Merge tag 'nfsd-4.5' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Smaller bugfixes and cleanup, including a fix for a failures of
  kerberized NFSv4.1 mounts, and Scott Mayhew's work addressing ACK
  storms that can affect some high-availability NFS setups"

* tag 'nfsd-4.5' of git://linux-nfs.org/~bfields/linux:
  nfsd: add new io class tracepoint
  nfsd: give up on CB_LAYOUTRECALLs after two lease periods
  nfsd: Fix nfsd leaks sunrpc module references
  lockd: constify nlmsvc_binding structure
  lockd: use to_delayed_work
  nfsd: use to_delayed_work
  Revert "svcrdma: Do not send XDR roundup bytes for a write chunk"
  lockd: Register callbacks on the inetaddr_chain and inet6addr_chain
  nfsd: Register callbacks on the inetaddr_chain and inet6addr_chain
  sunrpc: Add a function to close temporary transports immediately
  nfsd: don't base cl_cb_status on stale information
  nfsd4: fix gss-proxy 4.1 mounts for some AD principals
  nfsd: fix unlikely NULL deref in mach_creds_match
  nfsd: minor consolidation of mach_cred handling code
  nfsd: helper for dup of possibly NULL string
  svcrpc: move some initialization to common code
  nfsd: fix a warning message
  nfsd: constify nfsd4_callback_ops structure
  nfsd: recover: constify nfsd4_client_tracking_ops structures
  svcrdma: Do not send XDR roundup bytes for a write chunk

fs/lockd/svc.c

@@ -25,13 +25,17 @@
 #include <linux/mutex.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/inetdevice.h>
 
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
+#include <linux/sunrpc/svc_xprt.h>
 #include <net/ip.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
 #include <linux/lockd/lockd.h>
 #include <linux/nfs.h>
 
@@ -44,7 +48,7 @@
 
 static struct svc_program	nlmsvc_program;
 
-struct nlmsvc_binding *		nlmsvc_ops;
+const struct nlmsvc_binding	*nlmsvc_ops;
 EXPORT_SYMBOL_GPL(nlmsvc_ops);
 
 static DEFINE_MUTEX(nlmsvc_mutex);
@@ -90,8 +94,7 @@ static unsigned long get_lockd_grace_period(void)
 
 static void grace_ender(struct work_struct *grace)
 {
-	struct delayed_work *dwork = container_of(grace, struct delayed_work,
-						  work);
+	struct delayed_work *dwork = to_delayed_work(grace);
 	struct lockd_net *ln = container_of(dwork, struct lockd_net,
 					    grace_period_end);
 
@@ -279,6 +282,68 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
 	}
 }
 
+static int lockd_inetaddr_event(struct notifier_block *this,
+	unsigned long event, void *ptr)
+{
+	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
+	struct sockaddr_in sin;
+
+	if (event != NETDEV_DOWN)
+		goto out;
+
+	if (nlmsvc_rqst) {
+		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);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block lockd_inetaddr_notifier = {
+	.notifier_call = lockd_inetaddr_event,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int lockd_inet6addr_event(struct notifier_block *this,
+	unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
+	struct sockaddr_in6 sin6;
+
+	if (event != NETDEV_DOWN)
+		goto out;
+
+	if (nlmsvc_rqst) {
+		dprintk("lockd_inet6addr_event: removed %pI6\n", &ifa->addr);
+		sin6.sin6_family = AF_INET6;
+		sin6.sin6_addr = ifa->addr;
+		svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
+			(struct sockaddr *)&sin6);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block lockd_inet6addr_notifier = {
+	.notifier_call = lockd_inet6addr_event,
+};
+#endif
+
+static void lockd_svc_exit_thread(void)
+{
+	unregister_inetaddr_notifier(&lockd_inetaddr_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
+	unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
+#endif
+	svc_exit_thread(nlmsvc_rqst);
+}
+
 static int lockd_start_svc(struct svc_serv *serv)
 {
 	int error;
@@ -315,7 +380,7 @@ static int lockd_start_svc(struct svc_serv *serv)
 	return 0;
 
 out_task:
-	svc_exit_thread(nlmsvc_rqst);
+	lockd_svc_exit_thread();
 	nlmsvc_task = NULL;
 out_rqst:
 	nlmsvc_rqst = NULL;
@@ -360,6 +425,10 @@ static struct svc_serv *lockd_create_svc(void)
 		printk(KERN_WARNING "lockd_up: create service failed\n");
 		return ERR_PTR(-ENOMEM);
 	}
+	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;
 }
@@ -428,7 +497,7 @@ lockd_down(struct net *net)
 	}
 	kthread_stop(nlmsvc_task);
 	dprintk("lockd_down: service stopped\n");
-	svc_exit_thread(nlmsvc_rqst);
+	lockd_svc_exit_thread();
 	dprintk("lockd_down: service destroyed\n");
 	nlmsvc_task = NULL;
 	nlmsvc_rqst = NULL;

