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

9 files changed, 97 insertions, 57 deletions

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index ce6474594872..b9a8b925db43 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -41,6 +41,11 @@
 #include <linux/mempool.h>
 
 /*
+ * These are the default for number of transports to different server IPs
+ */
+#define NFS_MAX_TRANSPORTS 16
+
+/*
  * These are the default flags for swap requests
  */
 #define NFS_RPC_SWAPFLAGS		(RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS)
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index d71a0e90faeb..2a9acbfe00f0 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -62,6 +62,7 @@ struct nfs_client {
 
 	u32			cl_minorversion;/* NFSv4 minorversion */
 	unsigned int		cl_nconnect;	/* Number of connections */
+	unsigned int		cl_max_connect; /* max number of xprts allowed */
 	const char *		cl_principal;  /* used for machine cred */
 
 #if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 8b5d5c97553e..a4661646adc9 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -14,6 +14,7 @@
 #include <linux/socket.h>
 #include <linux/in.h>
 #include <linux/in6.h>
+#include <linux/refcount.h>
 
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/sunrpc/sched.h>
@@ -35,7 +36,7 @@ struct rpc_sysfs_client;
  * The high-level client handle
  */
 struct rpc_clnt {
-	atomic_t		cl_count;	/* Number of references */
+	refcount_t		cl_count;	/* Number of references */
 	unsigned int		cl_clid;	/* client id */
 	struct list_head	cl_clients;	/* Global list of clients */
 	struct list_head	cl_tasks;	/* List of tasks */
@@ -81,6 +82,7 @@ struct rpc_clnt {
 		struct work_struct	cl_work;
 	};
 	const struct cred	*cl_cred;
+	unsigned int		cl_max_connect; /* max number of transports not to the same IP */
 };
 
 /*
@@ -135,6 +137,7 @@ struct rpc_create_args {
 	char			*client_name;
 	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
 	const struct cred	*cred;
+	unsigned int		max_connect;
 };
 
 struct rpc_add_xprt_test {
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index f0f846fa396e..064c96157d1f 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -277,13 +277,13 @@ struct svc_rqst {
 #define	RQ_VICTIM	(5)			/* about to be shut down */
 #define	RQ_BUSY		(6)			/* request is busy */
 #define	RQ_DATA		(7)			/* request has data */
-#define RQ_AUTHERR	(8)			/* Request status is auth error */
 	unsigned long		rq_flags;	/* flags field */
 	ktime_t			rq_qtime;	/* enqueue time */
 
 	void *			rq_argp;	/* decoded arguments */
 	void *			rq_resp;	/* xdr'd results */
 	void *			rq_auth_data;	/* flavor-specific data */
+	__be32			rq_auth_stat;	/* authentication status */
 	int			rq_auth_slack;	/* extra space xdr code
 						 * should leave in head
 						 * for krb5i, krb5p.
@@ -537,7 +537,6 @@ unsigned int	   svc_fill_write_vector(struct svc_rqst *rqstp,
 char		  *svc_fill_symlink_pathname(struct svc_rqst *rqstp,
 					     struct kvec *first, void *p,
 					     size_t total);
-__be32		   svc_return_autherr(struct svc_rqst *rqstp, __be32 auth_err);
 __be32		   svc_generic_init_request(struct svc_rqst *rqstp,
 					    const struct svc_program *progp,
 					    struct svc_process_info *procinfo);
diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index b0003866a249..6d9cc9080aca 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -127,7 +127,7 @@ struct auth_ops {
 	char *	name;
 	struct module *owner;
 	int	flavour;
-	int	(*accept)(struct svc_rqst *rq, __be32 *authp);
+	int	(*accept)(struct svc_rqst *rq);
 	int	(*release)(struct svc_rqst *rq);
 	void	(*domain_release)(struct auth_domain *);
 	int	(*set_client)(struct svc_rqst *rq);
@@ -149,7 +149,7 @@ struct auth_ops {
 
 struct svc_xprt;
 
