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
  ...

Author: torvalds

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);
 }

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 @@ static int nfs_delegation_claim_opens(struct inode *inode,
 		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)

fs/nfs/direct.c

@@ -606,13 +606,15 @@ 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;
 		dreq->flags = NFS_ODIRECT_DONE;
 	} 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)

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)) {

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)

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;

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);

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();

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);

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