette_lock);
-}
-
-static void
-nfsd_del_fcache_disposal(struct nfsd_fcache_disposal *l)
-{
-	spin_lock(&laundrette_lock);
-	list_del_rcu(&l->list);
-	spin_unlock(&laundrette_lock);
-}
-
-static int
-nfsd_alloc_fcache_disposal_net(struct net *net)
-{
-	struct nfsd_fcache_disposal *l;
-
-	l = nfsd_alloc_fcache_disposal(net);
-	if (!l)
-		return -ENOMEM;
-	nfsd_add_fcache_disposal(l);
-	return 0;
+	kfree(l);
 }
 
 static void
 nfsd_free_fcache_disposal_net(struct net *net)
 {
-	struct nfsd_fcache_disposal *l;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct nfsd_fcache_disposal *l = nn->fcache_disposal;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(l, &laundrettes, list) {
-		if (l->net != net)
-			continue;
-		nfsd_del_fcache_disposal(l);
-		rcu_read_unlock();
-		nfsd_free_fcache_disposal(l);
-		return;
-	}
-	rcu_read_unlock();
+	nfsd_free_fcache_disposal(l);
 }
 
 int
 nfsd_file_cache_start_net(struct net *net)
 {
-	return nfsd_alloc_fcache_disposal_net(net);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	nn->fcache_disposal = nfsd_alloc_fcache_disposal();
+	return nn->fcache_disposal ? 0 : -ENOMEM;
 }
 
 void

fs/nfsd/filecache.h

@@ -46,7 +46,6 @@ struct nfsd_file {
 	refcount_t		nf_ref;
 	unsigned char		nf_may;
 	struct nfsd_file_mark	*nf_mark;
-	struct rw_semaphore	nf_rwsem;
 };
 
 int nfsd_file_cache_init(void);

fs/nfsd/netns.h

@@ -11,6 +11,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <linux/percpu_counter.h>
+#include <linux/siphash.h>
 
 /* Hash tables for nfs4_clientid state */
 #define CLIENT_HASH_BITS                 4
@@ -108,9 +109,8 @@ struct nfsd_net {
 	bool nfsd_net_up;
 	bool lockd_up;
 
-	/* Time of server startup */
-	struct timespec64 nfssvc_boot;
-	seqlock_t boot_lock;
+	seqlock_t writeverf_lock;
+	unsigned char writeverf[8];
 
 	/*
 	 * Max number of connections this nfsd container will allow. Defaults
@@ -123,12 +123,13 @@ struct nfsd_net {
 	u32 clverifier_counter;
 
 	struct svc_serv *nfsd_serv;
-
-	wait_queue_head_t ntf_wq;
-	atomic_t ntf_refcnt;
-
-	/* Allow umount to wait for nfsd state cleanup */
-	struct completion nfsd_shutdown_complete;
+	/* When a listening socket is added to nfsd, keep_active is set
+	 * and this justifies a reference on nfsd_serv.  This stops
+	 * nfsd_serv from being freed.  When the number of threads is
+	 * set, keep_active is cleared and the reference is dropped.  So
+	 * when the last thread exits, the service will be destroyed.
+	 */
+	int keep_active;
 
 	/*
 	 * clientid and stateid data for construction of net unique COPY
@@ -184,6 +185,10 @@ struct nfsd_net {
 
 	/* utsname taken from the process that starts the server */
 	char			nfsd_name[UNX_MAXNODENAME+1];
+
+	struct nfsd_fcache_disposal *fcache_disposal;
+
+	siphash_key_t		siphash_key;
 };
 
 /* Simple check to find out if a given net was properly initialized */
@@ -193,6 +198,6 @@ extern void nfsd_netns_free_versions(struct nfsd_net *nn);
 
 extern unsigned int nfsd_net_id;
 
-void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn);
-void nfsd_reset_boot_verifier(struct nfsd_net *nn);
+void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
+void nfsd_reset_write_verifier(struct nfsd_net *nn);
 #endif /* __NFSD_NETNS_H__ */

fs/nfsd/nfs3proc.c

@@ -202,15 +202,11 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
 	fh_copy(&resp->fh, &argp->fh);
 	resp->committed = argp->stable;
 	nvecs = svc_fill_write_vector(rqstp, &argp->payload);
-	if (!nvecs) {
-		resp->status = nfserr_io;
-		goto out;
-	}
+
 	resp->status = nfsd_write(rqstp, &resp->fh, argp->offset,
 				  rqstp->rq_vec, nvecs, &cnt,
 				  resp->committed, resp->verf);
 	resp->count = cnt;
-out:
 	return rpc_success;
 }
 

fs/nfsd/nfs3xdr.c

@@ -487,71 +487,6 @@ neither:
 	return true;
 }
 
-static bool fs_supports_change_attribute(struct super_block *sb)
-{
-	return sb->s_flags & SB_I_VERSION || sb->s_export_op->fetch_iversion;
-}
-
-/*
- * Fill in the pre_op attr for the wcc data
- */
-void fill_pre_wcc(struct svc_fh *fhp)
-{
-	struct inode    *inode;
-	struct kstat	stat;
-	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
-
-	if (fhp->fh_no_wcc || fhp->fh_pre_saved)
-		return;
-	inode = d_inode(fhp->fh_dentry);
-	if (fs_supports_change_attribute(inode->i_sb) || !v4) {
-		__be32 err = fh_getattr(fhp, &stat);
-
-		if (err) {
-			/* Grab the times from inode anyway */
-			stat.mtime = inode->i_mtime;
-			stat.ctime = inode->i_ctime;
-			stat.size  = inode->i_size;
-		}
-		fhp->fh_pre_mtime = stat.mtime;
-		fhp->fh_pre_ctime = stat.ctime;
-		fhp->fh_pre_size  = stat.size;
-	}
-	if (v4)
-		fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
-
-	fhp->fh_pre_saved = true;
-}
-
-/*
- * Fill in the post_op attr for the wcc data
- */
-void fill_post_wcc(struct svc_fh *fhp)
-{
-	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
-	struct inode *inode = d_inode(fhp->fh_dentry);
-
-	if (fhp->fh_no_wcc)
-		return;
-
-	if (fhp->fh_post_saved)
-		printk("nfsd: inode locked twice during operation.\n");
-
-	fhp->fh_post_saved = true;
-
-	if (fs_supports_change_attribute(inode->i_sb) || !v4) {
-		__be32 err = fh_getattr(fhp, &fhp->fh_post_attr);
-
-		if (err) {
-			fhp->fh_post_saved = false;
-			fhp->fh_post_attr.ctime = inode->i_ctime;
-		}
-	}
-	if (v4)
-		fhp->fh_post_change =
-			nfsd4_change_attribute(&fhp->fh_post_attr, inode);
-}
-
 /*
  * XDR decode functions
  */

fs/nfsd/nfs4proc.c

@@ -598,7 +598,7 @@ static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
 
 	BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data));
 
-	nfsd_copy_boot_verifier(verf, net_generic(net, nfsd_net_id));
+	nfsd_copy_write_verifier(verf, net_generic(net, nfsd_net_id));
 }
 
 static __be32
@@ -1101,7 +1101,7 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out;
 
-	status = nfsd4_clone_file_range(src, clone->cl_src_pos,
+	status = nfsd4_clone_file_range(rqstp, src, clone->cl_src_pos,
 			dst, clone->cl_dst_pos, clone->cl_count,
 			EX_ISSYNC(cstate->current_fh.fh_export));
 
@@ -1510,11 +1510,14 @@ static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync)
 
 static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
 {
+	struct file *dst = copy->nf_dst->nf_file;
+	struct file *src = copy->nf_src->nf_file;
+	errseq_t since;
 	ssize_t bytes_copied = 0;
 	u64 bytes_total = copy->cp_count;
 	u64 src_pos = copy->cp_src_pos;
 	u64 dst_pos = copy->cp_dst_pos;
-	__be32 status;
+	int status;
 
 	/* See RFC 7862 p.67: */
 	if (bytes_total == 0)
@@ -1522,9 +1525,8 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
 	do {
 		if (kthread_should_stop())
 			break;
-		bytes_copied = nfsd_copy_file_range(copy->nf_src->nf_file,
-				src_pos, copy->nf_dst->nf_file, dst_pos,
-				bytes_total);
+		bytes_copied = nfsd_copy_file_range(src, src_pos, dst, dst_pos,
+						    bytes_total);
 		if (bytes_copied <= 0)
 			break;
 		bytes_total -= bytes_copied;
@@ -1534,11 +1536,11 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
 	} while (bytes_total > 0 && !copy->cp_synchronous);
 	/* for a non-zero asynchronous copy do a commit of data */
 	if (!copy->cp_synchronous && copy->cp_res.wr_bytes_written > 0) {
-		down_write(&copy->nf_dst->nf_rwsem);
-		status = vfs_fsync_range(copy->nf_dst->nf_file,
-					 copy->cp_dst_pos,
+		since = READ_ONCE(dst->f_wb_err);
+		status = vfs_fsync_range(dst, copy->cp_dst_pos,
 					 copy->cp_res.wr_bytes_written, 0);
-		up_write(&copy->nf_dst->nf_rwsem);
+		if (!status)
+			status = filemap_check_wb_err(dst->f_mapping, since);
 		if (!status)
 			copy->committed = true;
 	}
@@ -2528,7 +2530,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 			goto encode_op;
 		}
 
-		fh_clear_wcc(current_fh);
+		fh_clear_pre_post_attrs(current_fh);
 