-extern int	svc_authenticate(struct svc_rqst *rqstp, __be32 *authp);
+extern int	svc_authenticate(struct svc_rqst *rqstp);
 extern int	svc_authorise(struct svc_rqst *rqstp);
 extern int	svc_set_client(struct svc_rqst *rqstp);
 extern int	svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index b15c1f07162d..955ea4d7af0b 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -431,6 +431,7 @@ void			xprt_release_write(struct rpc_xprt *, struct rpc_task *);
 #define XPRT_CONGESTED		(9)
 #define XPRT_CWND_WAIT		(10)
 #define XPRT_WRITE_SPACE	(11)
+#define XPRT_SND_IS_COOKIE	(12)
 
 static inline void xprt_set_connected(struct rpc_xprt *xprt)
 {
diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h
index b19addc8b715..bbb8a5fa0816 100644
--- a/include/linux/sunrpc/xprtmultipath.h
+++ b/include/linux/sunrpc/xprtmultipath.h
@@ -18,6 +18,7 @@ struct rpc_xprt_switch {
 	unsigned int		xps_id;
 	unsigned int		xps_nxprts;
 	unsigned int		xps_nactive;
+	unsigned int		xps_nunique_destaddr_xprts;
 	atomic_long_t		xps_queuelen;
 	struct list_head	xps_xprt_list;
 
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index bd55908c1bef..de4195499592 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -793,6 +793,39 @@ TRACE_EVENT(xprtrdma_post_send,
 	)
 );
 
+TRACE_EVENT(xprtrdma_post_send_err,
+	TP_PROTO(
+		const struct rpcrdma_xprt *r_xprt,
+		const struct rpcrdma_req *req,
+		int rc
+	),
+
+	TP_ARGS(r_xprt, req, rc),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(int, rc)
+	),
+
+	TP_fast_assign(
+		const struct rpc_rqst *rqst = &req->rl_slot;
+		const struct rpcrdma_ep *ep = r_xprt->rx_ep;
+
+		__entry->cq_id = ep ? ep->re_attr.recv_cq->res.id : 0;
+		__entry->task_id = rqst->rq_task->tk_pid;
+		__entry->client_id = rqst->rq_task->tk_client ?
+				     rqst->rq_task->tk_client->cl_clid : -1;
+		__entry->rc = rc;
+	),
+
+	TP_printk("task:%u@%u cq.id=%u rc=%d",
+		__entry->task_id, __entry->client_id,
+		__entry->cq_id, __entry->rc
+	)
+);
+
 TRACE_EVENT(xprtrdma_post_recv,
 	TP_PROTO(
 		const struct rpcrdma_rep *rep
@@ -818,16 +851,14 @@ TRACE_EVENT(xprtrdma_post_recv,
 TRACE_EVENT(xprtrdma_post_recvs,
 	TP_PROTO(
 		const struct rpcrdma_xprt *r_xprt,
-		unsigned int count,
-		int status
+		unsigned int count
 	),
 
-	TP_ARGS(r_xprt, count, status),
+	TP_ARGS(r_xprt, count),
 
 	TP_STRUCT__entry(
 		__field(u32, cq_id)
 		__field(unsigned int, count)
-		__field(int, status)
 		__field(int, posted)
 		__string(addr, rpcrdma_addrstr(r_xprt))
 		__string(port, rpcrdma_portstr(r_xprt))
@@ -838,15 +869,44 @@ TRACE_EVENT(xprtrdma_post_recvs,
 
 		__entry->cq_id = ep->re_attr.recv_cq->res.id;
 		__entry->count = count;
-		__entry->status = status;
 		__entry->posted = ep->re_receive_count;
 		__assign_str(addr, rpcrdma_addrstr(r_xprt));
 		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("peer=[%s]:%s cq.id=%d %u new recvs, %d active (rc %d)",
+	TP_printk("peer=[%s]:%s cq.id=%d %u new recvs, %d active",
+		__get_str(addr), __get_str(port), __entry->cq_id,
+		__entry->count, __entry->posted
+	)
+);
+
+TRACE_EVENT(xprtrdma_post_recvs_err,
+	TP_PROTO(
+		const struct rpcrdma_xprt *r_xprt,
+		int status
+	),
+
+	TP_ARGS(r_xprt, status),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, status)
+		__string(addr, rpcrdma_addrstr(r_xprt))
+		__string(port, rpcrdma_portstr(r_xprt))
+	),
+
+	TP_fast_assign(
+		const struct rpcrdma_ep *ep = r_xprt->rx_ep;
+
+		__entry->cq_id = ep->re_attr.recv_cq->res.id;
+		__entry->status = status;
+		__assign_str(addr, rpcrdma_addrstr(r_xprt));
+		__assign_str(port, rpcrdma_portstr(r_xprt));
+	),
+
+	TP_printk("peer=[%s]:%s cq.id=%d rc=%d",
 		__get_str(addr), __get_str(port), __entry->cq_id,
-		__entry->count, __entry->posted, __entry->status
+		__entry->status
 	)
 );
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index d323f5a049c8..2d04eb96d418 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -295,25 +295,11 @@ TRACE_EVENT(rpc_request,
 		)
 );
 
