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.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJWmVZHAAoJECebzXlCjuG+Cn4P/3zwSuwIeLuv9b89vzFXU8Xv
 AbBWHk7WkFXJQGTKdclYjwxqU+l15D5lYHCae1cuD5eXdviraxXf7EcnqrMhJUc0
 oRiQx0rAwlEkKUAVrxGCFP7WKjlX3TsEBV6wPpTCP3BEMzTPDEeaDek7+hICFkLF
 9a/miEXAopm3jxP7WNmXEkdKpFEHklDDwtv6Av7iIKCW6+7XCGp7Prqo4NQKAKp6
 hjE+nvt2HiD06MZhUeyb14cn6547smzt1rbSfK4IB4yHMwLyaoqPrT7ekDh9LDrE
 uGgo+Y2PBbEcTAE6tJ88EjZx7cMCFPn0te+eKPgnpPy9RqrNqSxj5N/b7JAecKgW
 a/09BtvFOoYs8fO5ovqeRY5THrE3IRyMIwn4gt7fCYaaAbG3dwGKG1uklTAVXtb1
 95DkhOb8He2VhOCCoJ6ybbTnRfjB6b/cv7ZuEGlQfvTE+BtU3Jj9I76ruWFhb3zd
 HM1dRI20UfwL/0Y8yYhZ+/rje9SSk2jOmVgSCqY9hnCmEqOqOdUU0X/uumIWaBym
 zfGx9GIM0jQuYVdLQRXtJJbUgJUUN3MilGyU5wx7YoXip5guqTalXqAdQpShzXeW
 s1ATYh/mY5X9ig51KogkkVlm9bXDQAzJBAnDRpLtJZqy5Cgkrj9RSu0ExN1Rmlhw
 LKQCddBQxUSWJ+XWycgK
 =G7V3
 -----END PGP SIGNATURE-----

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,
+	struct delayed_work *dwork = to_delayed_work(grace);
-						  work);
 	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 @@ out_err:
 		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,

fs/nfsd/nfs4state.c

@@ -98,7 +98,7 @@ static struct kmem_cache *odstate_slab;
 
 static void free_session(struct nfsd4_session *);
 
-static struct nfsd4_callback_ops nfsd4_cb_recall_ops;
+static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
 
 static bool is_session_dead(struct nfsd4_session *ses)
 {
@@ -1857,15 +1857,28 @@ static void copy_clid(struct nfs4_client *target, struct nfs4_client *source)
 	target->cl_clientid.cl_id = source->cl_clientid.cl_id; 
 }
 
-static int copy_cred(struct svc_cred *target, struct svc_cred *source)
+int strdup_if_nonnull(char **target, char *source)
 {
-	if (source->cr_principal) {
+	if (source) {
-		target->cr_principal =
+		*target = kstrdup(source, GFP_KERNEL);
-				kstrdup(source->cr_principal, GFP_KERNEL);
+		if (!*target)
-		if (target->cr_principal == NULL)
 			return -ENOMEM;
 	} else
-		target->cr_principal = NULL;
+		*target = NULL;
+	return 0;
+}
+
+static int copy_cred(struct svc_cred *target, struct svc_cred *source)
+{
+	int ret;
+
+	ret = strdup_if_nonnull(&target->cr_principal, source->cr_principal);
+	if (ret)
+		return ret;
+	ret = strdup_if_nonnull(&target->cr_raw_principal,
+					source->cr_raw_principal);
+	if (ret)
+		return ret;
 	target->cr_flavor = source->cr_flavor;
 	target->cr_uid = source->cr_uid;
 	target->cr_gid = source->cr_gid;
@@ -1969,6 +1982,9 @@ static bool mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
 		return false;
 	if (!svc_rqst_integrity_protected(rqstp))
 		return false;
+	if (cl->cl_cred.cr_raw_principal)
+		return 0 == strcmp(cl->cl_cred.cr_raw_principal,
+						cr->cr_raw_principal);
 	if (!cr->cr_principal)
 		return false;
 	return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal);
@@ -2240,7 +2256,8 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
 	base = resp->cstate.data_offset;
 	slot->sl_datalen = buf->len - base;
 	if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen))
-		WARN("%s: sessions DRC could not cache compound\n", __func__);
+		WARN(1, "%s: sessions DRC could not cache compound\n",
+		     __func__);
 	return;
 }
 
