Merge tag 'nfs-for-5.15-1' of git://git.linux-nfs.org/projects/anna/l…

…inux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Better client responsiveness when server isn't replying
   - Use refcount_t in sunrpc rpc_client refcount tracking
   - Add srcaddr and dst_port to the sunrpc sysfs info files
   - Add basic support for connection sharing between servers with multiple NICs`

  Bugfixes and Cleanups:
   - Sunrpc tracepoint cleanups
   - Disconnect after ib_post_send() errors to avoid deadlocks
   - Fix for tearing down rpcrdma_reps
   - Fix a potential pNFS layoutget livelock loop
   - pNFS layout barrier fixes
   - Fix a potential memory corruption in rpc_wake_up_queued_task_set_status()
   - Fix reconnection locking
   - Fix return value of get_srcport()
   - Remove rpcrdma_post_sends()
   - Remove pNFS dead code
   - Remove copy size restriction for inter-server copies
   - Overhaul the NFS callback service
   - Clean up sunrpc TCP socket shutdowns
   - Always provide aligned buffers to RPC read layers"

* tag 'nfs-for-5.15-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (39 commits)
  NFS: Always provide aligned buffers to the RPC read layers
  NFSv4.1 add network transport when session trunking is detected
  SUNRPC enforce creation of no more than max_connect xprts
  NFSv4 introduce max_connect mount options
  SUNRPC add xps_nunique_destaddr_xprts to xprt_switch_info in sysfs
  SUNRPC keep track of number of transports to unique addresses
  NFSv3: Delete duplicate judgement in nfs3_async_handle_jukebox
  SUNRPC: Tweak TCP socket shutdown in the RPC client
  SUNRPC: Simplify socket shutdown when not reusing TCP ports
  NFSv4.2: remove restriction of copy size for inter-server copy.
  NFS: Clean up the synopsis of callback process_op()
  NFS: Extract the xdr_init_encode/decode() calls from decode_compound
  NFS: Remove unused callback void decoder
  NFS: Add a private local dispatcher for NFSv4 callback operations
  SUNRPC: Eliminate the RQ_AUTHERR flag
  SUNRPC: Set rq_auth_stat in the pg_authenticate() callout
  SUNRPC: Add svc_rqst::rq_auth_stat
  SUNRPC: Add dst_port to the sysfs xprt info file
  SUNRPC: Add srcaddr as a file in sysfs
  sunrpc: Fix return value of get_srcport()
  ...

fs/lockd/svc.c

@@ -649,6 +649,7 @@ static int lockd_authenticate(struct svc_rqst *rqstp)
 	switch (rqstp->rq_authop->flavour) {
 		case RPC_AUTH_NULL:
 		case RPC_AUTH_UNIX:
+			rqstp->rq_auth_stat = rpc_auth_ok;
 			if (rqstp->rq_proc == 0)
 				return SVC_OK;
 			if (is_callback(rqstp->rq_proc)) {
@@ -659,6 +660,7 @@ static int lockd_authenticate(struct svc_rqst *rqstp)
 			}
 			return svc_set_client(rqstp);
 	}
+	rqstp->rq_auth_stat = rpc_autherr_badcred;
 	return SVC_DENIED;
 }
 

fs/nfs/callback.c

@@ -429,6 +429,8 @@ check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
  */
 static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 {
+	rqstp->rq_auth_stat = rpc_autherr_badcred;
+
 	switch (rqstp->rq_authop->flavour) {
 	case RPC_AUTH_NULL:
 		if (rqstp->rq_proc != CB_NULL)
@@ -439,6 +441,8 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 		 if (svc_is_backchannel(rqstp))
 			return SVC_DENIED;
 	}
+
+	rqstp->rq_auth_stat = rpc_auth_ok;
 	return SVC_OK;
 }
 

fs/nfs/callback_xdr.c

@@ -63,11 +63,10 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp)
 	return htonl(NFS4_OK);
 }
 
