Merge: NFS/NFSD/LOCKD/SUNRPC fixes/stable updates for RHEL 9.8

CKI KWF Bot · CKI KWF Bot · commit 2c04075e4a77 · 2025-10-21T08:22:03.000Z
MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7471 NFS/NFSD/LOCKD/SUNRPC fixes/stable updates for RHEL 9.8. We already got most of the commits we want via RHEL-108616, so this is mostly a handful of commits from v6.17 and later. JIRA: https://issues.redhat.com/browse/RHEL-115855 Signed-off-by: Scott Mayhew <smayhew@redhat.com> Approved-by: Steve Dickson <steved@redhat.com> Approved-by: Olga Kornievskaia <okorniev@redhat.com> Approved-by: Benjamin Coddington <bcodding@redhat.com> Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com> Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
@@ -409,10 +409,11 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset,
 	dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n",
 		 folio->index, offset, length);
 
-	if (offset != 0 || length < folio_size(folio))
-		return;
 	/* Cancel any unstarted writes on this page */
-	nfs_wb_folio_cancel(inode, folio);
+	if (offset != 0 || length < folio_size(folio))
+		nfs_wb_folio(inode, folio);
+	else
+		nfs_wb_folio_cancel(inode, folio);
 	folio_wait_fscache(folio);
 	trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length);
 }
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
@@ -721,8 +721,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	trace_nfs_setattr_enter(inode);
 
 	/* Write all dirty data */
-	if (S_ISREG(inode->i_mode))
+	if (S_ISREG(inode->i_mode)) {
+		nfs_file_block_o_direct(NFS_I(inode));
 		nfs_sync_inode(inode);
+	}
 
 	fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
 	if (fattr == NULL) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
@@ -478,6 +478,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi)
 	return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0;
 }
 
+/* Must be called with exclusively locked inode->i_rwsem */
+static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi)
+{
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
+		inode_dio_wait(&nfsi->vfs_inode);
+	}
+}
+
+
 /* namespace.c */
 #define NFS_PATH_CANONICAL 1
 extern char *nfs_path(char **p, struct dentry *dentry,
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
@@ -14,15 +14,6 @@
 
 #include "internal.h"
 
-/* Call with exclusively locked inode->i_rwsem */
-static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode)
-{
-	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
-		clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
-		inode_dio_wait(inode);
-	}
-}
-
 /**
  * nfs_start_io_read - declare the file is being used for buffered reads
  * @inode: file inode
@@ -50,7 +41,7 @@ nfs_start_io_read(struct inode *inode)
 	up_read(&inode->i_rwsem);
 	/* Slow path.... */
 	down_write(&inode->i_rwsem);
-	nfs_block_o_direct(nfsi, inode);
+	nfs_file_block_o_direct(nfsi);
 	downgrade_write(&inode->i_rwsem);
 }
 
@@ -78,7 +69,7 @@ void
 nfs_start_io_write(struct inode *inode)
 {
 	down_write(&inode->i_rwsem);
-	nfs_block_o_direct(NFS_I(inode), inode);
+	nfs_file_block_o_direct(NFS_I(inode));
 }
 
 /**
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
@@ -112,6 +112,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	exception.inode = inode;
 	exception.state = lock->open_context->state;
 
+	nfs_file_block_o_direct(NFS_I(inode));
 	err = nfs_sync_inode(inode);
 	if (err)
 		goto out;
@@ -355,6 +356,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 		return status;
 	}
 
+	nfs_file_block_o_direct(NFS_I(dst_inode));
 	status = nfs_sync_inode(dst_inode);
 	if (status)
 		return status;
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
@@ -282,9 +282,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 
 	/* flush all pending writes on both src and dst so that server
 	 * has the latest data */
+	nfs_file_block_o_direct(NFS_I(src_inode));
 	ret = nfs_sync_inode(src_inode);
 	if (ret)
 		goto out_unlock;
+	nfs_file_block_o_direct(NFS_I(dst_inode));
 	ret = nfs_sync_inode(dst_inode);
 	if (ret)
 		goto out_unlock;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
@@ -7826,10 +7826,10 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
 		return err;
 	do {
 		err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
-		if (err != -NFS4ERR_DELAY)
+		if (err != -NFS4ERR_DELAY && err != -NFS4ERR_GRACE)
 			break;
 		ssleep(1);
-	} while (err == -NFS4ERR_DELAY);
+	} while (err == -NFS4ERR_DELAY || err == -NFSERR_GRACE);
 	return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err);
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
@@ -2050,6 +2050,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio)
 		 * release it */
 		nfs_inode_remove_request(req);
 		nfs_unlock_and_release_request(req);
+		folio_cancel_dirty(folio);
 	}
 
 	return ret;
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
@@ -1086,28 +1086,62 @@ static struct svc_export *exp_find(struct cache_detail *cd,
 	return exp;
 }
 
