Merge tag 'nfs-for-3.19-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Features:
   - NFSv4.2 client support for hole punching and preallocation.
   - Further RPC/RDMA client improvements.
   - Add more RPC transport debugging tracepoints.
   - Add RPC debugging tools in debugfs.

  Bugfixes:
   - Stable fix for layoutget error handling
   - Fix a change in COMMIT behaviour resulting from the recent io code
     updates"

* tag 'nfs-for-3.19-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (28 commits)
  sunrpc: add a debugfs rpc_xprt directory with an info file in it
  sunrpc: add debugfs file for displaying client rpc_task queue
  nfs: Add DEALLOCATE support
  nfs: Add ALLOCATE support
  NFS: Clean up nfs4_init_callback()
  NFS: SETCLIENTID XDR buffer sizes are incorrect
  SUNRPC: serialize iostats updates
  xprtrdma: Display async errors
  xprtrdma: Enable pad optimization
  xprtrdma: Re-write rpcrdma_flush_cqs()
  xprtrdma: Refactor tasklet scheduling
  xprtrdma: unmap all FMRs during transport disconnect
  xprtrdma: Cap req_cqinit
  xprtrdma: Return an errno from rpcrdma_register_external()
  nfs: define nfs_inc_fscache_stats and using it as possible
  nfs: replace nfs_add_stats with nfs_inc_stats when add one
  NFS: Deletion of unnecessary checks before the function call "nfs_put_client"
  sunrpc: eliminate RPC_TRACEPOINTS
  sunrpc: eliminate RPC_DEBUG
  lockd: eliminate LOCKD_DEBUG
  ...

14 files changed, 305 insertions, 28 deletions

diff --git a/include/linux/lockd/debug.h b/include/linux/lockd/debug.h
index 257d3779f2ab..0ca8109934e4 100644
--- a/include/linux/lockd/debug.h
+++ b/include/linux/lockd/debug.h
@@ -17,12 +17,8 @@
  * Enable lockd debugging.
  * Requires RPC_DEBUG.
  */
-#ifdef RPC_DEBUG
-# define LOCKD_DEBUG		1
-#endif
-
 #undef ifdebug
-#if defined(RPC_DEBUG) && defined(LOCKD_DEBUG)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define ifdebug(flag)		if (unlikely(nlm_debug & NLMDBG_##flag))
 #else
 # define ifdebug(flag)		if (0)
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 356acc2846fd..022b761dbf0a 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -490,6 +490,8 @@ enum {
 
 	/* nfs42 */
 	NFSPROC4_CLNT_SEEK,
+	NFSPROC4_CLNT_ALLOCATE,
+	NFSPROC4_CLNT_DEALLOCATE,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index c72d1ad41ad4..6d627b92df53 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -163,7 +163,7 @@ struct nfs_inode {
 	 */
 	__be32			cookieverf[2];
 
-	unsigned long		npages;
+	unsigned long		nrequests;
 	struct nfs_mds_commit_info commit_info;
 
 	/* Open contexts for shared mmap writes */
@@ -520,7 +520,7 @@ extern void nfs_commit_free(struct nfs_commit_data *data);
 static inline int
 nfs_have_writebacks(struct inode *inode)
 {
-	return NFS_I(inode)->npages != 0;
+	return NFS_I(inode)->nrequests != 0;
 }
 
 /*
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a32ba0d7a98f..1e37fbb78f7a 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -231,5 +231,7 @@ struct nfs_server {
 #define NFS_CAP_ATOMIC_OPEN_V1	(1U << 17)
 #define NFS_CAP_SECURITY_LABEL	(1U << 18)
 #define NFS_CAP_SEEK		(1U << 19)
+#define NFS_CAP_ALLOCATE	(1U << 20)
+#define NFS_CAP_DEALLOCATE	(1U << 21)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 47ebb4fafd87..467c84efb596 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1243,6 +1243,20 @@ nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
 #endif /* CONFIG_NFS_V4_1 */
 
 #ifdef CONFIG_NFS_V4_2
+struct nfs42_falloc_args {
+	struct nfs4_sequence_args	seq_args;
+
+	struct nfs_fh			*falloc_fh;
+	nfs4_stateid			 falloc_stateid;
+	u64				 falloc_offset;
+	u64				 falloc_length;
+};
+
+struct nfs42_falloc_res {
+	struct nfs4_sequence_res	seq_res;
+	unsigned int			status;
+};
+
 struct nfs42_seek_args {
 	struct nfs4_sequence_args	seq_args;
 