 		/* If op is non-idempotent */
 		if (op->opdesc->op_flags & OP_MODIFIES_SOMETHING) {

fs/nfsd/nfs4state.c

@@ -246,6 +246,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 	list_for_each_entry(cur, &lo->lo_blocked, nbl_list) {
 		if (fh_match(fh, &cur->nbl_fh)) {
 			list_del_init(&cur->nbl_list);
+			WARN_ON(list_empty(&cur->nbl_lru));
 			list_del_init(&cur->nbl_lru);
 			found = cur;
 			break;
@@ -271,6 +272,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 			INIT_LIST_HEAD(&nbl->nbl_lru);
 			fh_copy_shallow(&nbl->nbl_fh, fh);
 			locks_init_lock(&nbl->nbl_lock);
+			kref_init(&nbl->nbl_kref);
 			nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client,
 					&nfsd4_cb_notify_lock_ops,
 					NFSPROC4_CLNT_CB_NOTIFY_LOCK);
@@ -279,12 +281,21 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 	return nbl;
 }
 
+static void
+free_nbl(struct kref *kref)
+{
+	struct nfsd4_blocked_lock *nbl;
+
+	nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref);
+	kfree(nbl);
+}
+
 static void
 free_blocked_lock(struct nfsd4_blocked_lock *nbl)
 {
 	locks_delete_block(&nbl->nbl_lock);
 	locks_release_private(&nbl->nbl_lock);
-	kfree(nbl);
+	kref_put(&nbl->nbl_kref, free_nbl);
 }
 
 static void
@@ -302,6 +313,7 @@ remove_blocked_locks(struct nfs4_lockowner *lo)
 					struct nfsd4_blocked_lock,
 					nbl_list);
 		list_del_init(&nbl->nbl_list);
+		WARN_ON(list_empty(&nbl->nbl_lru));
 		list_move(&nbl->nbl_lru, &reaplist);
 	}
 	spin_unlock(&nn->blocked_locks_lock);
@@ -360,11 +372,13 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
  * st_{access,deny}_bmap field of the stateid, in order to track not
  * only what share bits are currently in force, but also what
  * combinations of share bits previous opens have used.  This allows us
- * to enforce the recommendation of rfc 3530 14.2.19 that the server
- * return an error if the client attempt to downgrade to a combination
- * of share bits not explicable by closing some of its previous opens.
+ * to enforce the recommendation in
+ * https://datatracker.ietf.org/doc/html/rfc7530#section-16.19.4 that
+ * the server return an error if the client attempt to downgrade to a
+ * combination of share bits not explicable by closing some of its
+ * previous opens.
  *
- * XXX: This enforcement is actually incomplete, since we don't keep
+ * This enforcement is arguably incomplete, since we don't keep
  * track of access/deny bit combinations; so, e.g., we allow:
  *
  *	OPEN allow read, deny write
@@ -372,6 +386,10 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
  *	DOWNGRADE allow read, deny none
  *
  * which we should reject.
+ *
+ * But you could also argue that our current code is already overkill,
+ * since it only exists to return NFS4ERR_INVAL on incorrect client
+ * behavior.
  */
 static unsigned int
 bmap_to_share_mode(unsigned long bmap)
@@ -6040,7 +6058,11 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		*nfp = NULL;
 
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) {
-		status = check_special_stateids(net, fhp, stateid, flags);
+		if (cstid)
+			status = nfserr_bad_stateid;
+		else
+			status = check_special_stateids(net, fhp, stateid,
+									flags);
 		goto done;
 	}
 
@@ -6836,7 +6858,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct nfsd4_blocked_lock *nbl = NULL;
 	struct file_lock *file_lock = NULL;
 	struct file_lock *conflock = NULL;
-	struct super_block *sb;
 	__be32 status = 0;
 	int lkflg;
 	int err;
@@ -6858,7 +6879,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		dprintk("NFSD: nfsd4_lock: permission denied!\n");
 		return status;
 	}
-	sb = cstate->current_fh.fh_dentry->d_sb;
 
 	if (lock->lk_is_new) {
 		if (nfsd4_has_session(cstate))
@@ -6910,8 +6930,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	fp = lock_stp->st_stid.sc_file;
 	switch (lock->lk_type) {
 		case NFS4_READW_LT:
-			if (nfsd4_has_session(cstate) &&
-			    !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS))
+			if (nfsd4_has_session(cstate))
 				fl_flags |= FL_SLEEP;
 			fallthrough;
 		case NFS4_READ_LT:
@@ -6923,8 +6942,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			fl_type = F_RDLCK;
 			break;
 		case NFS4_WRITEW_LT:
-			if (nfsd4_has_session(cstate) &&
-			    !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS))
+			if (nfsd4_has_session(cstate))
 				fl_flags |= FL_SLEEP;
 			fallthrough;
 		case NFS4_WRITE_LT:
@@ -6945,6 +6963,16 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 	}
 
+	/*
+	 * Most filesystems with their own ->lock operations will block
+	 * the nfsd thread waiting to acquire the lock.  That leads to
+	 * deadlocks (we don't want every nfsd thread tied up waiting
+	 * for file locks), so don't attempt blocking lock notifications
+	 * on those filesystems:
+	 */
+	if (nf->nf_file->f_op->lock)
+		fl_flags &= ~FL_SLEEP;
+
 	nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn);
 	if (!nbl) {
 		dprintk("NFSD: %s: unable to allocate block!\n", __func__);
@@ -6975,6 +7003,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		spin_lock(&nn->blocked_locks_lock);
 		list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
 		list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru);
+		kref_get(&nbl->nbl_kref);
 		spin_unlock(&nn->blocked_locks_lock);
 	}
 
@@ -6987,6 +7016,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			nn->somebody_reclaimed = true;
 		break;
 	case FILE_LOCK_DEFERRED:
+		kref_put(&nbl->nbl_kref, free_nbl);
 		nbl = NULL;
 		fallthrough;
 	case -EAGAIN:		/* conflock holds conflicting lock */
@@ -7007,8 +7037,13 @@ out:
 		/* dequeue it if we queued it before */
 		if (fl_flags & FL_SLEEP) {
 			spin_lock(&nn->blocked_locks_lock);
-			list_del_init(&nbl->nbl_list);
-			list_del_init(&nbl->nbl_lru);
+			if (!list_empty(&nbl->nbl_list) &&
+			    !list_empty(&nbl->nbl_lru)) {
+				list_del_init(&nbl->nbl_list);
+				list_del_init(&nbl->nbl_lru);
+				kref_put(&nbl->nbl_kref, free_nbl);
+			}
+			/* nbl can use one of lists to be linked to reaplist */
 			spin_unlock(&nn->blocked_locks_lock);
 		}
 		free_blocked_lock(nbl);

fs/nfsd/nfs4xdr.c

@@ -277,21 +277,10 @@ nfsd4_decode_verifier4(struct nfsd4_compoundargs *argp, nfs4_verifier *verf)
 static __be32
 nfsd4_decode_bitmap4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen)
 {
-	u32 i, count;
-	__be32 *p;
+	ssize_t status;
 
-	if (xdr_stream_decode_u32(argp->xdr, &count) < 0)
-		return nfserr_bad_xdr;
-	/* request sanity */
-	if (count > 1000)
-		return nfserr_bad_xdr;
-	p = xdr_inline_decode(argp->xdr, count << 2);
-	if (!p)
-		return nfserr_bad_xdr;
-	for (i = 0; i < bmlen; i++)
-		bmval[i] = (i < count) ? be32_to_cpup(p++) : 0;
-
-	return nfs_ok;
+	status = xdr_stream_decode_uint32_array(argp->xdr, bmval, bmlen);
+	return status == -EBADMSG ? nfserr_bad_xdr : nfs_ok;
 }
 
 static __be32
@@ -4804,8 +4793,8 @@ nfsd4_encode_read_plus_hole(struct nfsd4_compoundres *resp,
 		return nfserr_resource;
 
 	*p++ = htonl(NFS4_CONTENT_HOLE);
-	 p   = xdr_encode_hyper(p, read->rd_offset);
-	 p   = xdr_encode_hyper(p, count);
+	p = xdr_encode_hyper(p, read->rd_offset);
+	p = xdr_encode_hyper(p, count);
 
 	*eof = (read->rd_offset + count) >= f_size;
 	*maxcount = min_t(unsigned long, count, *maxcount);

fs/nfsd/nfscache.c

@@ -87,7 +87,7 @@ nfsd_hashsize(unsigned int limit)
 static u32
 nfsd_cache_hash(__be32 xid, struct nfsd_net *nn)
 {
-	return hash_32(be32_to_cpu(xid), nn->maskbits);
+	return hash_32((__force u32)xid, nn->maskbits);
 }
 
 static struct svc_cacherep *

fs/nfsd/nfsctl.c

@@ -742,13 +742,12 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 		return err;
 
 	err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
-	if (err < 0) {
-		nfsd_destroy(net);
-		return err;
-	}
 
-	/* Decrease the count, but don't shut down the service */
-	nn->nfsd_serv->sv_nrthreads--;
+	if (err >= 0 &&
+	    !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
+		svc_get(nn->nfsd_serv);
+
+	nfsd_put(net);
 	return err;
 }
 
@@ -783,8 +782,10 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
 	if (err < 0 && err != -EAFNOSUPPORT)
 		goto out_close;
 
-	/* Decrease the count, but don't shut down the service */
-	nn->nfsd_serv->sv_nrthreads--;
+	if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
+		svc_get(nn->nfsd_serv);
+
+	nfsd_put(net);
 	return 0;
 out_close:
 	xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port);
@@ -793,10 +794,7 @@ out_close:
 		svc_xprt_put(xprt);
 	}
 out_err:
-	if (!list_empty(&nn->nfsd_serv->sv_permsocks))
-		nn->nfsd_serv->sv_nrthreads--;
-	 else
-		nfsd_destroy(net);
+	nfsd_put(net);
 	return err;
 }
 
@@ -1485,9 +1483,8 @@ static __net_init int nfsd_init_net(struct net *net)
 	nn->clientid_counter = nn->clientid_base + 1;
 	nn->s2s_cp_cl_id = nn->clientid_counter++;
 
-	atomic_set(&nn->ntf_refcnt, 0);
-	init_waitqueue_head(&nn->ntf_wq);
-	seqlock_init(&nn->boot_lock);
+	get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key));
+	seqlock_init(&nn->writeverf_lock);
 
 	return 0;
 

fs/nfsd/nfsd.h

@@ -97,7 +97,7 @@ int		nfsd_pool_stats_open(struct inode *, struct file *);
 int		nfsd_pool_stats_release(struct inode *, struct file *);
 void		nfsd_shutdown_threads(struct net *net);
 
