Merge tag 'nfs-for-6.9-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Bugfixes:
   - Fix for an Oops in the NFSv4.2 listxattr handler
   - Correct an incorrect buffer size in listxattr
   - Fix for an Oops in the pNFS flexfiles layout
   - Fix a refcount leak in NFS O_DIRECT writes
   - Fix missing locking in NFS O_DIRECT
   - Avoid an infinite loop in pnfs_update_layout
   - Fix an overflow in the RPC waitqueue queue length counter
   - Ensure that pNFS I/O is also protected by TLS when xprtsec is
     specified by the mount options
   - Fix a leaked folio lock in the netfs read code
   - Fix a potential deadlock in fscache
   - Allow setting the fscache uniquifier in NFSv4
   - Fix an off by one in root_nfs_cat()
   - Fix another off by one in rpc_sockaddr2uaddr()
   - nfs4_do_open() can incorrectly trigger state recovery
   - Various fixes for connection shutdown

  Features and cleanups:
   - Ensure that containers only see their own RPC and NFS stats
   - Enable nconnect for RDMA
   - Remove dead code from nfs_writepage_locked()
   - Various tracepoint additions to track EXCHANGE_ID, GETDEVICEINFO,
     and mount options"

* tag 'nfs-for-6.9-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (29 commits)
  nfs: fix panic when nfs4_ff_layout_prepare_ds() fails
  NFS: trace the uniquifier of fscache
  NFS: Read unlock folio on nfs_page_create_from_folio() error
  NFS: remove unused variable nfs_rpcstat
  nfs: fix UAF in direct writes
  nfs: properly protect nfs_direct_req fields
  NFS: enable nconnect for RDMA
  NFSv4: nfs4_do_open() is incorrectly triggering state recovery
  NFS: avoid infinite loop in pnfs_update_layout.
  NFS: remove sync_mode test from nfs_writepage_locked()
  NFSv4.1/pnfs: fix NFS with TLS in pnfs
  NFS: Fix an off by one in root_nfs_cat()
  nfs: make the rpc_stat per net namespace
  nfs: expose /proc/net/sunrpc/nfs in net namespaces
  sunrpc: add a struct rpc_stats arg to rpc_create_args
  nfs: remove unused NFS_CALL macro
  NFSv4.1: add tracepoint to trunked nfs4_exchange_id calls
  NFS: Fix nfs_netfs_issue_read() xarray locking for writeback interrupt
  SUNRPC: increase size of rpc_wait_queue.qlen from unsigned short to unsigned int
  nfs: fix regression in handling of fsc= option in NFSv4
  ...

25 files changed, 210 insertions, 57 deletions

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index fbdc9ca80f71..de77848ae654 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -73,14 +73,9 @@ const struct rpc_program nfs_program = {
 	.number			= NFS_PROGRAM,
 	.nrvers			= ARRAY_SIZE(nfs_version),
 	.version		= nfs_version,
-	.stats			= &nfs_rpcstat,
 	.pipe_dir_name		= NFS_PIPE_DIRNAME,
 };
 
-struct rpc_stat nfs_rpcstat = {
-	.program		= &nfs_program
-};
-
 static struct nfs_subversion *find_nfs_version(unsigned int version)
 {
 	struct nfs_subversion *nfs;
@@ -502,6 +497,7 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 			  const struct nfs_client_initdata *cl_init,
 			  rpc_authflavor_t flavor)
 {
+	struct nfs_net		*nn = net_generic(clp->cl_net, nfs_net_id);
 	struct rpc_clnt		*clnt = NULL;
 	struct rpc_create_args args = {
 		.net		= clp->cl_net,
@@ -513,6 +509,7 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 		.servername	= clp->cl_hostname,
 		.nodename	= cl_init->nodename,
 		.program	= &nfs_program,
+		.stats		= &nn->rpcstats,
 		.version	= clp->rpc_ops->version,
 		.authflavor	= flavor,
 		.cred		= cl_init->cred,
@@ -1182,6 +1179,8 @@ void nfs_clients_init(struct net *net)
 #endif
 	spin_lock_init(&nn->nfs_client_lock);
 	nn->boot_time = ktime_get_real();
+	memset(&nn->rpcstats, 0, sizeof(nn->rpcstats));
+	nn->rpcstats.program = &nfs_program;
 
