Merge tag 'nfsd-4.3' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Nothing major, but:

   - Add Jeff Layton as an nfsd co-maintainer: no change to existing
     practice, just an acknowledgement of the status quo.

   - Two patches ("nfsd: ensure that...") for a race overlooked by the
     state locking rewrite, causing a crash noticed by multiple users.

   - Lots of smaller bugfixes all over from Kinglong Mee.

   - From Jeff, some cleanup of server rpc code in preparation for
     possible shift of nfsd threads to workqueues"

* tag 'nfsd-4.3' of git://linux-nfs.org/~bfields/linux: (52 commits)
  nfsd: deal with DELEGRETURN racing with CB_RECALL
  nfsd: return CLID_INUSE for unexpected SETCLIENTID_CONFIRM case
  nfsd: ensure that delegation stateid hash references are only put once
  nfsd: ensure that the ol stateid hash reference is only put once
  net: sunrpc: fix tracepoint Warning: unknown op '->'
  nfsd: allow more than one laundry job to run at a time
  nfsd: don't WARN/backtrace for invalid container deployment.
  fs: fix fs/locks.c kernel-doc warning
  nfsd: Add Jeff Layton as co-maintainer
  NFSD: Return word2 bitmask if setting security label in OPEN/CREATE
  NFSD: Set the attributes used to store the verifier for EXCLUSIVE4_1
  nfsd: SUPPATTR_EXCLCREAT must be encoded before SECURITY_LABEL.
  nfsd: Fix an FS_LAYOUT_TYPES/LAYOUT_TYPES encode bug
  NFSD: Store parent's stat in a separate value
  nfsd: Fix two typos in comments
  lockd: NLM grace period shouldn't block NFSv4 opens
  nfsd: include linux/nfs4.h in export.h
  sunrpc: Switch to using hash list instead single list
  sunrpc/nfsd: Remove redundant code by exports seq_operations functions
  sunrpc: Store cache_detail in seq_file's private directly
  ...

7 files changed, 83 insertions, 114 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 864203c..dc634a5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -943,12 +943,18 @@ struct lock_manager_operations {
 
 struct lock_manager {
 	struct list_head list;
+	/*
+	 * NFSv4 and up also want opens blocked during the grace period;
+	 * NLM doesn't care:
+	 */
+	bool block_opens;
 };
 
 struct net;
 void locks_start_grace(struct net *, struct lock_manager *);
 void locks_end_grace(struct lock_manager *);
 int locks_in_grace(struct net *);
+int opens_in_grace(struct net *);
 
 /* that will die - we need it for nfs_lock_info */
 #include <linux/nfs_fs_i.h>
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 437ddb6..03d3b4c 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -46,7 +46,7 @@
  * 
  */
 struct cache_head {
-	struct cache_head * next;
+	struct hlist_node	cache_list;
 	time_t		expiry_time;	/* After time time, don't use the data */
 	time_t		last_refresh;   /* If CACHE_PENDING, this is when upcall 
 					 * was sent, else this is when update was received
@@ -73,7 +73,7 @@ struct cache_detail_pipefs {
 struct cache_detail {
 	struct module *		owner;
 	int			hash_size;
-	struct cache_head **	hash_table;
+	struct hlist_head *	hash_table;
 	rwlock_t		hash_lock;
 
 	atomic_t		inuse; /* active user-space update or lookup */
@@ -224,6 +224,11 @@ extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *,
 					umode_t, struct cache_detail *);
 extern void sunrpc_cache_unregister_pipefs(struct cache_detail *);
 
+/* Must store cache_detail in seq_file->private if using next three functions */
+extern void *cache_seq_start(struct seq_file *file, loff_t *pos);
+extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos);
+extern void cache_seq_stop(struct seq_file *file, void *p);
+
 extern void qword_add(char **bpp, int *lp, char *str);
 extern void qword_addhex(char **bpp, int *lp, char *buf, int blen);
 extern int qword_get(char **bpp, char *dest, int bufsize);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index fae6fb9..cc0fc71 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -19,11 +19,6 @@
 #include <linux/wait.h>
 #include <linux/mm.h>
 
-/*
- * This is the RPC server thread function prototype
- */
-typedef int		(*svc_thread_fn)(void *);
-
 /* statistics for svc_pool structures */
 struct svc_pool_stats {
 	atomic_long_t	packets;
@@ -54,6 +49,25 @@ struct svc_pool {
 	unsigned long		sp_flags;
 } ____cacheline_aligned_in_smp;
 