@@ -2365,10 +2382,27 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 	if (exid->flags & ~EXCHGID4_FLAG_MASK_A)
 		return nfserr_inval;
 
+	new = create_client(exid->clname, rqstp, &verf);
+	if (new == NULL)
+		return nfserr_jukebox;
+
 	switch (exid->spa_how) {
 	case SP4_MACH_CRED:
-		if (!svc_rqst_integrity_protected(rqstp))
+		if (!svc_rqst_integrity_protected(rqstp)) {
-			return nfserr_inval;
+			status = nfserr_inval;
+			goto out_nolock;
+		}
+		/*
+		 * Sometimes userspace doesn't give us a principal.
+		 * Which is a bug, really.  Anyway, we can't enforce
+		 * MACH_CRED in that case, better to give up now:
+		 */
+		if (!new->cl_cred.cr_principal &&
+					!new->cl_cred.cr_raw_principal) {
+			status = nfserr_serverfault;
+			goto out_nolock;
+		}
+		new->cl_mach_cred = true;
 	case SP4_NONE:
 		break;
 	default:				/* checked by xdr code */
@@ -2377,10 +2411,6 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 		return nfserr_encr_alg_unsupp;
 	}
 
-	new = create_client(exid->clname, rqstp, &verf);
-	if (new == NULL)
-		return nfserr_jukebox;
-
 	/* Cases below refer to rfc 5661 section 18.35.4: */
 	spin_lock(&nn->client_lock);
 	conf = find_confirmed_client_by_name(&exid->clname, nn);
@@ -2442,7 +2472,6 @@ out_new:
 			goto out;
 	}
 	new->cl_minorversion = cstate->minorversion;
-	new->cl_mach_cred = (exid->spa_how == SP4_MACH_CRED);
 
 	gen_clid(new, nn);
 	add_to_unconfirmed(new);
@@ -2460,6 +2489,7 @@ out_copy:
 
 out:
 	spin_unlock(&nn->client_lock);
+out_nolock:
 	if (new)
 		expire_client(new);
 	if (unconf)
@@ -3648,7 +3678,7 @@ static void nfsd4_cb_recall_release(struct nfsd4_callback *cb)
 	nfs4_put_stid(&dp->dl_stid);
 }
 
-static struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
+static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
 	.prepare	= nfsd4_cb_recall_prepare,
 	.done		= nfsd4_cb_recall_done,
 	.release	= nfsd4_cb_recall_release,
@@ -4541,8 +4571,7 @@ static void
 laundromat_main(struct work_struct *laundry)
 {
 	time_t t;
-	struct delayed_work *dwork = container_of(laundry, struct delayed_work,
+	struct delayed_work *dwork = to_delayed_work(laundry);
-						  work);
 	struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
 					   laundromat_work);
 

fs/nfsd/nfsfh.h

@@ -7,6 +7,7 @@
 #ifndef _LINUX_NFSD_NFSFH_H
 #define _LINUX_NFSD_NFSFH_H
 
+#include <linux/crc32.h>
 #include <linux/sunrpc/svc.h>
 #include <uapi/linux/nfsd/nfsfh.h>
 
@@ -205,6 +206,28 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
 	return true;
 }
 
+#ifdef CONFIG_CRC32
+/**
+ * knfsd_fh_hash - calculate the crc32 hash for the filehandle
+ * @fh - pointer to filehandle
+ *
+ * returns a crc32 hash for the filehandle that is compatible with
+ * the one displayed by "wireshark".
+ */
+
+static inline u32
+knfsd_fh_hash(struct knfsd_fh *fh)
+{
+	return ~crc32_le(0xFFFFFFFF, (unsigned char *)&fh->fh_base, fh->fh_size);
+}
+#else
+static inline u32
+knfsd_fh_hash(struct knfsd_fh *fh)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_NFSD_V3
 /*
  * The wcc data stored in current_fh should be cleared

fs/nfsd/nfssvc.c

@@ -14,9 +14,13 @@
 
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/svcsock.h>
+#include <linux/sunrpc/svc_xprt.h>
 #include <linux/lockd/bind.h>
 #include <linux/nfsacl.h>
 #include <linux/seq_file.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include "nfsd.h"
 #include "cache.h"
@@ -306,22 +310,81 @@ static void nfsd_shutdown_net(struct net *net)
 	nfsd_shutdown_generic();
 }
 
