Merge tag 'nfs-for-6.15-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
"Bugfixes:

- Three fixes for looping in the NFSv4 state manager delegation code

- Fix for the NFSv4 state XDR code (Neil Brown)

- Fix a leaked reference in nfs_lock_and_join_requests()

- Fix a use-after-free in the delegation return code

Features:

- Implement the NFSv4.2 copy offload OFFLOAD_STATUS operation to
allow monitoring of an in-progress copy

- Add a mount option to force NFSv3/NFSv4 to use READDIRPLUS in a
getdents() call

- SUNRPC now allows some basic management of an existing RPC client's
connections using sysfs

- Improvements to the automated teardown of a NFS client when the
container it was initiated from gets killed

- Improvements to prevent tasks from getting stuck in a killable wait
state after calling exit_signals()"

* tag 'nfs-for-6.15-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (29 commits)
nfs: Add missing release on error in nfs_lock_and_join_requests()
NFSv4: Check for delegation validity in nfs_start_delegation_return_locked()
NFS: Don't allow waiting for exiting tasks
SUNRPC: Don't allow waiting for exiting tasks
NFSv4: Treat ENETUNREACH errors as fatal for state recovery
NFSv4: clp->cl_cons_state < 0 signifies an invalid nfs_client
NFSv4: Further cleanups to shutdown loops
NFS: Shut down the nfs_client only after all the superblocks
SUNRPC: rpc_clnt_set_transport() must not change the autobind setting
SUNRPC: rpcbind should never reset the port to the value '0'
pNFS/flexfiles: Report ENETDOWN as a connection error
pNFS/flexfiles: Treat ENETUNREACH errors as fatal in containers
NFS: Treat ENETUNREACH errors as fatal in containers
NFS: Add a mount option to make ENETUNREACH errors fatal
sunrpc: Add a sysfs file for one-step xprt deletion
sunrpc: Add a sysfs file for adding a new xprt
sunrpc: Add a sysfs files for rpc_clnt information
sunrpc: Add a sysfs attr for xprtsec
NFS: Add implid to sysfs
NFS: Extend rdirplus mount option with "force|none"
...

fs/nfs/client.c

···
 		args.flags |= RPC_CLNT_CREATE_NOPING;
 	if (test_bit(NFS_CS_REUSEPORT, &clp->cl_flags))
 		args.flags |= RPC_CLNT_CREATE_REUSEPORT;
+	if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+		args.flags |= RPC_CLNT_CREATE_NETUNREACH_FATAL;
 
 	if (!IS_ERR(clp->cl_rpcclient))
 		return 0;
···
 				ctx->timeo, ctx->retrans);
 	if (ctx->flags & NFS_MOUNT_NORESVPORT)
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
+	if (ctx->flags & NFS_MOUNT_NETUNREACH_FATAL)
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init);

fs/nfs/delegation.c

···
 				       struct nfs_delegation *delegation)
 {
 	set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
+	set_bit(NFS4SERV_DELEGRETURN, &server->delegation_flags);
 	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
 }
 
···
 	if (delegation == NULL)
 		goto out;
 	spin_lock(&delegation->lock);
-	if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
+	if (delegation->inode &&
+	    !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
 		clear_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags);
 		/* Refcount matched in nfs_end_delegation_return() */
 		ret = nfs_get_delegation(delegation);
···
 }
 
 static void nfs_abort_delegation_return(struct nfs_delegation *delegation,
-					struct nfs_client *clp, int err)
+					struct nfs_server *server, int err)
 {
-
 	spin_lock(&delegation->lock);
 	clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
 	if (err == -EAGAIN) {
 		set_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags);
-		set_bit(NFS4CLNT_DELEGRETURN_DELAYED, &clp->cl_state);
+		set_bit(NFS4SERV_DELEGRETURN_DELAYED,
+			&server->delegation_flags);
+		set_bit(NFS4CLNT_DELEGRETURN_DELAYED,
+			&server->nfs_client->cl_state);
 	}
 	spin_unlock(&delegation->lock);
 }
···
  */
 static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation *delegation, int issync)
 {
-	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+	struct nfs_server *server = NFS_SERVER(inode);
 	unsigned int mode = O_WRONLY | O_RDWR;
 	int err = 0;
 
···
 		/*
 		 * Guard against state recovery
 		 */
-		err = nfs4_wait_clnt_recover(clp);
+		err = nfs4_wait_clnt_recover(server->nfs_client);
 	}
 
 	if (err) {
-		nfs_abort_delegation_return(delegation, clp, err);
+		nfs_abort_delegation_return(delegation, server, err);
 		goto out;
 	}
 
···
 
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
-	else if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) {
-		struct inode *inode;
-
-		spin_lock(&delegation->lock);
-		inode = delegation->inode;
-		if (inode && list_empty(&NFS_I(inode)->open_files))
-			ret = true;
-		spin_unlock(&delegation->lock);
-	}
-	if (ret)
-		clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
 	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) ||
 	    test_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags) ||
 	    test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
···
 	struct nfs_delegation *place_holder_deleg = NULL;
 	int err = 0;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGRETURN,
+				&server->delegation_flags))
+		return 0;
 restart:
 	/*
 	 * To avoid quadratic looping we hold a reference
···
 		cond_resched();
 		if (!err)
 			goto restart;
+		set_bit(NFS4SERV_DELEGRETURN, &server->delegation_flags);
 		set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
 		goto out;
 	}
···
 	struct nfs_delegation *d;
 	bool ret = false;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGRETURN_DELAYED,
+				&server->delegation_flags))
+		goto out;
 	list_for_each_entry_rcu (d, &server->delegations, super_list) {
 		if (!test_bit(NFS_DELEGATION_RETURN_DELAYED, &d->flags))
 			continue;
···
 		clear_bit(NFS_DELEGATION_RETURN_DELAYED, &d->flags);
 		ret = true;
 	}
+out:
 	return ret;
 }
 
···
 	return nfs4_inode_return_delegation(inode);
 }
 
-static void nfs_mark_return_if_closed_delegation(struct nfs_server *server,
-		struct nfs_delegation *delegation)
+static void
+nfs_mark_return_if_closed_delegation(struct nfs_server *server,
+				     struct nfs_delegation *delegation)
 {
-	set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
-	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
+	struct inode *inode;
+
+	if (test_bit(NFS_DELEGATION_RETURN, &delegation->flags) ||
+	    test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags))
+		return;
+	spin_lock(&delegation->lock);
+	inode = delegation->inode;
+	if (!inode)
+		goto out;
+	if (list_empty(&NFS_I(inode)->open_files))
+		nfs_mark_return_delegation(server, delegation);
+	else
+		set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
+out:
+	spin_unlock(&delegation->lock);
 }
 
 static bool nfs_server_mark_return_all_delegations(struct nfs_server *server)
···
 		return;
 	clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
 	set_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags);
+	set_bit(NFS4SERV_DELEGATION_EXPIRED, &server->delegation_flags);
 	set_bit(NFS4CLNT_DELEGATION_EXPIRED, &server->nfs_client->cl_state);
 }
 