 	nfs_netns_sysfs_setup(nn, net);
 }
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index d4a42ce0c7e3..6bace5fece04 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -181,7 +181,6 @@ static int nfs_delegation_claim_opens(struct inode *inode,
 	struct nfs_open_context *ctx;
 	struct nfs4_state_owner *sp;
 	struct nfs4_state *state;
-	unsigned int seq;
 	int err;
 
 again:
@@ -202,12 +201,9 @@ again:
 		sp = state->owner;
 		/* Block nfs4_proc_unlck */
 		mutex_lock(&sp->so_delegreturn_mutex);
-		seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
 		err = nfs4_open_delegation_recall(ctx, state, stateid);
 		if (!err)
 			err = nfs_delegation_claim_locks(state, stateid);
-		if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
-			err = -EAGAIN;
 		mutex_unlock(&sp->so_delegreturn_mutex);
 		put_nfs_open_context(ctx);
 		if (err != 0)
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 7af5d270de28..bb2f583eb28b 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -606,6 +606,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 
 	trace_nfs_direct_commit_complete(dreq);
 
+	spin_lock(&dreq->lock);
 	if (status < 0) {
 		/* Errors in commit are fatal */
 		dreq->error = status;
@@ -613,6 +614,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 	} else {
 		status = dreq->error;
 	}
+	spin_unlock(&dreq->lock);
 
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
 
@@ -625,7 +627,10 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 			spin_unlock(&dreq->lock);
 			nfs_release_request(req);
 		} else if (!nfs_write_match_verf(verf, req)) {
-			dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+			spin_lock(&dreq->lock);
+			if (dreq->flags == 0)
+				dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+			spin_unlock(&dreq->lock);
 			/*
 			 * Despite the reboot, the write was successful,
 			 * so reset wb_nio.
@@ -667,10 +672,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq)
 	LIST_HEAD(mds_list);
 
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
+	nfs_commit_begin(cinfo.mds);
 	nfs_scan_commit(dreq->inode, &mds_list, &cinfo);
 	res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo);
-	if (res < 0) /* res == -ENOMEM */
-		nfs_direct_write_reschedule(dreq);
+	if (res < 0) { /* res == -ENOMEM */
+		spin_lock(&dreq->lock);
+		if (dreq->flags == 0)
+			dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+		spin_unlock(&dreq->lock);
+	}
+	if (nfs_commit_end(cinfo.mds))
+		nfs_direct_write_complete(dreq);
 }
 
 static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq)
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index acf4b88889dc..4fa304fa5bc4 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -35,6 +35,7 @@
 #include "../internal.h"
 #include "../nfs4session.h"
 #include "filelayout.h"
+#include "../nfs4trace.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
@@ -172,6 +173,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
 		if (!dsaddr->ds_list[i])
 			goto out_err_drain_dsaddrs;
+		trace_fl_getdevinfo(server, &pdev->dev_id, dsaddr->ds_list[i]->ds_remotestr);
 
 		/* If DS was already in cache, free ds addrs */
 		while (!list_empty(&dsaddrs)) {
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index ef817a0475ff..3e724cb7ef01 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -2016,7 +2016,7 @@ static void ff_layout_cancel_io(struct pnfs_layout_segment *lseg)
 	for (idx = 0; idx < flseg->mirror_array_cnt; idx++) {
 		mirror = flseg->mirror_array[idx];
 		mirror_ds = mirror->mirror_ds;
-		if (!mirror_ds)
+		if (IS_ERR_OR_NULL(mirror_ds))
 			continue;
 		ds = mirror->mirror_ds->ds;
 		if (!ds)
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 853e8d609bb3..d0a0956f8a13 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -652,6 +652,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		ctx->fscache_uniq = NULL;
 		break;
 	case Opt_fscache:
+		trace_nfs_mount_assign(param->key, param->string);
 		ctx->options |= NFS_OPTION_FSCACHE;
 		kfree(ctx->fscache_uniq);
 		ctx->fscache_uniq = param->string;
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 2d1bfee225c3..ddc1ee031955 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -301,11 +301,11 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq)
 	struct inode *inode = sreq->rreq->inode;
 	struct nfs_open_context *ctx = sreq->rreq->netfs_priv;
 	struct page *page;
+	unsigned long idx;
 	int err;
 	pgoff_t start = (sreq->start + sreq->transferred) >> PAGE_SHIFT;
 	pgoff_t last = ((sreq->start + sreq->len -
 			 sreq->transferred - 1) >> PAGE_SHIFT);
-	XA_STATE(xas, &sreq->rreq->mapping->i_pages, start);
 