-static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p)
-{
-	return xdr_argsize_check(rqstp, p);
-}
-
+/*
+ * svc_process_common() looks for an XDR encoder to know when
+ * not to drop a Reply.
+ */
 static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
@@ -864,17 +863,16 @@ preprocess_nfs4_op(unsigned int op_nr, struct callback_op **op)
 }
 
 static __be32 process_op(int nop, struct svc_rqst *rqstp,
-		struct xdr_stream *xdr_in, void *argp,
-		struct xdr_stream *xdr_out, void *resp,
-		struct cb_process_state *cps)
+			 struct cb_process_state *cps)
 {
+	struct xdr_stream *xdr_out = &rqstp->rq_res_stream;
 	struct callback_op *op = &callback_ops[0];
 	unsigned int op_nr;
 	__be32 status;
 	long maxlen;
 	__be32 res;
 
-	status = decode_op_hdr(xdr_in, &op_nr);
+	status = decode_op_hdr(&rqstp->rq_arg_stream, &op_nr);
 	if (unlikely(status))
 		return status;
 
@@ -904,9 +902,11 @@ static __be32 process_op(int nop, struct svc_rqst *rqstp,
 
 	maxlen = xdr_out->end - xdr_out->p;
 	if (maxlen > 0 && maxlen < PAGE_SIZE) {
-		status = op->decode_args(rqstp, xdr_in, argp);
+		status = op->decode_args(rqstp, &rqstp->rq_arg_stream,
+					 rqstp->rq_argp);
 		if (likely(status == 0))
-			status = op->process_op(argp, resp, cps);
+			status = op->process_op(rqstp->rq_argp, rqstp->rq_resp,
+						cps);
 	} else
 		status = htonl(NFS4ERR_RESOURCE);
 
@@ -915,7 +915,7 @@ static __be32 process_op(int nop, struct svc_rqst *rqstp,
 	if (unlikely(res))
 		return res;
 	if (op->encode_res != NULL && status == 0)
-		status = op->encode_res(rqstp, xdr_out, resp);
+		status = op->encode_res(rqstp, xdr_out, rqstp->rq_resp);
 	return status;
 }
 
@@ -926,22 +926,15 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 {
 	struct cb_compound_hdr_arg hdr_arg = { 0 };
 	struct cb_compound_hdr_res hdr_res = { NULL };
-	struct xdr_stream xdr_in, xdr_out;
-	__be32 *p, status;
 	struct cb_process_state cps = {
 		.drc_status = 0,
 		.clp = NULL,
 		.net = SVC_NET(rqstp),
 	};
 	unsigned int nops = 0;
+	__be32 status;
 
-	xdr_init_decode(&xdr_in, &rqstp->rq_arg,
-			rqstp->rq_arg.head[0].iov_base, NULL);
-
-	p = (__be32*)((char *)rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len);
-	xdr_init_encode(&xdr_out, &rqstp->rq_res, p, NULL);
-
-	status = decode_compound_hdr_arg(&xdr_in, &hdr_arg);
+	status = decode_compound_hdr_arg(&rqstp->rq_arg_stream, &hdr_arg);
 	if (status == htonl(NFS4ERR_RESOURCE))
 		return rpc_garbage_args;
 
@@ -961,15 +954,13 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 	cps.minorversion = hdr_arg.minorversion;
 	hdr_res.taglen = hdr_arg.taglen;
 	hdr_res.tag = hdr_arg.tag;
-	if (encode_compound_hdr_res(&xdr_out, &hdr_res) != 0) {
+	if (encode_compound_hdr_res(&rqstp->rq_res_stream, &hdr_res) != 0) {
 		if (cps.clp)
 			nfs_put_client(cps.clp);
 		return rpc_system_err;
 	}
 	while (status == 0 && nops != hdr_arg.nops) {
-		status = process_op(nops, rqstp, &xdr_in,
-				    rqstp->rq_argp, &xdr_out, rqstp->rq_resp,
-				    &cps);
+		status = process_op(nops, rqstp, &cps);
 		nops++;
 	}
 
@@ -988,7 +979,20 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 
 out_invalidcred:
 	pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n");
-	return svc_return_autherr(rqstp, rpc_autherr_badcred);
+	rqstp->rq_auth_stat = rpc_autherr_badcred;
+	return rpc_success;
+}
+
+static int
+nfs_callback_dispatch(struct svc_rqst *rqstp, __be32 *statp)
+{
+	const struct svc_procedure *procp = rqstp->rq_procinfo;
+
+	svcxdr_init_decode(rqstp);
+	svcxdr_init_encode(rqstp);
+
+	*statp = procp->pc_func(rqstp);
+	return 1;
 }
 