···
 	nfs4_stateid stateid;
 	unsigned long gen = ++server->delegation_gen;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGATION_EXPIRED,
+				&server->delegation_flags))
+		return 0;
 restart:
 	rcu_read_lock();
 	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
···
 			goto restart;
 		}
 		nfs_inode_mark_test_expired_delegation(server,inode);
+		set_bit(NFS4SERV_DELEGATION_EXPIRED, &server->delegation_flags);
+		set_bit(NFS4CLNT_DELEGATION_EXPIRED,
+			&server->nfs_client->cl_state);
 		iput(inode);
 		return -EAGAIN;
 	}

fs/nfs/dir.c

···
 {
 	if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS))
 		return false;
+	if (NFS_SERVER(dir)->flags & NFS_MOUNT_FORCE_RDIRPLUS)
+		return true;
 	if (ctx->pos == 0 ||
 	    cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD)
 		return true;

fs/nfs/flexfilelayout/flexfilelayout.c

···
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		goto reset;
 	/* RPC connection errors */
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+			return -NFS4ERR_FATAL_IOERROR;
+		fallthrough;
 	case -ECONNREFUSED:
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
-	case -ENETUNREACH:
 	case -EIO:
 	case -ETIMEDOUT:
 	case -EPIPE:
···
 
 /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
 static int ff_layout_async_handle_error_v3(struct rpc_task *task,
+					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
 					   u32 idx)
 {
···
 	case -EJUKEBOX:
 		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
 		goto out_retry;
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+			return -NFS4ERR_FATAL_IOERROR;
+		fallthrough;
 	default:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
···
 
 	switch (vers) {
 	case 3:
-		return ff_layout_async_handle_error_v3(task, lseg, idx);
+		return ff_layout_async_handle_error_v3(task, clp, lseg, idx);
 	case 4:
 		return ff_layout_async_handle_error_v4(task, state, clp,
 						       lseg, idx);
···
 		case -ECONNRESET:
 		case -EHOSTDOWN:
 		case -EHOSTUNREACH:
+		case -ENETDOWN:
 		case -ENETUNREACH:
 		case -EADDRINUSE:
 		case -ENOBUFS:
···
 		return task->tk_status;
 	case -EAGAIN:
 		goto out_eagain;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	return 0;
···
 		return task->tk_status;
 	case -EAGAIN:
 		return -EAGAIN;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	if (hdr->res.verf->committed == NFS_FILE_SYNC ||
···
 	case -EAGAIN:
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	ff_layout_set_layoutcommit(data->inode, data->lseg, data->lwb);

fs/nfs/fs_context.c

···
 	Opt_clientaddr,
 	Opt_cto,
 	Opt_alignwrite,
+	Opt_fatal_neterrors,
 	Opt_fg,
 	Opt_fscache,
 	Opt_fscache_flag,
···
 	Opt_posix,
 	Opt_proto,
 	Opt_rdirplus,
+	Opt_rdirplus_none,
+	Opt_rdirplus_force,
 	Opt_rdma,
 	Opt_resvport,
 	Opt_retrans,
···
 	Opt_wsize,
 	Opt_write,
 	Opt_xprtsec,
+};
+
+enum {
+	Opt_fatal_neterrors_default,
+	Opt_fatal_neterrors_enetunreach,
+	Opt_fatal_neterrors_none,
+};
+
+static const struct constant_table nfs_param_enums_fatal_neterrors[] = {
+	{ "default",			Opt_fatal_neterrors_default },
+	{ "ENETDOWN:ENETUNREACH",	Opt_fatal_neterrors_enetunreach },
+	{ "ENETUNREACH:ENETDOWN",	Opt_fatal_neterrors_enetunreach },
+	{ "none",			Opt_fatal_neterrors_none },
+	{}
 };
 
 enum {
···
 	fsparam_string("clientaddr",	Opt_clientaddr),
 	fsparam_flag_no("cto",		Opt_cto),
 	fsparam_flag_no("alignwrite",	Opt_alignwrite),
+	fsparam_enum("fatal_neterrors", Opt_fatal_neterrors,
+		     nfs_param_enums_fatal_neterrors),
 	fsparam_flag  ("fg",		Opt_fg),
 	fsparam_flag_no("fsc",		Opt_fscache_flag),
 	fsparam_string("fsc",		Opt_fscache),
···
 	fsparam_u32   ("port",		Opt_port),
 	fsparam_flag_no("posix",	Opt_posix),
 	fsparam_string("proto",		Opt_proto),
-	fsparam_flag_no("rdirplus",	Opt_rdirplus),
+	fsparam_flag_no("rdirplus", Opt_rdirplus), // rdirplus|nordirplus
+	fsparam_string("rdirplus",  Opt_rdirplus), // rdirplus=...
 	fsparam_flag  ("rdma",		Opt_rdma),
 	fsparam_flag_no("resvport",	Opt_resvport),
 	fsparam_u32   ("retrans",	Opt_retrans),
···
 	{ "none",	Opt_xprtsec_none },
 	{ "tls",	Opt_xprtsec_tls },
 	{ "mtls",	Opt_xprtsec_mtls },
+	{}
+};
+
+static const struct constant_table nfs_rdirplus_tokens[] = {
+	{ "none",	Opt_rdirplus_none },
+	{ "force",	Opt_rdirplus_force },
 	{}
 };
 
···
 			ctx->flags &= ~NFS_MOUNT_NOACL;
 		break;
 	case Opt_rdirplus:
-		if (result.negated)
+		if (result.negated) {
+			ctx->flags &= ~NFS_MOUNT_FORCE_RDIRPLUS;
 			ctx->flags |= NFS_MOUNT_NORDIRPLUS;
-		else
-			ctx->flags &= ~NFS_MOUNT_NORDIRPLUS;
+		} else if (!param->string) {
+			ctx->flags &= ~(NFS_MOUNT_NORDIRPLUS | NFS_MOUNT_FORCE_RDIRPLUS);
+		} else {
+			switch (lookup_constant(nfs_rdirplus_tokens, param->string, -1)) {
+			case Opt_rdirplus_none:
+				ctx->flags &= ~NFS_MOUNT_FORCE_RDIRPLUS;
+				ctx->flags |= NFS_MOUNT_NORDIRPLUS;
+				break;
+			case Opt_rdirplus_force:
+				ctx->flags &= ~NFS_MOUNT_NORDIRPLUS;
+				ctx->flags |= NFS_MOUNT_FORCE_RDIRPLUS;
+				break;
+			default:
+				goto out_invalid_value;
+			}
+		}
 		break;
 	case Opt_sharecache:
 		if (result.negated)
···
 		if (result.uint_32 < 1 || result.uint_32 > NFS_MAX_TRANSPORTS)
 			goto out_of_bounds;
 		ctx->nfs_server.max_connect = result.uint_32;
+		break;
+	case Opt_fatal_neterrors:
+		trace_nfs_mount_assign(param->key, param->string);
+		switch (result.uint_32) {
+		case Opt_fatal_neterrors_default:
+			if (fc->net_ns != &init_net)
+				ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL;
+			else
+				ctx->flags &= ~NFS_MOUNT_NETUNREACH_FATAL;
+			break;
+		case Opt_fatal_neterrors_enetunreach:
+			ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL;
+			break;
+		case Opt_fatal_neterrors_none:
+			ctx->flags &= ~NFS_MOUNT_NETUNREACH_FATAL;
+			break;
+		default:
+			goto out_invalid_value;
+		}
 		break;
 	case Opt_lookupcache:
 		trace_nfs_mount_assign(param->key, param->string);
···
 		ctx->xprtsec.policy	= RPC_XPRTSEC_NONE;
 		ctx->xprtsec.cert_serial	= TLS_NO_CERT;
 		ctx->xprtsec.privkey_serial	= TLS_NO_PRIVKEY;
+
+		if (fc->net_ns != &init_net)
+			ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL;
 
 		fc->s_iflags		|= SB_I_STABLE_WRITES;
 	}

fs/nfs/inode.c

···
 
 int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
+	if (unlikely(nfs_current_task_exiting()))
+		return -EINTR;
 	schedule();
 	if (signal_pending_state(mode, current))
 		return -ERESTARTSYS;

fs/nfs/internal.h

···
 }
 #endif
 
+static inline bool nfs_current_task_exiting(void)
+{
+	return (current->flags & PF_EXITING) != 0;
+}
+
 static inline bool nfs_error_is_fatal(int err)
 {
 	switch (err) {

fs/nfs/nfs3client.c

···
 
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+	if (test_bit(NFS_CS_NETUNREACH_FATAL, &mds_clp->cl_flags))
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
 