 	nfs_pageio_init_read(&pgio, inode, false,
 			     &nfs_async_read_completion_ops);
@@ -316,19 +316,14 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq)
 
 	pgio.pg_netfs = netfs; /* used in completion */
 
-	xas_lock(&xas);
-	xas_for_each(&xas, page, last) {
+	xa_for_each_range(&sreq->rreq->mapping->i_pages, idx, page, start, last) {
 		/* nfs_read_add_folio() may schedule() due to pNFS layout and other RPCs  */
-		xas_pause(&xas);
-		xas_unlock(&xas);
 		err = nfs_read_add_folio(&pgio, ctx, page_folio(page));
 		if (err < 0) {
 			netfs->error = err;
 			goto out;
 		}
-		xas_lock(&xas);
 	}
-	xas_unlock(&xas);
 out:
 	nfs_pageio_complete_read(&pgio);
 	nfs_netfs_put(netfs);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 93ea49a7eb61..c709c296ea9a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2426,12 +2426,16 @@ EXPORT_SYMBOL_GPL(nfs_net_id);
 
 static int nfs_net_init(struct net *net)
 {
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
 	nfs_clients_init(net);
+	rpc_proc_register(net, &nn->rpcstats);
 	return nfs_fs_proc_net_init(net);
 }
 
 static void nfs_net_exit(struct net *net)
 {
+	rpc_proc_unregister(net, "nfs");
 	nfs_fs_proc_net_exit(net);
 	nfs_clients_exit(net);
 }
@@ -2486,15 +2490,12 @@ static int __init init_nfs_fs(void)
 	if (err)
 		goto out1;
 
-	rpc_proc_register(&init_net, &nfs_rpcstat);
-
 	err = register_nfs_fs();
 	if (err)
 		goto out0;
 
 	return 0;
 out0:
-	rpc_proc_unregister(&init_net, "nfs");
 	nfs_destroy_directcache();
 out1:
 	nfs_destroy_writepagecache();
@@ -2524,7 +2525,6 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_inodecache();
 	nfs_destroy_nfspagecache();
 	unregister_pernet_subsys(&nfs_net_ops);
-	rpc_proc_unregister(&init_net, "nfs");
 	unregister_nfs_fs();
 	nfs_fs_proc_exit();
 	nfsiod_stop();
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index e3722ce6722e..06253695fe53 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -449,8 +449,6 @@ int nfs_try_get_tree(struct fs_context *);
 int nfs_get_tree_common(struct fs_context *);
 void nfs_kill_super(struct super_block *);
 
-extern struct rpc_stat nfs_rpcstat;
-
 extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
 extern bool nfs_sb_active(struct super_block *sb);
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index c8374f74dce1..a68b21603ea9 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -9,6 +9,7 @@
 #include <linux/nfs4.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <linux/sunrpc/stats.h>
 
 struct bl_dev_msg {
 	int32_t status;
@@ -34,6 +35,7 @@ struct nfs_net {
 	struct nfs_netns_client *nfs_client;
 	spinlock_t nfs_client_lock;
 	ktime_t boot_time;
+	struct rpc_stat rpcstats;
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry *proc_nfsfs;
 #endif
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index 674c012868b1..b0c8a39c2bbd 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -111,6 +111,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 	cl_init.hostname = buf;
 