-__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
+/**
+ * check_xprtsec_policy - check if access to export is allowed by the
+ * 			  xprtsec policy
+ * @exp: svc_export that is being accessed.
+ * @rqstp: svc_rqst attempting to access @exp.
+ *
+ * Helper function for check_nfsd_access().  Note that callers should be
+ * using check_nfsd_access() instead of calling this function directly.  The
+ * one exception is fh_verify() since it has logic that may result in one
+ * or both of the helpers being skipped.
+ *
+ * Return values:
+ *   %nfs_ok if access is granted, or
+ *   %nfserr_acces or %nfserr_wrongsec if access is denied
+ */
+__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp)
 {
-	struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors;
 	struct svc_xprt *xprt = rqstp->rq_xprt;
 
 	if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_NONE) {
 		if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags))
-			goto ok;
+			return nfs_ok;
 	}
 	if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_TLS) {
 		if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) &&
 		    !test_bit(XPT_PEER_AUTH, &xprt->xpt_flags))
-			goto ok;
+			return nfs_ok;
 	}
 	if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_MTLS) {
 		if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) &&
 		    test_bit(XPT_PEER_AUTH, &xprt->xpt_flags))
-			goto ok;
+			return nfs_ok;
 	}
-	goto denied;
 
-ok:
+	return nfserr_wrongsec;
+}
+
+/**
+ * check_security_flavor - check if access to export is allowed by the
+ * 			  xprtsec policy
+ * @exp: svc_export that is being accessed.
+ * @rqstp: svc_rqst attempting to access @exp.
+ *
+ * Helper function for check_nfsd_access().  Note that callers should be
+ * using check_nfsd_access() instead of calling this function directly.  The
+ * one exception is fh_verify() since it has logic that may result in one
+ * or both of the helpers being skipped.
+ *
+ * Return values:
+ *   %nfs_ok if access is granted, or
+ *   %nfserr_acces or %nfserr_wrongsec if access is denied
+ */
+__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp)
+{
+	struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors;
+
 	/* legacy gss-only clients are always OK: */
 	if (exp->ex_client == rqstp->rq_gssclient)
 		return 0;
@@ -1132,10 +1166,20 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
 	if (nfsd4_spo_must_allow(rqstp))
 		return 0;
 
-denied:
 	return nfserr_wrongsec;
 }
 
+__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
+{
+	__be32 status;
+
+	status = check_xprtsec_policy(exp, rqstp);
+	if (status != nfs_ok)
+		return status;
+
+	return check_security_flavor(exp, rqstp);
+}
+
 /*
  * Uses rq_client and rq_gssclient to find an export; uses rq_client (an
  * auth_unix client) if it's available and has secinfo information;
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
@@ -100,6 +100,8 @@ struct svc_expkey {
 #define EX_WGATHER(exp)		((exp)->ex_flags & NFSEXP_GATHERED_WRITES)
 
 int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp);
+__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp);
+__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp);
 __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp);
 
 /*
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
@@ -48,6 +48,21 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp,
 	switch (nfserr) {
 	case nfs_ok:
 		return 0;
+	case nfserr_jukebox:
+		/* this error can indicate a presence of a conflicting
+		 * delegation to an NLM lock request. Options are:
+		 * (1) For now, drop this request and make the client
+		 * retry. When delegation is returned, client's lock retry
+		 * will complete.
+		 * (2) NLM4_DENIED as per "spec" signals to the client
+		 * that the lock is unavailable now but client can retry.
+		 * Linux client implementation does not. It treats
+		 * NLM4_DENIED same as NLM4_FAILED and errors the request.
+		 * (3) For the future, treat this as blocked lock and try
+		 * to callback when the delegation is returned but might
+		 * not have a proper lock request to block on.
+		 */
+		fallthrough;
 	case nfserr_dropit:
 		return nlm_drop_reply;
 	case nfserr_stale:
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
@@ -7998,11 +7998,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (check_lock_length(lock->lk_offset, lock->lk_length))
 		 return nfserr_inval;
 