-void		nfsd_destroy(struct net *net);
+void		nfsd_put(struct net *net);
 
 bool		i_am_nfsd(void);
 

fs/nfsd/nfsfh.c

@@ -611,6 +611,70 @@ out_negative:
 	return nfserr_serverfault;
 }
 
+#ifdef CONFIG_NFSD_V3
+
+/**
+ * fh_fill_pre_attrs - Fill in pre-op attributes
+ * @fhp: file handle to be updated
+ *
+ */
+void fh_fill_pre_attrs(struct svc_fh *fhp)
+{
+	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
+	struct inode *inode;
+	struct kstat stat;
+	__be32 err;
+
+	if (fhp->fh_no_wcc || fhp->fh_pre_saved)
+		return;
+
+	inode = d_inode(fhp->fh_dentry);
+	err = fh_getattr(fhp, &stat);
+	if (err) {
+		/* Grab the times from inode anyway */
+		stat.mtime = inode->i_mtime;
+		stat.ctime = inode->i_ctime;
+		stat.size  = inode->i_size;
+	}
+	if (v4)
+		fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
+
+	fhp->fh_pre_mtime = stat.mtime;
+	fhp->fh_pre_ctime = stat.ctime;
+	fhp->fh_pre_size  = stat.size;
+	fhp->fh_pre_saved = true;
+}
+
+/**
+ * fh_fill_post_attrs - Fill in post-op attributes
+ * @fhp: file handle to be updated
+ *
+ */
+void fh_fill_post_attrs(struct svc_fh *fhp)
+{
+	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
+	struct inode *inode = d_inode(fhp->fh_dentry);
+	__be32 err;
+
+	if (fhp->fh_no_wcc)
+		return;
+
+	if (fhp->fh_post_saved)
+		printk("nfsd: inode locked twice during operation.\n");
+
+	err = fh_getattr(fhp, &fhp->fh_post_attr);
+	if (err) {
+		fhp->fh_post_saved = false;
+		fhp->fh_post_attr.ctime = inode->i_ctime;
+	} else
+		fhp->fh_post_saved = true;
+	if (v4)
+		fhp->fh_post_change =
+			nfsd4_change_attribute(&fhp->fh_post_attr, inode);
+}
+
+#endif /* CONFIG_NFSD_V3 */
+
 /*
  * Release a file handle.
  */
@@ -623,7 +687,7 @@ fh_put(struct svc_fh *fhp)
 		fh_unlock(fhp);
 		fhp->fh_dentry = NULL;
 		dput(dentry);
-		fh_clear_wcc(fhp);
+		fh_clear_pre_post_attrs(fhp);
 	}
 	fh_drop_write(fhp);
 	if (exp) {

fs/nfsd/nfsfh.h

@@ -284,12 +284,13 @@ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
 #endif
 
 #ifdef CONFIG_NFSD_V3
-/*
- * The wcc data stored in current_fh should be cleared
- * between compound ops.
+
+/**
+ * fh_clear_pre_post_attrs - Reset pre/post attributes
+ * @fhp: file handle to be updated
+ *
  */
-static inline void
-fh_clear_wcc(struct svc_fh *fhp)
+static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp)
 {
 	fhp->fh_post_saved = false;
 	fhp->fh_pre_saved = false;
@@ -323,13 +324,24 @@ static inline u64 nfsd4_change_attribute(struct kstat *stat,
 		return time_to_chattr(&stat->ctime);
 }
 
-extern void fill_pre_wcc(struct svc_fh *fhp);
-extern void fill_post_wcc(struct svc_fh *fhp);
-#else
-#define fh_clear_wcc(ignored)
-#define fill_pre_wcc(ignored)
-#define fill_post_wcc(notused)
-#endif /* CONFIG_NFSD_V3 */
+extern void fh_fill_pre_attrs(struct svc_fh *fhp);
+extern void fh_fill_post_attrs(struct svc_fh *fhp);
+
+#else /* !CONFIG_NFSD_V3 */
+
+static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp)
+{
+}
+
+static inline void fh_fill_pre_attrs(struct svc_fh *fhp)
+{
+}
+
+static inline void fh_fill_post_attrs(struct svc_fh *fhp)
+{
+}
+
+#endif /* !CONFIG_NFSD_V3 */
 
 
 /*
@@ -355,7 +367,7 @@ fh_lock_nested(struct svc_fh *fhp, unsigned int subclass)
 
 	inode = d_inode(dentry);
 	inode_lock_nested(inode, subclass);
-	fill_pre_wcc(fhp);
+	fh_fill_pre_attrs(fhp);
 	fhp->fh_locked = true;
 }
 
@@ -372,7 +384,7 @@ static inline void
 fh_unlock(struct svc_fh *fhp)
 {
 	if (fhp->fh_locked) {
-		fill_post_wcc(fhp);
+		fh_fill_post_attrs(fhp);
 		inode_unlock(d_inode(fhp->fh_dentry));
 		fhp->fh_locked = false;
 	}

fs/nfsd/nfsproc.c

@@ -235,10 +235,6 @@ nfsd_proc_write(struct svc_rqst *rqstp)
 		argp->len, argp->offset);
 
 	nvecs = svc_fill_write_vector(rqstp, &argp->payload);
-	if (!nvecs) {
-		resp->status = nfserr_io;
-		goto out;
-	}
 
 	resp->status = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh),
 				  argp->offset, rqstp->rq_vec, nvecs,
@@ -247,7 +243,6 @@ nfsd_proc_write(struct svc_rqst *rqstp)
 		resp->status = fh_getattr(&resp->fh, &resp->stat);
 	else if (resp->status == nfserr_jukebox)
 		return rpc_drop_reply;
-out:
 	return rpc_success;
 }
 
@@ -850,6 +845,7 @@ nfserrno (int errno)
 		{ nfserr_io, -EIO },
 		{ nfserr_nxio, -ENXIO },
 		{ nfserr_fbig, -E2BIG },
+		{ nfserr_stale, -EBADF },
 		{ nfserr_acces, -EACCES },
 		{ nfserr_exist, -EEXIST },
 		{ nfserr_xdev, -EXDEV },
@@ -878,6 +874,8 @@ nfserrno (int errno)
 		{ nfserr_toosmall, -ETOOSMALL },
 		{ nfserr_serverfault, -ESERVERFAULT },
 		{ nfserr_serverfault, -ENFILE },
+		{ nfserr_io, -EREMOTEIO },
+		{ nfserr_stale, -EOPENSTALE },
 		{ nfserr_io, -EUCLEAN },
 		{ nfserr_perm, -ENOKEY },
 		{ nfserr_no_grace, -ENOGRACE},

fs/nfsd/nfssvc.c

@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/fs_struct.h>
 #include <linux/swap.h>
+#include <linux/siphash.h>
 
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/svcsock.h>
@@ -55,18 +56,17 @@ static __be32			nfsd_init_request(struct svc_rqst *,
 						struct svc_process_info *);
 
 /*
- * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members
- * of the svc_serv struct. In particular, ->sv_nrthreads but also to some
- * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt
+ * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members
+ * of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks.
  *
  * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
- * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number
- * of nfsd threads must exist and each must listed in ->sp_all_threads in each
- * entry of ->sv_pools[].
+ * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless
+ * nn->keep_active is set).  That number of nfsd threads must
+ * exist and each must be listed in ->sp_all_threads in some entry of
+ * ->sv_pools[].
  *
- * Transitions of the thread count between zero and non-zero are of particular
- * interest since the svc_serv needs to be created and initialized at that
- * point, or freed.
+ * Each active thread holds a counted reference on nn->nfsd_serv, as does
+ * the nn->keep_active flag and various transient calls to svc_get().
  *
  * Finally, the nfsd_mutex also protects some of the global variables that are
  * accessed when nfsd starts and that are settable via the write_* routines in
@@ -345,33 +345,57 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn)
 	return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST);
 }
 
-void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn)
+/**
+ * nfsd_copy_write_verifier - Atomically copy a write verifier
+ * @verf: buffer in which to receive the verifier cookie
+ * @nn: NFS net namespace
+ *
+ * This function provides a wait-free mechanism for copying the
+ * namespace's write verifier without tearing it.
+ */
+void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn)
 {
 	int seq = 0;
 
 	do {
-		read_seqbegin_or_lock(&nn->boot_lock, &seq);
-		/*
-		 * This is opaque to client, so no need to byte-swap. Use
-		 * __force to keep sparse happy. y2038 time_t overflow is
-		 * irrelevant in this usage
-		 */
-		verf[0] = (__force __be32)nn->nfssvc_boot.tv_sec;
-		verf[1] = (__force __be32)nn->nfssvc_boot.tv_nsec;
-	} while (need_seqretry(&nn->boot_lock, seq));
-	done_seqretry(&nn->boot_lock, seq);
+		read_seqbegin_or_lock(&nn->writeverf_lock, &seq);
+		memcpy(verf, nn->writeverf, sizeof(*verf));
+	} while (need_seqretry(&nn->writeverf_lock, seq));
+	done_seqretry(&nn->writeverf_lock, seq);
 }
 
-static void nfsd_reset_boot_verifier_locked(struct nfsd_net *nn)
+static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn)
 {
-	ktime_get_real_ts64(&nn->nfssvc_boot);
+	struct timespec64 now;
+	u64 verf;
+
+	/*
+	 * Because the time value is hashed, y2038 time_t overflow
+	 * is irrelevant in this usage.
+	 */
+	ktime_get_raw_ts64(&now);
+	verf = siphash_2u64(now.tv_sec, now.tv_nsec, &nn->siphash_key);
+	memcpy(nn->writeverf, &verf, sizeof(nn->writeverf));
 }
 