 	__set_bit(NFS_CS_DS, &cl_init.init_flags);
 

fs/nfs/nfs3proc.c

···
 		__set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 		schedule_timeout(NFS_JUKEBOX_RETRY_TIME);
 		res = -ERESTARTSYS;
-	} while (!fatal_signal_pending(current));
+	} while (!fatal_signal_pending(current) && !nfs_current_task_exiting());
 	return res;
 }
 

fs/nfs/nfs42proc.c

···
 
 #define NFSDBG_FACILITY NFSDBG_PROC
 static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std);
+static int nfs42_proc_offload_status(struct file *file, nfs4_stateid *stateid,
+				     u64 *copied);
 
 static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr *naddr)
 {
···
 	return err;
 }
 
+static void nfs4_copy_dequeue_callback(struct nfs_server *dst_server,
+				       struct nfs_server *src_server,
+				       struct nfs4_copy_state *copy)
+{
+	spin_lock(&dst_server->nfs_client->cl_lock);
+	list_del_init(&copy->copies);
+	spin_unlock(&dst_server->nfs_client->cl_lock);
+	if (dst_server != src_server) {
+		spin_lock(&src_server->nfs_client->cl_lock);
+		list_del_init(&copy->src_copies);
+		spin_unlock(&src_server->nfs_client->cl_lock);
+	}
+}
+
 static int handle_async_copy(struct nfs42_copy_res *res,
 			     struct nfs_server *dst_server,
 			     struct nfs_server *src_server,
···
 			     bool *restart)
 {
 	struct nfs4_copy_state *copy, *tmp_copy = NULL, *iter;
-	int status = NFS4_OK;
 	struct nfs_open_context *dst_ctx = nfs_file_open_context(dst);
 	struct nfs_open_context *src_ctx = nfs_file_open_context(src);
+	struct nfs_client *clp = dst_server->nfs_client;
+	unsigned long timeout = 3 * HZ;
+	int status = NFS4_OK;
+	u64 copied;
 
 	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL);
 	if (!copy)
···
 		spin_unlock(&src_server->nfs_client->cl_lock);
 	}
 
-	status = wait_for_completion_interruptible(&copy->completion);
-	spin_lock(&dst_server->nfs_client->cl_lock);
-	list_del_init(&copy->copies);
-	spin_unlock(&dst_server->nfs_client->cl_lock);
-	if (dst_server != src_server) {
-		spin_lock(&src_server->nfs_client->cl_lock);
-		list_del_init(&copy->src_copies);
-		spin_unlock(&src_server->nfs_client->cl_lock);
-	}
+wait:
+	status = wait_for_completion_interruptible_timeout(&copy->completion,
+							   timeout);
+	if (!status)
+		goto timeout;
+	nfs4_copy_dequeue_callback(dst_server, src_server, copy);
 	if (status == -ERESTARTSYS) {
 		goto out_cancel;
 	} else if (copy->flags || copy->error == NFS4ERR_PARTNER_NO_AUTH) {
···
 	}
 out:
 	res->write_res.count = copy->count;
+	/* Copy out the updated write verifier provided by CB_OFFLOAD. */
 	memcpy(&res->write_res.verifier, &copy->verf, sizeof(copy->verf));
 	status = -copy->error;
 
···
 	nfs42_do_offload_cancel_async(dst, &copy->stateid);
 	if (!nfs42_files_from_same_server(src, dst))
 		nfs42_do_offload_cancel_async(src, src_stateid);
+	goto out_free;
+timeout:
+	timeout <<= 1;
+	if (timeout > (clp->cl_lease_time >> 1))
+		timeout = clp->cl_lease_time >> 1;
+	status = nfs42_proc_offload_status(dst, &copy->stateid, &copied);
+	if (status == -EINPROGRESS)
+		goto wait;
+	nfs4_copy_dequeue_callback(dst_server, src_server, copy);
+	switch (status) {
+	case 0:
+		/* The server recognized the copy stateid, so it hasn't
+		 * rebooted. Don't overwrite the verifier returned in the
+		 * COPY result. */
+		res->write_res.count = copied;
+		goto out_free;
+	case -EREMOTEIO:
+		/* COPY operation failed on the server. */
+		status = -EOPNOTSUPP;
+		res->write_res.count = copied;
+		goto out_free;
+	case -EBADF:
+		/* Server did not recognize the copy stateid. It has
+		 * probably restarted and lost the plot. */
+		res->write_res.count = 0;
+		status = -EOPNOTSUPP;
+		break;
+	case -EOPNOTSUPP:
+		/* RFC 7862 REQUIREs server to support OFFLOAD_STATUS when
+		 * it has signed up for an async COPY, so server is not
+		 * spec-compliant. */
+		res->write_res.count = 0;
+	}
 	goto out_free;
 }
 
···
 	if (status == -ENOTSUPP)
 		dst_server->caps &= ~NFS_CAP_OFFLOAD_CANCEL;
 	rpc_put_task(task);
+	return status;
+}
+
+static int
+_nfs42_proc_offload_status(struct nfs_server *server, struct file *file,
+			   struct nfs42_offload_data *data)
+{
+	struct nfs_open_context *ctx = nfs_file_open_context(file);
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_OFFLOAD_STATUS],
+		.rpc_argp	= &data->args,
+		.rpc_resp	= &data->res,
+		.rpc_cred	= ctx->cred,
+	};
+	int status;
+
+	status = nfs4_call_sync(server->client, server, &msg,
+				&data->args.osa_seq_args,
+				&data->res.osr_seq_res, 1);
+	trace_nfs4_offload_status(&data->args, status);
+	switch (status) {
+	case 0:
+		break;
+
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+		/*
+		 * Server does not recognize the COPY stateid. CB_OFFLOAD
+		 * could have purged it, or server might have rebooted.
+		 * Since COPY stateids don't have an associated inode,
+		 * avoid triggering state recovery.
+		 */
+		status = -EBADF;
+		break;
+	case -NFS4ERR_NOTSUPP:
+	case -ENOTSUPP:
+	case -EOPNOTSUPP:
+		server->caps &= ~NFS_CAP_OFFLOAD_STATUS;
+		status = -EOPNOTSUPP;
+		break;
+	}
+
+	return status;
+}
+
+/**
+ * nfs42_proc_offload_status - Poll completion status of an async copy operation
+ * @dst: handle of file being copied into
+ * @stateid: copy stateid (from async COPY result)
+ * @copied: OUT: number of bytes copied so far
+ *
+ * Return values:
+ *   %0: Server returned an NFS4_OK completion status
+ *   %-EINPROGRESS: Server returned no completion status
+ *   %-EREMOTEIO: Server returned an error completion status
+ *   %-EBADF: Server did not recognize the copy stateid
+ *   %-EOPNOTSUPP: Server does not support OFFLOAD_STATUS
+ *   %-ERESTARTSYS: Wait interrupted by signal
+ *
+ * Other negative errnos indicate the client could not complete the
+ * request.
+ */
+static int
+nfs42_proc_offload_status(struct file *dst, nfs4_stateid *stateid, u64 *copied)
+{
+	struct inode *inode = file_inode(dst);
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs4_exception exception = {
+		.inode = inode,
+	};
+	struct nfs42_offload_data *data;
+	int status;
+
+	if (!(server->caps & NFS_CAP_OFFLOAD_STATUS))
+		return -EOPNOTSUPP;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	data->seq_server = server;
+	data->args.osa_src_fh = NFS_FH(inode);
+	memcpy(&data->args.osa_stateid, stateid,
+		sizeof(data->args.osa_stateid));
+	exception.stateid = &data->args.osa_stateid;
+	do {
+		status = _nfs42_proc_offload_status(server, dst, data);
+		if (status == -EOPNOTSUPP)
+			goto out;
+		status = nfs4_handle_exception(server, status, &exception);
+	} while (exception.retry);
+	if (status)
+		goto out;
+
+	*copied = data->res.osr_count;
+	if (!data->res.complete_count)
+		status = -EINPROGRESS;
+	else if (data->res.osr_complete != NFS_OK)
+		status = -EREMOTEIO;
+
+out:
+	kfree(data);
 	return status;
 }
 

