Merge tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable fixes:

   - SUNRPC: Ensure bvecs are re-synced when we re-encode the RPC
     request

   - Fix an Oops in ff_layout_track_ds_error due to a PTR_ERR()
     dereference

   - Revert buggy NFS readdirplus optimisation

   - NFSv4: Handle the special Linux file open access mode

   - pnfs: Fix a problem where we gratuitously start doing I/O through
     the MDS

  Features:

   - Allow NFS client to set up multiple TCP connections to the server
     using a new 'nconnect=X' mount option. Queue length is used to
     balance load.

   - Enhance statistics reporting to report on all transports when using
     multiple connections.

   - Speed up SUNRPC by removing bh-safe spinlocks

   - Add a mechanism to allow NFSv4 to request that containers set a
     unique per-host identifier for when the hostname is not set.

   - Ensure NFSv4 updates the lease_time after a clientid update

  Bugfixes and cleanup:

   - Fix use-after-free in rpcrdma_post_recvs

   - Fix a memory leak when nfs_match_client() is interrupted

   - Fix buggy file access checking in NFSv4 open for execute

   - disable unsupported client side deduplication

   - Fix spurious client disconnections

   - Fix occasional RDMA transport deadlock

   - Various RDMA cleanups

   - Various tracepoint fixes

   - Fix the TCP callback channel to guarantee the server can actually
     send the number of callback requests that was negotiated at mount
     time"

* tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (68 commits)
  pnfs/flexfiles: Add tracepoints for detecting pnfs fallback to MDS
  pnfs: Fix a problem where we gratuitously start doing I/O through the MDS
  SUNRPC: Optimise transport balancing code
  SUNRPC: Ensure the bvecs are reset when we re-encode the RPC request
  pnfs/flexfiles: Fix PTR_ERR() dereferences in ff_layout_track_ds_error
  NFSv4: Don't use the zero stateid with layoutget
  SUNRPC: Fix up backchannel slot table accounting
  SUNRPC: Fix initialisation of struct rpc_xprt_switch
  SUNRPC: Skip zero-refcount transports
  SUNRPC: Replace division by multiplication in calculation of queue length
  NFSv4: Validate the stateid before applying it to state recovery
  nfs4.0: Refetch lease_time after clientid update
  nfs4: Rename nfs41_setup_state_renewal
  nfs4: Make nfs4_proc_get_lease_time available for nfs4.0
  nfs: Fix copy-and-paste error in debug message
  NFS: Replace 16 seq_printf() calls by seq_puts()
  NFS: Use seq_putc() in nfs_show_stats()
  Revert "NFS: readdirplus optimization by cache mechanism" (memleak)
  SUNRPC: Fix transport accounting when caller specifies an rpc_xprt
  NFS: Record task, client ID, and XID in xdr_status trace points
  ...

7 files changed, 29 insertions, 4 deletions

diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index d4229a78524a..87d27e13d885 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -43,6 +43,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
 int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs);
 void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs);
 void xprt_free_bc_rqst(struct rpc_rqst *req);
+unsigned int xprt_bc_max_slots(struct rpc_xprt *xprt);
 
 /*
  * Determine if a shared backchannel is in use
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 6e8073140a5d..abc63bd1be2b 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -124,6 +124,7 @@ struct rpc_create_args {
 	u32			prognumber;	/* overrides program->number */
 	u32			version;
 	rpc_authflavor_t	authflavor;
+	u32			nconnect;
 	unsigned long		flags;
 	char			*client_name;
 	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
@@ -163,6 +164,8 @@ void		rpc_shutdown_client(struct rpc_clnt *);
 void		rpc_release_client(struct rpc_clnt *);
 void		rpc_task_release_transport(struct rpc_task *);
 void		rpc_task_release_client(struct rpc_task *);
+struct rpc_xprt	*rpc_task_get_xprt(struct rpc_clnt *clnt,
+		struct rpc_xprt *xprt);
 
 int		rpcb_create_local(struct net *);
 void		rpcb_put_local(struct net *);
@@ -191,6 +194,7 @@ void		rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
 struct net *	rpc_net_ns(struct rpc_clnt *);
 size_t		rpc_max_payload(struct rpc_clnt *);
 size_t		rpc_max_bc_payload(struct rpc_clnt *);
+unsigned int	rpc_num_bc_slots(struct rpc_clnt *);
 void		rpc_force_rebind(struct rpc_clnt *);
 size_t		rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
 const char	*rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h
index 1b3751327575..0ee3f7052846 100644
--- a/include/linux/sunrpc/metrics.h
+++ b/include/linux/sunrpc/metrics.h
@@ -30,7 +30,7 @@
 #include <linux/ktime.h>
 #include <linux/spinlock.h>
 