-void nfsd_reset_boot_verifier(struct nfsd_net *nn)
+/**
+ * nfsd_reset_write_verifier - Generate a new write verifier
+ * @nn: NFS net namespace
+ *
+ * This function updates the ->writeverf field of @nn. This field
+ * contains an opaque cookie that, according to Section 18.32.3 of
+ * RFC 8881, "the client can use to determine whether a server has
+ * changed instance state (e.g., server restart) between a call to
+ * WRITE and a subsequent call to either WRITE or COMMIT.  This
+ * cookie MUST be unchanged during a single instance of the NFSv4.1
+ * server and MUST be unique between instances of the NFSv4.1
+ * server."
+ */
+void nfsd_reset_write_verifier(struct nfsd_net *nn)
 {
-	write_seqlock(&nn->boot_lock);
-	nfsd_reset_boot_verifier_locked(nn);
-	write_sequnlock(&nn->boot_lock);
+	write_seqlock(&nn->writeverf_lock);
+	nfsd_reset_write_verifier_locked(nn);
+	write_sequnlock(&nn->writeverf_lock);
 }
 
 static int nfsd_startup_net(struct net *net, const struct cred *cred)
@@ -435,6 +459,7 @@ static void nfsd_shutdown_net(struct net *net)
 	nfsd_shutdown_generic();
 }
 
+static DEFINE_SPINLOCK(nfsd_notifier_lock);
 static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
 	void *ptr)
 {
@@ -444,18 +469,17 @@ 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) ||
-	    !atomic_inc_not_zero(&nn->ntf_refcnt))
+	if (event != NETDEV_DOWN || !nn->nfsd_serv)
 		goto out;
 
+	spin_lock(&nfsd_notifier_lock);
 	if (nn->nfsd_serv) {
 		dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local);
 		sin.sin_family = AF_INET;
 		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);
+	spin_unlock(&nfsd_notifier_lock);
 
 out:
 	return NOTIFY_DONE;
@@ -475,10 +499,10 @@ 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) ||
-	    !atomic_inc_not_zero(&nn->ntf_refcnt))
+	if (event != NETDEV_DOWN || !nn->nfsd_serv)
 		goto out;
 
+	spin_lock(&nfsd_notifier_lock);
 	if (nn->nfsd_serv) {
 		dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr);
 		sin6.sin6_family = AF_INET6;
@@ -487,8 +511,8 @@ 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);
+	spin_unlock(&nfsd_notifier_lock);
+
 out:
 	return NOTIFY_DONE;
 }
@@ -505,7 +529,6 @@ 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);
@@ -513,7 +536,6 @@ 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
@@ -594,20 +616,9 @@ static const struct svc_serv_ops nfsd_thread_sv_ops = {
 	.svo_shutdown		= nfsd_last_thread,
 	.svo_function		= nfsd,
 	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
-	.svo_setup		= svc_set_num_threads,
 	.svo_module		= THIS_MODULE,
 };
 
-static void nfsd_complete_shutdown(struct net *net)
-{
-	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
-	WARN_ON(!mutex_is_locked(&nfsd_mutex));
-
-	nn->nfsd_serv = NULL;
-	complete(&nn->nfsd_shutdown_complete);
-}
-
 void nfsd_shutdown_threads(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
@@ -622,11 +633,9 @@ void nfsd_shutdown_threads(struct net *net)
 
 	svc_get(serv);
 	/* Kill outstanding nfsd threads */
-	serv->sv_ops->svo_setup(serv, NULL, 0);
-	nfsd_destroy(net);
+	svc_set_num_threads(serv, NULL, 0);
+	nfsd_put(net);
 	mutex_unlock(&nfsd_mutex);
-	/* Wait for shutdown of nfsd_serv to complete */
-	wait_for_completion(&nn->nfsd_shutdown_complete);
 }
 
 bool i_am_nfsd(void)
@@ -638,6 +647,7 @@ int nfsd_create_serv(struct net *net)
 {
 	int error;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_serv *serv;
 
 	WARN_ON(!mutex_is_locked(&nfsd_mutex));
 	if (nn->nfsd_serv) {
@@ -647,19 +657,23 @@ int nfsd_create_serv(struct net *net)
 	if (nfsd_max_blksize == 0)
 		nfsd_max_blksize = nfsd_get_default_max_blksize();
 	nfsd_reset_versions(nn);
-	nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
-						&nfsd_thread_sv_ops);
-	if (nn->nfsd_serv == NULL)
+	serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
+				 &nfsd_thread_sv_ops);
+	if (serv == NULL)
 		return -ENOMEM;
-	init_completion(&nn->nfsd_shutdown_complete);
 
-	nn->nfsd_serv->sv_maxconn = nn->max_connections;
-	error = svc_bind(nn->nfsd_serv, net);
+	serv->sv_maxconn = nn->max_connections;
+	error = svc_bind(serv, net);
 	if (error < 0) {
-		svc_destroy(nn->nfsd_serv);
-		nfsd_complete_shutdown(net);
+		/* NOT nfsd_put() as notifiers (see below) haven't
+		 * been set up yet.
+		 */
+		svc_put(serv);
 		return error;
 	}
+	spin_lock(&nfsd_notifier_lock);
+	nn->nfsd_serv = serv;
+	spin_unlock(&nfsd_notifier_lock);
 
 	set_max_drc();
 	/* check if the notifier is already set */
@@ -669,8 +683,7 @@ int nfsd_create_serv(struct net *net)
 		register_inet6addr_notifier(&nfsd_inet6addr_notifier);
 #endif
 	}
-	atomic_inc(&nn->ntf_refcnt);
-	nfsd_reset_boot_verifier(nn);
+	nfsd_reset_write_verifier(nn);
 	return 0;
 }
 
@@ -697,16 +710,26 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
 	return 0;
 }
 
-void nfsd_destroy(struct net *net)
+/* This is the callback for kref_put() below.
+ * There is no code here as the first thing to be done is
+ * call svc_shutdown_net(), but we cannot get the 'net' from
+ * the kref.  So do all the work when kref_put returns true.
+ */
+static void nfsd_noop(struct kref *ref)
+{
+}
+
+void nfsd_put(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-	int destroy = (nn->nfsd_serv->sv_nrthreads == 1);
 
-	if (destroy)
+	if (kref_put(&nn->nfsd_serv->sv_refcnt, nfsd_noop)) {
 		svc_shutdown_net(nn->nfsd_serv, net);
-	svc_destroy(nn->nfsd_serv);
-	if (destroy)
-		nfsd_complete_shutdown(net);
+		svc_destroy(&nn->nfsd_serv->sv_refcnt);
+		spin_lock(&nfsd_notifier_lock);
+		nn->nfsd_serv = NULL;
+		spin_unlock(&nfsd_notifier_lock);
+	}
 }
 
 int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
@@ -733,7 +756,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 	if (tot > NFSD_MAXSERVS) {
 		/* total too large: scale down requested numbers */
 		for (i = 0; i < n && tot > 0; i++) {
-		    	int new = nthreads[i] * NFSD_MAXSERVS / tot;
+			int new = nthreads[i] * NFSD_MAXSERVS / tot;
 			tot -= (nthreads[i] - new);
 			nthreads[i] = new;
 		}
@@ -753,12 +776,13 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 	/* apply the new numbers */
 	svc_get(nn->nfsd_serv);
 	for (i = 0; i < n; i++) {
-		err = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv,
-				&nn->nfsd_serv->sv_pools[i], nthreads[i]);
+		err = svc_set_num_threads(nn->nfsd_serv,
+					  &nn->nfsd_serv->sv_pools[i],
+					  nthreads[i]);
 		if (err)
 			break;
 	}
-	nfsd_destroy(net);
+	nfsd_put(net);
 	return err;
 }
 
@@ -795,21 +819,19 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 
 	error = nfsd_startup_net(net, cred);
 	if (error)
-		goto out_destroy;
-	error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv,
-			NULL, nrservs);
+		goto out_put;
+	error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs);
 	if (error)
 		goto out_shutdown;
-	/* We are holding a reference to nn->nfsd_serv which
-	 * we don't want to count in the return value,
-	 * so subtract 1
-	 */
-	error = nn->nfsd_serv->sv_nrthreads - 1;
+	error = nn->nfsd_serv->sv_nrthreads;
 out_shutdown:
 	if (error < 0 && !nfsd_up_before)
 		nfsd_shutdown_net(net);
-out_destroy:
-	nfsd_destroy(net);		/* Release server */
+out_put:
+	/* Threads now hold service active */
+	if (xchg(&nn->keep_active, 0))
+		nfsd_put(net);
+	nfsd_put(net);
 out:
 	mutex_unlock(&nfsd_mutex);
 	return error;
@@ -923,9 +945,6 @@ nfsd(void *vrqstp)
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	int err;
 
-	/* Lock module and set up kernel thread */
-	mutex_lock(&nfsd_mutex);
-
 	/* At this point, the thread shares current->fs
 	 * with the init process. We need to create files with the
 	 * umask as defined by the client instead of init's umask. */
@@ -945,8 +964,7 @@ nfsd(void *vrqstp)
 	allow_signal(SIGINT);
 	allow_signal(SIGQUIT);
 
-	nfsdstats.th_cnt++;
-	mutex_unlock(&nfsd_mutex);
+	atomic_inc(&nfsdstats.th_cnt);
 
 	set_freezable();
 
@@ -973,19 +991,35 @@ nfsd(void *vrqstp)
 	/* Clear signals before calling svc_exit_thread() */
 	flush_signals(current);
 
-	mutex_lock(&nfsd_mutex);
-	nfsdstats.th_cnt --;
+	atomic_dec(&nfsdstats.th_cnt);
 
 out:
-	rqstp->rq_server = NULL;
+	/* Take an extra ref so that the svc_put in svc_exit_thread()
+	 * doesn't call svc_destroy()
+	 */
+	svc_get(nn->nfsd_serv);
 
 	/* Release the thread */
 	svc_exit_thread(rqstp);
 