fs/nfs/nfs42xdr.c

···
 #define encode_offload_cancel_maxsz	(op_encode_hdr_maxsz + \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE))
 #define decode_offload_cancel_maxsz	(op_decode_hdr_maxsz)
+#define encode_offload_status_maxsz	(op_encode_hdr_maxsz + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE))
+#define decode_offload_status_maxsz	(op_decode_hdr_maxsz + \
+					 2 /* osr_count */ + \
+					 2 /* osr_complete */)
 #define encode_copy_notify_maxsz	(op_encode_hdr_maxsz + \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
 					 1 + /* nl4_type */ \
···
 					 decode_sequence_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_offload_cancel_maxsz)
+#define NFS4_enc_offload_status_sz	(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_offload_status_maxsz)
+#define NFS4_dec_offload_status_sz	(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_offload_status_maxsz)
 #define NFS4_enc_copy_notify_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
···
 				  struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_OFFLOAD_CANCEL, decode_offload_cancel_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->osa_stateid);
+}
+
+static void encode_offload_status(struct xdr_stream *xdr,
+				  const struct nfs42_offload_status_args *args,
+				  struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_OFFLOAD_STATUS, decode_offload_status_maxsz, hdr);
 	encode_nfs4_stateid(xdr, &args->osa_stateid);
 }
 
···
 	encode_sequence(xdr, &args->osa_seq_args, &hdr);
 	encode_putfh(xdr, args->osa_src_fh, &hdr);
 	encode_offload_cancel(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
+ * Encode OFFLOAD_STATUS request
+ */
+static void nfs4_xdr_enc_offload_status(struct rpc_rqst *req,
+					struct xdr_stream *xdr,
+					const void *data)
+{
+	const struct nfs42_offload_status_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->osa_seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->osa_seq_args, &hdr);
+	encode_putfh(xdr, args->osa_src_fh, &hdr);
+	encode_offload_status(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
 
···
 				 struct nfs42_offload_status_res *res)
 {
 	return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
+}
+
+static int decode_offload_status(struct xdr_stream *xdr,
+				 struct nfs42_offload_status_res *res)
+{
+	ssize_t result;
+	int status;
+
+	status = decode_op_hdr(xdr, OP_OFFLOAD_STATUS);
+	if (status)
+		return status;
+	/* osr_count */
+	if (xdr_stream_decode_u64(xdr, &res->osr_count) < 0)
+		return -EIO;
+	/* osr_complete<1> */
+	result = xdr_stream_decode_uint32_array(xdr, &res->osr_complete, 1);
+	if (result < 0)
+		return -EIO;
+	res->complete_count = result;
+	return 0;
 }
 
 static int decode_copy_notify(struct xdr_stream *xdr,
···
 	if (status)
 		goto out;
 	status = decode_offload_cancel(xdr, res);
+
+out:
+	return status;
+}
+
+/*
+ * Decode OFFLOAD_STATUS response
+ */
+static int nfs4_xdr_dec_offload_status(struct rpc_rqst *rqstp,
+				       struct xdr_stream *xdr,
+				       void *data)
+{
+	struct nfs42_offload_status_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->osr_seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_offload_status(xdr, res);
 
 out:
 	return status;

fs/nfs/nfs4client.c

···
 	__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
 	if (test_bit(NFS_CS_PNFS, &cl_init->init_flags))
 		__set_bit(NFS_CS_PNFS, &clp->cl_flags);
+	if (test_bit(NFS_CS_NETUNREACH_FATAL, &cl_init->init_flags))
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags);
 	/*
 	 * Set up the connection to the server before we add add to the
 	 * global list.
···
 		__set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
 	server->port = rpc_get_port((struct sockaddr *)addr);
 
+	if (server->flags & NFS_MOUNT_NETUNREACH_FATAL)
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
+
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init);
 	if (IS_ERR(clp))
···
 
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+	if (test_bit(NFS_CS_NETUNREACH_FATAL, &mds_clp->cl_flags))
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
 
 	__set_bit(NFS_CS_PNFS, &cl_init.init_flags);
 	cl_init.max_connect = NFS_MAX_TRANSPORTS;

fs/nfs/nfs4proc.c

···
 		return -EBUSY;
 	case -NFS4ERR_NOT_SAME:
 		return -ENOTSYNC;
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		break;
 	default:
 		dprintk("%s could not handle NFSv4 error %d\n",
 				__func__, -err);
···
 {
 	might_sleep();
 
+	if (unlikely(nfs_current_task_exiting()))
+		return -EINTR;
 	__set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 	schedule_timeout(nfs4_update_delay(timeout));
 	if (!__fatal_signal_pending(current))
···
 {
 	might_sleep();
 
+	if (unlikely(nfs_current_task_exiting()))
+		return -EINTR;
 	__set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE_UNSAFE);
 	schedule_timeout(nfs4_update_delay(timeout));
 	if (!signal_pending(current))
···
 		rcu_read_unlock();
 		trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0);
 
-		if (!fatal_signal_pending(current)) {
+		if (!fatal_signal_pending(current) &&
+		    !nfs_current_task_exiting()) {
 			if (schedule_timeout(5*HZ) == 0)
 				status = -EAGAIN;
 			else
···
 		write_sequnlock(&state->seqlock);
 		trace_nfs4_close_stateid_update_wait(state->inode, dst, 0);
 
-		if (fatal_signal_pending(current))
+		if (fatal_signal_pending(current) || nfs_current_task_exiting())
 			status = -EINTR;
 		else
 			if (schedule_timeout(5*HZ) != 0)
···
 		return;
 
 	trace_nfs4_sequence(clp, task->tk_status);
-	if (task->tk_status < 0 && !task->tk_client->cl_shutdown) {
+	if (task->tk_status < 0 && clp->cl_cons_state >= 0) {
 		dprintk("%s ERROR %d\n", __func__, task->tk_status);
 		if (refcount_read(&clp->cl_count) == 1)
 			return;
···
 		| NFS_CAP_CLONE
 		| NFS_CAP_LAYOUTERROR
 		| NFS_CAP_READ_PLUS
-		| NFS_CAP_MOVEABLE,
+		| NFS_CAP_MOVEABLE
+		| NFS_CAP_OFFLOAD_STATUS,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,

fs/nfs/nfs4state.c

···
 	struct rpc_clnt *clnt = clp->cl_rpcclient;
 	bool swapon = false;
 
