Merge tag 'nfs-for-6.10-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Stable fixes:
   - nfs: fix undefined behavior in nfs_block_bits()
   - NFSv4.2: Fix READ_PLUS when server doesn't support OP_READ_PLUS

  Bugfixes:
   - Fix mixing of the lock/nolock and local_lock mount options
   - NFSv4: Fixup smatch warning for ambiguous return
   - NFSv3: Fix remount when using the legacy binary mount api
   - SUNRPC: Fix the handling of expired RPCSEC_GSS contexts
   - SUNRPC: fix the NFSACL RPC retries when soft mounts are enabled
   - rpcrdma: fix handling for RDMA_CM_EVENT_DEVICE_REMOVAL

  Features and cleanups:
   - NFSv3: Use the atomic_open API to fix open(O_CREAT|O_TRUNC)
   - pNFS/filelayout: S layout segment range in LAYOUTGET
   - pNFS: rework pnfs_generic_pg_check_layout to check IO range
   - NFSv2: Turn off enabling of NFS v2 by default"

* tag 'nfs-for-6.10-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  nfs: fix undefined behavior in nfs_block_bits()
  pNFS: rework pnfs_generic_pg_check_layout to check IO range
  pNFS/filelayout: check layout segment range
  pNFS/filelayout: fixup pNfs allocation modes
  rpcrdma: fix handling for RDMA_CM_EVENT_DEVICE_REMOVAL
  NFS: Don't enable NFS v2 by default
  NFS: Fix READ_PLUS when server doesn't support OP_READ_PLUS
  sunrpc: fix NFSACL RPC retry on soft mount
  SUNRPC: fix handling expired GSS context
  nfs: keep server info for remounts
  NFSv4: Fixup smatch warning for ambiguous return
  NFS: make sure lock/nolock overriding local_lock mount option
  NFS: add atomic_open for NFSv3 to handle O_TRUNC correctly.
  pNFS/filelayout: Specify the layout segment range in LAYOUTGET
  pNFS/filelayout: Remove the whole file layout requirement

fs/nfs/Kconfig

@@ -33,12 +33,12 @@ config NFS_FS
 config NFS_V2
 	tristate "NFS client support for NFS version 2"
 	depends on NFS_FS
-	default y
+	default n
 	help
 	  This option enables support for version 2 of the NFS protocol
 	  (RFC 1094) in the kernel's NFS client.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config NFS_V3
 	tristate "NFS client support for NFS version 3"

fs/nfs/dir.c

@@ -56,6 +56,8 @@ static int nfs_readdir(struct file *, struct dir_context *);
 static int nfs_fsync_dir(struct file *, loff_t, loff_t, int);
 static loff_t nfs_llseek_dir(struct file *, loff_t, int);
 static void nfs_readdir_clear_array(struct folio *);
+static int nfs_do_create(struct inode *dir, struct dentry *dentry,
+			 umode_t mode, int open_flags);
 
 const struct file_operations nfs_dir_operations = {
 	.llseek		= nfs_llseek_dir,
@@ -2243,6 +2245,41 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 
 #endif /* CONFIG_NFSV4 */
 
+int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry,
+			struct file *file, unsigned int open_flags,
+			umode_t mode)
+{
+
+	/* Same as look+open from lookup_open(), but with different O_TRUNC
+	 * handling.
+	 */
+	int error = 0;
+
+	if (open_flags & O_CREAT) {
+		file->f_mode |= FMODE_CREATED;
+		error = nfs_do_create(dir, dentry, mode, open_flags);
+		if (error)
+			return error;
+		return finish_open(file, dentry, NULL);
+	} else if (d_in_lookup(dentry)) {
+		/* The only flags nfs_lookup considers are
+		 * LOOKUP_EXCL and LOOKUP_RENAME_TARGET, and
+		 * we want those to be zero so the lookup isn't skipped.
+		 */
+		struct dentry *res = nfs_lookup(dir, dentry, 0);
+
+		d_lookup_done(dentry);
+		if (unlikely(res)) {
+			if (IS_ERR(res))
+				return PTR_ERR(res);
+			return finish_no_open(file, res);
+		}
+	}
+	return finish_no_open(file, NULL);
+
+}
+EXPORT_SYMBOL_GPL(nfs_atomic_open_v23);
+
 struct dentry *
 nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle,
 				struct nfs_fattr *fattr)
@@ -2303,18 +2340,23 @@ EXPORT_SYMBOL_GPL(nfs_instantiate);
  * that the operation succeeded on the server, but an error in the
  * reply path made it appear to have failed.
  */
-int nfs_create(struct mnt_idmap *idmap, struct inode *dir,
-	       struct dentry *dentry, umode_t mode, bool excl)
+static int nfs_do_create(struct inode *dir, struct dentry *dentry,
+			 umode_t mode, int open_flags)
 {
 	struct iattr attr;
-	int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT;
 	int error;
 