-	nfsd_destroy(net);
+	/* We need to drop a ref, but may not drop the last reference
+	 * without holding nfsd_mutex, and we cannot wait for nfsd_mutex as that
+	 * could deadlock with nfsd_shutdown_threads() waiting for us.
+	 * So three options are:
+	 * - drop a non-final reference,
+	 * - get the mutex without waiting
+	 * - sleep briefly andd try the above again
+	 */
+	while (!svc_put_not_last(nn->nfsd_serv)) {
+		if (mutex_trylock(&nfsd_mutex)) {
+			nfsd_put(net);
+			mutex_unlock(&nfsd_mutex);
+			break;
+		}
+		msleep(20);
+	}
 
 	/* Release module */
-	mutex_unlock(&nfsd_mutex);
 	module_put_and_exit(0);
 	return 0;
 }
@@ -1096,7 +1130,6 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file)
 		mutex_unlock(&nfsd_mutex);
 		return -ENODEV;
 	}
-	/* bump up the psudo refcount while traversing */
 	svc_get(nn->nfsd_serv);
 	ret = svc_pool_stats_open(nn->nfsd_serv, file);
 	mutex_unlock(&nfsd_mutex);
@@ -1109,8 +1142,7 @@ int nfsd_pool_stats_release(struct inode *inode, struct file *file)
 	struct net *net = inode->i_sb->s_fs_info;
 
 	mutex_lock(&nfsd_mutex);
-	/* this function really, really should have been called svc_put() */
-	nfsd_destroy(net);
+	nfsd_put(net);
 	mutex_unlock(&nfsd_mutex);
 	return ret;
 }

fs/nfsd/state.h

@@ -568,6 +568,10 @@ struct nfs4_ol_stateid {
 	struct list_head		st_locks;
 	struct nfs4_stateowner		*st_stateowner;
 	struct nfs4_clnt_odstate	*st_clnt_odstate;
+/*
+ * These bitmasks use 3 separate bits for READ, ALLOW, and BOTH; see the
+ * comment above bmap_to_share_mode() for explanation:
+ */
 	unsigned char			st_access_bmap;
 	unsigned char			st_deny_bmap;
 	struct nfs4_ol_stateid		*st_openstp;
@@ -629,6 +633,7 @@ struct nfsd4_blocked_lock {
 	struct file_lock	nbl_lock;
 	struct knfsd_fh		nbl_fh;
 	struct nfsd4_callback	nbl_cb;
+	struct kref		nbl_kref;
 };
 
 struct nfsd4_compound_state;

fs/nfsd/stats.c

@@ -45,7 +45,7 @@ static int nfsd_proc_show(struct seq_file *seq, void *v)
 		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_WRITE]));
 
 	/* thread usage: */
-	seq_printf(seq, "th %u 0", nfsdstats.th_cnt);
+	seq_printf(seq, "th %u 0", atomic_read(&nfsdstats.th_cnt));
 
 	/* deprecated thread usage histogram stats */
 	for (i = 0; i < 10; i++)

fs/nfsd/stats.h

@@ -29,11 +29,9 @@ enum {
 struct nfsd_stats {
 	struct percpu_counter	counter[NFSD_STATS_COUNTERS_NUM];
 
-	/* Protected by nfsd_mutex */
-	unsigned int	th_cnt;		/* number of available threads */
+	atomic_t	th_cnt;		/* number of available threads */
 };
 
-
 extern struct nfsd_stats	nfsdstats;
 
 extern struct svc_stat		nfsd_svcstats;

fs/nfsd/trace.h

@@ -47,7 +47,7 @@
 			       rqstp->rq_xprt->xpt_remotelen); \
 		} while (0);
 
-TRACE_EVENT(nfsd_garbage_args_err,
+DECLARE_EVENT_CLASS(nfsd_xdr_err_class,
 	TP_PROTO(
 		const struct svc_rqst *rqstp
 	),
@@ -69,27 +69,13 @@ TRACE_EVENT(nfsd_garbage_args_err,
 	)
 );
 
-TRACE_EVENT(nfsd_cant_encode_err,
-	TP_PROTO(
-		const struct svc_rqst *rqstp
-	),
-	TP_ARGS(rqstp),
-	TP_STRUCT__entry(
-		NFSD_TRACE_PROC_ARG_FIELDS
+#define DEFINE_NFSD_XDR_ERR_EVENT(name) \
+DEFINE_EVENT(nfsd_xdr_err_class, nfsd_##name##_err, \
+	TP_PROTO(const struct svc_rqst *rqstp), \
+	TP_ARGS(rqstp))
 
-		__field(u32, vers)
-		__field(u32, proc)
-	),
-	TP_fast_assign(
-		NFSD_TRACE_PROC_ARG_ASSIGNMENTS
-
-		__entry->vers = rqstp->rq_vers;
-		__entry->proc = rqstp->rq_proc;
-	),
-	TP_printk("xid=0x%08x vers=%u proc=%u",
-		__entry->xid, __entry->vers, __entry->proc
-	)
-);
+DEFINE_NFSD_XDR_ERR_EVENT(garbage_args);
+DEFINE_NFSD_XDR_ERR_EVENT(cant_encode);
 
 #define show_nfsd_may_flags(x)						\
 	__print_flags(x, "|",						\
@@ -413,6 +399,56 @@ TRACE_EVENT(nfsd_dirent,
 	)
 )
 
+DECLARE_EVENT_CLASS(nfsd_copy_err_class,
+	TP_PROTO(struct svc_rqst *rqstp,
+		 struct svc_fh	*src_fhp,
+		 loff_t		src_offset,
+		 struct svc_fh	*dst_fhp,
+		 loff_t		dst_offset,
+		 u64		count,
+		 int		status),
+	TP_ARGS(rqstp, src_fhp, src_offset, dst_fhp, dst_offset, count, status),
+	TP_STRUCT__entry(
+		__field(u32, xid)
+		__field(u32, src_fh_hash)
+		__field(loff_t, src_offset)
+		__field(u32, dst_fh_hash)
+		__field(loff_t, dst_offset)
+		__field(u64, count)
+		__field(int, status)
+	),
+	TP_fast_assign(
+		__entry->xid = be32_to_cpu(rqstp->rq_xid);
+		__entry->src_fh_hash = knfsd_fh_hash(&src_fhp->fh_handle);
+		__entry->src_offset = src_offset;
+		__entry->dst_fh_hash = knfsd_fh_hash(&dst_fhp->fh_handle);
+		__entry->dst_offset = dst_offset;
+		__entry->count = count;
+		__entry->status = status;
+	),
+	TP_printk("xid=0x%08x src_fh_hash=0x%08x src_offset=%lld "
+			"dst_fh_hash=0x%08x dst_offset=%lld "
+			"count=%llu status=%d",
+		  __entry->xid, __entry->src_fh_hash, __entry->src_offset,
+		  __entry->dst_fh_hash, __entry->dst_offset,
+		  (unsigned long long)__entry->count,
+		  __entry->status)
+)
+
+#define DEFINE_NFSD_COPY_ERR_EVENT(name)		\
+DEFINE_EVENT(nfsd_copy_err_class, nfsd_##name,		\
+	TP_PROTO(struct svc_rqst	*rqstp,		\
+		 struct svc_fh		*src_fhp,	\
+		 loff_t			src_offset,	\
+		 struct svc_fh		*dst_fhp,	\
+		 loff_t			dst_offset,	\
+		 u64			count,		\
+		 int			status),	\
+	TP_ARGS(rqstp, src_fhp, src_offset, dst_fhp, dst_offset, \
+		count, status))
+
+DEFINE_NFSD_COPY_ERR_EVENT(clone_file_range_err);
+
 #include "state.h"
 #include "filecache.h"
 #include "vfs.h"
@@ -538,6 +574,34 @@ DEFINE_EVENT(nfsd_net_class, nfsd_##name, \
 DEFINE_NET_EVENT(grace_start);
 DEFINE_NET_EVENT(grace_complete);
 
+TRACE_EVENT(nfsd_writeverf_reset,
+	TP_PROTO(
+		const struct nfsd_net *nn,
+		const struct svc_rqst *rqstp,
+		int error
+	),
+	TP_ARGS(nn, rqstp, error),
+	TP_STRUCT__entry(
+		__field(unsigned long long, boot_time)
+		__field(u32, xid)
+		__field(int, error)
+		__array(unsigned char, verifier, NFS4_VERIFIER_SIZE)
+	),
+	TP_fast_assign(
+		__entry->boot_time = nn->boot_time;
+		__entry->xid = be32_to_cpu(rqstp->rq_xid);
+		__entry->error = error;
+
+		/* avoid seqlock inside TP_fast_assign */
+		memcpy(__entry->verifier, nn->writeverf,
+		       NFS4_VERIFIER_SIZE);
+	),
+	TP_printk("boot_time=%16llx xid=0x%08x error=%d new verifier=0x%s",
+		__entry->boot_time, __entry->xid, __entry->error,
+		__print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE)
+	)
+);
+
 TRACE_EVENT(nfsd_clid_cred_mismatch,
 	TP_PROTO(
 		const struct nfs4_client *clp,

fs/nfsd/vfs.c

@@ -40,6 +40,7 @@
 #include "../internal.h"
 #include "acl.h"
 #include "idmap.h"
+#include "xdr4.h"
 #endif /* CONFIG_NFSD_V4 */
 
 #include "nfsd.h"
@@ -517,15 +518,23 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
 }
 #endif
 
-__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
-		struct nfsd_file *nf_dst, u64 dst_pos, u64 count, bool sync)
+static struct nfsd4_compound_state *nfsd4_get_cstate(struct svc_rqst *rqstp)
+{
+	return &((struct nfsd4_compoundres *)rqstp->rq_resp)->cstate;
+}
+
+__be32 nfsd4_clone_file_range(struct svc_rqst *rqstp,
+		struct nfsd_file *nf_src, u64 src_pos,
+		struct nfsd_file *nf_dst, u64 dst_pos,
+		u64 count, bool sync)
 {
 	struct file *src = nf_src->nf_file;
 	struct file *dst = nf_dst->nf_file;
+	errseq_t since;
 	loff_t cloned;
 	__be32 ret = 0;
 