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 8e030075fe79..a7cbb570cc5c 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -53,7 +53,7 @@ struct rpc_cred {
 	struct rcu_head		cr_rcu;
 	struct rpc_auth *	cr_auth;
 	const struct rpc_credops *cr_ops;
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	unsigned long		cr_magic;	/* 0x0f4aa4f0 */
 #endif
 	unsigned long		cr_expire;	/* when to gc */
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 70736b98c721..d86acc63b25f 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -63,6 +63,9 @@ struct rpc_clnt {
 	struct rpc_rtt		cl_rtt_default;
 	struct rpc_timeout	cl_timeout_default;
 	const struct rpc_program *cl_program;
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+	struct dentry		*cl_debugfs;	/* debugfs directory */
+#endif
 };
 
 /*
@@ -176,5 +179,6 @@ size_t		rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
 const char	*rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
 int		rpc_localaddr(struct rpc_clnt *, struct sockaddr *, size_t);
 
+const char *rpc_proc_name(const struct rpc_task *task);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h
index 9385bd74c860..c57d8ea0716c 100644
--- a/include/linux/sunrpc/debug.h
+++ b/include/linux/sunrpc/debug.h
@@ -10,22 +10,10 @@
 
 #include <uapi/linux/sunrpc/debug.h>
 
-
-/*
- * Enable RPC debugging/profiling.
- */
-#ifdef CONFIG_SUNRPC_DEBUG
-#define  RPC_DEBUG
-#endif
-#ifdef CONFIG_TRACEPOINTS
-#define RPC_TRACEPOINTS
-#endif
-/* #define  RPC_PROFILE */
-
 /*
  * Debugging macros etc
  */
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 extern unsigned int		rpc_debug;
 extern unsigned int		nfs_debug;
 extern unsigned int		nfsd_debug;
@@ -36,7 +24,7 @@ extern unsigned int		nlm_debug;
 #define dprintk_rcu(args...)	dfprintk_rcu(FACILITY, ## args)
 
 #undef ifdebug
-#ifdef RPC_DEBUG			
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define ifdebug(fac)		if (unlikely(rpc_debug & RPCDBG_##fac))
 
 # define dfprintk(fac, args...)	\
@@ -65,9 +53,55 @@ extern unsigned int		nlm_debug;
 /*
  * Sysctl interface for RPC debugging
  */
-#ifdef RPC_DEBUG
+
+struct rpc_clnt;
+struct rpc_xprt;
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 void		rpc_register_sysctl(void);
 void		rpc_unregister_sysctl(void);
+int		sunrpc_debugfs_init(void);
+void		sunrpc_debugfs_exit(void);
+int		rpc_clnt_debugfs_register(struct rpc_clnt *);
+void		rpc_clnt_debugfs_unregister(struct rpc_clnt *);
+int		rpc_xprt_debugfs_register(struct rpc_xprt *);
+void		rpc_xprt_debugfs_unregister(struct rpc_xprt *);
+#else
+static inline int
+sunrpc_debugfs_init(void)
+{
+	return 0;
+}
+
+static inline void
+sunrpc_debugfs_exit(void)
+{
+	return;
+}
+
+static inline int
+rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
+{
+	return 0;
+}
+
+static inline void
+rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt)
+{
+	return;
+}
+
+static inline int
+rpc_xprt_debugfs_register(struct rpc_xprt *xprt)
+{
+	return 0;
+}
+
+static inline void
+rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt)
+{
+	return;
+}
 #endif
 
 #endif /* _LINUX_SUNRPC_DEBUG_H_ */
diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h
index 1565bbe86d51..eecb5a71e6c0 100644
--- a/include/linux/sunrpc/metrics.h
+++ b/include/linux/sunrpc/metrics.h
@@ -27,10 +27,13 @@
 
 #include <linux/seq_file.h>
 #include <linux/ktime.h>
+#include <linux/spinlock.h>
 
 #define RPC_IOSTATS_VERS	"1.0"
 
 struct rpc_iostats {
+	spinlock_t		om_lock;
+
 	/*
 	 * These counters give an idea about how many request
 	 * transmissions are required, on average, to complete that
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 1a8959944c5f..5f1e6bd4c316 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -79,7 +79,7 @@ struct rpc_task {
 	unsigned short		tk_flags;	/* misc flags */
 	unsigned short		tk_timeouts;	/* maj timeouts */
 
-#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
 	unsigned short		tk_pid;		/* debugging aid */
 #endif
 	unsigned char		tk_priority : 2,/* Task priority */
@@ -187,7 +187,7 @@ struct rpc_wait_queue {
 	unsigned char		nr;			/* # tasks remaining for cookie */
 	unsigned short		qlen;			/* total # tasks waiting in queue */
 	struct rpc_timer	timer_list;
-#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
 	const char *		name;
 #endif
 };
@@ -237,7 +237,7 @@ void		rpc_free(void *);
 int		rpciod_up(void);
 void		rpciod_down(void);
 int		__rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *);
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 struct net;
 void		rpc_show_tasks(struct net *);
 #endif
@@ -251,7 +251,7 @@ static inline int rpc_wait_for_completion_task(struct rpc_task *task)
 	return __rpc_wait_for_completion_task(task, NULL);
 }
 