+static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
+	void *ptr)
+{
+	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
+	struct net_device *dev = ifa->ifa_dev->dev;
+	struct net *net = dev_net(dev);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct sockaddr_in sin;
+
+	if (event != NETDEV_DOWN)
+		goto out;
+
+	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);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block nfsd_inetaddr_notifier = {
+	.notifier_call = nfsd_inetaddr_event,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int nfsd_inet6addr_event(struct notifier_block *this,
+	unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
+	struct net_device *dev = ifa->idev->dev;
+	struct net *net = dev_net(dev);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct sockaddr_in6 sin6;
+
+	if (event != NETDEV_DOWN)
+		goto out;
+
+	if (nn->nfsd_serv) {
+		dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr);
+		sin6.sin6_family = AF_INET6;
+		sin6.sin6_addr = ifa->addr;
+		svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block nfsd_inet6addr_notifier = {
+	.notifier_call = nfsd_inet6addr_event,
+};
+#endif
+
 static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
+	unregister_inetaddr_notifier(&nfsd_inetaddr_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
+	unregister_inet6addr_notifier(&nfsd_inet6addr_notifier);
+#endif
 	/*
 	 * write_ports can create the server without actually starting
 	 * any threads--if we get shut down before any threads are
 	 * started, then nfsd_last_thread will be run before any of this
-	 * other initialization has been done.
+	 * other initialization has been done except the rpcb information.
 	 */
+	svc_rpcb_cleanup(serv, net);
 	if (!nn->nfsd_net_up)
 		return;
+
 	nfsd_shutdown_net(net);
-
-	svc_rpcb_cleanup(serv, net);
-
 	printk(KERN_WARNING "nfsd: last server has exited, flushing export "
 			    "cache\n");
 	nfsd_export_flush(net);
@@ -425,6 +488,10 @@ int nfsd_create_serv(struct net *net)
 	}
 
 	set_max_drc();
+	register_inetaddr_notifier(&nfsd_inetaddr_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
+	register_inet6addr_notifier(&nfsd_inet6addr_notifier);
+#endif
 	do_gettimeofday(&nn->nfssvc_boot);		/* record boot time */
 	return 0;
 }

fs/nfsd/state.h

@@ -65,7 +65,7 @@ struct nfsd4_callback {
 	struct nfs4_client *cb_clp;
 	u32 cb_minorversion;
 	struct rpc_message cb_msg;
-	struct nfsd4_callback_ops *cb_ops;
+	const struct nfsd4_callback_ops *cb_ops;
 	struct work_struct cb_work;
 	int cb_seq_status;
 	int cb_status;
@@ -599,7 +599,7 @@ extern void nfsd4_probe_callback(struct nfs4_client *clp);
 extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
 extern 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);
 extern void nfsd4_run_cb(struct nfsd4_callback *cb);
 extern int nfsd4_create_callback_queue(void);
 extern void nfsd4_destroy_callback_queue(void);

fs/nfsd/trace.h

@@ -8,6 +8,47 @@
 #define _NFSD_TRACE_H
 
 #include <linux/tracepoint.h>
+#include "nfsfh.h"
+
+DECLARE_EVENT_CLASS(nfsd_io_class,
+	TP_PROTO(struct svc_rqst *rqstp,
+		 struct svc_fh	*fhp,
+		 loff_t		offset,
+		 int		len),
+	TP_ARGS(rqstp, fhp, offset, len),
+	TP_STRUCT__entry(
+		__field(__be32, xid)
+		__field_struct(struct knfsd_fh, fh)
+		__field(loff_t, offset)
+		__field(int, len)
+	),
+	TP_fast_assign(
+		__entry->xid = rqstp->rq_xid,
+		fh_copy_shallow(&__entry->fh, &fhp->fh_handle);
+		__entry->offset = offset;
+		__entry->len = len;
+	),
+	TP_printk("xid=0x%x fh=0x%x offset=%lld len=%d",
+		  __be32_to_cpu(__entry->xid), knfsd_fh_hash(&__entry->fh),
+		  __entry->offset, __entry->len)
+)
+
+#define DEFINE_NFSD_IO_EVENT(name)		\
+DEFINE_EVENT(nfsd_io_class, name,		\
+	TP_PROTO(struct svc_rqst *rqstp,	\
+		 struct svc_fh	*fhp,		\
+		 loff_t		offset,		\
+		 int		len),		\
+	TP_ARGS(rqstp, fhp, offset, len))
+
+DEFINE_NFSD_IO_EVENT(read_start);
+DEFINE_NFSD_IO_EVENT(read_opened);
+DEFINE_NFSD_IO_EVENT(read_io_done);
+DEFINE_NFSD_IO_EVENT(read_done);
+DEFINE_NFSD_IO_EVENT(write_start);
+DEFINE_NFSD_IO_EVENT(write_opened);
+DEFINE_NFSD_IO_EVENT(write_io_done);
+DEFINE_NFSD_IO_EVENT(write_done);
 