-TRACE_DEFINE_ENUM(RPC_TASK_ASYNC);
-TRACE_DEFINE_ENUM(RPC_TASK_SWAPPER);
-TRACE_DEFINE_ENUM(RPC_TASK_NULLCREDS);
-TRACE_DEFINE_ENUM(RPC_CALL_MAJORSEEN);
-TRACE_DEFINE_ENUM(RPC_TASK_ROOTCREDS);
-TRACE_DEFINE_ENUM(RPC_TASK_DYNAMIC);
-TRACE_DEFINE_ENUM(RPC_TASK_NO_ROUND_ROBIN);
-TRACE_DEFINE_ENUM(RPC_TASK_SOFT);
-TRACE_DEFINE_ENUM(RPC_TASK_SOFTCONN);
-TRACE_DEFINE_ENUM(RPC_TASK_SENT);
-TRACE_DEFINE_ENUM(RPC_TASK_TIMEOUT);
-TRACE_DEFINE_ENUM(RPC_TASK_NOCONNECT);
-TRACE_DEFINE_ENUM(RPC_TASK_NO_RETRANS_TIMEOUT);
-TRACE_DEFINE_ENUM(RPC_TASK_CRED_NOREF);
-
 #define rpc_show_task_flags(flags)					\
 	__print_flags(flags, "|",					\
 		{ RPC_TASK_ASYNC, "ASYNC" },				\
 		{ RPC_TASK_SWAPPER, "SWAPPER" },			\
+		{ RPC_TASK_MOVEABLE, "MOVEABLE" },			\
 		{ RPC_TASK_NULLCREDS, "NULLCREDS" },			\
 		{ RPC_CALL_MAJORSEEN, "MAJORSEEN" },			\
 		{ RPC_TASK_ROOTCREDS, "ROOTCREDS" },			\
@@ -327,14 +313,6 @@ TRACE_DEFINE_ENUM(RPC_TASK_CRED_NOREF);
 		{ RPC_TASK_NO_RETRANS_TIMEOUT, "NORTO" },		\
 		{ RPC_TASK_CRED_NOREF, "CRED_NOREF" })
 
-TRACE_DEFINE_ENUM(RPC_TASK_RUNNING);
-TRACE_DEFINE_ENUM(RPC_TASK_QUEUED);
-TRACE_DEFINE_ENUM(RPC_TASK_ACTIVE);
-TRACE_DEFINE_ENUM(RPC_TASK_NEED_XMIT);
-TRACE_DEFINE_ENUM(RPC_TASK_NEED_RECV);
-TRACE_DEFINE_ENUM(RPC_TASK_MSG_PIN_WAIT);
-TRACE_DEFINE_ENUM(RPC_TASK_SIGNALLED);
-
 #define rpc_show_runstate(flags)					\
 	__print_flags(flags, "|",					\
 		{ (1UL << RPC_TASK_RUNNING), "RUNNING" },		\
@@ -945,17 +923,6 @@ TRACE_EVENT(rpc_socket_nospace,
 	)
 );
 