-#if defined(RPC_DEBUG) || defined (RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
 static inline const char * rpc_qname(const struct rpc_wait_queue *q)
 {
 	return ((q && q->name) ? q->name : "unknown");
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index cf391eef2e6d..9d27ac45b909 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -239,6 +239,9 @@ struct rpc_xprt {
 	struct net		*xprt_net;
 	const char		*servername;
 	const char		*address_strings[RPC_DISPLAY_MAX];
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+	struct dentry		*debugfs;		/* debugfs directory */
+#endif
 };
 
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index 1ad36cc25b2e..7591788e9fbf 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -17,6 +17,65 @@ void		cleanup_socket_xprt(void);
 #define RPC_DEF_MIN_RESVPORT	(665U)
 #define RPC_DEF_MAX_RESVPORT	(1023U)
 
+struct sock_xprt {
+	struct rpc_xprt		xprt;
+
+	/*
+	 * Network layer
+	 */
+	struct socket *		sock;
+	struct sock *		inet;
+
+	/*
+	 * State of TCP reply receive
+	 */
+	__be32			tcp_fraghdr,
+				tcp_xid,
+				tcp_calldir;
+
+	u32			tcp_offset,
+				tcp_reclen;
+
+	unsigned long		tcp_copied,
+				tcp_flags;
+
+	/*
+	 * Connection of transports
+	 */
+	struct delayed_work	connect_worker;
+	struct sockaddr_storage	srcaddr;
+	unsigned short		srcport;
+
+	/*
+	 * UDP socket buffer size parameters
+	 */
+	size_t			rcvsize,
+				sndsize;
+
+	/*
+	 * Saved socket callback addresses
+	 */
+	void			(*old_data_ready)(struct sock *);
+	void			(*old_state_change)(struct sock *);
+	void			(*old_write_space)(struct sock *);
+	void			(*old_error_report)(struct sock *);
+};
+
+/*
+ * 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)
+
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_SUNRPC_XPRTSOCK_H */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 1fef3e6e9436..171ca4ff6d99 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -6,6 +6,8 @@
 
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/svc.h>
+#include <linux/sunrpc/xprtsock.h>
 #include <net/tcp_states.h>
 #include <linux/net.h>
 #include <linux/tracepoint.h>
@@ -306,6 +308,164 @@ DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection);
 DEFINE_RPC_SOCKET_EVENT(rpc_socket_close);
 DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown);
 