+struct svc_serv;
+
+struct svc_serv_ops {
+	/* Callback to use when last thread exits. */
+	void		(*svo_shutdown)(struct svc_serv *, struct net *);
+
+	/* function for service threads to run */
+	int		(*svo_function)(void *);
+
+	/* queue up a transport for servicing */
+	void		(*svo_enqueue_xprt)(struct svc_xprt *);
+
+	/* set up thread (or whatever) execution context */
+	int		(*svo_setup)(struct svc_serv *, struct svc_pool *, int);
+
+	/* optional module to count when adding threads (pooled svcs only) */
+	struct module	*svo_module;
+};
+
 /*
  * RPC service.
  *
@@ -85,16 +99,7 @@ struct svc_serv {
 
 	unsigned int		sv_nrpools;	/* number of thread pools */
 	struct svc_pool *	sv_pools;	/* array of thread pools */
-
-	void			(*sv_shutdown)(struct svc_serv *serv,
-					       struct net *net);
-						/* Callback to use when last thread
-						 * exits.
-						 */
-
-	struct module *		sv_module;	/* optional module to count when
-						 * adding threads */
-	svc_thread_fn		sv_function;	/* main function for threads */
+	struct svc_serv_ops	*sv_ops;	/* server operations */
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	struct list_head	sv_cb_list;	/* queue for callback requests
 						 * that arrive over the same
@@ -423,19 +428,46 @@ struct svc_procedure {
 };
 
 /*
+ * Mode for mapping cpus to pools.
+ */
+enum {
+	SVC_POOL_AUTO = -1,	/* choose one of the others */
+	SVC_POOL_GLOBAL,	/* no mapping, just a single global pool
+				 * (legacy & UP mode) */
+	SVC_POOL_PERCPU,	/* one pool per cpu */
+	SVC_POOL_PERNODE	/* one pool per numa node */
+};
+
+struct svc_pool_map {
+	int count;			/* How many svc_servs use us */
+	int mode;			/* Note: int not enum to avoid
+					 * warnings about "enumeration value
+					 * not handled in switch" */
+	unsigned int npools;
+	unsigned int *pool_to;		/* maps pool id to cpu or node */
+	unsigned int *to_pool;		/* maps cpu or node to pool id */
+};
+
+extern struct svc_pool_map svc_pool_map;
+
+/*
  * Function prototypes.
  */
 int svc_rpcb_setup(struct svc_serv *serv, struct net *net);
 void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net);
 int svc_bind(struct svc_serv *serv, struct net *net);
 struct svc_serv *svc_create(struct svc_program *, unsigned int,
-			    void (*shutdown)(struct svc_serv *, struct net *net));
+			    struct svc_serv_ops *);
+struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv,
+					struct svc_pool *pool, int node);
 struct svc_rqst *svc_prepare_thread(struct svc_serv *serv,
 					struct svc_pool *pool, int node);
+void		   svc_rqst_free(struct svc_rqst *);
 void		   svc_exit_thread(struct svc_rqst *);
+unsigned int	   svc_pool_map_get(void);
+void		   svc_pool_map_put(void);
 struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
-			void (*shutdown)(struct svc_serv *, struct net *net),
-			svc_thread_fn, struct module *);
+			struct svc_serv_ops *);
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
 void		   svc_destroy(struct svc_serv *);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index cb94ee4..d5ee6d8 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -172,13 +172,6 @@ struct svcxprt_rdma {
 #define RDMAXPRT_SQ_PENDING	2
 #define RDMAXPRT_CONN_PENDING	3
 
-#define RPCRDMA_MAX_SVC_SEGS	(64)	/* server max scatter/gather */
-#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_SVC_SEGS << PAGE_SHIFT)
-#define RPCRDMA_MAXPAYLOAD	RPCSVC_MAXPAYLOAD
-#else
-#define RPCRDMA_MAXPAYLOAD	(RPCRDMA_MAX_SVC_SEGS << PAGE_SHIFT)
-#endif
-
 #define RPCRDMA_LISTEN_BACKLOG  10
 /* The default ORD value is based on two outstanding full-size writes with a
  * page size of 4k, or 32k * 2 ops / 4k = 16 outstanding RDMA_READ.  */
@@ -187,6 +180,8 @@ struct svcxprt_rdma {
 #define RPCRDMA_MAX_REQUESTS    32
 #define RPCRDMA_MAX_REQ_SIZE    4096
 
+#define RPCSVC_MAXPAYLOAD_RDMA	RPCSVC_MAXPAYLOAD
+
 /* svc_rdma_marshal.c */
 extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *);
 extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
@@ -213,6 +208,8 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
 
 /* svc_rdma_sendto.c */
 extern int svc_rdma_sendto(struct svc_rqst *);
+extern struct rpcrdma_read_chunk *
+	svc_rdma_get_read_chunk(struct rpcrdma_msg *);
 
 /* svc_rdma_transport.c */
 extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *);
@@ -225,7 +222,6 @@ extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
 extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt);
 extern struct svc_rdma_req_map *svc_rdma_get_req_map(void);
 extern void svc_rdma_put_req_map(struct svc_rdma_req_map *);
-extern int svc_rdma_fastreg(struct svcxprt_rdma *, struct svc_rdma_fastreg_mr *);
 extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *);
 extern void svc_rdma_put_frmr(struct svcxprt_rdma *,
 			      struct svc_rdma_fastreg_mr *);
@@ -238,83 +234,4 @@ extern void svc_rdma_prep_reply_hdr(struct svc_rqst *);
 extern int svc_rdma_init(void);
 extern void svc_rdma_cleanup(void);
 
