Merge branch 'for-3.19' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "A comparatively quieter cycle for nfsd this time, but still with two
  larger changes:

   - RPC server scalability improvements from Jeff Layton (using RCU
     instead of a spinlock to find idle threads).

   - server-side NFSv4.2 ALLOCATE/DEALLOCATE support from Anna
     Schumaker, enabling fallocate on new clients"

* 'for-3.19' of git://linux-nfs.org/~bfields/linux: (32 commits)
  nfsd4: fix xdr4 count of server in fs_location4
  nfsd4: fix xdr4 inclusion of escaped char
  sunrpc/cache: convert to use string_escape_str()
  sunrpc: only call test_bit once in svc_xprt_received
  fs: nfsd: Fix signedness bug in compare_blob
  sunrpc: add some tracepoints around enqueue and dequeue of svc_xprt
  sunrpc: convert to lockless lookup of queued server threads
  sunrpc: fix potential races in pool_stats collection
  sunrpc: add a rcu_head to svc_rqst and use kfree_rcu to free it
  sunrpc: require svc_create callers to pass in meaningful shutdown routine
  sunrpc: have svc_wake_up only deal with pool 0
  sunrpc: convert sp_task_pending flag to use atomic bitops
  sunrpc: move rq_cachetype field to better optimize space
  sunrpc: move rq_splice_ok flag into rq_flags
  sunrpc: move rq_dropme flag into rq_flags
  sunrpc: move rq_usedeferral flag to rq_flags
  sunrpc: move rq_local field to rq_flags
  sunrpc: add a generic rq_flags field to svc_rqst and move rq_secure to it
  nfsd: minor off by one checks in __write_versions()
  sunrpc: release svc_pool_map reference when serv allocation fails
  ...

4 files changed, 137 insertions, 26 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 88157253b9e6..eeaccd37184f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2086,7 +2086,7 @@ struct filename {
 extern long vfs_truncate(struct path *, loff_t);
 extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
 		       struct file *filp);
-extern int do_fallocate(struct file *file, int mode, loff_t offset,
+extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
 			loff_t len);
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
 			umode_t mode);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 21678464883a..6f22cfeef5e3 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -26,10 +26,10 @@ typedef int		(*svc_thread_fn)(void *);
 
 /* statistics for svc_pool structures */
 struct svc_pool_stats {
-	unsigned long	packets;
+	atomic_long_t	packets;
 	unsigned long	sockets_queued;
-	unsigned long	threads_woken;
-	unsigned long	threads_timedout;
+	atomic_long_t	threads_woken;
+	atomic_long_t	threads_timedout;
 };
 
 /*
@@ -45,12 +45,13 @@ struct svc_pool_stats {
 struct svc_pool {
 	unsigned int		sp_id;	    	/* pool id; also node id on NUMA */
 	spinlock_t		sp_lock;	/* protects all fields */
-	struct list_head	sp_threads;	/* idle server threads */
 	struct list_head	sp_sockets;	/* pending sockets */
 	unsigned int		sp_nrthreads;	/* # of threads in pool */
 	struct list_head	sp_all_threads;	/* all server threads */
 	struct svc_pool_stats	sp_stats;	/* statistics on pool operation */
-	int			sp_task_pending;/* has pending task */
+#define	SP_TASK_PENDING		(0)		/* still work to do even if no
+						 * xprt is queued. */
+	unsigned long		sp_flags;
 } ____cacheline_aligned_in_smp;
 
 /*
@@ -219,8 +220,8 @@ static inline void svc_putu32(struct kvec *iov, __be32 val)
  * processed.
  */
 struct svc_rqst {
-	struct list_head	rq_list;	/* idle list */
 	struct list_head	rq_all;		/* all threads list */
+	struct rcu_head		rq_rcu_head;	/* for RCU deferred kfree */
 	struct svc_xprt *	rq_xprt;	/* transport ptr */
 
 	struct sockaddr_storage	rq_addr;	/* peer address */
@@ -236,7 +237,6 @@ struct svc_rqst {
 	struct svc_cred		rq_cred;	/* auth info */
 	void *			rq_xprt_ctxt;	/* transport specific context ptr */
 	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */
-	bool			rq_usedeferral;	/* use deferral */
 
