Merge tag 'nfs-for-4.20-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

backmerge to do fixup of iov_iter_kvec() conflict

12 files changed, 95 insertions, 54 deletions

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index a0831e9d19c9..6e0417c02279 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -62,6 +62,7 @@ struct nfs_lock_context {
 	struct nfs_open_context *open_context;
 	fl_owner_t lockowner;
 	atomic_t io_count;
+	struct rcu_head	rcu_head;
 };
 
 struct nfs4_state;
@@ -82,6 +83,7 @@ struct nfs_open_context {
 
 	struct list_head list;
 	struct nfs4_threshold	*mdsthreshold;
+	struct rcu_head	rcu_head;
 };
 
 struct nfs_open_dir_context {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index bf39d9c92201..0fc0b9135d46 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -228,6 +228,9 @@ struct nfs_server {
 	unsigned short		mountd_port;
 	unsigned short		mountd_protocol;
 	struct rpc_wait_queue	uoc_rpcwaitq;
+
+	/* XDR related information */
+	unsigned int		read_hdrsize;
 };
 
 /* Server capabilities */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index bd1c889a9ed9..0e016252cfc6 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -608,8 +608,13 @@ struct nfs_pgio_args {
 	__u32			count;
 	unsigned int		pgbase;
 	struct page **		pages;
-	const u32 *		bitmask;	/* used by write */
-	enum nfs3_stable_how	stable;		/* used by write */
+	union {
+		unsigned int		replen;			/* used by read */
+		struct {
+			const u32 *		bitmask;	/* used by write */
+			enum nfs3_stable_how	stable;		/* used by write */
+		};
+	};
 };
 
 struct nfs_pgio_res {
@@ -617,10 +622,16 @@ struct nfs_pgio_res {
 	struct nfs_fattr *	fattr;
 	__u32			count;
 	__u32			op_status;
-	int			eof;		/* used by read */
-	struct nfs_writeverf *	verf;		/* used by write */
-	const struct nfs_server *server;	/* used by write */
-
+	union {
+		struct {
+			unsigned int		replen;		/* used by read */
+			int			eof;		/* used by read */
+		};
+		struct {
+			struct nfs_writeverf *	verf;		/* used by write */
+			const struct nfs_server *server;	/* used by write */
+		};
+	};
 };
 
 /*
@@ -1471,11 +1482,10 @@ struct nfs_pgio_header {
 	const struct nfs_rw_ops	*rw_ops;
 	struct nfs_io_completion *io_completion;
 	struct nfs_direct_req	*dreq;
-	spinlock_t		lock;
-	/* fields protected by lock */
+
 	int			pnfs_error;
 	int			error;		/* merge with pnfs_error */
-	unsigned long		good_bytes;	/* boundary of good data */
+	unsigned int		good_bytes;	/* boundary of good data */
 	unsigned long		flags;
 
 	/*
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 58a6765c1c5e..c4db9424b63b 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -67,7 +67,7 @@ struct rpc_cred {
 	const struct rpc_credops *cr_ops;
 	unsigned long		cr_expire;	/* when to gc */
 	unsigned long		cr_flags;	/* various flags */
-	atomic_t		cr_count;	/* ref count */
+	refcount_t		cr_count;	/* ref count */
 
 	kuid_t			cr_uid;
 
@@ -100,7 +100,7 @@ struct rpc_auth {
 						 * differ from the flavor in
 						 * au_ops->au_flavor in gss
 						 * case) */
-	atomic_t		au_count;	/* Reference counter */
+	refcount_t		au_count;	/* Reference counter */
 
 	struct rpc_cred_cache *	au_credcache;
 	/* per-flavor data */
@@ -157,6 +157,7 @@ struct rpc_credops {
 	int			(*crkey_timeout)(struct rpc_cred *);
 	bool			(*crkey_to_expire)(struct rpc_cred *);
 	char *			(*crstringify_acceptor)(struct rpc_cred *);
+	bool			(*crneed_reencode)(struct rpc_task *);
 };
 
 extern const struct rpc_authops	authunix_ops;
@@ -192,6 +193,7 @@ __be32 *		rpcauth_marshcred(struct rpc_task *, __be32 *);
 __be32 *		rpcauth_checkverf(struct rpc_task *, __be32 *);
 int			rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj);
 int			rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj);
+bool			rpcauth_xmit_need_reencode(struct rpc_task *task);
 int			rpcauth_refreshcred(struct rpc_task *);
 void			rpcauth_invalcred(struct rpc_task *);
 int			rpcauth_uptodatecred(struct rpc_task *);
@@ -204,11 +206,11 @@ bool			rpcauth_cred_key_to_expire(struct rpc_auth *, struct rpc_cred *);
 char *			rpcauth_stringify_acceptor(struct rpc_cred *);
 
 static inline
-struct rpc_cred *	get_rpccred(struct rpc_cred *cred)
+struct rpc_cred *get_rpccred(struct rpc_cred *cred)
 {
-	if (cred != NULL)
-		atomic_inc(&cred->cr_count);
-	return cred;
+	if (cred != NULL && refcount_inc_not_zero(&cred->cr_count))
+		return cred;
+	return NULL;
 }
 