-/*
- * Returns the address of the first read chunk or <nul> if no read chunk is
- * present
- */
-static inline struct rpcrdma_read_chunk *
-svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp)
-{
-	struct rpcrdma_read_chunk *ch =
-		(struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-
-	if (ch->rc_discrim == 0)
-		return NULL;
-
-	return ch;
-}
-
-/*
- * Returns the address of the first read write array element or <nul> if no
- * write array list is present
- */
-static inline struct rpcrdma_write_array *
-svc_rdma_get_write_array(struct rpcrdma_msg *rmsgp)
-{
-	if (rmsgp->rm_body.rm_chunks[0] != 0
-	    || rmsgp->rm_body.rm_chunks[1] == 0)
-		return NULL;
-
-	return (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[1];
-}
-
-/*
- * Returns the address of the first reply array element or <nul> if no
- * reply array is present
- */
-static inline struct rpcrdma_write_array *
-svc_rdma_get_reply_array(struct rpcrdma_msg *rmsgp)
-{
-	struct rpcrdma_read_chunk *rch;
-	struct rpcrdma_write_array *wr_ary;
-	struct rpcrdma_write_array *rp_ary;
-
-	/* XXX: Need to fix when reply list may occur with read-list and/or
-	 * write list */
-	if (rmsgp->rm_body.rm_chunks[0] != 0 ||
-	    rmsgp->rm_body.rm_chunks[1] != 0)
-		return NULL;
-
-	rch = svc_rdma_get_read_chunk(rmsgp);
-	if (rch) {
-		while (rch->rc_discrim)
-			rch++;
-
-		/* The reply list follows an empty write array located
-		 * at 'rc_position' here. The reply array is at rc_target.
-		 */
-		rp_ary = (struct rpcrdma_write_array *)&rch->rc_target;
-
-		goto found_it;
-	}
-
-	wr_ary = svc_rdma_get_write_array(rmsgp);
-	if (wr_ary) {
-		rp_ary = (struct rpcrdma_write_array *)
-			&wr_ary->
-			wc_array[ntohl(wr_ary->wc_nchunks)].wc_target.rs_length;
-
-		goto found_it;
-	}
-
-	/* No read list, no write list */
-	rp_ary = (struct rpcrdma_write_array *)
-		&rmsgp->rm_body.rm_chunks[2];
-
- found_it:
-	if (rp_ary->wc_discrim == 0)
-		return NULL;
-
-	return rp_ary;
-}
 #endif
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 79f6f8f..78512cf 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -116,6 +116,7 @@ void	svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *,
 		      struct svc_serv *);
 int	svc_create_xprt(struct svc_serv *, const char *, struct net *,
 			const int, const unsigned short, int);
+void	svc_xprt_do_enqueue(struct svc_xprt *xprt);
 void	svc_xprt_enqueue(struct svc_xprt *xprt);
 void	svc_xprt_put(struct svc_xprt *xprt);
 void	svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt);
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index fd1a02c..003dca9 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -529,18 +529,21 @@ TRACE_EVENT(svc_xprt_do_enqueue,
 
 	TP_STRUCT__entry(
 		__field(struct svc_xprt *, xprt)
-		__field(struct svc_rqst *, rqst)
+		__field_struct(struct sockaddr_storage, ss)
+		__field(int, pid)
+		__field(unsigned long, flags)
 	),
 
 	TP_fast_assign(
 		__entry->xprt = xprt;
-		__entry->rqst = rqst;
+		xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss));
+		__entry->pid = rqst? rqst->rq_task->pid : 0;
+		__entry->flags = xprt ? xprt->xpt_flags : 0;
 	),
 
 	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))
+		(struct sockaddr *)&__entry->ss,
+		__entry->pid, show_svc_xprt_flags(__entry->flags))
 );
 
 TRACE_EVENT(svc_xprt_dequeue,
@@ -589,16 +592,20 @@ TRACE_EVENT(svc_handle_xprt,
 	TP_STRUCT__entry(
 		__field(struct svc_xprt *, xprt)
 		__field(int, len)
+		__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->len = len;
+		__entry->flags = xprt ? xprt->xpt_flags : 0;
 	),
 
 	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))
+		(struct sockaddr *)&__entry->ss,
+		__entry->len, show_svc_xprt_flags(__entry->flags))
 );
 #endif /* _TRACE_SUNRPC_H */
 
diff --git a/include/uapi/linux/nfsacl.h b/include/uapi/linux/nfsacl.h
index 9bb9771..5527266 100644
--- a/include/uapi/linux/nfsacl.h
+++ b/include/uapi/linux/nfsacl.h
@@ -22,6 +22,7 @@
 #define NFS_ACLCNT		0x0002
 #define NFS_DFACL		0x0004
 #define NFS_DFACLCNT		0x0008
+#define NFS_ACL_MASK		0x000f
 
 /* Flag for Default ACL entries */
 #define NFS_ACL_DEFAULT		0x1000