-	if ((status = fh_verify(rqstp, &cstate->current_fh,
-				S_IFREG, NFSD_MAY_LOCK))) {
-		dprintk("NFSD: nfsd4_lock: permission denied!\n");
+	status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0);
+	if (status != nfs_ok)
 		return status;
-	}
 
 	if (lock->lk_is_new) {
 		if (nfsd4_has_session(cstate))
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
@@ -364,6 +364,16 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
 	if (error)
 		goto out;
 
+	/*
+	 * NLM is allowed to bypass the xprtsec policy check because lockd
+	 * doesn't support xprtsec.
+	 */
+	if (!(access & NFSD_MAY_LOCK)) {
+		error = check_xprtsec_policy(exp, rqstp);
+		if (error)
+			goto out;
+	}
+
 	/*
 	 * pseudoflavor restrictions are not enforced on NLM,
 	 * which clients virtually always use auth_sys for,
@@ -380,7 +390,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
 			&& exp->ex_path.dentry == dentry)
 		goto skip_pseudoflavor_check;
 
-	error = check_nfsd_access(exp, rqstp);
+	error = check_security_flavor(exp, rqstp);
 	if (error)
 		goto out;
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
@@ -468,7 +468,15 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
 	if (!iap->ia_valid)
 		return 0;
 
-	iap->ia_valid |= ATTR_CTIME;
+	/*
+	 * If ATTR_DELEG is set, then this is an update from a client that
+	 * holds a delegation. If this is an update for only the atime, the
+	 * ctime should not be changed. If the update contains the mtime
+	 * too, then ATTR_CTIME should already be set.
+	 */
+	if (!(iap->ia_valid & ATTR_DELEG))
+		iap->ia_valid |= ATTR_CTIME;
+
 	return notify_change(&nop_mnt_idmap, dentry, iap, NULL);
 }
 
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
@@ -99,6 +99,9 @@ enum {
 	XPT_HANDSHAKE,		/* xprt requests a handshake */
 	XPT_TLS_SESSION,	/* transport-layer security established */
 	XPT_PEER_AUTH,		/* peer has been authenticated */
+	XPT_RPCB_UNREG,		/* transport that needs unregistering
+				 * with rpcbind (TCP, UDP) on destroy
+				 */
 };
 
 static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
@@ -1038,6 +1038,19 @@ static void svc_delete_xprt(struct svc_xprt *xprt)
 	struct svc_serv	*serv = xprt->xpt_server;
 	struct svc_deferred_req *dr;
 
+	/* unregister with rpcbind for when transport type is TCP or UDP.
+	 */
+	if (test_bit(XPT_RPCB_UNREG, &xprt->xpt_flags)) {
+		struct svc_sock *svsk = container_of(xprt, struct svc_sock,
+						     sk_xprt);
+		struct socket *sock = svsk->sk_sock;
+
+		if (svc_register(serv, xprt->xpt_net, sock->sk->sk_family,
+				 sock->sk->sk_protocol, 0) < 0)
+			pr_warn("failed to unregister %s with rpcbind\n",
+				xprt->xpt_class->xcl_name);
+	}
+
 	if (test_and_set_bit(XPT_DEAD, &xprt->xpt_flags))
 		return;
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
@@ -836,6 +836,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	/* data might have come in before data_ready set up */
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 	set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
+	set_bit(XPT_RPCB_UNREG, &svsk->sk_xprt.xpt_flags);
 
 	/* make sure we get destination address info */
 	switch (svsk->sk_sk->sk_family) {
@@ -1406,6 +1407,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	if (sk->sk_state == TCP_LISTEN) {
 		strcpy(svsk->sk_xprt.xpt_remotebuf, "listener");
 		set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
+		set_bit(XPT_RPCB_UNREG, &svsk->sk_xprt.xpt_flags);
 		sk->sk_data_ready = svc_tcp_listen_data_ready;
 		set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
 	} else {

Original file line number	Diff line number	Diff line change
`@@ -2050,6 +2050,7 @@ int nfs_wb_folio_cancel(struct inode inode, struct folio folio)`
`2050`	`2050`	`* release it */`
`2051`	`2051`	`nfs_inode_remove_request(req);`
`2052`	`2052`	`nfs_unlock_and_release_request(req);`
	`2053`	`+ folio_cancel_dirty(folio);`
`2053`	`2054`	`}`
`2054`	`2055`
`2055`	`2056`	`return ret;`