-#define RPC_IOSTATS_VERS	"1.0"
+#define RPC_IOSTATS_VERS	"1.1"
 
 struct rpc_iostats {
 	spinlock_t		om_lock;
@@ -66,6 +66,11 @@ struct rpc_iostats {
 	ktime_t			om_queue,	/* queued for xmit */
 				om_rtt,		/* RPC RTT */
 				om_execute;	/* RPC execution */
+	/*
+	 * The count of operations that complete with tk_status < 0.
+	 * These statuses usually indicate error conditions.
+	 */
+	unsigned long           om_error_status;
 } ____cacheline_aligned;
 
 struct rpc_task;
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index d0e451868f02..baa3ecdb882f 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -126,6 +126,7 @@ struct rpc_task_setup {
 #define RPC_CALL_MAJORSEEN	0x0020		/* major timeout seen */
 #define RPC_TASK_ROOTCREDS	0x0040		/* force root creds */
 #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 */
 #define RPC_TASK_SOFTCONN	0x0400		/* Fail if can't connect */
 #define RPC_TASK_SENT		0x0800		/* message was sent */
@@ -183,8 +184,9 @@ struct rpc_task_setup {
 #define RPC_NR_PRIORITY		(1 + RPC_PRIORITY_PRIVILEGED - RPC_PRIORITY_LOW)
 
 struct rpc_timer {
-	struct timer_list timer;
 	struct list_head list;
+	unsigned long expires;
+	struct delayed_work dwork;
 };
 
 /*
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index a6d9fce7f20e..13e108bcc9eb 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -158,6 +158,7 @@ struct rpc_xprt_ops {
 	int		(*bc_setup)(struct rpc_xprt *xprt,
 				    unsigned int min_reqs);
 	size_t		(*bc_maxpayload)(struct rpc_xprt *xprt);
+	unsigned int	(*bc_num_slots)(struct rpc_xprt *xprt);
 	void		(*bc_free_rqst)(struct rpc_rqst *rqst);
 	void		(*bc_destroy)(struct rpc_xprt *xprt,
 				      unsigned int max_reqs);
@@ -238,6 +239,7 @@ struct rpc_xprt {
 	/*
 	 * Send stuff
 	 */
+	atomic_long_t		queuelen;
 	spinlock_t		transport_lock;	/* lock transport info */
 	spinlock_t		reserve_lock;	/* lock slot table */
 	spinlock_t		queue_lock;	/* send/receive queue lock */
@@ -250,8 +252,9 @@ struct rpc_xprt {
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	struct svc_serv		*bc_serv;       /* The RPC service which will */
 						/* process the callback */
-	int			bc_alloc_count;	/* Total number of preallocs */
-	atomic_t		bc_free_slots;
+	unsigned int		bc_alloc_max;
+	unsigned int		bc_alloc_count;	/* Total number of preallocs */
+	atomic_t		bc_slot_count;	/* Number of allocated slots */
 	spinlock_t		bc_pa_lock;	/* Protects the preallocated
 						 * items */
 	struct list_head	bc_pa_list;	/* List of preallocated
@@ -334,6 +337,9 @@ struct xprt_class {
  */
 struct rpc_xprt		*xprt_create_transport(struct xprt_create *args);
 void			xprt_connect(struct rpc_task *task);
+unsigned long		xprt_reconnect_delay(const struct rpc_xprt *xprt);
+void			xprt_reconnect_backoff(struct rpc_xprt *xprt,
+					       unsigned long init_to);
 void			xprt_reserve(struct rpc_task *task);
 void			xprt_retry_reserve(struct rpc_task *task);
 int			xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h
index af1257c030d2..c6cce3fbf29d 100644
--- a/include/linux/sunrpc/xprtmultipath.h
+++ b/include/linux/sunrpc/xprtmultipath.h
@@ -15,6 +15,8 @@ struct rpc_xprt_switch {
 	struct kref		xps_kref;
 
 	unsigned int		xps_nxprts;
+	unsigned int		xps_nactive;
+	atomic_long_t		xps_queuelen;
 	struct list_head	xps_xprt_list;
 
 	struct net *		xps_net;
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index b81d0b3e0799..7638dbe7bc50 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -56,6 +56,7 @@ struct sock_xprt {
 	 */
 	unsigned long		sock_state;
 	struct delayed_work	connect_worker;
+	struct work_struct	error_worker;
 	struct work_struct	recv_worker;
 	struct mutex		recv_mutex;
 	struct sockaddr_storage	srcaddr;
@@ -84,6 +85,10 @@ struct sock_xprt {
 #define XPRT_SOCK_CONNECTING	1U
 #define XPRT_SOCK_DATA_READY	(2)
 #define XPRT_SOCK_UPD_TIMEOUT	(3)
+#define XPRT_SOCK_WAKE_ERROR	(4)
+#define XPRT_SOCK_WAKE_WRITE	(5)
+#define XPRT_SOCK_WAKE_PENDING	(6)
+#define XPRT_SOCK_WAKE_DISCONNECT	(7)
 
 #endif /* __KERNEL__ */