+	open_flags |= O_CREAT;
+
 	dfprintk(VFS, "NFS: create(%s/%lu), %pd\n",
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
 	attr.ia_mode = mode;
 	attr.ia_valid = ATTR_MODE;
+	if (open_flags & O_TRUNC) {
+		attr.ia_size = 0;
+		attr.ia_valid |= ATTR_SIZE;
+	}
 
 	trace_nfs_create_enter(dir, dentry, open_flags);
 	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags);
@@ -2326,6 +2368,12 @@ int nfs_create(struct mnt_idmap *idmap, struct inode *dir,
 	d_drop(dentry);
 	return error;
 }
+
+int nfs_create(struct mnt_idmap *idmap, struct inode *dir,
+	       struct dentry *dentry, umode_t mode, bool excl)
+{
+	return nfs_do_create(dir, dentry, mode, excl ? O_EXCL : 0);
+}
 EXPORT_SYMBOL_GPL(nfs_create);
 
 /*

fs/nfs/filelayout/filelayout.c

@@ -605,14 +605,6 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 
 	dprintk("--> %s\n", __func__);
 
-	/* FIXME: remove this check when layout segment support is added */
-	if (lgr->range.offset != 0 ||
-	    lgr->range.length != NFS4_MAX_UINT64) {
-		dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
-			__func__);
-		goto out;
-	}
-
 	if (fl->pattern_offset > lgr->range.offset) {
 		dprintk("%s pattern_offset %lld too large\n",
 				__func__, fl->pattern_offset);
@@ -875,15 +867,15 @@ static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
-	pnfs_generic_pg_check_layout(pgio);
+	pnfs_generic_pg_check_layout(pgio, req);
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
 						      nfs_req_openctx(req),
-						      0,
-						      NFS4_MAX_UINT64,
+						      req_offset(req),
+						      req->wb_bytes,
 						      IOMODE_READ,
 						      false,
-						      GFP_KERNEL);
+						      nfs_io_gfp_mask());
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;
@@ -899,15 +891,15 @@ static void
 filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			 struct nfs_page *req)
 {
-	pnfs_generic_pg_check_layout(pgio);
+	pnfs_generic_pg_check_layout(pgio, req);
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
 						      nfs_req_openctx(req),
-						      0,
-						      NFS4_MAX_UINT64,
+						      req_offset(req),
+						      req->wb_bytes,
 						      IOMODE_RW,
 						      false,
-						      GFP_NOFS);
+						      nfs_io_gfp_mask());
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;

fs/nfs/flexfilelayout/flexfilelayout.c

@@ -822,14 +822,6 @@ ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
 	}
 }
 
-static void
-ff_layout_pg_check_layout(struct nfs_pageio_descriptor *pgio,
-			  struct nfs_page *req)
-{
-	pnfs_generic_pg_check_layout(pgio);
-	pnfs_generic_pg_check_range(pgio, req);
-}
-
 static void
 ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
@@ -840,7 +832,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	u32 ds_idx;
 
 retry:
-	ff_layout_pg_check_layout(pgio, req);
+	pnfs_generic_pg_check_layout(pgio, req);
 	/* Use full layout for now */
 	if (!pgio->pg_lseg) {
 		ff_layout_pg_get_read(pgio, req, false);
@@ -895,7 +887,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	u32 i;
 
 retry:
-	ff_layout_pg_check_layout(pgio, req);
+	pnfs_generic_pg_check_layout(pgio, req);
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg =
 			pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req),

fs/nfs/fs_context.c

@@ -600,9 +600,11 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		break;
 	case Opt_lock:
 		if (result.negated) {
+			ctx->lock_status = NFS_LOCK_NOLOCK;
 			ctx->flags |= NFS_MOUNT_NONLM;
 			ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL);
 		} else {
+			ctx->lock_status = NFS_LOCK_LOCK;
 			ctx->flags &= ~NFS_MOUNT_NONLM;
 			ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL);
 		}
@@ -1112,9 +1114,12 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 		ctx->acdirmax	= data->acdirmax;
 		ctx->need_mount	= false;
 