 	switch (ds_proto) {
+	case XPRT_TRANSPORT_RDMA:
 	case XPRT_TRANSPORT_TCP:
 	case XPRT_TRANSPORT_TCP_TLS:
 		if (mds_clp->cl_nconnect > 1)
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index b59876b01a1e..0282d93c8bcc 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -55,11 +55,14 @@ int nfs42_proc_removexattr(struct inode *inode, const char *name);
  * They would be 7 bytes long in the eventual buffer ("user.x\0"), and
  * 8 bytes long XDR-encoded.
  *
- * Include the trailing eof word as well.
+ * Include the trailing eof word as well and make the result a multiple
+ * of 4 bytes.
  */
 static inline u32 nfs42_listxattr_xdrsize(u32 buflen)
 {
-	return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4;
+	u32 size = 8 * buflen / (XATTR_USER_PREFIX_LEN + 2) + 4;
+
+	return (size + 3) & ~3;
 }
 #endif /* CONFIG_NFS_V4_2 */
 #endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 6ff41ceb9f1c..7024230f0d1d 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -120,7 +120,6 @@ struct nfs4_state_owner {
 	unsigned long	     so_flags;
 	struct list_head     so_states;
 	struct nfs_seqid_counter so_seqid;
-	seqcount_spinlock_t  so_reclaim_seqcount;
 	struct mutex	     so_delegreturn_mutex;
 };
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 11e3a285594c..84573df5cf5a 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -924,6 +924,7 @@ static int nfs4_set_client(struct nfs_server *server,
 	else
 		cl_init.max_connect = max_connect;
 	switch (proto) {
+	case XPRT_TRANSPORT_RDMA:
 	case XPRT_TRANSPORT_TCP:
 	case XPRT_TRANSPORT_TCP_TLS:
 		cl_init.nconnect = nconnect;
@@ -1000,6 +1001,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 	cl_init.hostname = buf;
 
 	switch (ds_proto) {
+	case XPRT_TRANSPORT_RDMA:
 	case XPRT_TRANSPORT_TCP:
 	case XPRT_TRANSPORT_TCP_TLS:
 		if (mds_clp->cl_nconnect > 1) {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 815996cb27fc..ea390db94b62 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3069,10 +3069,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	fmode_t acc_mode = _nfs4_ctx_to_accessmode(ctx);
 	struct inode *dir = d_inode(opendata->dir);
 	unsigned long dir_verifier;
-	unsigned int seq;
 	int ret;
 
-	seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
 	dir_verifier = nfs_save_change_attribute(dir);
 
 	ret = _nfs4_proc_open(opendata, ctx);
@@ -3125,11 +3123,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	if (ret != 0)
 		goto out;
 
-	if (d_inode(dentry) == state->inode) {
+	if (d_inode(dentry) == state->inode)
 		nfs_inode_attach_open_context(ctx);
-		if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
-			nfs4_schedule_stateid_recovery(server, state);
-	}
 
 out:
 	if (!opendata->cancelled) {
@@ -8973,10 +8968,12 @@ try_again:
 		return;
 
 	status = task->tk_status;
-	if (status == 0)
+	if (status == 0) {
 		status = nfs4_detect_session_trunking(adata->clp,
 				task->tk_msg.rpc_resp, xprt);
-
+		trace_nfs4_trunked_exchange_id(adata->clp,
+			xprt->address_strings[RPC_DISPLAY_ADDR], status);
+	}
 	if (status == 0)
 		rpc_clnt_xprt_switch_add_xprt(clnt, xprt);
 	else if (status != -NFS4ERR_DELAY && rpc_clnt_xprt_switch_has_addr(clnt,
@@ -10618,29 +10615,33 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 {
 	ssize_t error, error2, error3;
+	size_t left = size;
 
-	error = generic_listxattr(dentry, list, size);
+	error = generic_listxattr(dentry, list, left);
 	if (error < 0)
 		return error;
 	if (list) {
 		list += error;
-		size -= error;
+		left -= error;
 	}
 
-	error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size);
+	error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, left);
 	if (error2 < 0)
 		return error2;
 
 	if (list) {
 		list += error2;
-		size -= error2;
+		left -= error2;
 	}
 
-	error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size);
+	error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left);
 	if (error3 < 0)
 		return error3;
 