-	down_write(&nf_dst->nf_rwsem);
+	since = READ_ONCE(dst->f_wb_err);
 	cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0);
 	if (cloned < 0) {
 		ret = nfserrno(cloned);
@@ -539,16 +548,26 @@ __be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
 		loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX;
 		int status = vfs_fsync_range(dst, dst_pos, dst_end, 0);
 
+		if (!status)
+			status = filemap_check_wb_err(dst->f_mapping, since);
 		if (!status)
 			status = commit_inode_metadata(file_inode(src));
 		if (status < 0) {
-			nfsd_reset_boot_verifier(net_generic(nf_dst->nf_net,
-						 nfsd_net_id));
+			struct nfsd_net *nn = net_generic(nf_dst->nf_net,
+							  nfsd_net_id);
+
+			trace_nfsd_clone_file_range_err(rqstp,
+					&nfsd4_get_cstate(rqstp)->save_fh,
+					src_pos,
+					&nfsd4_get_cstate(rqstp)->current_fh,
+					dst_pos,
+					count, status);
+			nfsd_reset_write_verifier(nn);
+			trace_nfsd_writeverf_reset(nn, rqstp, status);
 			ret = nfserrno(status);
 		}
 	}
 out_err:
-	up_write(&nf_dst->nf_rwsem);
 	return ret;
 }
 
@@ -777,6 +796,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 		int may_flags, struct file **filp)
 {
 	__be32 err;
+	bool retried = false;
 
 	validate_process_creds();
 	/*
@@ -792,9 +812,16 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 	 */
 	if (type == S_IFREG)
 		may_flags |= NFSD_MAY_OWNER_OVERRIDE;
+retry:
 	err = fh_verify(rqstp, fhp, type, may_flags);
-	if (!err)
+	if (!err) {
 		err = __nfsd_open(rqstp, fhp, type, may_flags, filp);
+		if (err == nfserr_stale && !retried) {
+			retried = true;
+			fh_put(fhp);
+			goto retry;
+		}
+	}
 	validate_process_creds();
 	return err;
 }
@@ -944,10 +971,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 				unsigned long *cnt, int stable,
 				__be32 *verf)
 {
+	struct nfsd_net		*nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct file		*file = nf->nf_file;
 	struct super_block	*sb = file_inode(file)->i_sb;
 	struct svc_export	*exp;
 	struct iov_iter		iter;
+	errseq_t		since;
 	__be32			nfserr;
 	int			host_err;
 	int			use_wgather;
@@ -985,36 +1014,28 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 		flags |= RWF_SYNC;
 
 	iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt);
-	if (flags & RWF_SYNC) {
-		down_write(&nf->nf_rwsem);
-		host_err = vfs_iter_write(file, &iter, &pos, flags);
-		if (host_err < 0)
-			nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
-						 nfsd_net_id));
-		up_write(&nf->nf_rwsem);
-	} else {
-		down_read(&nf->nf_rwsem);
-		if (verf)
-			nfsd_copy_boot_verifier(verf,
-					net_generic(SVC_NET(rqstp),
-					nfsd_net_id));
-		host_err = vfs_iter_write(file, &iter, &pos, flags);
-		up_read(&nf->nf_rwsem);
-	}
+	since = READ_ONCE(file->f_wb_err);
+	if (verf)
+		nfsd_copy_write_verifier(verf, nn);
+	host_err = vfs_iter_write(file, &iter, &pos, flags);
 	if (host_err < 0) {
-		nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
-					 nfsd_net_id));
+		nfsd_reset_write_verifier(nn);
+		trace_nfsd_writeverf_reset(nn, rqstp, host_err);
 		goto out_nfserr;
 	}
 	*cnt = host_err;
 	nfsd_stats_io_write_add(exp, *cnt);
 	fsnotify_modify(file);
+	host_err = filemap_check_wb_err(file->f_mapping, since);
+	if (host_err < 0)
+		goto out_nfserr;
 
 	if (stable && use_wgather) {
 		host_err = wait_for_concurrent_writes(file);
-		if (host_err < 0)
-			nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
-						 nfsd_net_id));
+		if (host_err < 0) {
+			nfsd_reset_write_verifier(nn);
+			trace_nfsd_writeverf_reset(nn, rqstp, host_err);
+		}
 	}
 
 out_nfserr:
@@ -1089,19 +1110,6 @@ out:
 }
 
 #ifdef CONFIG_NFSD_V3
-static int
-nfsd_filemap_write_and_wait_range(struct nfsd_file *nf, loff_t offset,
-				  loff_t end)
-{
-	struct address_space *mapping = nf->nf_file->f_mapping;
-	int ret = filemap_fdatawrite_range(mapping, offset, end);
-
-	if (ret)
-		return ret;
-	filemap_fdatawait_range_keep_errors(mapping, offset, end);
-	return 0;
-}
-
 /*
  * Commit all pending writes to stable storage.
  *
@@ -1115,6 +1123,7 @@ __be32
 nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
                loff_t offset, unsigned long count, __be32 *verf)
 {
+	struct nfsd_net		*nn;
 	struct nfsd_file	*nf;
 	loff_t			end = LLONG_MAX;
 	__be32			err = nfserr_inval;
@@ -1131,29 +1140,28 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf);
 	if (err)
 		goto out;
+	nn = net_generic(nf->nf_net, nfsd_net_id);
 	if (EX_ISSYNC(fhp->fh_export)) {
-		int err2 = nfsd_filemap_write_and_wait_range(nf, offset, end);
+		errseq_t since = READ_ONCE(nf->nf_file->f_wb_err);
+		int err2;
 
-		down_write(&nf->nf_rwsem);
-		if (!err2)
-			err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
+		err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
 		switch (err2) {
 		case 0:
-			nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
-						nfsd_net_id));
+			nfsd_copy_write_verifier(verf, nn);
+			err2 = filemap_check_wb_err(nf->nf_file->f_mapping,
+						    since);
 			break;
 		case -EINVAL:
 			err = nfserr_notsupp;
 			break;
 		default:
-			err = nfserrno(err2);
-			nfsd_reset_boot_verifier(net_generic(nf->nf_net,
-						 nfsd_net_id));
+			nfsd_reset_write_verifier(nn);
+			trace_nfsd_writeverf_reset(nn, rqstp, err2);
 		}
-		up_write(&nf->nf_rwsem);
+		err = nfserrno(err2);
 	} else
-		nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
-					nfsd_net_id));
+		nfsd_copy_write_verifier(verf, nn);
 
 	nfsd_file_put(nf);
 out:
@@ -1747,8 +1755,8 @@ retry:
 	 * so do it by hand */
 	trap = lock_rename(tdentry, fdentry);
 	ffhp->fh_locked = tfhp->fh_locked = true;
-	fill_pre_wcc(ffhp);
-	fill_pre_wcc(tfhp);
+	fh_fill_pre_attrs(ffhp);
+	fh_fill_pre_attrs(tfhp);
 
 	odentry = lookup_one_len(fname, fdentry, flen);
 	host_err = PTR_ERR(odentry);
@@ -1808,8 +1816,8 @@ retry:
 	 * were the same, so again we do it by hand.
 	 */
 	if (!close_cached) {
-		fill_post_wcc(ffhp);
-		fill_post_wcc(tfhp);
+		fh_fill_post_attrs(ffhp);
+		fh_fill_post_attrs(tfhp);
 	}
 	unlock_rename(tdentry, fdentry);
 	ffhp->fh_locked = tfhp->fh_locked = false;

fs/nfsd/vfs.h

@@ -57,7 +57,8 @@ __be32          nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *,
 		    struct xdr_netobj *);
 __be32		nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
 				    struct file *, loff_t, loff_t, int);
-__be32		nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
+__be32		nfsd4_clone_file_range(struct svc_rqst *rqstp,
+				       struct nfsd_file *nf_src, u64 src_pos,
 				       struct nfsd_file *nf_dst, u64 dst_pos,
 				       u64 count, bool sync);
 #endif /* CONFIG_NFSD_V4 */

include/linux/exportfs.h

@@ -221,8 +221,6 @@ struct export_operations {
 #define EXPORT_OP_NOATOMIC_ATTR		(0x10) /* Filesystem cannot supply
 						  atomic attribute updates
 						*/
-#define EXPORT_OP_SYNC_LOCKS		(0x20) /* Filesystem can't do
-						  asychronous blocking locks */
 	unsigned long	flags;
 };
 

include/linux/fs.h

@@ -1221,13 +1221,13 @@ static inline int fcntl_setlk(unsigned int fd, struct file *file,
 
 #if BITS_PER_LONG == 32
 static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
-				struct flock64 __user *user)
+				struct flock64 *user)
 {
 	return -EINVAL;
 }
 
 static inline int fcntl_setlk64(unsigned int fd, struct file *file,
-				unsigned int cmd, struct flock64 __user *user)
+				unsigned int cmd, struct flock64 *user)
 {
 	return -EACCES;
 }

include/linux/lockd/lockd.h

@@ -303,10 +303,15 @@ void		  nlmsvc_invalidate_all(void);
 int           nlmsvc_unlock_all_by_sb(struct super_block *sb);
 int           nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr);
 
+static inline struct file *nlmsvc_file_file(struct nlm_file *file)
+{
+	return file->f_file[O_RDONLY] ?
+	       file->f_file[O_RDONLY] : file->f_file[O_WRONLY];
+}
+
 static inline struct inode *nlmsvc_file_inode(struct nlm_file *file)
 {
-	return locks_inode(file->f_file[O_RDONLY] ?
-			   file->f_file[O_RDONLY] : file->f_file[O_WRONLY]);
+	return locks_inode(nlmsvc_file_file(file));
 }
 
 static inline int __nlm_privileged_request4(const struct sockaddr *sap)

include/linux/sunrpc/svc.h

@@ -64,10 +64,9 @@ struct svc_serv_ops {
 	/* queue up a transport for servicing */
 	void		(*svo_enqueue_xprt)(struct svc_xprt *);
 