 /**
@@ -224,9 +226,7 @@ struct rpc_cred *	get_rpccred(struct rpc_cred *cred)
 static inline struct rpc_cred *
 get_rpccred_rcu(struct rpc_cred *cred)
 {
-	if (atomic_inc_not_zero(&cred->cr_count))
-		return cred;
-	return NULL;
+	return get_rpccred(cred);
 }
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h
index 0c9eac351aab..30427b729070 100644
--- a/include/linux/sunrpc/auth_gss.h
+++ b/include/linux/sunrpc/auth_gss.h
@@ -70,6 +70,7 @@ struct gss_cl_ctx {
 	refcount_t		count;
 	enum rpc_gss_proc	gc_proc;
 	u32			gc_seq;
+	u32			gc_seq_xmit;
 	spinlock_t		gc_seq_lock;
 	struct gss_ctx		*gc_gss_ctx;
 	struct xdr_netobj	gc_wire_ctx;
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index 4397a4824c81..28721cf73ec3 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -34,6 +34,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid);
 void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied);
+void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task);
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
 void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h
index 7df625d41e35..69f749afa617 100644
--- a/include/linux/sunrpc/gss_krb5.h
+++ b/include/linux/sunrpc/gss_krb5.h
@@ -118,7 +118,8 @@ struct krb5_ctx {
 	u8			acceptor_integ[GSS_KRB5_MAX_KEYLEN];
 };
 
-extern spinlock_t krb5_seq_lock;
+extern u32 gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx);
+extern u64 gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx);
 
 /* The length of the Kerberos GSS token header */
 #define GSS_KRB5_TOK_HDR_LEN	(16)
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 592653becd91..7b540c066594 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -140,8 +140,9 @@ struct rpc_task_setup {
 #define RPC_TASK_RUNNING	0
 #define RPC_TASK_QUEUED		1
 #define RPC_TASK_ACTIVE		2
-#define RPC_TASK_MSG_RECV	3
-#define RPC_TASK_MSG_RECV_WAIT	4
+#define RPC_TASK_NEED_XMIT	3
+#define RPC_TASK_NEED_RECV	4
+#define RPC_TASK_MSG_PIN_WAIT	5
 
 #define RPC_IS_RUNNING(t)	test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
 #define rpc_set_running(t)	set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
@@ -188,7 +189,6 @@ struct rpc_timer {
 struct rpc_wait_queue {
 	spinlock_t		lock;
 	struct list_head	tasks[RPC_NR_PRIORITY];	/* task queue for each priority level */
-	pid_t			owner;			/* process id of last task serviced */
 	unsigned char		maxpriority;		/* maximum priority (0 if queue is not a priority queue) */
 	unsigned char		priority;		/* current priority */
 	unsigned char		nr;			/* # tasks remaining for cookie */
@@ -204,7 +204,6 @@ struct rpc_wait_queue {
  * from a single cookie.  The aim is to improve
  * performance of NFS operations such as read/write.
  */
-#define RPC_BATCH_COUNT			16
 #define RPC_IS_PRIORITY(q)		((q)->maxpriority > 0)
 
 /*
@@ -234,6 +233,9 @@ void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq,
 		struct rpc_task *task);
 void		rpc_wake_up_queued_task(struct rpc_wait_queue *,
 					struct rpc_task *);
+void		rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *,
+						   struct rpc_task *,
+						   int);
 void		rpc_wake_up(struct rpc_wait_queue *);
 struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *);
 struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq,
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index c3d72066d4b1..6b7a86c4d6e6 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -84,7 +84,6 @@ struct svc_xprt {
 	struct sockaddr_storage	xpt_remote;	/* remote peer's address */
 	size_t			xpt_remotelen;	/* length of address */
 	char			xpt_remotebuf[INET6_ADDRSTRLEN + 10];
-	struct rpc_wait_queue	xpt_bc_pending;	/* backchannel wait queue */
 	struct list_head	xpt_users;	/* callbacks on free */
 
 	struct net		*xpt_net;
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 2bd68177a442..43106ffa6788 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -18,6 +18,7 @@
 #include <asm/unaligned.h>
 #include <linux/scatterlist.h>
 