-	return error + error2 + error3;
+	error += error2 + error3;
+	if (size && error > size)
+		return -ERANGE;
+	return error;
 }
 
 static void nfs4_enable_swap(struct inode *inode)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 8cfabdbda336..662e86ea3a2d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -513,7 +513,6 @@ nfs4_alloc_state_owner(struct nfs_server *server,
 	nfs4_init_seqid_counter(&sp->so_seqid);
 	atomic_set(&sp->so_count, 1);
 	INIT_LIST_HEAD(&sp->so_lru);
-	seqcount_spinlock_init(&sp->so_reclaim_seqcount, &sp->so_lock);
 	mutex_init(&sp->so_delegreturn_mutex);
 	return sp;
 }
@@ -1667,7 +1666,6 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp,
 	 * server that doesn't support a grace period.
 	 */
 	spin_lock(&sp->so_lock);
-	raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
 restart:
 	list_for_each_entry(state, &sp->so_states, open_states) {
 		if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1735,7 +1733,6 @@ restart:
 		spin_lock(&sp->so_lock);
 		goto restart;
 	}
-	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
 #ifdef CONFIG_NFS_V4_2
 	if (found_ssc_copy_state)
@@ -1745,7 +1742,6 @@ restart:
 out_err:
 	nfs4_put_open_state(state);
 	spin_lock(&sp->so_lock);
-	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
 	return status;
 }
@@ -1928,9 +1924,12 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
 	struct nfs_server *server;
 	struct rb_node *pos;
 	LIST_HEAD(freeme);
-	int status = 0;
 	int lost_locks = 0;
+	int status;
 
+	status = nfs4_begin_drain_session(clp);
+	if (status < 0)
+		return status;
 restart:
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
@@ -2694,6 +2693,9 @@ static void nfs4_state_manager(struct nfs_client *clp)
 		/* Detect expired delegations... */
 		if (test_and_clear_bit(NFS4CLNT_DELEGATION_EXPIRED, &clp->cl_state)) {
 			section = "detect expired delegations";
+			status = nfs4_begin_drain_session(clp);
+			if (status < 0)
+				goto out_error;
 			nfs_reap_expired_delegations(clp);
 			continue;
 		}
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index d09bcfd7db89..8da5a9c000f4 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -145,6 +145,7 @@ static int do_nfs4_mount(struct nfs_server *server,
 			 const char *export_path)
 {
 	struct nfs_fs_context *root_ctx;
+	struct nfs_fs_context *ctx;
 	struct fs_context *root_fc;
 	struct vfsmount *root_mnt;
 	struct dentry *dentry;
@@ -157,6 +158,12 @@ static int do_nfs4_mount(struct nfs_server *server,
 		.dirfd	= -1,
 	};
 
+	struct fs_parameter param_fsc = {
+		.key	= "fsc",
+		.type	= fs_value_is_string,
+		.dirfd	= -1,
+	};
+
 	if (IS_ERR(server))
 		return PTR_ERR(server);
 
@@ -168,9 +175,26 @@ static int do_nfs4_mount(struct nfs_server *server,
 	kfree(root_fc->source);
 	root_fc->source = NULL;
 
+	ctx = nfs_fc2context(fc);
 	root_ctx = nfs_fc2context(root_fc);
 	root_ctx->internal = true;
 	root_ctx->server = server;
+
+	if (ctx->fscache_uniq) {
+		len = strlen(ctx->fscache_uniq);
+		param_fsc.size = len;
+		param_fsc.string = kmemdup_nul(ctx->fscache_uniq, len, GFP_KERNEL);
+		if (param_fsc.string == NULL) {
+			put_fs_context(root_fc);
+			return -ENOMEM;
+		}
+		ret = vfs_parse_fs_param(root_fc, &param_fsc);
+		kfree(param_fsc.string);
+		if (ret < 0) {
+			put_fs_context(root_fc);
+			return ret;
+		}
+	}
 	/* We leave export_path unset as it's not used to find the root. */
 
 	len = strlen(hostname) + 5;
diff --git a/fs/nfs/nfs4trace.c b/fs/nfs/nfs4trace.c
index d9ac556bebcf..d22c6670f770 100644
--- a/fs/nfs/nfs4trace.c
+++ b/fs/nfs/nfs4trace.c
@@ -28,4 +28,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_write_pagelist);
 EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_read_error);
 EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_write_error);
 EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_commit_error);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(fl_getdevinfo);
 #endif
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index fd7cb15b08b2..10985a4b8259 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -77,6 +77,36 @@ DEFINE_NFS4_CLIENTID_EVENT(nfs4_bind_conn_to_session);
 DEFINE_NFS4_CLIENTID_EVENT(nfs4_sequence);
 DEFINE_NFS4_CLIENTID_EVENT(nfs4_reclaim_complete);
 