-	/* set up thread (or whatever) execution context */
-	int		(*svo_setup)(struct svc_serv *, struct svc_pool *, int);
-
-	/* optional module to count when adding threads (pooled svcs only) */
+	/* optional module to count when adding threads.
+	 * Thread function must call module_put_and_exit() to exit.
+	 */
 	struct module	*svo_module;
 };
 
@@ -85,6 +84,7 @@ struct svc_serv {
 	struct svc_program *	sv_program;	/* RPC program */
 	struct svc_stat *	sv_stats;	/* RPC statistics */
 	spinlock_t		sv_lock;
+	struct kref		sv_refcnt;
 	unsigned int		sv_nrthreads;	/* # of server threads */
 	unsigned int		sv_maxconn;	/* max connections allowed or
 						 * '0' causing max to be based
@@ -114,15 +114,43 @@ struct svc_serv {
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 };
 
-/*
- * We use sv_nrthreads as a reference count.  svc_destroy() drops
- * this refcount, so we need to bump it up around operations that
- * change the number of threads.  Horrible, but there it is.
- * Should be called with the "service mutex" held.
+/**
+ * svc_get() - increment reference count on a SUNRPC serv
+ * @serv:  the svc_serv to have count incremented
+ *
+ * Returns: the svc_serv that was passed in.
  */
-static inline void svc_get(struct svc_serv *serv)
+static inline struct svc_serv *svc_get(struct svc_serv *serv)
 {
-	serv->sv_nrthreads++;
+	kref_get(&serv->sv_refcnt);
+	return serv;
+}
+
+void svc_destroy(struct kref *);
+
+/**
+ * svc_put - decrement reference count on a SUNRPC serv
+ * @serv:  the svc_serv to have count decremented
+ *
+ * When the reference count reaches zero, svc_destroy()
+ * is called to clean up and free the serv.
+ */
+static inline void svc_put(struct svc_serv *serv)
+{
+	kref_put(&serv->sv_refcnt, svc_destroy);
+}
+
+/**
+ * svc_put_not_last - decrement non-final reference count on SUNRPC serv
+ * @serv:  the svc_serv to have count decremented
+ *
+ * Returns: %true is refcount was decremented.
+ *
+ * If the refcount is 1, it is not decremented and instead failure is reported.
+ */
+static inline bool svc_put_not_last(struct svc_serv *serv)
+{
+	return refcount_dec_not_one(&serv->sv_refcnt.refcount);
 }
 
 /*
@@ -468,29 +496,6 @@ struct svc_procedure {
 	const char *		pc_name;	/* for display */
 };
 
-/*
- * Mode for mapping cpus to pools.
- */
-enum {
-	SVC_POOL_AUTO = -1,	/* choose one of the others */
-	SVC_POOL_GLOBAL,	/* no mapping, just a single global pool
-				 * (legacy & UP mode) */
-	SVC_POOL_PERCPU,	/* one pool per cpu */
-	SVC_POOL_PERNODE	/* one pool per numa node */
-};
-
-struct svc_pool_map {
-	int count;			/* How many svc_servs use us */
-	int mode;			/* Note: int not enum to avoid
-					 * warnings about "enumeration value
-					 * not handled in switch" */
-	unsigned int npools;
-	unsigned int *pool_to;		/* maps pool id to cpu or node */
-	unsigned int *to_pool;		/* maps cpu or node to pool id */
-};
-
-extern struct svc_pool_map svc_pool_map;
-
 /*
  * Function prototypes.
  */
@@ -501,20 +506,14 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int,
 			    const struct svc_serv_ops *);
 struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv,
 					struct svc_pool *pool, int node);
-struct svc_rqst *svc_prepare_thread(struct svc_serv *serv,
-					struct svc_pool *pool, int node);
 void		   svc_rqst_replace_page(struct svc_rqst *rqstp,
 					 struct page *page);
 void		   svc_rqst_free(struct svc_rqst *);
 void		   svc_exit_thread(struct svc_rqst *);
-unsigned int	   svc_pool_map_get(void);
-void		   svc_pool_map_put(void);
 struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
 			const struct svc_serv_ops *);
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
-int		   svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
-void		   svc_destroy(struct svc_serv *);
 void		   svc_shutdown_net(struct svc_serv *, struct net *);
 int		   svc_process(struct svc_rqst *);
 int		   bc_svc_process(struct svc_serv *, struct rpc_rqst *,

include/trace/events/sunrpc.h

@@ -1744,10 +1744,11 @@ TRACE_EVENT(svc_xprt_create_err,
 		const char *program,
 		const char *protocol,
 		struct sockaddr *sap,
+		size_t salen,
 		const struct svc_xprt *xprt
 	),
 
-	TP_ARGS(program, protocol, sap, xprt),
+	TP_ARGS(program, protocol, sap, salen, xprt),
 
 	TP_STRUCT__entry(
 		__field(long, error)
@@ -1760,7 +1761,7 @@ TRACE_EVENT(svc_xprt_create_err,
 		__entry->error = PTR_ERR(xprt);
 		__assign_str(program, program);
 		__assign_str(protocol, protocol);
-		memcpy(__entry->addr, sap, sizeof(__entry->addr));
+		memcpy(__entry->addr, sap, min(salen, sizeof(__entry->addr)));
 	),
 
 	TP_printk("addr=%pISpc program=%s protocol=%s error=%ld",
@@ -1768,7 +1769,7 @@ TRACE_EVENT(svc_xprt_create_err,
 		__entry->error)
 );
 
-TRACE_EVENT(svc_xprt_do_enqueue,
+TRACE_EVENT(svc_xprt_enqueue,
 	TP_PROTO(struct svc_xprt *xprt, struct svc_rqst *rqst),
 
 	TP_ARGS(xprt, rqst),
@@ -1815,7 +1816,6 @@ DECLARE_EVENT_CLASS(svc_xprt_event,
 			), \
 			TP_ARGS(xprt))
 
-DEFINE_SVC_XPRT_EVENT(received);
 DEFINE_SVC_XPRT_EVENT(no_write_space);
 DEFINE_SVC_XPRT_EVENT(close);
 DEFINE_SVC_XPRT_EVENT(detach);
@@ -1902,27 +1902,6 @@ TRACE_EVENT(svc_alloc_arg_err,
 	TP_printk("pages=%u", __entry->pages)
 );
 
-TRACE_EVENT(svc_handle_xprt,
-	TP_PROTO(struct svc_xprt *xprt, int len),
-
-	TP_ARGS(xprt, len),
-
-	TP_STRUCT__entry(
-		__field(int, len)
-		__field(unsigned long, flags)
-		__string(addr, xprt->xpt_remotebuf)
-	),
-
-	TP_fast_assign(
-		__entry->len = len;
-		__entry->flags = xprt->xpt_flags;
-		__assign_str(addr, xprt->xpt_remotebuf);
-	),
-
-	TP_printk("addr=%s len=%d flags=%s", __get_str(addr),
-		__entry->len, show_svc_xprt_flags(__entry->flags))
-);
-
 TRACE_EVENT(svc_stats_latency,
 	TP_PROTO(const struct svc_rqst *rqst),
 
@@ -2146,17 +2125,17 @@ DECLARE_EVENT_CLASS(svcsock_accept_class,
 	TP_STRUCT__entry(
 		__field(long, status)
 		__string(service, service)
-		__array(unsigned char, addr, sizeof(struct sockaddr_in6))
+		__field(unsigned int, netns_ino)
 	),
 
 	TP_fast_assign(
 		__entry->status = status;
 		__assign_str(service, service);
-		memcpy(__entry->addr, &xprt->xpt_local, sizeof(__entry->addr));
+		__entry->netns_ino = xprt->xpt_net->ns.inum;
 	),
 
-	TP_printk("listener=%pISpc service=%s status=%ld",
-		__entry->addr, __get_str(service), __entry->status
+	TP_printk("addr=listener service=%s status=%ld",
+		__get_str(service), __entry->status
 	)
 );
 

net/sunrpc/svc.c

@@ -37,18 +37,37 @@
 
 static void svc_unregister(const struct svc_serv *serv, struct net *net);
 
-#define svc_serv_is_pooled(serv)    ((serv)->sv_ops->svo_function)
-
 #define SVC_POOL_DEFAULT	SVC_POOL_GLOBAL
 
+/*
+ * Mode for mapping cpus to pools.
+ */
+enum {
+	SVC_POOL_AUTO = -1,	/* choose one of the others */
+	SVC_POOL_GLOBAL,	/* no mapping, just a single global pool
+				 * (legacy & UP mode) */
+	SVC_POOL_PERCPU,	/* one pool per cpu */
+	SVC_POOL_PERNODE	/* one pool per numa node */
+};
+
 /*
  * Structure for mapping cpus to pools and vice versa.
  * Setup once during sunrpc initialisation.
  */
-struct svc_pool_map svc_pool_map = {
+
+struct svc_pool_map {
+	int count;			/* How many svc_servs use us */
+	int mode;			/* Note: int not enum to avoid
+					 * warnings about "enumeration value
+					 * not handled in switch" */
+	unsigned int npools;
+	unsigned int *pool_to;		/* maps pool id to cpu or node */
+	unsigned int *to_pool;		/* maps cpu or node to pool id */
+};
+
+static struct svc_pool_map svc_pool_map = {
 	.mode = SVC_POOL_DEFAULT
 };
-EXPORT_SYMBOL_GPL(svc_pool_map);
 
 static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */
 
@@ -219,10 +238,12 @@ svc_pool_map_init_pernode(struct svc_pool_map *m)
 
