Merge tag 'nfsd-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "I'm thrilled to announce that the Linux in-kernel NFS server now
  offers NFSv4 write delegations. A write delegation enables a client to
  cache data and metadata for a single file more aggressively, reducing
  network round trips and server workload. Many thanks to Dai Ngo for
  contributing this facility, and to Jeff Layton and Neil Brown for
  reviewing and testing it.

  This release also sees the removal of all support for DES- and
  triple-DES-based Kerberos encryption types in the kernel's SunRPC
  implementation. These encryption types have been deprecated by the
  Internet community for years and are considered insecure. This change
  affects both the in-kernel NFS client and server.

  The server's UDP and TCP socket transports have now fully adopted
  David Howells' new bio_vec iterator so that no more than one sendmsg()
  call is needed to transmit each RPC message. In particular, this helps
  kTLS optimize record boundaries when sending RPC-with-TLS replies, and
  it takes the server a baby step closer to handling file I/O via
  folios.

  We've begun work on overhauling the SunRPC thread scheduler to remove
  a costly linked-list walk when looking for an idle RPC service thread
  to wake. The pre-requisites are included in this release. Thanks to
  Neil Brown for his ongoing work on this improvement"

* tag 'nfsd-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (56 commits)
  Documentation: Add missing documentation for EXPORT_OP flags
  SUNRPC: Remove unused declaration rpc_modcount()
  SUNRPC: Remove unused declarations
  NFSD: da_addr_body field missing in some GETDEVICEINFO replies
  SUNRPC: Remove return value of svc_pool_wake_idle_thread()
  SUNRPC: make rqst_should_sleep() idempotent()
  SUNRPC: Clean up svc_set_num_threads
  SUNRPC: Count ingress RPC messages per svc_pool
  SUNRPC: Deduplicate thread wake-up code
  SUNRPC: Move trace_svc_xprt_enqueue
  SUNRPC: Add enum svc_auth_status
  SUNRPC: change svc_xprt::xpt_flags bits to enum
  SUNRPC: change svc_rqst::rq_flags bits to enum
  SUNRPC: change svc_pool::sp_flags bits to enum
  SUNRPC: change cache_head.flags bits to enum
  SUNRPC: remove timeout arg from svc_recv()
  SUNRPC: change svc_recv() to return void.
  SUNRPC: call svc_process() from svc_recv().
  nfsd: separate nfsd_last_thread() from nfsd_put()
  nfsd: Simplify code around svc_exit_thread() call in nfsd()
  ...

1 files changed, 27 insertions, 84 deletions

diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 2154fa63c5f2..1582af33e204 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -542,9 +542,14 @@ static struct notifier_block nfsd_inet6addr_notifier = {
 /* Only used under nfsd_mutex, so this atomic may be overkill: */
 static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0);
 
-static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
+static void nfsd_last_thread(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_serv *serv = nn->nfsd_serv;
+
+	spin_lock(&nfsd_notifier_lock);
+	nn->nfsd_serv = NULL;
+	spin_unlock(&nfsd_notifier_lock);
 
 	/* check if the notifier still has clients */
 	if (atomic_dec_return(&nfsd_notifier_refcount) == 0) {
@@ -554,6 +559,8 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
 #endif
 	}
 
+	svc_xprt_destroy_all(serv, net);
+
 	/*
 	 * write_ports can create the server without actually starting
 	 * any threads--if we get shut down before any threads are
@@ -644,7 +651,8 @@ void nfsd_shutdown_threads(struct net *net)
 	svc_get(serv);
 	/* Kill outstanding nfsd threads */
 	svc_set_num_threads(serv, NULL, 0);
-	nfsd_put(net);
+	nfsd_last_thread(net);
+	svc_put(serv);
 	mutex_unlock(&nfsd_mutex);
 }
 
@@ -674,9 +682,6 @@ int nfsd_create_serv(struct net *net)
 	serv->sv_maxconn = nn->max_connections;
 	error = svc_bind(serv, net);
 	if (error < 0) {
-		/* NOT nfsd_put() as notifiers (see below) haven't
-		 * been set up yet.
-		 */
 		svc_put(serv);
 		return error;
 	}
@@ -719,29 +724,6 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
 	return 0;
 }
 