+TRACE_EVENT(nfs4_trunked_exchange_id,
+		TP_PROTO(
+			const struct nfs_client *clp,
+			const char *addr,
+			int error
+		),
+
+		TP_ARGS(clp, addr, error),
+
+		TP_STRUCT__entry(
+			__string(main_addr, clp->cl_hostname)
+			__string(trunk_addr, addr)
+			__field(unsigned long, error)
+		),
+
+		TP_fast_assign(
+			__entry->error = error < 0 ? -error : 0;
+			__assign_str(main_addr, clp->cl_hostname);
+			__assign_str(trunk_addr, addr);
+		),
+
+		TP_printk(
+			"error=%ld (%s) main_addr=%s trunk_addr=%s",
+			-__entry->error,
+			show_nfs4_status(__entry->error),
+			__get_str(main_addr),
+			__get_str(trunk_addr)
+		)
+);
+
 TRACE_EVENT(nfs4_sequence_done,
 		TP_PROTO(
 			const struct nfs4_session *session,
@@ -1991,6 +2021,34 @@ DECLARE_EVENT_CLASS(nfs4_deviceid_status,
 DEFINE_PNFS_DEVICEID_STATUS(nfs4_getdeviceinfo);
 DEFINE_PNFS_DEVICEID_STATUS(nfs4_find_deviceid);
 
+TRACE_EVENT(fl_getdevinfo,
+		TP_PROTO(
+			const struct nfs_server *server,
+			const struct nfs4_deviceid *deviceid,
+			char *ds_remotestr
+		),
+		TP_ARGS(server, deviceid, ds_remotestr),
+
+		TP_STRUCT__entry(
+			__string(mds_addr, server->nfs_client->cl_hostname)
+			__array(unsigned char, deviceid, NFS4_DEVICEID4_SIZE)
+			__string(ds_ips, ds_remotestr)
+		),
+
+		TP_fast_assign(
+			__assign_str(mds_addr, server->nfs_client->cl_hostname);
+			__assign_str(ds_ips, ds_remotestr);
+			memcpy(__entry->deviceid, deviceid->data,
+			       NFS4_DEVICEID4_SIZE);
+		),
+		TP_printk(
+			"deviceid=%s, mds_addr=%s, ds_ips=%s",
+			__print_hex(__entry->deviceid, NFS4_DEVICEID4_SIZE),
+			__get_str(mds_addr),
+			__get_str(ds_ips)
+		)
+);
+
 DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 		TP_PROTO(
 			const struct nfs_pgio_header *hdr
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 7600100ba26f..432612d22437 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -175,10 +175,10 @@ static int __init root_nfs_cat(char *dest, const char *src,
 	size_t len = strlen(dest);
 
 	if (len && dest[len - 1] != ',')
-		if (strlcat(dest, ",", destlen) > destlen)
+		if (strlcat(dest, ",", destlen) >= destlen)
 			return -1;
 
-	if (strlcat(dest, src, destlen) > destlen)
+	if (strlcat(dest, src, destlen) >= destlen)
 		return -1;
 	return 0;
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0c0fed1ecd0b..a5cc6199127f 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1999,6 +1999,14 @@ pnfs_update_layout(struct inode *ino,
 	}
 
 lookup_again:
+	if (!nfs4_valid_open_stateid(ctx->state)) {
+		trace_pnfs_update_layout(ino, pos, count,
+					 iomode, lo, lseg,
+					 PNFS_UPDATE_LAYOUT_INVALID_OPEN);
+		lseg = ERR_PTR(-EIO);
+		goto out;
+	}
+
 	lseg = ERR_PTR(nfs4_client_recover_expired_lease(clp));
 	if (IS_ERR(lseg))
 		goto out;
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index afd23910f3bf..88e061bd711b 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -919,6 +919,8 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 	dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr);
 
 	list_for_each_entry(da, &ds->ds_addrs, da_node) {
+		char servername[48];
+
 		dprintk("%s: DS %s: trying address %s\n",
 			__func__, ds->ds_remotestr, da->da_remotestr);
 
@@ -929,6 +931,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				.dstaddr = (struct sockaddr *)&da->da_addr,
 				.addrlen = da->da_addrlen,
 				.servername = clp->cl_hostname,
+				.xprtsec = clp->cl_xprtsec,
 			};
 			struct nfs4_add_xprt_data xprtdata = {
 				.clp = clp,
@@ -938,10 +941,45 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				.data = &xprtdata,
 			};
 