 /*
  * Add a reference to the global map of cpus to pools (and
- * vice versa).  Initialise the map if we're the first user.
- * Returns the number of pools.
+ * vice versa) if pools are in use.
+ * Initialise the map if we're the first user.
+ * Returns the number of pools. If this is '1', no reference
+ * was taken.
  */
-unsigned int
+static unsigned int
 svc_pool_map_get(void)
 {
 	struct svc_pool_map *m = &svc_pool_map;
@@ -232,6 +253,7 @@ svc_pool_map_get(void)
 
 	if (m->count++) {
 		mutex_unlock(&svc_pool_map_mutex);
+		WARN_ON_ONCE(m->npools <= 1);
 		return m->npools;
 	}
 
@@ -247,30 +269,36 @@ svc_pool_map_get(void)
 		break;
 	}
 
-	if (npools < 0) {
+	if (npools <= 0) {
 		/* default, or memory allocation failure */
 		npools = 1;
 		m->mode = SVC_POOL_GLOBAL;
 	}
 	m->npools = npools;
 
+	if (npools == 1)
+		/* service is unpooled, so doesn't hold a reference */
+		m->count--;
+
 	mutex_unlock(&svc_pool_map_mutex);
-	return m->npools;
+	return npools;
 }
-EXPORT_SYMBOL_GPL(svc_pool_map_get);
 
 /*
- * Drop a reference to the global map of cpus to pools.
+ * Drop a reference to the global map of cpus to pools, if
+ * pools were in use, i.e. if npools > 1.
  * When the last reference is dropped, the map data is
  * freed; this allows the sysadmin to change the pool
  * mode using the pool_mode module option without
  * rebooting or re-loading sunrpc.ko.
  */
-void
-svc_pool_map_put(void)
+static void
+svc_pool_map_put(int npools)
 {
 	struct svc_pool_map *m = &svc_pool_map;
 
+	if (npools <= 1)
+		return;
 	mutex_lock(&svc_pool_map_mutex);
 
 	if (!--m->count) {
@@ -283,7 +311,6 @@ svc_pool_map_put(void)
 
 	mutex_unlock(&svc_pool_map_mutex);
 }
-EXPORT_SYMBOL_GPL(svc_pool_map_put);
 
 static int svc_pool_map_get_node(unsigned int pidx)
 {
@@ -340,21 +367,18 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu)
 	struct svc_pool_map *m = &svc_pool_map;
 	unsigned int pidx = 0;
 
-	/*
-	 * An uninitialised map happens in a pure client when
-	 * lockd is brought up, so silently treat it the
-	 * same as SVC_POOL_GLOBAL.
-	 */
-	if (svc_serv_is_pooled(serv)) {
-		switch (m->mode) {
-		case SVC_POOL_PERCPU:
-			pidx = m->to_pool[cpu];
-			break;
-		case SVC_POOL_PERNODE:
-			pidx = m->to_pool[cpu_to_node(cpu)];
-			break;
-		}
+	if (serv->sv_nrpools <= 1)
+		return serv->sv_pools;
+
+	switch (m->mode) {
+	case SVC_POOL_PERCPU:
+		pidx = m->to_pool[cpu];
+		break;
+	case SVC_POOL_PERNODE:
+		pidx = m->to_pool[cpu_to_node(cpu)];
+		break;
 	}
+
 	return &serv->sv_pools[pidx % serv->sv_nrpools];
 }
 
@@ -435,7 +459,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 		return NULL;
 	serv->sv_name      = prog->pg_name;
 	serv->sv_program   = prog;
-	serv->sv_nrthreads = 1;
+	kref_init(&serv->sv_refcnt);
 	serv->sv_stats     = prog->pg_stats;
 	if (bufsize > RPCSVC_MAXPAYLOAD)
 		bufsize = RPCSVC_MAXPAYLOAD;
@@ -507,7 +531,7 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
 		goto out_err;
 	return serv;
 out_err:
-	svc_pool_map_put();
+	svc_pool_map_put(npools);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(svc_create_pooled);
@@ -523,23 +547,14 @@ EXPORT_SYMBOL_GPL(svc_shutdown_net);
 
 /*
  * Destroy an RPC service. Should be called with appropriate locking to
- * protect the sv_nrthreads, sv_permsocks and sv_tempsocks.
+ * protect sv_permsocks and sv_tempsocks.
  */
 void
-svc_destroy(struct svc_serv *serv)
+svc_destroy(struct kref *ref)
 {
-	dprintk("svc: svc_destroy(%s, %d)\n",
-				serv->sv_program->pg_name,
-				serv->sv_nrthreads);
-
-	if (serv->sv_nrthreads) {
-		if (--(serv->sv_nrthreads) != 0) {
-			svc_sock_update_bufs(serv);
-			return;
-		}
-	} else
-		printk("svc_destroy: no threads for serv=%p!\n", serv);
+	struct svc_serv *serv = container_of(ref, struct svc_serv, sv_refcnt);
 
+	dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name);
 	del_timer_sync(&serv->sv_temptimer);
 
 	/*
@@ -551,8 +566,7 @@ svc_destroy(struct svc_serv *serv)
 
 	cache_clean_deferred(serv);
 
-	if (svc_serv_is_pooled(serv))
-		svc_pool_map_put();
+	svc_pool_map_put(serv->sv_nrpools);
 
 	kfree(serv->sv_pools);
 	kfree(serv);
@@ -638,7 +652,7 @@ out_enomem:
 }
 EXPORT_SYMBOL_GPL(svc_rqst_alloc);
 
-struct svc_rqst *
+static struct svc_rqst *
 svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 {
 	struct svc_rqst	*rqstp;
@@ -647,14 +661,17 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	if (!rqstp)
 		return ERR_PTR(-ENOMEM);
 
-	serv->sv_nrthreads++;
+	svc_get(serv);
+	spin_lock_bh(&serv->sv_lock);
+	serv->sv_nrthreads += 1;
+	spin_unlock_bh(&serv->sv_lock);
+
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads++;
 	list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
 	spin_unlock_bh(&pool->sp_lock);
 	return rqstp;
 }
-EXPORT_SYMBOL_GPL(svc_prepare_thread);
 
 /*
  * Choose a pool in which to create a new thread, for svc_set_num_threads
@@ -748,59 +765,13 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 	return 0;
 }
 
-
-/* destroy old threads */
-static int
-svc_signal_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
-{
-	struct task_struct *task;
-	unsigned int state = serv->sv_nrthreads-1;
-
-	/* destroy old threads */
-	do {
-		task = choose_victim(serv, pool, &state);
-		if (task == NULL)
-			break;
-		send_sig(SIGINT, task, 1);
-		nrservs++;
-	} while (nrservs < 0);
-
-	return 0;
-}
-
 /*
  * Create or destroy enough new threads to make the number
  * of threads the given number.  If `pool' is non-NULL, applies
  * only to threads in that pool, otherwise round-robins between
  * all pools.  Caller must ensure that mutual exclusion between this and
  * server startup or shutdown.
- *
- * Destroying threads relies on the service threads filling in
- * rqstp->rq_task, which only the nfs ones do.  Assumes the serv
- * has been created using svc_create_pooled().
- *
- * Based on code that used to be in nfsd_svc() but tweaked
- * to be pool-aware.
  */
-int
-svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
-{
-	if (pool == NULL) {
-		/* The -1 assumes caller has done a svc_get() */
-		nrservs -= (serv->sv_nrthreads-1);
-	} else {
-		spin_lock_bh(&pool->sp_lock);
-		nrservs -= pool->sp_nrthreads;
-		spin_unlock_bh(&pool->sp_lock);
-	}
-
-	if (nrservs > 0)
-		return svc_start_kthreads(serv, pool, nrservs);
-	if (nrservs < 0)
-		return svc_signal_kthreads(serv, pool, nrservs);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(svc_set_num_threads);
 
 /* destroy old threads */
 static int
@@ -821,11 +792,10 @@ svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 }
 
 int
-svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 {
 	if (pool == NULL) {
-		/* The -1 assumes caller has done a svc_get() */
-		nrservs -= (serv->sv_nrthreads-1);
+		nrservs -= serv->sv_nrthreads;
 	} else {
 		spin_lock_bh(&pool->sp_lock);
 		nrservs -= pool->sp_nrthreads;
@@ -838,7 +808,7 @@ svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrser
 		return svc_stop_kthreads(serv, pool, nrservs);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(svc_set_num_threads_sync);
+EXPORT_SYMBOL_GPL(svc_set_num_threads);
 
 /**
  * svc_rqst_replace_page - Replace one page in rq_pages[]
@@ -890,11 +860,14 @@ svc_exit_thread(struct svc_rqst *rqstp)
 		list_del_rcu(&rqstp->rq_all);
 	spin_unlock_bh(&pool->sp_lock);
 
+	spin_lock_bh(&serv->sv_lock);
+	serv->sv_nrthreads -= 1;
+	spin_unlock_bh(&serv->sv_lock);
+	svc_sock_update_bufs(serv);
+
 	svc_rqst_free(rqstp);
 
-	/* Release the server */
-	if (serv)
-		svc_destroy(serv);
+	svc_put(serv);
 }
 EXPORT_SYMBOL_GPL(svc_exit_thread);
 

net/sunrpc/svc_xprt.c

@@ -244,7 +244,7 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 	xprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
 	if (IS_ERR(xprt))
 		trace_svc_xprt_create_err(serv->sv_program->pg_name,
-					  xcl->xcl_name, sap, xprt);
+					  xcl->xcl_name, sap, len, xprt);
 	return xprt;
 }
 
@@ -265,8 +265,6 @@ void svc_xprt_received(struct svc_xprt *xprt)
 		return;
 	}
 
-	trace_svc_xprt_received(xprt);
-
 	/* As soon as we clear busy, the xprt could be closed and
 	 * 'put', so we need a reference to call svc_enqueue_xprt with:
 	 */
@@ -467,7 +465,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 out_unlock:
 	rcu_read_unlock();
 	put_cpu();
-	trace_svc_xprt_do_enqueue(xprt, rqstp);
+	trace_svc_xprt_enqueue(xprt, rqstp);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue);
 
@@ -843,8 +841,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
 	} else
 		svc_xprt_received(xprt);
+
 out:
-	trace_svc_handle_xprt(xprt, len);
 	return len;
 }