 	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
@@ -253,9 +253,17 @@ struct svc_rqst {
 	u32			rq_vers;	/* program version */
 	u32			rq_proc;	/* procedure number */
 	u32			rq_prot;	/* IP protocol */
-	unsigned short
-				rq_secure  : 1;	/* secure port */
-	unsigned short		rq_local   : 1;	/* local request */
+	int			rq_cachetype;	/* catering to nfsd */
+#define	RQ_SECURE	(0)			/* secure port */
+#define	RQ_LOCAL	(1)			/* local request */
+#define	RQ_USEDEFERRAL	(2)			/* use deferral */
+#define	RQ_DROPME	(3)			/* drop current reply */
+#define	RQ_SPLICE_OK	(4)			/* turned off in gss privacy
+						 * to prevent encrypting page
+						 * cache pages */
+#define	RQ_VICTIM	(5)			/* about to be shut down */
+#define	RQ_BUSY		(6)			/* request is busy */
+	unsigned long		rq_flags;	/* flags field */
 
 	void *			rq_argp;	/* decoded arguments */
 	void *			rq_resp;	/* xdr'd results */
@@ -271,16 +279,12 @@ struct svc_rqst {
 	struct cache_req	rq_chandle;	/* handle passed to caches for 
 						 * request delaying 
 						 */
-	bool			rq_dropme;
 	/* Catering to nfsd */
 	struct auth_domain *	rq_client;	/* RPC peer info */
 	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
-	int			rq_cachetype;
 	struct svc_cacherep *	rq_cacherep;	/* cache info */
-	bool			rq_splice_ok;   /* turned off in gss privacy
-						 * to prevent encrypting page
-						 * cache pages */
 	struct task_struct	*rq_task;	/* service thread */
+	spinlock_t		rq_lock;	/* per-request lock */
 };
 
 #define SVC_NET(svc_rqst)	(svc_rqst->rq_xprt->xpt_net)
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index ce6e4182a5b2..79f6f8f3dc0a 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -63,10 +63,9 @@ struct svc_xprt {
 #define	XPT_CHNGBUF	7		/* need to change snd/rcv buf sizes */
 #define	XPT_DEFERRED	8		/* deferred request pending */
 #define	XPT_OLD		9		/* used for xprt aging mark+sweep */
-#define	XPT_DETACHED	10		/* detached from tempsocks list */
-#define XPT_LISTENER	11		/* listening endpoint */
-#define XPT_CACHE_AUTH	12		/* cache auth info */
-#define XPT_LOCAL	13		/* connection from loopback interface */
+#define XPT_LISTENER	10		/* listening endpoint */
+#define XPT_CACHE_AUTH	11		/* cache auth info */
+#define XPT_LOCAL	12		/* connection from loopback interface */
 
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 171ca4ff6d99..b9c1dc6c825a 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -8,6 +8,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/xprtsock.h>
+#include <linux/sunrpc/svc_xprt.h>
 #include <net/tcp_states.h>
 #include <linux/net.h>
 #include <linux/tracepoint.h>
@@ -412,6 +413,16 @@ TRACE_EVENT(xs_tcp_data_recv,
 			__entry->copied, __entry->reclen, __entry->offset)
 );
 
+#define show_rqstp_flags(flags)						\
+	__print_flags(flags, "|",					\
+		{ (1UL << RQ_SECURE),		"RQ_SECURE"},		\
+		{ (1UL << RQ_LOCAL),		"RQ_LOCAL"},		\
+		{ (1UL << RQ_USEDEFERRAL),	"RQ_USEDEFERRAL"},	\
+		{ (1UL << RQ_DROPME),		"RQ_DROPME"},		\
+		{ (1UL << RQ_SPLICE_OK),	"RQ_SPLICE_OK"},	\
+		{ (1UL << RQ_VICTIM),		"RQ_VICTIM"},		\
+		{ (1UL << RQ_BUSY),		"RQ_BUSY"})
+
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
 
@@ -421,16 +432,19 @@ TRACE_EVENT(svc_recv,
 		__field(struct sockaddr *, addr)
 		__field(__be32, xid)
 		__field(int, status)
+		__field(unsigned long, flags)
 	),
 
 	TP_fast_assign(
 		__entry->addr = (struct sockaddr *)&rqst->rq_addr;
 		__entry->xid = status > 0 ? rqst->rq_xid : 0;
 		__entry->status = status;
+		__entry->flags = rqst->rq_flags;
 	),
 
-	TP_printk("addr=%pIScp xid=0x%x status=%d", __entry->addr,
-			be32_to_cpu(__entry->xid), __entry->status)
+	TP_printk("addr=%pIScp xid=0x%x status=%d flags=%s", __entry->addr,
+			be32_to_cpu(__entry->xid), __entry->status,
+			show_rqstp_flags(__entry->flags))
 );
 
 DECLARE_EVENT_CLASS(svc_rqst_status,
@@ -444,18 +458,19 @@ DECLARE_EVENT_CLASS(svc_rqst_status,
 		__field(__be32, xid)
 		__field(int, dropme)
 		__field(int, status)
+		__field(unsigned long, flags)
 	),
 