-/* 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);
-
-	if (kref_put(&nn->nfsd_serv->sv_refcnt, nfsd_noop)) {
-		svc_xprt_destroy_all(nn->nfsd_serv, net);
-		nfsd_last_thread(nn->nfsd_serv, 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)
 {
 	int i = 0;
@@ -792,7 +774,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 		if (err)
 			break;
 	}
-	nfsd_put(net);
+	svc_put(nn->nfsd_serv);
 	return err;
 }
 
@@ -807,6 +789,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 	int	error;
 	bool	nfsd_up_before;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_serv *serv;
 
 	mutex_lock(&nfsd_mutex);
 	dprintk("nfsd: creating service\n");
@@ -826,22 +809,25 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 		goto out;
 
 	nfsd_up_before = nn->nfsd_net_up;
+	serv = nn->nfsd_serv;
 
 	error = nfsd_startup_net(net, cred);
 	if (error)
 		goto out_put;
-	error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs);
+	error = svc_set_num_threads(serv, NULL, nrservs);
 	if (error)
 		goto out_shutdown;
-	error = nn->nfsd_serv->sv_nrthreads;
+	error = serv->sv_nrthreads;
+	if (error == 0)
+		nfsd_last_thread(net);
 out_shutdown:
 	if (error < 0 && !nfsd_up_before)
 		nfsd_shutdown_net(net);
 out_put:
 	/* Threads now hold service active */
 	if (xchg(&nn->keep_active, 0))
-		nfsd_put(net);
-	nfsd_put(net);
+		svc_put(serv);
+	svc_put(serv);
 out:
 	mutex_unlock(&nfsd_mutex);
 	return error;
@@ -953,7 +939,6 @@ nfsd(void *vrqstp)
 	struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list);
 	struct net *net = perm_sock->xpt_net;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-	int err;
 
 	/* At this point, the thread shares current->fs
 	 * with the init process. We need to create files with the
@@ -965,15 +950,6 @@ nfsd(void *vrqstp)
 
 	current->fs->umask = 0;
 
-	/*
-	 * thread is spawned with all signals set to SIG_IGN, re-enable
-	 * the ones that will bring down the thread
-	 */
-	allow_signal(SIGKILL);
-	allow_signal(SIGHUP);
-	allow_signal(SIGINT);
-	allow_signal(SIGQUIT);
-
 	atomic_inc(&nfsdstats.th_cnt);
 
 	set_freezable();
@@ -981,54 +957,19 @@ nfsd(void *vrqstp)
 	/*
 	 * The main request loop
 	 */
-	for (;;) {
+	while (!kthread_should_stop()) {
 		/* Update sv_maxconn if it has changed */
 		rqstp->rq_server->sv_maxconn = nn->max_connections;
 
-		/*
-		 * Find a socket with data available and call its
-		 * recvfrom routine.
-		 */
-		while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN)
-			;
-		if (err == -EINTR)
-			break;
-		validate_process_creds();
-		svc_process(rqstp);
+		svc_recv(rqstp);
 		validate_process_creds();
 	}
 
-	/* Clear signals before calling svc_exit_thread() */
-	flush_signals(current);
-
 	atomic_dec(&nfsdstats.th_cnt);
 
 out:
-	/* 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);
-
-	/* 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);
-	}
-
 	return 0;
 }
 
@@ -1046,6 +987,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 {
 	const struct svc_procedure *proc = rqstp->rq_procinfo;
 	__be32 *statp = rqstp->rq_accept_statp;
+	struct nfsd_cacherep *rp;
 
 	/*
 	 * Give the xdr decoder a chance to change this if it wants
@@ -1056,7 +998,8 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream))
 		goto out_decode_err;
 
-	switch (nfsd_cache_lookup(rqstp)) {
+	rp = NULL;
+	switch (nfsd_cache_lookup(rqstp, &rp)) {
 	case RC_DOIT:
 		break;
 	case RC_REPLY:
@@ -1072,7 +1015,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream))
 		goto out_encode_err;
 
-	nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1);
+	nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1);
 out_cached_reply:
 	return 1;
 
@@ -1082,13 +1025,13 @@ out_decode_err:
 	return 1;
 
 out_update_drop:
-	nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
+	nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL);
 out_dropit:
 	return 0;
 
 out_encode_err:
 	trace_nfsd_cant_encode_err(rqstp);
-	nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
+	nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL);
 	*statp = rpc_system_err;
 	return 1;
 }