1 files changed, 126 insertions, 94 deletions

diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 80431921e5d7..07193595b8e0 100644
--- a/fs/nfsd/nfssvc.c
+++ b/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;
 }