 /*
@@ -1057,7 +1061,6 @@ static struct callback_op callback_ops[] = {
 static const struct svc_procedure nfs4_callback_procedures1[] = {
 	[CB_NULL] = {
 		.pc_func = nfs4_callback_null,
-		.pc_decode = nfs4_decode_void,
 		.pc_encode = nfs4_encode_void,
 		.pc_xdrressize = 1,
 		.pc_name = "NULL",
@@ -1079,7 +1082,7 @@ const struct svc_version nfs4_callback_version1 = {
 	.vs_proc = nfs4_callback_procedures1,
 	.vs_count = nfs4_callback_count1,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
-	.vs_dispatch = NULL,
+	.vs_dispatch = nfs_callback_dispatch,
 	.vs_hidden = true,
 	.vs_need_cong_ctrl = true,
 };
@@ -1091,7 +1094,7 @@ const struct svc_version nfs4_callback_version4 = {
 	.vs_proc = nfs4_callback_procedures1,
 	.vs_count = nfs4_callback_count4,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
-	.vs_dispatch = NULL,
+	.vs_dispatch = nfs_callback_dispatch,
 	.vs_hidden = true,
 	.vs_need_cong_ctrl = true,
 };

fs/nfs/client.c

@@ -179,6 +179,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 
 	clp->cl_proto = cl_init->proto;
 	clp->cl_nconnect = cl_init->nconnect;
+	clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
 	clp->cl_net = get_net(cl_init->net);
 
 	clp->cl_principal = "*";
@@ -540,6 +541,7 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 
 	clnt->cl_principal = clp->cl_principal;
 	clp->cl_rpcclient = clnt;
+	clnt->cl_max_connect = clp->cl_max_connect;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nfs_create_rpc_client);

fs/nfs/fs_context.c

@@ -60,6 +60,7 @@ enum nfs_param {
 	Opt_mountvers,
 	Opt_namelen,
 	Opt_nconnect,
+	Opt_max_connect,
 	Opt_port,
 	Opt_posix,
 	Opt_proto,
@@ -158,6 +159,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_u32   ("mountvers",	Opt_mountvers),
 	fsparam_u32   ("namlen",	Opt_namelen),
 	fsparam_u32   ("nconnect",	Opt_nconnect),
+	fsparam_u32   ("max_connect",	Opt_max_connect),
 	fsparam_string("nfsvers",	Opt_vers),
 	fsparam_u32   ("port",		Opt_port),
 	fsparam_flag_no("posix",	Opt_posix),
@@ -770,6 +772,11 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 			goto out_of_bounds;
 		ctx->nfs_server.nconnect = result.uint_32;
 		break;
+	case Opt_max_connect:
+		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_lookupcache:
 		switch (result.uint_32) {
 		case Opt_lookupcache_all:

fs/nfs/internal.h

@@ -67,6 +67,7 @@ struct nfs_client_initdata {
 	int proto;
 	u32 minorversion;
 	unsigned int nconnect;
+	unsigned int max_connect;
 	struct net *net;
 	const struct rpc_timeout *timeparms;
 	const struct cred *cred;
@@ -121,6 +122,7 @@ struct nfs_fs_context {
 		int			port;
 		unsigned short		protocol;
 		unsigned short		nconnect;
+		unsigned short		max_connect;
 		unsigned short		export_path_len;
 	} nfs_server;
 

fs/nfs/nfs3proc.c

@@ -49,8 +49,7 @@ nfs3_async_handle_jukebox(struct rpc_task *task, struct inode *inode)
 {
 	if (task->tk_status != -EJUKEBOX)
 		return 0;
-	if (task->tk_status == -EJUKEBOX)
-		nfs_inc_stats(inode, NFSIOS_DELAY);
+	nfs_inc_stats(inode, NFSIOS_DELAY);
 	task->tk_status = 0;
 	rpc_restart_call(task);
 	rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);

fs/nfs/nfs4client.c

@@ -402,6 +402,33 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
 	return nfs4_init_callback(clp);
 }
 