-		memcpy(sap, &data->addr, sizeof(data->addr));
-		ctx->nfs_server.addrlen = sizeof(data->addr);
-		ctx->nfs_server.port = ntohs(data->addr.sin_port);
+		if (!is_remount_fc(fc)) {
+			memcpy(sap, &data->addr, sizeof(data->addr));
+			ctx->nfs_server.addrlen = sizeof(data->addr);
+			ctx->nfs_server.port = ntohs(data->addr.sin_port);
+		}
+
 		if (sap->ss_family != AF_INET ||
 		    !nfs_verify_server_address(sap))
 			goto out_no_address;

fs/nfs/internal.h

@@ -112,6 +112,7 @@ struct nfs_fs_context {
 	unsigned short		protofamily;
 	unsigned short		mountfamily;
 	bool			has_sec_mnt_opts;
+	int			lock_status;
 
 	struct {
 		union {
@@ -153,6 +154,12 @@ struct nfs_fs_context {
 	} clone_data;
 };
 
+enum nfs_lock_status {
+	NFS_LOCK_NOT_SET	= 0,
+	NFS_LOCK_LOCK		= 1,
+	NFS_LOCK_NOLOCK		= 2,
+};
+
 #define nfs_errorf(fc, fmt, ...) ((fc)->log.log ?		\
 	errorf(fc, fmt, ## __VA_ARGS__) :			\
 	({ dprintk(fmt "\n", ## __VA_ARGS__); }))
@@ -710,9 +717,9 @@ unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp)
 	if ((bsize & (bsize - 1)) || nrbitsp) {
 		unsigned char	nrbits;
 
-		for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--)
+		for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--)
 			;
-		bsize = 1 << nrbits;
+		bsize = 1UL << nrbits;
 		if (nrbitsp)
 			*nrbitsp = nrbits;
 	}

fs/nfs/nfs3proc.c

@@ -986,6 +986,7 @@ static int nfs3_have_delegation(struct inode *inode, fmode_t flags)
 
 static const struct inode_operations nfs3_dir_inode_operations = {
 	.create		= nfs_create,
+	.atomic_open	= nfs_atomic_open_v23,
 	.lookup		= nfs_lookup,
 	.link		= nfs_link,
 	.unlink		= nfs_unlink,

fs/nfs/nfs4proc.c

@@ -5456,7 +5456,7 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task,
 	struct rpc_message *msg = &task->tk_msg;
 
 	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] &&
-	    server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) {
+	    task->tk_status == -ENOTSUPP) {
 		server->caps &= ~NFS_CAP_READ_PLUS;
 		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
 		rpc_restart_call_prepare(task);

fs/nfs/nfs4state.c

@@ -2116,6 +2116,7 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_fs_locations *locations = NULL;
+	struct nfs_fattr *fattr;
 	struct inode *inode;
 	struct page *page;
 	int status, result;
@@ -2125,19 +2126,16 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
 			(unsigned long long)server->fsid.minor,
 			clp->cl_hostname);
 
-	result = 0;
 	page = alloc_page(GFP_KERNEL);
 	locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
-	if (page == NULL || locations == NULL) {
-		dprintk("<-- %s: no memory\n", __func__);
-		goto out;
-	}
-	locations->fattr = nfs_alloc_fattr();
-	if (locations->fattr == NULL) {
+	fattr = nfs_alloc_fattr();
+	if (page == NULL || locations == NULL || fattr == NULL) {
 		dprintk("<-- %s: no memory\n", __func__);
+		result = 0;
 		goto out;
 	}
 
+	locations->fattr = fattr;
 	inode = d_inode(server->super->s_root);
 	result = nfs4_proc_get_locations(server, NFS_FH(inode), locations,
 					 page, cred);

fs/nfs/pnfs.c

@@ -2705,38 +2705,28 @@ pnfs_layout_return_unused_byclid(struct nfs_client *clp,
 			&range);
 }
 
+/* Check if we have we have a valid layout but if there isn't an intersection
+ * between the request and the pgio->pg_lseg, put this pgio->pg_lseg away.
+ */
 void
-pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio)
+pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio,
+			     struct nfs_page *req)
 {
 	if (pgio->pg_lseg == NULL ||
-	    test_bit(NFS_LSEG_VALID, &pgio->pg_lseg->pls_flags))
+	    (test_bit(NFS_LSEG_VALID, &pgio->pg_lseg->pls_flags) &&
+	    pnfs_lseg_request_intersecting(pgio->pg_lseg, req)))
 		return;
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_layout);
 
-/*
- * Check for any intersection between the request and the pgio->pg_lseg,
- * and if none, put this pgio->pg_lseg away.
- */
-void
-pnfs_generic_pg_check_range(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
-{
-	if (pgio->pg_lseg && !pnfs_lseg_request_intersecting(pgio->pg_lseg, req)) {
-		pnfs_put_lseg(pgio->pg_lseg);
-		pgio->pg_lseg = NULL;
-	}
-}
-EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_range);
-
 void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	u64 rd_size;
 