-	if (clnt->cl_shutdown)
+	if (clp->cl_cons_state < 0)
 		return;
 
 	set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
···
 	dprintk("%s: scheduling stateid recovery for server %s\n", __func__,
 			clp->cl_hostname);
 	nfs4_schedule_state_manager(clp);
-	return 0;
+	return clp->cl_cons_state < 0 ? clp->cl_cons_state : 0;
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery);
 
···
 	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
 			" with error %d\n", section_sep, section,
 			clp->cl_hostname, -status);
-	ssleep(1);
+	switch (status) {
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		nfs_mark_client_ready(clp, -EIO);
+		break;
+	default:
+		ssleep(1);
+		break;
+	}
 out_drain:
 	memalloc_nofs_restore(memflags);
 	nfs4_end_drain_session(clp);

fs/nfs/nfs4trace.h

···
 		)
 );
 
-TRACE_EVENT(nfs4_offload_cancel,
+DECLARE_EVENT_CLASS(nfs4_offload_class,
 		TP_PROTO(
 			const struct nfs42_offload_status_args *args,
 			int error
···
 			__entry->stateid_seq, __entry->stateid_hash
 		)
 );
+#define DEFINE_NFS4_OFFLOAD_EVENT(name) \
+	DEFINE_EVENT(nfs4_offload_class, name,  \
+			TP_PROTO( \
+				const struct nfs42_offload_status_args *args, \
+				int error \
+			), \
+			TP_ARGS(args, error))
+DEFINE_NFS4_OFFLOAD_EVENT(nfs4_offload_cancel);
+DEFINE_NFS4_OFFLOAD_EVENT(nfs4_offload_status);
 
 DECLARE_EVENT_CLASS(nfs4_xattr_event,
 		TP_PROTO(

fs/nfs/nfs4xdr.c

···
  * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT  >> 2)
  */
 #define pagepad_maxsz		(1)
-#define open_owner_id_maxsz	(1 + 2 + 1 + 1 + 2)
-#define lock_owner_id_maxsz	(1 + 1 + 4)
-#define decode_lockowner_maxsz	(1 + XDR_QUADLEN(IDMAP_NAMESZ))
+#define open_owner_id_maxsz	(2 + 1 + 2 + 2)
+#define lock_owner_id_maxsz	(2 + 1 + 2)
 #define compound_encode_hdr_maxsz	(3 + (NFS4_MAXTAGLEN >> 2))
 #define compound_decode_hdr_maxsz	(3 + (NFS4_MAXTAGLEN >> 2))
 #define op_encode_hdr_maxsz	(1)
···
 #define encode_claim_null_maxsz	(1 + nfs4_name_maxsz)
 #define encode_open_maxsz	(op_encode_hdr_maxsz + \
 				2 + encode_share_access_maxsz + 2 + \
-				open_owner_id_maxsz + \
+				1 + open_owner_id_maxsz + \
 				encode_opentype_maxsz + \
 				encode_claim_null_maxsz)
 #define decode_space_limit_maxsz	(3)
···
 #define encode_link_maxsz	(op_encode_hdr_maxsz + \
 				nfs4_name_maxsz)
 #define decode_link_maxsz	(op_decode_hdr_maxsz + decode_change_info_maxsz)
-#define encode_lockowner_maxsz	(7)
+#define encode_lockowner_maxsz	(2 + 1 + lock_owner_id_maxsz)
+
 #define encode_lock_maxsz	(op_encode_hdr_maxsz + \
 				 7 + \
 				 1 + encode_stateid_maxsz + 1 + \
 				 encode_lockowner_maxsz)
 #define decode_lock_denied_maxsz \
-				(8 + decode_lockowner_maxsz)
+				(2 + 2 + 1 + 2 + 1 + lock_owner_id_maxsz)
 #define decode_lock_maxsz	(op_decode_hdr_maxsz + \
 				 decode_lock_denied_maxsz)
 #define encode_lockt_maxsz	(op_encode_hdr_maxsz + 5 + \
···
 				 encode_lockowner_maxsz)
 #define NFS4_dec_release_lockowner_sz \
 				(compound_decode_hdr_maxsz + \
-				 decode_lockowner_maxsz)
+				 decode_release_lockowner_maxsz)
 #define NFS4_enc_access_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
···
 	__be32 *p;
  /*
  * opcode 4, seqid 4, share_access 4, share_deny 4, clientid 8, ownerlen 4,
- * owner 4 = 32
+ * owner 28
  */
 	encode_nfs4_seqid(xdr, arg->seqid);
 	encode_share_access(xdr, arg->share_access);
···
 /*
  * We create the owner, so we know a proper owner.id length is 4.
  */
-static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl)
+static int decode_lock_denied(struct xdr_stream *xdr, struct file_lock *fl)
 {
 	uint64_t offset, length, clientid;
 	__be32 *p;
···
 	PROC42(CLONE,		enc_clone,		dec_clone),
 	PROC42(COPY,		enc_copy,		dec_copy),
 	PROC42(OFFLOAD_CANCEL,	enc_offload_cancel,	dec_offload_cancel),
+	PROC42(OFFLOAD_STATUS,	enc_offload_status,	dec_offload_status),
 	PROC42(COPY_NOTIFY,	enc_copy_notify,	dec_copy_notify),
 	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC42(LAYOUTERROR,	enc_layouterror,	dec_layouterror),

fs/nfs/super.c

···
 		{ NFS_MOUNT_NONLM, ",nolock", "" },
 		{ NFS_MOUNT_NOACL, ",noacl", "" },
 		{ NFS_MOUNT_NORDIRPLUS, ",nordirplus", "" },
+		{ NFS_MOUNT_FORCE_RDIRPLUS, ",rdirplus=force", "" },
 		{ NFS_MOUNT_UNSHARED, ",nosharecache", "" },
 		{ NFS_MOUNT_NORESVPORT, ",noresvport", "" },
+		{ NFS_MOUNT_NETUNREACH_FATAL,
+		  ",fatal_neterrors=ENETDOWN:ENETUNREACH",
+		  ",fatal_neterrors=none" },
 		{ 0, NULL, NULL }
 	};
 	const struct proc_nfs_info *nfs_infop;

fs/nfs/sysfs.c

···
 #include <linux/rcupdate.h>
 #include <linux/lockd/lockd.h>
 
+#include "internal.h"
 #include "nfs4_fs.h"
 #include "netns.h"
 #include "sysfs.h"
···
 	rpc_cancel_tasks(clnt, -EIO, shutdown_match_client, NULL);
 }
 
+/*
+ * Shut down the nfs_client only once all the superblocks
+ * have been shut down.
+ */
+static void shutdown_nfs_client(struct nfs_client *clp)
+{
+	struct nfs_server *server;
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		if (!(server->flags & NFS_MOUNT_SHUTDOWN)) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+	nfs_mark_client_ready(clp, -EIO);
+	shutdown_client(clp->cl_rpcclient);
+}
+
 static ssize_t
 shutdown_show(struct kobject *kobj, struct kobj_attribute *attr,
 				char *buf)
···
 
 	server->flags |= NFS_MOUNT_SHUTDOWN;
 	shutdown_client(server->client);
-	shutdown_client(server->nfs_client->cl_rpcclient);
 
 	if (!IS_ERR(server->client_acl))
 		shutdown_client(server->client_acl);
···
 	if (server->nlm_host)
 		shutdown_client(server->nlm_host->h_rpcclnt);
 out:
+	shutdown_nfs_client(server->nfs_client);
 	return count;
 }
 
 static struct kobj_attribute nfs_sysfs_attr_shutdown = __ATTR_RW(shutdown);
+
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+static ssize_t
+implid_domain_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	struct nfs41_impl_id *impl_id = server->nfs_client->cl_implid;
+
+	if (!impl_id || strlen(impl_id->domain) == 0)
+		return 0; //sysfs_emit(buf, "");
+	return sysfs_emit(buf, "%s\n", impl_id->domain);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_implid_domain = __ATTR_RO(implid_domain);
+
+
+static ssize_t
+implid_name_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	struct nfs41_impl_id *impl_id = server->nfs_client->cl_implid;
+
+	if (!impl_id || strlen(impl_id->name) == 0)
+		return 0; //sysfs_emit(buf, "");
+	return sysfs_emit(buf, "%s\n", impl_id->name);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_implid_name = __ATTR_RO(implid_name);
+
+#endif /* IS_ENABLED(CONFIG_NFS_V4_1) */
 