+DECLARE_EVENT_CLASS(rpc_xprt_event,
+	TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
+
+	TP_ARGS(xprt, xid, status),
+
+	TP_STRUCT__entry(
+		__field(__be32, xid)
+		__field(int, status)
+		__string(addr, xprt->address_strings[RPC_DISPLAY_ADDR])
+		__string(port, xprt->address_strings[RPC_DISPLAY_PORT])
+	),
+
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->status = status;
+		__assign_str(addr, xprt->address_strings[RPC_DISPLAY_ADDR]);
+		__assign_str(port, xprt->address_strings[RPC_DISPLAY_PORT]);
+	),
+
+	TP_printk("peer=[%s]:%s xid=0x%x status=%d", __get_str(addr),
+			__get_str(port), be32_to_cpu(__entry->xid),
+			__entry->status)
+);
+
+DEFINE_EVENT(rpc_xprt_event, xprt_lookup_rqst,
+	TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
+	TP_ARGS(xprt, xid, status));
+
+DEFINE_EVENT(rpc_xprt_event, xprt_transmit,
+	TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
+	TP_ARGS(xprt, xid, status));
+
+DEFINE_EVENT(rpc_xprt_event, xprt_complete_rqst,
+	TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
+	TP_ARGS(xprt, xid, status));
+
+TRACE_EVENT(xs_tcp_data_ready,
+	TP_PROTO(struct rpc_xprt *xprt, int err, unsigned int total),
+
+	TP_ARGS(xprt, err, total),
+
+	TP_STRUCT__entry(
+		__field(int, err)
+		__field(unsigned int, total)
+		__string(addr, xprt ? xprt->address_strings[RPC_DISPLAY_ADDR] :
+				"(null)")
+		__string(port, xprt ? xprt->address_strings[RPC_DISPLAY_PORT] :
+				"(null)")
+	),
+
+	TP_fast_assign(
+		__entry->err = err;
+		__entry->total = total;
+		__assign_str(addr, xprt ?
+			xprt->address_strings[RPC_DISPLAY_ADDR] : "(null)");
+		__assign_str(port, xprt ?
+			xprt->address_strings[RPC_DISPLAY_PORT] : "(null)");
+	),
+
+	TP_printk("peer=[%s]:%s err=%d total=%u", __get_str(addr),
+			__get_str(port), __entry->err, __entry->total)
+);
+
+#define rpc_show_sock_xprt_flags(flags) \
+	__print_flags(flags, "|", \
+		{ TCP_RCV_LAST_FRAG, "TCP_RCV_LAST_FRAG" }, \
+		{ TCP_RCV_COPY_FRAGHDR, "TCP_RCV_COPY_FRAGHDR" }, \
+		{ TCP_RCV_COPY_XID, "TCP_RCV_COPY_XID" }, \
+		{ TCP_RCV_COPY_DATA, "TCP_RCV_COPY_DATA" }, \
+		{ TCP_RCV_READ_CALLDIR, "TCP_RCV_READ_CALLDIR" }, \
+		{ TCP_RCV_COPY_CALLDIR, "TCP_RCV_COPY_CALLDIR" }, \
+		{ TCP_RPC_REPLY, "TCP_RPC_REPLY" })
+
+TRACE_EVENT(xs_tcp_data_recv,
+	TP_PROTO(struct sock_xprt *xs),
+
+	TP_ARGS(xs),
+
+	TP_STRUCT__entry(
+		__string(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR])
+		__string(port, xs->xprt.address_strings[RPC_DISPLAY_PORT])
+		__field(__be32, xid)
+		__field(unsigned long, flags)
+		__field(unsigned long, copied)
+		__field(unsigned int, reclen)
+		__field(unsigned long, offset)
+	),
+
+	TP_fast_assign(
+		__assign_str(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR]);
+		__assign_str(port, xs->xprt.address_strings[RPC_DISPLAY_PORT]);
+		__entry->xid = xs->tcp_xid;
+		__entry->flags = xs->tcp_flags;
+		__entry->copied = xs->tcp_copied;
+		__entry->reclen = xs->tcp_reclen;
+		__entry->offset = xs->tcp_offset;
+	),
+
+	TP_printk("peer=[%s]:%s xid=0x%x flags=%s copied=%lu reclen=%u offset=%lu",
+			__get_str(addr), __get_str(port), be32_to_cpu(__entry->xid),
+			rpc_show_sock_xprt_flags(__entry->flags),
+			__entry->copied, __entry->reclen, __entry->offset)
+);
+
+TRACE_EVENT(svc_recv,
+	TP_PROTO(struct svc_rqst *rqst, int status),
+
+	TP_ARGS(rqst, status),
+
+	TP_STRUCT__entry(
+		__field(struct sockaddr *, addr)
+		__field(__be32, xid)
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->addr = (struct sockaddr *)&rqst->rq_addr;
+		__entry->xid = status > 0 ? rqst->rq_xid : 0;
+		__entry->status = status;
+	),
+
+	TP_printk("addr=%pIScp xid=0x%x status=%d", __entry->addr,
+			be32_to_cpu(__entry->xid), __entry->status)
+);
+
+DECLARE_EVENT_CLASS(svc_rqst_status,
+
+	TP_PROTO(struct svc_rqst *rqst, int status),
+
+	TP_ARGS(rqst, status),
+
+	TP_STRUCT__entry(
+		__field(struct sockaddr *, addr)
+		__field(__be32, xid)
+		__field(int, dropme)
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->addr = (struct sockaddr *)&rqst->rq_addr;
+		__entry->xid = rqst->rq_xid;
+		__entry->dropme = (int)rqst->rq_dropme;
+		__entry->status = status;
+	),
+
+	TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d",
+		__entry->addr, be32_to_cpu(__entry->xid), __entry->dropme,
+		__entry->status)
+);
+
+DEFINE_EVENT(svc_rqst_status, svc_process,
+	TP_PROTO(struct svc_rqst *rqst, int status),
+	TP_ARGS(rqst, status));
+
+DEFINE_EVENT(svc_rqst_status, svc_send,
+	TP_PROTO(struct svc_rqst *rqst, int status),
+	TP_ARGS(rqst, status));
+
 #endif /* _TRACE_SUNRPC_H */
 
 #include <trace/define_trace.h>
diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h
index a6f453c740b8..1fdc95bb2375 100644
--- a/include/uapi/linux/nfsd/debug.h
+++ b/include/uapi/linux/nfsd/debug.h
@@ -15,7 +15,7 @@
  * Enable debugging for nfsd.
  * Requires RPC_DEBUG.
  */
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define NFSD_DEBUG		1
 #endif