 #include "state.h"
 

fs/nfsd/vfs.c

@@ -43,6 +43,7 @@
 
 #include "nfsd.h"
 #include "vfs.h"
+#include "trace.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_FILEOP
 
@@ -997,16 +998,23 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	struct raparms	*ra;
 	__be32 err;
 
+	trace_read_start(rqstp, fhp, offset, vlen);
 	err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
 	if (err)
 		return err;
 
 	ra = nfsd_init_raparms(file);
+
+	trace_read_opened(rqstp, fhp, offset, vlen);
 	err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count);
+	trace_read_io_done(rqstp, fhp, offset, vlen);
+
 	if (ra)
 		nfsd_put_raparams(file, ra);
 	fput(file);
 
+	trace_read_done(rqstp, fhp, offset, vlen);
+
 	return err;
 }
 
@@ -1022,24 +1030,31 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 {
 	__be32			err = 0;
 
+	trace_write_start(rqstp, fhp, offset, vlen);
+
 	if (file) {
 		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
 				NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE);
 		if (err)
 			goto out;
+		trace_write_opened(rqstp, fhp, offset, vlen);
 		err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt,
 				stablep);
+		trace_write_io_done(rqstp, fhp, offset, vlen);
 	} else {
 		err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
 		if (err)
 			goto out;
 
+		trace_write_opened(rqstp, fhp, offset, vlen);
 		if (cnt)
 			err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen,
 					     cnt, stablep);
+		trace_write_io_done(rqstp, fhp, offset, vlen);
 		fput(file);
 	}
 out:
+	trace_write_done(rqstp, fhp, offset, vlen);
 	return err;
 }
 

include/linux/lockd/bind.h

@@ -29,7 +29,7 @@ struct nlmsvc_binding {
 	void			(*fclose)(struct file *);
 };
 
-extern struct nlmsvc_binding *	nlmsvc_ops;
+extern const struct nlmsvc_binding *nlmsvc_ops;
 
 /*
  * Similar to nfs_client_initdata, but without the NFS-specific

include/linux/sunrpc/svc_xprt.h

@@ -128,6 +128,7 @@ struct	svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name,
 			const unsigned short port);
 int	svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen);
 void	svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *xprt);
+void	svc_age_temp_xprts_now(struct svc_serv *, struct sockaddr *);
 
 static inline void svc_xprt_get(struct svc_xprt *xprt)
 {

include/linux/sunrpc/svcauth.h

@@ -23,13 +23,19 @@ struct svc_cred {
 	kgid_t			cr_gid;
 	struct group_info	*cr_group_info;
 	u32			cr_flavor; /* pseudoflavor */
-	char			*cr_principal; /* for gss */
+	/* name of form servicetype/hostname@REALM, passed down by
+	 * gss-proxy: */
+	char			*cr_raw_principal;
+	/* name of form servicetype@hostname, passed down by
+	 * rpc.svcgssd, or computed from the above: */
+	char			*cr_principal;
 	struct gss_api_mech	*cr_gss_mech;
 };
 
 static inline void init_svc_cred(struct svc_cred *cred)
 {
 	cred->cr_group_info = NULL;
+	cred->cr_raw_principal = NULL;
 	cred->cr_principal = NULL;
 	cred->cr_gss_mech = NULL;
 }
@@ -38,6 +44,7 @@ static inline void free_svc_cred(struct svc_cred *cred)
 {
 	if (cred->cr_group_info)
 		put_group_info(cred->cr_group_info);
+	kfree(cred->cr_raw_principal);
 	kfree(cred->cr_principal);
 	gss_mech_put(cred->cr_gss_mech);
 	init_svc_cred(cred);

net/sunrpc/auth_gss/gss_rpc_upcall.c

@@ -326,6 +326,9 @@ int gssp_accept_sec_context_upcall(struct net *net,
 	if (data->found_creds && client_name.data != NULL) {
 		char *c;
 
