Merge tag 'nfs-for-6.15-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:

 - NFS: Fix a couple of missed handlers for the ENETDOWN and ENETUNREACH
   transport errors

 - NFS: Handle Oopsable failure of nfs_get_lock_context in the unlock
   path

 - NFSv4: Fix a race in nfs_local_open_fh()

 - NFSv4/pNFS: Fix a couple of layout segment leaks in layoutreturn

 - NFSv4/pNFS Avoid sharing pNFS DS connections between net namespaces
   since IP addresses are not guaranteed to refer to the same nodes

 - NFS: Don't flush file data while holding multiple directory locks in
   nfs_rename()

* tag 'nfs-for-6.15-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS: Avoid flushing data while holding directory locks in nfs_rename()
  NFS/pnfs: Fix the error path in pnfs_layoutreturn_retry_later_locked()
  NFSv4/pnfs: Reset the layout state after a layoutreturn
  NFS/localio: Fix a race in nfs_local_open_fh()
  nfs: nfs3acl: drop useless assignment in nfs3_get_acl()
  nfs: direct: drop useless initializer in nfs_direct_write_completion()
  nfs: move the nfs4_data_server_cache into struct nfs_net
  nfs: don't share pNFS DS connections between net namespaces
  nfs: handle failure of nfs_get_lock_context in unlock path
  pNFS/flexfiles: Record the RPC errors in the I/O tracepoints
  NFSv4/pnfs: Layoutreturn on close must handle fatal networking errors
  NFSv4: Handle fatal ENETDOWN and ENETUNREACH errors

Author: torvalds

fs/nfs/client.c

@@ -1105,6 +1105,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc)
 		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
 			server->namelen = NFS2_MAXNAMLEN;
 	}
+	/* Linux 'subtree_check' borkenness mandates this setting */
+	server->fh_expire_type = NFS_FH_VOL_RENAME;
 
 	if (!(fattr->valid & NFS_ATTR_FATTR)) {
 		error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh,
@@ -1199,6 +1201,10 @@ void nfs_clients_init(struct net *net)
 	INIT_LIST_HEAD(&nn->nfs_volume_list);
 #if IS_ENABLED(CONFIG_NFS_V4)
 	idr_init(&nn->cb_ident_idr);
+#endif
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	INIT_LIST_HEAD(&nn->nfs4_data_server_cache);
+	spin_lock_init(&nn->nfs4_data_server_lock);
 #endif
 	spin_lock_init(&nn->nfs_client_lock);
 	nn->boot_time = ktime_get_real();
@@ -1216,6 +1222,9 @@ void nfs_clients_exit(struct net *net)
 	nfs_cleanup_cb_ident_idr(net);
 	WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
 	WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	WARN_ON_ONCE(!list_empty(&nn->nfs4_data_server_cache));
+#endif
 }
 
 #ifdef CONFIG_PROC_FS

fs/nfs/dir.c

@@ -2676,6 +2676,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data)
 	unblock_revalidate(new_dentry);
 }
 
+static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry,
+					   struct dentry *new_dentry)
+{
+	struct nfs_server *server = NFS_SB(old_dentry->d_sb);
+
+	if (old_dentry->d_parent != new_dentry->d_parent)
+		return false;
+	if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE)
+		return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN);
+	return true;
+}
+
 /*
  * RENAME
  * FIXME: Some nfsds, like the Linux user space nfsd, may generate a
@@ -2763,7 +2775,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 
 	}
 
-	if (S_ISREG(old_inode->i_mode))
+	if (S_ISREG(old_inode->i_mode) &&
+	    nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry))
 		nfs_sync_inode(old_inode);
 	task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry,
 				must_unblock ? nfs_unblock_rename : NULL);

fs/nfs/direct.c

@@ -757,7 +757,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_direct_req *dreq = hdr->dreq;
 	struct nfs_commit_info cinfo;
-	struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 	struct inode *inode = dreq->inode;
 	int flags = NFS_ODIRECT_DONE;
 
@@ -786,6 +785,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	spin_unlock(&inode->i_lock);
 
 	while (!list_empty(&hdr->pages)) {
+		struct nfs_page *req;
 
 		req = nfs_list_entry(hdr->pages.next);
 		nfs_list_remove_request(req);

fs/nfs/filelayout/filelayoutdev.c

@@ -76,6 +76,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct page *scratch;
 	struct list_head dsaddrs;
 	struct nfs4_pnfs_ds_addr *da;
+	struct net *net = server->nfs_client->cl_net;
 
 	/* set up xdr stream */
 	scratch = alloc_page(gfp_flags);
@@ -159,8 +160,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
-						    &stream, gfp_flags);
+			da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
 		}
@@ -170,7 +170,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 			goto out_err_free_deviceid;
 		}
 