+struct bio_vec;
 struct rpc_rqst;
 
 /*
@@ -52,12 +53,14 @@ struct xdr_buf {
 	struct kvec	head[1],	/* RPC header + non-page data */
 			tail[1];	/* Appended after page data */
 
+	struct bio_vec	*bvec;
 	struct page **	pages;		/* Array of pages */
 	unsigned int	page_base,	/* Start of page data */
 			page_len,	/* Length of page data */
 			flags;		/* Flags for data disposition */
 #define XDRBUF_READ		0x01		/* target of file read */
 #define XDRBUF_WRITE		0x02		/* source of file write */
+#define XDRBUF_SPARSE_PAGES	0x04		/* Page array is sparse */
 
 	unsigned int	buflen,		/* Total length of storage buffer */
 			len;		/* Length of XDR encoded message */
@@ -69,6 +72,8 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
 	buf->head[0].iov_base = start;
 	buf->head[0].iov_len = len;
 	buf->tail[0].iov_len = 0;
+	buf->bvec = NULL;
+	buf->pages = NULL;
 	buf->page_len = 0;
 	buf->flags = 0;
 	buf->len = 0;
@@ -115,6 +120,9 @@ __be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *);
 void	xdr_inline_pages(struct xdr_buf *, unsigned int,
 			 struct page **, unsigned int, unsigned int);
 void	xdr_terminate_string(struct xdr_buf *, const u32);
+size_t	xdr_buf_pagecount(struct xdr_buf *buf);
+int	xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp);
+void	xdr_free_bvec(struct xdr_buf *buf);
 
 static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int len)
 {
@@ -177,10 +185,7 @@ struct xdr_skb_reader {
 
 typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len);
 
-size_t xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len);
 extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *);
-extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int,
-		struct xdr_skb_reader *, xdr_skb_read_actor);
 
 extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32);
 extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 336fd1a19cca..a4ab4f8d9140 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -82,7 +82,14 @@ struct rpc_rqst {
 	struct page		**rq_enc_pages;	/* scratch pages for use by
 						   gss privacy code */
 	void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */
-	struct list_head	rq_list;
+
+	union {
+		struct list_head	rq_list;	/* Slot allocation list */
+		struct rb_node		rq_recv;	/* Receive queue */
+	};
+
+	struct list_head	rq_xmit;	/* Send queue */
+	struct list_head	rq_xmit2;	/* Send queue */
 
 	void			*rq_buffer;	/* Call XDR encode buffer */
 	size_t			rq_callsize;
@@ -103,6 +110,7 @@ struct rpc_rqst {
 						/* A cookie used to track the
 						   state of the transport
 						   connection */
+	atomic_t		rq_pin;
 	
 	/*
 	 * Partial send handling
@@ -133,7 +141,8 @@ struct rpc_xprt_ops {
 	void		(*connect)(struct rpc_xprt *xprt, struct rpc_task *task);
 	int		(*buf_alloc)(struct rpc_task *task);
 	void		(*buf_free)(struct rpc_task *task);
-	int		(*send_request)(struct rpc_task *task);
+	void		(*prepare_request)(struct rpc_rqst *req);
+	int		(*send_request)(struct rpc_rqst *req);
 	void		(*set_retrans_timeout)(struct rpc_task *task);
 	void		(*timer)(struct rpc_xprt *xprt, struct rpc_task *task);
 	void		(*release_request)(struct rpc_task *task);
@@ -234,9 +243,12 @@ struct rpc_xprt {
 	 */
 	spinlock_t		transport_lock;	/* lock transport info */
 	spinlock_t		reserve_lock;	/* lock slot table */
-	spinlock_t		recv_lock;	/* lock receive list */
+	spinlock_t		queue_lock;	/* send/receive queue lock */
 	u32			xid;		/* Next XID value to use */
 	struct rpc_task *	snd_task;	/* Task blocked in send */
+
+	struct list_head	xmit_queue;	/* Send queue */
+
 	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	struct svc_serv		*bc_serv;       /* The RPC service which will */
@@ -248,7 +260,8 @@ struct rpc_xprt {
 	struct list_head	bc_pa_list;	/* List of preallocated
 						 * backchannel rpc_rqst's */
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
-	struct list_head	recv;
+
+	struct rb_root		recv_queue;	/* Receive queue */
 