+		data->creds.cr_raw_principal = kstrndup(client_name.data,
+						client_name.len, GFP_KERNEL);
+
 		data->creds.cr_principal = kstrndup(client_name.data,
 						client_name.len, GFP_KERNEL);
 		if (data->creds.cr_principal) {

net/sunrpc/svc_xprt.c

@@ -10,11 +10,13 @@
 #include <linux/kthread.h>
 #include <linux/slab.h>
 #include <net/sock.h>
+#include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/svc_xprt.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/xprt.h>
 #include <linux/module.h>
+#include <linux/netdevice.h>
 #include <trace/events/sunrpc.h>
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
@@ -938,6 +940,49 @@ static void svc_age_temp_xprts(unsigned long closure)
 	mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
 }
 
+/* Close temporary transports whose xpt_local matches server_addr immediately
+ * instead of waiting for them to be picked up by the timer.
+ *
+ * This is meant to be called from a notifier_block that runs when an ip
+ * address is deleted.
+ */
+void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr)
+{
+	struct svc_xprt *xprt;
+	struct svc_sock *svsk;
+	struct socket *sock;
+	struct list_head *le, *next;
+	LIST_HEAD(to_be_closed);
+	struct linger no_linger = {
+		.l_onoff = 1,
+		.l_linger = 0,
+	};
+
+	spin_lock_bh(&serv->sv_lock);
+	list_for_each_safe(le, next, &serv->sv_tempsocks) {
+		xprt = list_entry(le, struct svc_xprt, xpt_list);
+		if (rpc_cmp_addr(server_addr, (struct sockaddr *)
+				&xprt->xpt_local)) {
+			dprintk("svc_age_temp_xprts_now: found %p\n", xprt);
+			list_move(le, &to_be_closed);
+		}
+	}
+	spin_unlock_bh(&serv->sv_lock);
+
+	while (!list_empty(&to_be_closed)) {
+		le = to_be_closed.next;
+		list_del_init(le);
+		xprt = list_entry(le, struct svc_xprt, xpt_list);
+		dprintk("svc_age_temp_xprts_now: closing %p\n", xprt);
+		svsk = container_of(xprt, struct svc_sock, sk_xprt);
+		sock = svsk->sk_sock;
+		kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
+				  (char *)&no_linger, sizeof(no_linger));
+		svc_close_xprt(xprt);
+	}
+}
+EXPORT_SYMBOL_GPL(svc_age_temp_xprts_now);
+
 static void call_xpt_users(struct svc_xprt *xprt)
 {
 	struct svc_xpt_user *u;

net/sunrpc/svcauth.c

@@ -55,6 +55,7 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
 	spin_unlock(&authtab_lock);
 
 	rqstp->rq_auth_slack = 0;
+	init_svc_cred(&rqstp->rq_cred);
 
 	rqstp->rq_authop = aops;
 	return aops->accept(rqstp, authp);
@@ -63,6 +64,7 @@ EXPORT_SYMBOL_GPL(svc_authenticate);
 
 int svc_set_client(struct svc_rqst *rqstp)
 {
+	rqstp->rq_client = NULL;
 	return rqstp->rq_authop->set_client(rqstp);
 }
 EXPORT_SYMBOL_GPL(svc_set_client);

net/sunrpc/svcauth_unix.c

@@ -728,10 +728,6 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp)
 	struct kvec	*resv = &rqstp->rq_res.head[0];
 	struct svc_cred	*cred = &rqstp->rq_cred;
 
-	cred->cr_group_info = NULL;
-	cred->cr_principal = NULL;
-	rqstp->rq_client = NULL;
-
 	if (argv->iov_len < 3*4)
 		return SVC_GARBAGE;
 
@@ -794,10 +790,6 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp)
 	u32		slen, i;
 	int		len   = argv->iov_len;
 
-	cred->cr_group_info = NULL;
-	cred->cr_principal = NULL;
-	rqstp->rq_client = NULL;
-
 	if ((len -= 3*4) < 0)
 		return SVC_GARBAGE;