 #define RPC_CLIENT_NAME_SIZE 64
 
···
 	.child_ns_type = nfs_netns_object_child_ns_type,
 };
 
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+static void nfs_sysfs_add_nfsv41_server(struct nfs_server *server)
+{
+	int ret;
+
+	if (!server->nfs_client->cl_implid)
+		return;
+
+	ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_implid_domain.attr,
+					   nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+
+	ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_implid_name.attr,
+				   nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+}
+#else /* CONFIG_NFS_V4_1 */
+static inline void nfs_sysfs_add_nfsv41_server(struct nfs_server *server)
+{
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 void nfs_sysfs_add_server(struct nfs_server *server)
 {
 	int ret;
···
 	if (ret < 0)
 		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
 			server->s_sysfs_id, ret);
+
+	nfs_sysfs_add_nfsv41_server(server);
 }
 EXPORT_SYMBOL_GPL(nfs_sysfs_add_server);
 

fs/nfs/write.c

···
 
 	while (!nfs_lock_request(head)) {
 		ret = nfs_wait_on_request(head);
-		if (ret < 0)
+		if (ret < 0) {
+			nfs_release_request(head);
 			return ERR_PTR(ret);
+		}
 	}
 
 	/* Ensure that nobody removed the request before we locked it */

include/linux/nfs4.h

···
 /* error codes for internal client use */
 #define NFS4ERR_RESET_TO_MDS   12001
 #define NFS4ERR_RESET_TO_PNFS  12002
+#define NFS4ERR_FATAL_IOERROR  12003
 
 static inline bool seqid_mutating_err(u32 err)
 {
···
 	NFSPROC4_CLNT_LISTXATTRS,
 	NFSPROC4_CLNT_REMOVEXATTR,
 	NFSPROC4_CLNT_READ_PLUS,
+	NFSPROC4_CLNT_OFFLOAD_STATUS,
 };
 
 /* nfs41 types */

include/linux/nfs_fs_sb.h

···
 #define NFS_CS_DS		7		/* - Server is a DS */
 #define NFS_CS_REUSEPORT	8		/* - reuse src port on reconnect */
 #define NFS_CS_PNFS		9		/* - Server used for pnfs */
+#define NFS_CS_NETUNREACH_FATAL	10		/* - ENETUNREACH errors are fatal */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
···
 #define NFS_MOUNT_TRUNK_DISCOVERY	0x04000000
 #define NFS_MOUNT_SHUTDOWN			0x08000000
 #define NFS_MOUNT_NO_ALIGNWRITE		0x10000000
+#define NFS_MOUNT_FORCE_RDIRPLUS	0x20000000
+#define NFS_MOUNT_NETUNREACH_FATAL	0x40000000
 
 	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
···
 	struct list_head	ss_copies;
 	struct list_head	ss_src_copies;
 
+	unsigned long		delegation_flags;
+#define NFS4SERV_DELEGRETURN		(1)
+#define NFS4SERV_DELEGATION_EXPIRED	(2)
+#define NFS4SERV_DELEGRETURN_DELAYED	(3)
 	unsigned long		delegation_gen;
 	unsigned long		mig_gen;
 	unsigned long		mig_status;
···
 #define NFS_CAP_CASE_INSENSITIVE	(1U << 6)
 #define NFS_CAP_CASE_PRESERVING	(1U << 7)
 #define NFS_CAP_REBOOT_LAYOUTRETURN	(1U << 8)
+#define NFS_CAP_OFFLOAD_STATUS	(1U << 9)
 #define NFS_CAP_OPEN_XOR	(1U << 12)
 #define NFS_CAP_DELEGTIME	(1U << 13)
 #define NFS_CAP_POSIX_LOCK	(1U << 14)

include/linux/nfs_xdr.h

···
 
 struct nfs42_offload_status_res {
 	struct nfs4_sequence_res	osr_seq_res;
-	uint64_t			osr_count;
-	int				osr_status;
+	u64				osr_count;
+	int				complete_count;
+	u32				osr_complete;
 };
 
 struct nfs42_copy_notify_args {

include/linux/sunrpc/clnt.h

···
 				cl_noretranstimeo: 1,/* No retransmit timeouts */
 				cl_autobind : 1,/* use getport() */
 				cl_chatty   : 1,/* be verbose */
-				cl_shutdown : 1;/* rpc immediate -EIO */
+				cl_shutdown : 1,/* rpc immediate -EIO */
+				cl_netunreach_fatal : 1;
+						/* Treat ENETUNREACH errors as fatal */
 	struct xprtsec_parms	cl_xprtsec;	/* transport security policy */
 
 	struct rpc_rtt *	cl_rtt;		/* RTO estimator data */
···
 #define RPC_CLNT_CREATE_SOFTERR		(1UL << 10)
 #define RPC_CLNT_CREATE_REUSEPORT	(1UL << 11)
 #define RPC_CLNT_CREATE_CONNECTED	(1UL << 12)
+#define RPC_CLNT_CREATE_NETUNREACH_FATAL	(1UL << 13)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,

include/linux/sunrpc/sched.h

···
 #define RPC_TASK_MOVEABLE	0x0004		/* nfs4.1+ rpc tasks */
 #define RPC_TASK_NULLCREDS	0x0010		/* Use AUTH_NULL credential */
 #define RPC_CALL_MAJORSEEN	0x0020		/* major timeout seen */
+#define RPC_TASK_NETUNREACH_FATAL 0x0040	/* ENETUNREACH is fatal */
 #define RPC_TASK_DYNAMIC	0x0080		/* task was kmalloc'ed */
 #define	RPC_TASK_NO_ROUND_ROBIN	0x0100		/* send requests on "main" xprt */
 #define RPC_TASK_SOFT		0x0200		/* Use soft timeouts */

include/linux/sunrpc/xprtmultipath.h

···
 		struct rpc_xprt *xprt);
 extern void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps,
 		struct rpc_xprt *xprt, bool offline);
+extern struct rpc_xprt *rpc_xprt_switch_get_main_xprt(struct rpc_xprt_switch *xps);
 
 extern void xprt_iter_init(struct rpc_xprt_iter *xpi,
 		struct rpc_xprt_switch *xps);

include/trace/events/sunrpc.h

···
 		{ RPC_TASK_MOVEABLE, "MOVEABLE" },			\
 		{ RPC_TASK_NULLCREDS, "NULLCREDS" },			\
 		{ RPC_CALL_MAJORSEEN, "MAJORSEEN" },			\
+		{ RPC_TASK_NETUNREACH_FATAL, "NETUNREACH_FATAL"},	\
 		{ RPC_TASK_DYNAMIC, "DYNAMIC" },			\
 		{ RPC_TASK_NO_ROUND_ROBIN, "NO_ROUND_ROBIN" },		\
 		{ RPC_TASK_SOFT, "SOFT" },				\

net/sunrpc/clnt.c

···
 	old = rcu_dereference_protected(clnt->cl_xprt,
 			lockdep_is_held(&clnt->cl_lock));
 