+static void nfs4_add_trunk(struct nfs_client *clp, struct nfs_client *old)
+{
+	struct sockaddr_storage clp_addr, old_addr;
+	struct sockaddr *clp_sap = (struct sockaddr *)&clp_addr;
+	struct sockaddr *old_sap = (struct sockaddr *)&old_addr;
+	size_t clp_salen;
+	struct xprt_create xprt_args = {
+		.ident = old->cl_proto,
+		.net = old->cl_net,
+		.servername = old->cl_hostname,
+	};
+
+	if (clp->cl_proto != old->cl_proto)
+		return;
+	clp_salen = rpc_peeraddr(clp->cl_rpcclient, clp_sap, sizeof(clp_addr));
+	rpc_peeraddr(old->cl_rpcclient, old_sap, sizeof(old_addr));
+
+	if (clp_addr.ss_family != old_addr.ss_family)
+		return;
+
+	xprt_args.dstaddr = clp_sap;
+	xprt_args.addrlen = clp_salen;
+
+	rpc_clnt_add_xprt(old->cl_rpcclient, &xprt_args,
+			  rpc_clnt_test_and_add_xprt, NULL);
+}
+
 /**
  * nfs4_init_client - Initialise an NFS4 client record
  *
@@ -436,6 +463,8 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 		 * won't try to use it.
 		 */
 		nfs_mark_client_ready(clp, -EPERM);
+		if (old->cl_mvops->session_trunk)
+			nfs4_add_trunk(clp, old);
 	}
 	clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags);
 	nfs_put_client(clp);
@@ -865,6 +894,7 @@ static int nfs4_set_client(struct nfs_server *server,
 		const char *ip_addr,
 		int proto, const struct rpc_timeout *timeparms,
 		u32 minorversion, unsigned int nconnect,
+		unsigned int max_connect,
 		struct net *net)
 {
 	struct nfs_client_initdata cl_init = {
@@ -883,6 +913,8 @@ static int nfs4_set_client(struct nfs_server *server,
 
 	if (minorversion == 0)
 		__set_bit(NFS_CS_REUSEPORT, &cl_init.init_flags);
+	else
+		cl_init.max_connect = max_connect;
 	if (proto == XPRT_TRANSPORT_TCP)
 		cl_init.nconnect = nconnect;
 
@@ -952,8 +984,10 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 		return ERR_PTR(-EINVAL);
 	cl_init.hostname = buf;
 
-	if (mds_clp->cl_nconnect > 1 && ds_proto == XPRT_TRANSPORT_TCP)
+	if (mds_clp->cl_nconnect > 1 && ds_proto == XPRT_TRANSPORT_TCP) {
 		cl_init.nconnect = mds_clp->cl_nconnect;
+		cl_init.max_connect = NFS_MAX_TRANSPORTS;
+	}
 
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
@@ -1122,6 +1156,7 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc)
 				&timeparms,
 				ctx->minorversion,
 				ctx->nfs_server.nconnect,
+				ctx->nfs_server.max_connect,
 				fc->net_ns);
 	if (error < 0)
 		return error;
@@ -1211,6 +1246,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc)
 				parent_server->client->cl_timeout,
 				parent_client->cl_mvops->minor_version,
 				parent_client->cl_nconnect,
+				parent_client->cl_max_connect,
 				parent_client->cl_net);
 	if (!error)
 		goto init_server;
@@ -1226,6 +1262,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc)
 				parent_server->client->cl_timeout,
 				parent_client->cl_mvops->minor_version,
 				parent_client->cl_nconnect,
+				parent_client->cl_max_connect,
 				parent_client->cl_net);
 	if (error < 0)
 		goto error;
@@ -1323,7 +1360,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
 	error = nfs4_set_client(server, hostname, sap, salen, buf,
 				clp->cl_proto, clnt->cl_timeout,
 				clp->cl_minorversion,
-				clp->cl_nconnect, net);
+				clp->cl_nconnect, clp->cl_max_connect, net);
 	clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
 	if (error != 0) {
 		nfs_server_insert_lists(server);

fs/nfs/nfs4file.c

@@ -158,13 +158,11 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 		sync = true;
 retry:
 	if (!nfs42_files_from_same_server(file_in, file_out)) {
-		/* for inter copy, if copy size if smaller than 12 RPC
-		 * payloads, fallback to traditional copy. There are
-		 * 14 RPCs during an NFSv4.x mount between source/dest
-		 * servers.
+		/*
+		 * for inter copy, if copy size is too small
+		 * then fallback to generic copy.
 		 */
-		if (sync ||
-			count <= 14 * NFS_SERVER(file_inode(file_in))->rsize)
+		if (sync)
 			return -EOPNOTSUPP;
 		cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res),
 				GFP_NOFS);