 	struct {
 		unsigned long		bind_count,	/* total number of binds */
@@ -325,15 +338,18 @@ struct xprt_class {
 struct rpc_xprt		*xprt_create_transport(struct xprt_create *args);
 void			xprt_connect(struct rpc_task *task);
 void			xprt_reserve(struct rpc_task *task);
-void			xprt_request_init(struct rpc_task *task);
 void			xprt_retry_reserve(struct rpc_task *task);
 int			xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
 int			xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_free_slot(struct rpc_xprt *xprt,
 				       struct rpc_rqst *req);
-void			xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
+void			xprt_request_prepare(struct rpc_rqst *req);
 bool			xprt_prepare_transmit(struct rpc_task *task);
+void			xprt_request_enqueue_transmit(struct rpc_task *task);
+void			xprt_request_enqueue_receive(struct rpc_task *task);
+void			xprt_request_wait_receive(struct rpc_task *task);
+bool			xprt_request_need_retransmit(struct rpc_task *task);
 void			xprt_transmit(struct rpc_task *task);
 void			xprt_end_transmit(struct rpc_task *task);
 int			xprt_adjust_timeout(struct rpc_rqst *req);
@@ -373,8 +389,8 @@ int			xprt_load_transport(const char *);
 void			xprt_set_retrans_timeout_def(struct rpc_task *task);
 void			xprt_set_retrans_timeout_rtt(struct rpc_task *task);
 void			xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status);
-void			xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action);
-void			xprt_write_space(struct rpc_xprt *xprt);
+void			xprt_wait_for_buffer_space(struct rpc_xprt *xprt);
+bool			xprt_write_space(struct rpc_xprt *xprt);
 void			xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result);
 struct rpc_rqst *	xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid);
 void			xprt_update_rtt(struct rpc_task *task);
@@ -382,6 +398,7 @@ void			xprt_complete_rqst(struct rpc_task *task, int copied);
 void			xprt_pin_rqst(struct rpc_rqst *req);
 void			xprt_unpin_rqst(struct rpc_rqst *req);
 void			xprt_release_rqst_cong(struct rpc_task *task);
+bool			xprt_request_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req);
 void			xprt_disconnect_done(struct rpc_xprt *xprt);
 void			xprt_force_disconnect(struct rpc_xprt *xprt);
 void			xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
@@ -400,6 +417,8 @@ void			xprt_unlock_connect(struct rpc_xprt *, void *);
 #define XPRT_BINDING		(5)
 #define XPRT_CLOSING		(6)
 #define XPRT_CONGESTED		(9)
+#define XPRT_CWND_WAIT		(10)
+#define XPRT_WRITE_SPACE	(11)
 
 static inline void xprt_set_connected(struct rpc_xprt *xprt)
 {
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index ae0f99b9b965..458bfe0137f5 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -30,15 +30,25 @@ struct sock_xprt {
 	/*
 	 * State of TCP reply receive
 	 */
-	__be32			tcp_fraghdr,
-				tcp_xid,
-				tcp_calldir;
+	struct {
+		struct {
+			__be32	fraghdr,
+				xid,
+				calldir;
+		} __attribute__((packed));
 
-	u32			tcp_offset,
-				tcp_reclen;
+		u32		offset,
+				len;
 
-	unsigned long		tcp_copied,
-				tcp_flags;
+		unsigned long	copied;
+	} recv;
+
+	/*
+	 * State of TCP transmit queue
+	 */
+	struct {
+		u32		offset;
+	} xmit;
 
 	/*
 	 * Connection of transports
@@ -68,20 +78,8 @@ struct sock_xprt {
 };
 
 /*
- * TCP receive state flags
- */
-#define TCP_RCV_LAST_FRAG	(1UL << 0)
-#define TCP_RCV_COPY_FRAGHDR	(1UL << 1)
-#define TCP_RCV_COPY_XID	(1UL << 2)
-#define TCP_RCV_COPY_DATA	(1UL << 3)
-#define TCP_RCV_READ_CALLDIR	(1UL << 4)
-#define TCP_RCV_COPY_CALLDIR	(1UL << 5)
-
-/*
  * TCP RPC flags
  */
-#define TCP_RPC_REPLY		(1UL << 6)
-
 #define XPRT_SOCK_CONNECTING	1U
 #define XPRT_SOCK_DATA_READY	(2)
 #define XPRT_SOCK_UPD_TIMEOUT	(3)