-TRACE_DEFINE_ENUM(XPRT_LOCKED);
-TRACE_DEFINE_ENUM(XPRT_CONNECTED);
-TRACE_DEFINE_ENUM(XPRT_CONNECTING);
-TRACE_DEFINE_ENUM(XPRT_CLOSE_WAIT);
-TRACE_DEFINE_ENUM(XPRT_BOUND);
-TRACE_DEFINE_ENUM(XPRT_BINDING);
-TRACE_DEFINE_ENUM(XPRT_CLOSING);
-TRACE_DEFINE_ENUM(XPRT_CONGESTED);
-TRACE_DEFINE_ENUM(XPRT_CWND_WAIT);
-TRACE_DEFINE_ENUM(XPRT_WRITE_SPACE);
-
 #define rpc_show_xprt_state(x)						\
 	__print_flags(x, "|",						\
 		{ (1UL << XPRT_LOCKED),		"LOCKED"},		\
@@ -965,6 +932,8 @@ TRACE_DEFINE_ENUM(XPRT_WRITE_SPACE);
 		{ (1UL << XPRT_BOUND),		"BOUND"},		\
 		{ (1UL << XPRT_BINDING),	"BINDING"},		\
 		{ (1UL << XPRT_CLOSING),	"CLOSING"},		\
+		{ (1UL << XPRT_OFFLINE),	"OFFLINE"},		\
+		{ (1UL << XPRT_REMOVE),		"REMOVE"},		\
 		{ (1UL << XPRT_CONGESTED),	"CONGESTED"},		\
 		{ (1UL << XPRT_CWND_WAIT),	"CWND_WAIT"},		\
 		{ (1UL << XPRT_WRITE_SPACE),	"WRITE_SPACE"})
@@ -1092,10 +1061,10 @@ TRACE_EVENT(xprt_retransmit,
 		__field(u32, xid)
 		__field(int, ntrans)
 		__field(int, version)
+		__field(unsigned long, timeout)
 		__string(progname,
 			 rqst->rq_task->tk_client->cl_program->name)
-		__string(procedure,
-			 rqst->rq_task->tk_msg.rpc_proc->p_name)
+		__string(procname, rpc_proc_name(rqst->rq_task))
 	),
 
 	TP_fast_assign(
@@ -1106,17 +1075,19 @@ TRACE_EVENT(xprt_retransmit,
 			task->tk_client->cl_clid : -1;
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
 		__entry->ntrans = rqst->rq_ntrans;
+		__entry->timeout = task->tk_timeout;
 		__assign_str(progname,
 			     task->tk_client->cl_program->name);
 		__entry->version = task->tk_client->cl_vers;
-		__assign_str(procedure, task->tk_msg.rpc_proc->p_name);
+		__assign_str(procname, rpc_proc_name(task));
 	),
 
 	TP_printk(
-		"task:%u@%u xid=0x%08x %sv%d %s ntrans=%d",
+		"task:%u@%u xid=0x%08x %sv%d %s ntrans=%d timeout=%lu",
 		__entry->task_id, __entry->client_id, __entry->xid,
-		__get_str(progname), __entry->version, __get_str(procedure),
-		__entry->ntrans)
+		__get_str(progname), __entry->version, __get_str(procname),
+		__entry->ntrans, __entry->timeout
+	)
 );
 
 TRACE_EVENT(xprt_ping,
@@ -1568,8 +1539,7 @@ DEFINE_SVCXDRBUF_EVENT(sendto);
 	svc_rqst_flag(SPLICE_OK)					\
 	svc_rqst_flag(VICTIM)						\
 	svc_rqst_flag(BUSY)						\
-	svc_rqst_flag(DATA)						\
-	svc_rqst_flag_end(AUTHERR)
+	svc_rqst_flag_end(DATA)
 
 #undef svc_rqst_flag
 #undef svc_rqst_flag_end
@@ -1611,9 +1581,9 @@ TRACE_DEFINE_ENUM(SVC_COMPLETE);
 		{ SVC_COMPLETE,	"SVC_COMPLETE" })
 
 TRACE_EVENT(svc_authenticate,
-	TP_PROTO(const struct svc_rqst *rqst, int auth_res, __be32 auth_stat),
+	TP_PROTO(const struct svc_rqst *rqst, int auth_res),
 
-	TP_ARGS(rqst, auth_res, auth_stat),
+	TP_ARGS(rqst, auth_res),
 
 	TP_STRUCT__entry(
 		__field(u32, xid)
@@ -1624,7 +1594,7 @@ TRACE_EVENT(svc_authenticate,
 	TP_fast_assign(
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
 		__entry->svc_status = auth_res;
-		__entry->auth_stat = be32_to_cpu(auth_stat);
+		__entry->auth_stat = be32_to_cpu(rqst->rq_auth_stat);
 	),
 
 	TP_printk("xid=0x%08x auth_res=%s auth_stat=%s",