-	if (!xprt_bound(xprt))
-		clnt->cl_autobind = 1;
-
 	clnt->cl_timeout = timeout;
 	rcu_assign_pointer(clnt->cl_xprt, xprt);
 	spin_unlock(&clnt->cl_lock);
···
 		clnt->cl_discrtry = 1;
 	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
 		clnt->cl_chatty = 1;
+	if (args->flags & RPC_CLNT_CREATE_NETUNREACH_FATAL)
+		clnt->cl_netunreach_fatal = 1;
 
 	return clnt;
 }
···
 	new->cl_noretranstimeo = clnt->cl_noretranstimeo;
 	new->cl_discrtry = clnt->cl_discrtry;
 	new->cl_chatty = clnt->cl_chatty;
+	new->cl_netunreach_fatal = clnt->cl_netunreach_fatal;
 	new->cl_principal = clnt->cl_principal;
 	new->cl_max_connect = clnt->cl_max_connect;
 	return new;
···
 		task->tk_flags |= RPC_TASK_TIMEOUT;
 	if (clnt->cl_noretranstimeo)
 		task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT;
+	if (clnt->cl_netunreach_fatal)
+		task->tk_flags |= RPC_TASK_NETUNREACH_FATAL;
 	atomic_inc(&clnt->cl_task_count);
 }
 
···
 	case -EPROTONOSUPPORT:
 		trace_rpcb_bind_version_err(task);
 		goto retry_timeout;
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL)
+			break;
+		fallthrough;
 	case -ECONNREFUSED:		/* connection problems */
 	case -ECONNRESET:
 	case -ECONNABORTED:
 	case -ENOTCONN:
 	case -EHOSTDOWN:
-	case -ENETDOWN:
 	case -EHOSTUNREACH:
-	case -ENETUNREACH:
 	case -EPIPE:
 		trace_rpcb_unreachable_err(task);
 		if (!RPC_IS_SOFTCONN(task)) {
···
 
 	task->tk_status = 0;
 	switch (status) {
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL)
+			break;
+		fallthrough;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
 		/* A positive refusal suggests a rebind is needed. */
-		if (RPC_IS_SOFTCONN(task))
-			break;
 		if (clnt->cl_autobind) {
 			rpc_force_rebind(clnt);
+			if (RPC_IS_SOFTCONN(task))
+				break;
 			goto out_retry;
 		}
 		fallthrough;
 	case -ECONNABORTED:
-	case -ENETDOWN:
-	case -ENETUNREACH:
 	case -EHOSTUNREACH:
 	case -EPIPE:
 	case -EPROTO:
···
 	trace_rpc_call_status(task);
 	task->tk_status = 0;
 	switch(status) {
-	case -EHOSTDOWN:
 	case -ENETDOWN:
-	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+		if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL)
+			goto out_exit;
+		fallthrough;
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
 	case -EPERM:
 		if (RPC_IS_SOFTCONN(task))
 			goto out_exit;

net/sunrpc/rpcb_clnt.c

···
 	}
 
 	trace_rpcb_setport(child, map->r_status, map->r_port);
-	xprt->ops->set_port(xprt, map->r_port);
-	if (map->r_port)
+	if (map->r_port) {
+		xprt->ops->set_port(xprt, map->r_port);
 		xprt_set_bound(xprt);
+	}
 }
 
 /*

net/sunrpc/sched.c

···
 
 static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
+	if (unlikely(current->flags & PF_EXITING))
+		return -EINTR;
 	schedule();
 	if (signal_pending_state(mode, current))
 		return -ERESTARTSYS;

net/sunrpc/sysfs.c

···
 	return NULL;
 }
 
+static inline struct rpc_clnt *
+rpc_sysfs_client_kobj_get_clnt(struct kobject *kobj)
+{
+	struct rpc_sysfs_client *c = container_of(kobj,
+		struct rpc_sysfs_client, kobject);
+	struct rpc_clnt *ret = c->clnt;
+
+	return refcount_inc_not_zero(&ret->cl_count) ? ret : NULL;
+}
+
 static inline struct rpc_xprt *
 rpc_sysfs_xprt_kobj_get_xprt(struct kobject *kobj)
 {
···
 		struct rpc_sysfs_xprt_switch, kobject);
 
 	return xprt_switch_get(x->xprt_switch);
+}
+
+static ssize_t rpc_sysfs_clnt_version_show(struct kobject *kobj,
+					   struct kobj_attribute *attr,
+					   char *buf)
+{
+	struct rpc_clnt *clnt = rpc_sysfs_client_kobj_get_clnt(kobj);
+	ssize_t ret;
+
+	if (!clnt)
+		return sprintf(buf, "<closed>\n");
+
+	ret = sprintf(buf, "%u", clnt->cl_vers);
+	refcount_dec(&clnt->cl_count);
+	return ret;
+}
+
+static ssize_t rpc_sysfs_clnt_program_show(struct kobject *kobj,
+					   struct kobj_attribute *attr,
+					   char *buf)
+{
+	struct rpc_clnt *clnt = rpc_sysfs_client_kobj_get_clnt(kobj);
+	ssize_t ret;
+
+	if (!clnt)
+		return sprintf(buf, "<closed>\n");
+
+	ret = sprintf(buf, "%s", clnt->cl_program->name);
+	refcount_dec(&clnt->cl_count);
+	return ret;
+}
+
+static ssize_t rpc_sysfs_clnt_max_connect_show(struct kobject *kobj,
+					       struct kobj_attribute *attr,
+					       char *buf)
+{
+	struct rpc_clnt *clnt = rpc_sysfs_client_kobj_get_clnt(kobj);
+	ssize_t ret;
+
+	if (!clnt)
+		return sprintf(buf, "<closed>\n");
+
+	ret = sprintf(buf, "%u\n", clnt->cl_max_connect);
+	refcount_dec(&clnt->cl_count);
+	return ret;
 }
 
 static ssize_t rpc_sysfs_xprt_dstaddr_show(struct kobject *kobj,
···
 		ret = sprintf(buf, "<not a socket>\n");
 	xprt_put(xprt);
 	return ret;
+}
+
+static const char *xprtsec_strings[] = {
+	[RPC_XPRTSEC_NONE] = "none",
+	[RPC_XPRTSEC_TLS_ANON] = "tls-anon",
+	[RPC_XPRTSEC_TLS_X509] = "tls-x509",
+};
+
+static ssize_t rpc_sysfs_xprt_xprtsec_show(struct kobject *kobj,
+					   struct kobj_attribute *attr,
+					   char *buf)
+{
+	struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj);
+	ssize_t ret;
+
+	if (!xprt) {
+		ret = sprintf(buf, "<closed>\n");
+		goto out;
+	}
+
+	ret = sprintf(buf, "%s\n", xprtsec_strings[xprt->xprtsec.policy]);
+	xprt_put(xprt);
+out:
+	return ret;
+
 }
 
 static ssize_t rpc_sysfs_xprt_info_show(struct kobject *kobj,
···
 	return ret;
 }
 