 	TP_fast_assign(
 		__entry->addr = (struct sockaddr *)&rqst->rq_addr;
 		__entry->xid = rqst->rq_xid;
-		__entry->dropme = (int)rqst->rq_dropme;
 		__entry->status = status;
+		__entry->flags = rqst->rq_flags;
 	),
 
-	TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d",
-		__entry->addr, be32_to_cpu(__entry->xid), __entry->dropme,
-		__entry->status)
+	TP_printk("addr=%pIScp rq_xid=0x%x status=%d flags=%s",
+		__entry->addr, be32_to_cpu(__entry->xid),
+		__entry->status, show_rqstp_flags(__entry->flags))
 );
 
 DEFINE_EVENT(svc_rqst_status, svc_process,
@@ -466,6 +481,99 @@ DEFINE_EVENT(svc_rqst_status, svc_send,
 	TP_PROTO(struct svc_rqst *rqst, int status),
 	TP_ARGS(rqst, status));
 
+#define show_svc_xprt_flags(flags)					\
+	__print_flags(flags, "|",					\
+		{ (1UL << XPT_BUSY),		"XPT_BUSY"},		\
+		{ (1UL << XPT_CONN),		"XPT_CONN"},		\
+		{ (1UL << XPT_CLOSE),		"XPT_CLOSE"},		\
+		{ (1UL << XPT_DATA),		"XPT_DATA"},		\
+		{ (1UL << XPT_TEMP),		"XPT_TEMP"},		\
+		{ (1UL << XPT_DEAD),		"XPT_DEAD"},		\
+		{ (1UL << XPT_CHNGBUF),		"XPT_CHNGBUF"},		\
+		{ (1UL << XPT_DEFERRED),	"XPT_DEFERRED"},	\
+		{ (1UL << XPT_OLD),		"XPT_OLD"},		\
+		{ (1UL << XPT_LISTENER),	"XPT_LISTENER"},	\
+		{ (1UL << XPT_CACHE_AUTH),	"XPT_CACHE_AUTH"},	\
+		{ (1UL << XPT_LOCAL),		"XPT_LOCAL"})
+
+TRACE_EVENT(svc_xprt_do_enqueue,
+	TP_PROTO(struct svc_xprt *xprt, struct svc_rqst *rqst),
+
+	TP_ARGS(xprt, rqst),
+
+	TP_STRUCT__entry(
+		__field(struct svc_xprt *, xprt)
+		__field(struct svc_rqst *, rqst)
+	),
+
+	TP_fast_assign(
+		__entry->xprt = xprt;
+		__entry->rqst = rqst;
+	),
+
+	TP_printk("xprt=0x%p addr=%pIScp pid=%d flags=%s", __entry->xprt,
+		(struct sockaddr *)&__entry->xprt->xpt_remote,
+		__entry->rqst ? __entry->rqst->rq_task->pid : 0,
+		show_svc_xprt_flags(__entry->xprt->xpt_flags))
+);
+
+TRACE_EVENT(svc_xprt_dequeue,
+	TP_PROTO(struct svc_xprt *xprt),
+
+	TP_ARGS(xprt),
+
+	TP_STRUCT__entry(
+		__field(struct svc_xprt *, xprt)
+		__field_struct(struct sockaddr_storage, ss)
+		__field(unsigned long, flags)
+	),
+
+	TP_fast_assign(
+		__entry->xprt = xprt,
+		xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss));
+		__entry->flags = xprt ? xprt->xpt_flags : 0;
+	),
+
+	TP_printk("xprt=0x%p addr=%pIScp flags=%s", __entry->xprt,
+		(struct sockaddr *)&__entry->ss,
+		show_svc_xprt_flags(__entry->flags))
+);
+
+TRACE_EVENT(svc_wake_up,
+	TP_PROTO(int pid),
+
+	TP_ARGS(pid),
+
+	TP_STRUCT__entry(
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->pid = pid;
+	),
+
+	TP_printk("pid=%d", __entry->pid)
+);
+
+TRACE_EVENT(svc_handle_xprt,
+	TP_PROTO(struct svc_xprt *xprt, int len),
+
+	TP_ARGS(xprt, len),
+
+	TP_STRUCT__entry(
+		__field(struct svc_xprt *, xprt)
+		__field(int, len)
+	),
+
+	TP_fast_assign(
+		__entry->xprt = xprt;
+		__entry->len = len;
+	),
+
+	TP_printk("xprt=0x%p addr=%pIScp len=%d flags=%s", __entry->xprt,
+		(struct sockaddr *)&__entry->xprt->xpt_remote, __entry->len,
+		show_svc_xprt_flags(__entry->xprt->xpt_flags))
+);
 #endif /* _TRACE_SUNRPC_H */
 
 #include <trace/define_trace.h>