-			if (da->da_transport != clp->cl_proto)
+			if (da->da_transport != clp->cl_proto &&
+					clp->cl_proto != XPRT_TRANSPORT_TCP_TLS)
 				continue;
+			if (da->da_transport == XPRT_TRANSPORT_TCP &&
+				mds_srv->nfs_client->cl_proto ==
+					XPRT_TRANSPORT_TCP_TLS) {
+				struct sockaddr *addr =
+					(struct sockaddr *)&da->da_addr;
+				struct sockaddr_in *sin =
+					(struct sockaddr_in *)&da->da_addr;
+				struct sockaddr_in6 *sin6 =
+					(struct sockaddr_in6 *)&da->da_addr;
+
+				/* for NFS with TLS we need to supply a correct
+				 * servername of the trunked transport, not the
+				 * servername of the main transport stored in
+				 * clp->cl_hostname. And set the protocol to
+				 * indicate to use TLS
+				 */
+				servername[0] = '\0';
+				switch(addr->sa_family) {
+				case AF_INET:
+					snprintf(servername, sizeof(servername),
+						"%pI4", &sin->sin_addr.s_addr);
+					break;
+				case AF_INET6:
+					snprintf(servername, sizeof(servername),
+						"%pI6", &sin6->sin6_addr);
+					break;
+				default:
+					/* do not consider this address */
+					continue;
+				}
+				xprt_args.ident = XPRT_TRANSPORT_TCP_TLS;
+				xprt_args.servername = servername;
+			}
 			if (da->da_addr.ss_family != clp->cl_addr.ss_family)
 				continue;
+
 			/**
 			* Test this address for session trunking and
 			* add as an alias
@@ -953,6 +991,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 			if (xprtdata.cred)
 				put_cred(xprtdata.cred);
 		} else {
+			if (da->da_transport == XPRT_TRANSPORT_TCP &&
+				mds_srv->nfs_client->cl_proto ==
+					XPRT_TRANSPORT_TCP_TLS)
+				da->da_transport = XPRT_TRANSPORT_TCP_TLS;
 			clp = nfs4_set_ds_client(mds_srv,
 						&da->da_addr,
 						da->da_addrlen,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 7dc21a48e3e7..a142287d86f6 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -305,6 +305,8 @@ int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio,
 	new = nfs_page_create_from_folio(ctx, folio, 0, aligned_len);
 	if (IS_ERR(new)) {
 		error = PTR_ERR(new);
+		if (nfs_netfs_folio_unlock(folio))
+			folio_unlock(folio);
 		goto out;
 	}
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 075b31c93f87..dc03f98f7616 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -516,8 +516,16 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	else
 		nfs_show_nfsv4_options(m, nfss, showdefaults);
 
-	if (nfss->options & NFS_OPTION_FSCACHE)
+	if (nfss->options & NFS_OPTION_FSCACHE) {
+#ifdef CONFIG_NFS_FSCACHE
+		if (nfss->fscache_uniq)
+			seq_printf(m, ",fsc=%s", nfss->fscache_uniq);
+		else
+			seq_puts(m, ",fsc");
+#else
 		seq_puts(m, ",fsc");
+#endif
+	}
 
 	if (nfss->options & NFS_OPTION_MIGRATION)
 		seq_puts(m, ",migration");
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 84bb85264572..5de85d725fb9 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -667,10 +667,6 @@ static int nfs_writepage_locked(struct folio *folio,
 	struct inode *inode = folio_file_mapping(folio)->host;
 	int err;
 
-	if (wbc->sync_mode == WB_SYNC_NONE &&
-	    NFS_SERVER(inode)->write_congested)
-		return AOP_WRITEPAGE_ACTIVATE;
-
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
 	nfs_pageio_init_write(&pgio, inode, 0, false,
 			      &nfs_async_write_completion_ops);
@@ -1650,7 +1646,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo)
 				       !atomic_read(&cinfo->rpcs_out));
 }
 
-static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo)
+void nfs_commit_begin(struct nfs_mds_commit_info *cinfo)
 {
 	atomic_inc(&cinfo->rpcs_out);
 }