-		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &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);

fs/nfs/flexfilelayout/flexfilelayout.c

@@ -1329,7 +1329,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 					    hdr->args.offset, hdr->args.count,
 					    &hdr->res.op_status, OP_READ,
 					    task->tk_status);
-		trace_ff_layout_read_error(hdr);
+		trace_ff_layout_read_error(hdr, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1502,7 +1502,7 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 					    hdr->args.offset, hdr->args.count,
 					    &hdr->res.op_status, OP_WRITE,
 					    task->tk_status);
-		trace_ff_layout_write_error(hdr);
+		trace_ff_layout_write_error(hdr, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1551,7 +1551,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 					    data->args.offset, data->args.count,
 					    &data->res.op_status, OP_COMMIT,
 					    task->tk_status);
-		trace_ff_layout_commit_error(data);
+		trace_ff_layout_commit_error(data, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, NULL, data->ds_clp,

fs/nfs/flexfilelayout/flexfilelayoutdev.c

@@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct nfs4_pnfs_ds_addr *da;
 	struct nfs4_ff_layout_ds *new_ds = NULL;
 	struct nfs4_ff_ds_version *ds_versions = NULL;
+	struct net *net = server->nfs_client->cl_net;
 	u32 mp_count;
 	u32 version_count;
 	__be32 *p;
@@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 	for (i = 0; i < mp_count; i++) {
 		/* multipath ds */
-		da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
-					    &stream, gfp_flags);
+		da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
 		if (da)
 			list_add_tail(&da->da_node, &dsaddrs);
 	}
@@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	new_ds->ds_versions = ds_versions;
 	new_ds->ds_versions_cnt = version_count;
 
-	new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+	new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
 	if (!new_ds->ds)
 		goto out_err_drain_dsaddrs;
 

fs/nfs/localio.c

@@ -278,6 +278,7 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 		new = __nfs_local_open_fh(clp, cred, fh, nfl, mode);
 		if (IS_ERR(new))
 			return NULL;
+		rcu_read_lock();
 		/* try to swap in the pointer */
 		spin_lock(&clp->cl_uuid.lock);
 		nf = rcu_dereference_protected(*pnf, 1);
@@ -287,7 +288,6 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 			rcu_assign_pointer(*pnf, nf);
 		}
 		spin_unlock(&clp->cl_uuid.lock);
-		rcu_read_lock();
 	}
 	nf = nfs_local_file_get(nf);
 	rcu_read_unlock();

fs/nfs/netns.h

@@ -31,7 +31,11 @@ struct nfs_net {
 	unsigned short nfs_callback_tcpport;
 	unsigned short nfs_callback_tcpport6;
 	int cb_users[NFS4_MAX_MINOR_VERSION + 1];
-#endif
+#endif /* CONFIG_NFS_V4 */
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	struct list_head nfs4_data_server_cache;
+	spinlock_t nfs4_data_server_lock;
+#endif /* CONFIG_NFS_V4_1 */
 	struct nfs_netns_client *nfs_client;
 	spinlock_t nfs_client_lock;
 	ktime_t boot_time;

fs/nfs/nfs3acl.c

@@ -104,7 +104,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu)
 
 	switch (status) {
 		case 0:
-			status = nfs_refresh_inode(inode, res.fattr);
+			nfs_refresh_inode(inode, res.fattr);
 			break;
 		case -EPFNOSUPPORT:
 		case -EPROTONOSUPPORT:

fs/nfs/nfs4proc.c

@@ -671,6 +671,15 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
 	struct nfs_client *clp = server->nfs_client;
 	int ret;
 
+	if ((task->tk_rpc_status == -ENETDOWN ||
+	     task->tk_rpc_status == -ENETUNREACH) &&
+	    task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+		exception->delay = 0;
+		exception->recovering = 0;
+		exception->retry = 0;
+		return -EIO;
+	}
+
 	ret = nfs4_do_handle_exception(server, errorcode, exception);
 	if (exception->delay) {
 		int ret2 = nfs4_exception_should_retrans(server, exception);
@@ -7074,18 +7083,25 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	struct nfs4_unlockdata *p;
 	struct nfs4_state *state = lsp->ls_state;
 	struct inode *inode = state->inode;
+	struct nfs_lock_context *l_ctx;
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (p == NULL)
 		return NULL;
+	l_ctx = nfs_get_lock_context(ctx);
+	if (!IS_ERR(l_ctx)) {
+		p->l_ctx = l_ctx;
+	} else {
+		kfree(p);
+		return NULL;
+	}
 	p->arg.fh = NFS_FH(inode);
 	p->arg.fl = &p->fl;
 	p->arg.seqid = seqid;
 	p->res.seqid = seqid;
 	p->lsp = lsp;
 	/* Ensure we don't close file until we're done freeing locks! */
 	p->ctx = get_nfs_open_context(ctx);
-	p->l_ctx = nfs_get_lock_context(ctx);
 	locks_init_lock(&p->fl);
 	locks_copy_lock(&p->fl, fl);
 	p->server = NFS_SERVER(inode);