-	pnfs_generic_pg_check_layout(pgio);
-	pnfs_generic_pg_check_range(pgio, req);
+	pnfs_generic_pg_check_layout(pgio, req);
 	if (pgio->pg_lseg == NULL) {
 		if (pgio->pg_dreq == NULL)
 			rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
@@ -2766,8 +2756,7 @@ void
 pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			   struct nfs_page *req, u64 wb_size)
 {
-	pnfs_generic_pg_check_layout(pgio);
-	pnfs_generic_pg_check_range(pgio, req);
+	pnfs_generic_pg_check_layout(pgio, req);
 	if (pgio->pg_lseg == NULL) {
 		pgio->pg_lseg =
 			pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req),

fs/nfs/pnfs.h

@@ -257,8 +257,7 @@ void pnfs_put_lseg(struct pnfs_layout_segment *lseg);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, struct nfs_fsinfo *);
 void unset_pnfs_layoutdriver(struct nfs_server *);
-void pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio);
-void pnfs_generic_pg_check_range(struct nfs_pageio_descriptor *pgio, struct nfs_page *req);
+void pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio, struct nfs_page *req);
 void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,

fs/nfs/proc.c

@@ -695,6 +695,7 @@ static int nfs_have_delegation(struct inode *inode, fmode_t flags)
 static const struct inode_operations nfs_dir_inode_operations = {
 	.create		= nfs_create,
 	.lookup		= nfs_lookup,
+	.atomic_open	= nfs_atomic_open_v23,
 	.link		= nfs_link,
 	.unlink		= nfs_unlink,
 	.symlink	= nfs_symlink,

fs/nfs/super.c

@@ -901,6 +901,16 @@ static struct nfs_server *nfs_try_mount_request(struct fs_context *fc)
 	rpc_authflavor_t authlist[NFS_MAX_SECFLAVORS];
 	unsigned int authlist_len = ARRAY_SIZE(authlist);
 
+	/* make sure 'nolock'/'lock' override the 'local_lock' mount option */
+	if (ctx->lock_status) {
+		if (ctx->lock_status == NFS_LOCK_NOLOCK) {
+			ctx->flags |= NFS_MOUNT_NONLM;
+			ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL);
+		} else {
+			ctx->flags &= ~NFS_MOUNT_NONLM;
+			ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL);
+		}
+	}
 	status = nfs_request_mount(fc, ctx->mntfh, authlist, &authlist_len);
 	if (status)
 		return ERR_PTR(status);

include/linux/nfs_fs.h

@@ -561,6 +561,9 @@ extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openfl
 extern void nfs_access_zap_cache(struct inode *inode);
 extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred,
 				 u32 *mask, bool may_block);
+extern int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry,
+			       struct file *file, unsigned int open_flags,
+			       umode_t mode);
 
 /*
  * linux/fs/nfs/symlink.c

net/sunrpc/clnt.c

@@ -1071,6 +1071,7 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old,
 		.authflavor	= old->cl_auth->au_flavor,
 		.cred		= old->cl_cred,
 		.stats		= old->cl_stats,
+		.timeout	= old->cl_timeout,
 	};
 	struct rpc_clnt *clnt;
 	int err;
@@ -2698,8 +2699,19 @@ rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr)
 		goto out_msg_denied;
 
 	error = rpcauth_checkverf(task, xdr);
-	if (error)
+	if (error) {
+		struct rpc_cred *cred = task->tk_rqstp->rq_cred;
+
+		if (!test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags)) {
+			rpcauth_invalcred(task);
+			if (!task->tk_cred_retry)
+				goto out_err;
+			task->tk_cred_retry--;
+			trace_rpc__stale_creds(task);
+			return -EKEYREJECTED;
+		}
 		goto out_verifier;
+	}
 
 	p = xdr_inline_decode(xdr, sizeof(*p));
 	if (!p)

net/sunrpc/xprtrdma/verbs.c

@@ -244,7 +244,11 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
 		pr_info("rpcrdma: removing device %s for %pISpc\n",
 			ep->re_id->device->name, sap);
-		fallthrough;
+		switch (xchg(&ep->re_connect_status, -ENODEV)) {
+		case 0: goto wake_connect_worker;
+		case 1: goto disconnected;
+		}
+		return 0;
 	case RDMA_CM_EVENT_ADDR_CHANGE:
 		ep->re_connect_status = -ENODEV;
 		goto disconnected;