fs/nfsd/lockd.c

@@ -58,7 +58,7 @@ nlm_fclose(struct file *filp)
 	fput(filp);
 }
 
-static struct nlmsvc_binding	nfsd_nlm_ops = {
+static const struct nlmsvc_binding nfsd_nlm_ops = {
 	.fopen		= nlm_fopen,		/* open file for locking */
 	.fclose		= nlm_fclose,		/* close file */
 };

fs/nfsd/netns.h

@@ -92,7 +92,7 @@ struct nfsd_net {
 
 	struct file *rec_file;
 	bool in_grace;
-	struct nfsd4_client_tracking_ops *client_tracking_ops;
+	const struct nfsd4_client_tracking_ops *client_tracking_ops;
 
 	time_t nfsd4_lease;
 	time_t nfsd4_grace;

fs/nfsd/nfs4callback.c

@@ -792,12 +792,16 @@ static void warn_no_callback_path(struct nfs4_client *clp, int reason)
 
 static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason)
 {
+	if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags))
+		return;
 	clp->cl_cb_state = NFSD4_CB_DOWN;
 	warn_no_callback_path(clp, reason);
 }
 
 static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason)
 {
+	if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags))
+		return;
 	clp->cl_cb_state = NFSD4_CB_FAULT;
 	warn_no_callback_path(clp, reason);
 }
@@ -1143,7 +1147,7 @@ nfsd4_run_cb_work(struct work_struct *work)
 }
 
 void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
-		struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op)
+		const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op)
 {
 	cb->cb_clp = clp;
 	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[op];

fs/nfsd/nfs4layouts.c

@@ -22,7 +22,7 @@ struct nfs4_layout {
 static struct kmem_cache *nfs4_layout_cache;
 static struct kmem_cache *nfs4_layout_stateid_cache;
 
-static struct nfsd4_callback_ops nfsd4_cb_layout_ops;
+static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
 static const struct lock_manager_operations nfsd4_layouts_lm_ops;
 
 const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
@@ -624,24 +624,39 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 {
 	struct nfs4_layout_stateid *ls =
 		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	struct nfsd_net *nn;
+	ktime_t now, cutoff;
 	LIST_HEAD(reaplist);
 
+
 	switch (task->tk_status) {
 	case 0:
-		return 1;
+	case -NFS4ERR_DELAY:
+		/*
+		 * Anything left? If not, then call it done. Note that we don't
+		 * take the spinlock since this is an optimization and nothing
+		 * should get added until the cb counter goes to zero.
+		 */
+		if (list_empty(&ls->ls_layouts))
+			return 1;
+
+		/* Poll the client until it's done with the layout */
+		now = ktime_get();
+		nn = net_generic(ls->ls_stid.sc_client->net, nfsd_net_id);
+
+		/* Client gets 2 lease periods to return it */
+		cutoff = ktime_add_ns(task->tk_start,
+					 nn->nfsd4_lease * NSEC_PER_SEC * 2);
+
+		if (ktime_before(now, cutoff)) {
+			rpc_delay(task, HZ/100); /* 10 mili-seconds */
+			return 0;
+		}
+		/* Fallthrough */
 	case -NFS4ERR_NOMATCHING_LAYOUT:
 		trace_layout_recall_done(&ls->ls_stid.sc_stateid);
 		task->tk_status = 0;
 		return 1;
-	case -NFS4ERR_DELAY:
-		/* Poll the client until it's done with the layout */
-		/* FIXME: cap number of retries.
-		 * The pnfs standard states that we need to only expire
-		 * the client after at-least "lease time" .eg lease-time * 2
-		 * when failing to communicate a recall
-		 */
-		rpc_delay(task, HZ/100); /* 10 mili-seconds */
-		return 0;
 	default:
 		/*
 		 * Unknown error or non-responding client, we'll need to fence.
@@ -665,7 +680,7 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb)
 	nfs4_put_stid(&ls->ls_stid);
 }
 
-static struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+static const struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
 	.prepare	= nfsd4_cb_layout_prepare,
 	.done		= nfsd4_cb_layout_done,
 	.release	= nfsd4_cb_layout_release,

fs/nfsd/nfs4recover.c

@@ -631,7 +631,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp)
 	return -ENOENT;
 }
 
-static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
+static const struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
 	.init		= nfsd4_legacy_tracking_init,
 	.exit		= nfsd4_legacy_tracking_exit,
 	.create		= nfsd4_create_clid_dir,
@@ -1050,7 +1050,7 @@ nfsd4_cld_grace_done(struct nfsd_net *nn)
 		printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret);
 }
 
-static struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = {
+static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = {
 	.init		= nfsd4_init_cld_pipe,
 	.exit		= nfsd4_remove_cld_pipe,
 	.create		= nfsd4_cld_create,
@@ -1394,7 +1394,7 @@ nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn)
 	kfree(legacy);
 }
 
-static struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
+static const struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
 	.init		= nfsd4_umh_cltrack_init,
 	.exit		= NULL,
 	.create		= nfsd4_umh_cltrack_create,