+static ssize_t rpc_sysfs_xprt_del_xprt_show(struct kobject *kobj,
+					    struct kobj_attribute *attr,
+					    char *buf)
+{
+	return sprintf(buf, "# delete this xprt\n");
+}
+
+
 static ssize_t rpc_sysfs_xprt_switch_info_show(struct kobject *kobj,
 					       struct kobj_attribute *attr,
 					       char *buf)
···
 		      atomic_long_read(&xprt_switch->xps_queuelen));
 	xprt_switch_put(xprt_switch);
 	return ret;
+}
+
+static ssize_t rpc_sysfs_xprt_switch_add_xprt_show(struct kobject *kobj,
+						   struct kobj_attribute *attr,
+						   char *buf)
+{
+	return sprintf(buf, "# add one xprt to this xprt_switch\n");
+}
+
+static ssize_t rpc_sysfs_xprt_switch_add_xprt_store(struct kobject *kobj,
+						    struct kobj_attribute *attr,
+						    const char *buf, size_t count)
+{
+	struct rpc_xprt_switch *xprt_switch =
+		rpc_sysfs_xprt_switch_kobj_get_xprt(kobj);
+	struct xprt_create xprt_create_args;
+	struct rpc_xprt *xprt, *new;
+
+	if (!xprt_switch)
+		return 0;
+
+	xprt = rpc_xprt_switch_get_main_xprt(xprt_switch);
+	if (!xprt)
+		goto out;
+
+	xprt_create_args.ident = xprt->xprt_class->ident;
+	xprt_create_args.net = xprt->xprt_net;
+	xprt_create_args.dstaddr = (struct sockaddr *)&xprt->addr;
+	xprt_create_args.addrlen = xprt->addrlen;
+	xprt_create_args.servername = xprt->servername;
+	xprt_create_args.bc_xprt = xprt->bc_xprt;
+	xprt_create_args.xprtsec = xprt->xprtsec;
+	xprt_create_args.connect_timeout = xprt->connect_timeout;
+	xprt_create_args.reconnect_timeout = xprt->max_reconnect_timeout;
+
+	new = xprt_create_transport(&xprt_create_args);
+	if (IS_ERR_OR_NULL(new)) {
+		count = PTR_ERR(new);
+		goto out_put_xprt;
+	}
+
+	rpc_xprt_switch_add_xprt(xprt_switch, new);
+	xprt_put(new);
+
+out_put_xprt:
+	xprt_put(xprt);
+out:
+	xprt_switch_put(xprt_switch);
+	return count;
 }
 
 static ssize_t rpc_sysfs_xprt_dstaddr_store(struct kobject *kobj,
···
 	return count;
 }
 
+static ssize_t rpc_sysfs_xprt_del_xprt(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       const char *buf, size_t count)
+{
+	struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj);
+	struct rpc_xprt_switch *xps = rpc_sysfs_xprt_kobj_get_xprt_switch(kobj);
+
+	if (!xprt || !xps) {
+		count = 0;
+		goto out;
+	}
+
+	if (xprt->main) {
+		count = -EINVAL;
+		goto release_tasks;
+	}
+
+	if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) {
+		count = -EINTR;
+		goto out_put;
+	}
+
+	xprt_set_offline_locked(xprt, xps);
+	xprt_delete_locked(xprt, xps);
+
+release_tasks:
+	xprt_release_write(xprt, NULL);
+out_put:
+	xprt_put(xprt);
+	xprt_switch_put(xps);
+out:
+	return count;
+}
+
 int rpc_sysfs_init(void)
 {
 	rpc_sunrpc_kset = kset_create_and_add("sunrpc", NULL, kernel_kobj);
···
 			    kobject)->xprt->xprt_net;
 }
 
+static struct kobj_attribute rpc_sysfs_clnt_version = __ATTR(rpc_version,
+	0444, rpc_sysfs_clnt_version_show, NULL);
+
+static struct kobj_attribute rpc_sysfs_clnt_program = __ATTR(program,
+	0444, rpc_sysfs_clnt_program_show, NULL);
+
+static struct kobj_attribute rpc_sysfs_clnt_max_connect = __ATTR(max_connect,
+	0444, rpc_sysfs_clnt_max_connect_show, NULL);
+
+static struct attribute *rpc_sysfs_rpc_clnt_attrs[] = {
+	&rpc_sysfs_clnt_version.attr,
+	&rpc_sysfs_clnt_program.attr,
+	&rpc_sysfs_clnt_max_connect.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(rpc_sysfs_rpc_clnt);
+
 static struct kobj_attribute rpc_sysfs_xprt_dstaddr = __ATTR(dstaddr,
 	0644, rpc_sysfs_xprt_dstaddr_show, rpc_sysfs_xprt_dstaddr_store);
 
 static struct kobj_attribute rpc_sysfs_xprt_srcaddr = __ATTR(srcaddr,
 	0644, rpc_sysfs_xprt_srcaddr_show, NULL);
+
+static struct kobj_attribute rpc_sysfs_xprt_xprtsec = __ATTR(xprtsec,
+	0644, rpc_sysfs_xprt_xprtsec_show, NULL);
 
 static struct kobj_attribute rpc_sysfs_xprt_info = __ATTR(xprt_info,
 	0444, rpc_sysfs_xprt_info_show, NULL);
···
 static struct kobj_attribute rpc_sysfs_xprt_change_state = __ATTR(xprt_state,
 	0644, rpc_sysfs_xprt_state_show, rpc_sysfs_xprt_state_change);
 
+static struct kobj_attribute rpc_sysfs_xprt_del = __ATTR(del_xprt,
+	0644, rpc_sysfs_xprt_del_xprt_show, rpc_sysfs_xprt_del_xprt);
+
 static struct attribute *rpc_sysfs_xprt_attrs[] = {
 	&rpc_sysfs_xprt_dstaddr.attr,
 	&rpc_sysfs_xprt_srcaddr.attr,
+	&rpc_sysfs_xprt_xprtsec.attr,
 	&rpc_sysfs_xprt_info.attr,
 	&rpc_sysfs_xprt_change_state.attr,
+	&rpc_sysfs_xprt_del.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(rpc_sysfs_xprt);
···
 static struct kobj_attribute rpc_sysfs_xprt_switch_info =
 	__ATTR(xprt_switch_info, 0444, rpc_sysfs_xprt_switch_info_show, NULL);
 
+static struct kobj_attribute rpc_sysfs_xprt_switch_add_xprt =
+	__ATTR(add_xprt, 0644, rpc_sysfs_xprt_switch_add_xprt_show,
+		rpc_sysfs_xprt_switch_add_xprt_store);
+
 static struct attribute *rpc_sysfs_xprt_switch_attrs[] = {
 	&rpc_sysfs_xprt_switch_info.attr,
+	&rpc_sysfs_xprt_switch_add_xprt.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(rpc_sysfs_xprt_switch);
 
 static const struct kobj_type rpc_sysfs_client_type = {
 	.release = rpc_sysfs_client_release,
+	.default_groups = rpc_sysfs_rpc_clnt_groups,
 	.sysfs_ops = &kobj_sysfs_ops,
 	.namespace = rpc_sysfs_client_namespace,
 };

net/sunrpc/xprtmultipath.c

···
 	xprt_put(xprt);
 }
 
+/**
+ * rpc_xprt_switch_get_main_xprt - Get the 'main' xprt for an xprt switch.
+ * @xps: pointer to struct rpc_xprt_switch.
+ */
+struct rpc_xprt *rpc_xprt_switch_get_main_xprt(struct rpc_xprt_switch *xps)
+{
+	struct rpc_xprt_iter xpi;
+	struct rpc_xprt *xprt;
+
+	xprt_iter_init_listall(&xpi, xps);
+
+	xprt = xprt_iter_get_next(&xpi);
+	while (xprt && !xprt->main) {
+		xprt_put(xprt);
+		xprt = xprt_iter_get_next(&xpi);
+	}
+
+	xprt_iter_destroy(&xpi);
+	return xprt;
+}
+
 static DEFINE_IDA(rpc_xprtswitch_ids);
 
 void xprt_multipath_cleanup_ids(void)