Merge tag 'nfsd-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "Bruce has announced he is leaving Red Hat at the end of the month and
  is stepping back from his role as NFSD co-maintainer. As a result,
  this includes a patch removing him from the MAINTAINERS file.

  There is one patch in here that Jeff Layton was carrying in the locks
  tree. Since he had only one for this cycle, he asked us to send it to
  you via the nfsd tree.

  There continues to be 0-day reports from Robert Morris @MIT. This time
  we include a fix for a crash in the COPY_NOTIFY operation.

  Highlights:
   - Bruce steps down as NFSD maintainer
   - Prepare for dynamic nfsd thread management
   - More work on supporting re-exporting NFS mounts
   - One fs/locks patch on behalf of Jeff Layton

  Notable bug fixes:
   - Fix zero-length NFSv3 WRITEs
   - Fix directory cinfo on FS's that do not support iversion
   - Fix WRITE verifiers for stable writes
   - Fix crash on COPY_NOTIFY with a special state ID"

* tag 'nfsd-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (51 commits)
  SUNRPC: Fix sockaddr handling in svcsock_accept_class trace points
  SUNRPC: Fix sockaddr handling in the svc_xprt_create_error trace point
  fs/locks: fix fcntl_getlk64/fcntl_setlk64 stub prototypes
  nfsd: fix crash on COPY_NOTIFY with special stateid
  MAINTAINERS: remove bfields
  NFSD: Move fill_pre_wcc() and fill_post_wcc()
  Revert "nfsd: skip some unnecessary stats in the v4 case"
  NFSD: Trace boot verifier resets
  NFSD: Rename boot verifier functions
  NFSD: Clean up the nfsd_net::nfssvc_boot field
  NFSD: Write verifier might go backwards
  nfsd: Add a tracepoint for errors in nfsd4_clone_file_range()
  NFSD: De-duplicate net_generic(nf->nf_net, nfsd_net_id)
  NFSD: De-duplicate net_generic(SVC_NET(rqstp), nfsd_net_id)
  NFSD: Clean up nfsd_vfs_write()
  nfsd: Replace use of rwsem with errseq_t
  NFSD: Fix verifier returned in stable WRITEs
  nfsd: Retry once in nfsd_open on an -EOPENSTALE return
  nfsd: Add errno mapping for EREMOTEIO
  nfsd: map EBADF
  ...

5 files changed, 56 insertions, 75 deletions

diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 3260fe714846..fe848901fcc3 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -221,8 +221,6 @@ struct export_operations {
 #define EXPORT_OP_NOATOMIC_ATTR		(0x10) /* Filesystem cannot supply
 						  atomic attribute updates
 						*/
-#define EXPORT_OP_SYNC_LOCKS		(0x20) /* Filesystem can't do
-						  asychronous blocking locks */
 	unsigned long	flags;
 };
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42ab6d71291c..c8510da6cc6d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1221,13 +1221,13 @@ static inline int fcntl_setlk(unsigned int fd, struct file *file,
 
 #if BITS_PER_LONG == 32
 static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
-				struct flock64 __user *user)
+				struct flock64 *user)
 {
 	return -EINVAL;
 }
 
 static inline int fcntl_setlk64(unsigned int fd, struct file *file,
-				unsigned int cmd, struct flock64 __user *user)
+				unsigned int cmd, struct flock64 *user)
 {
 	return -EACCES;
 }
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index c4ae6506b8b3..fcef192e5e45 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -303,10 +303,15 @@ void		  nlmsvc_invalidate_all(void);
 int           nlmsvc_unlock_all_by_sb(struct super_block *sb);
 int           nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr);
 
+static inline struct file *nlmsvc_file_file(struct nlm_file *file)
+{
+	return file->f_file[O_RDONLY] ?
+	       file->f_file[O_RDONLY] : file->f_file[O_WRONLY];
+}
+
 static inline struct inode *nlmsvc_file_inode(struct nlm_file *file)
 {
-	return locks_inode(file->f_file[O_RDONLY] ?
-			   file->f_file[O_RDONLY] : file->f_file[O_WRONLY]);
+	return locks_inode(nlmsvc_file_file(file));
 }
 
 static inline int __nlm_privileged_request4(const struct sockaddr *sap)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 0ae28ae6caf2..cf175d47c6b7 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -64,10 +64,9 @@ struct svc_serv_ops {
 	/* 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) */
+	/* optional module to count when adding threads.
+	 * Thread function must call module_put_and_exit() to exit.
+	 */
 	struct module	*svo_module;
 };
 
@@ -85,6 +84,7 @@ struct svc_serv {
 	struct svc_program *	sv_program;	/* RPC program */
 	struct svc_stat *	sv_stats;	/* RPC statistics */
 	spinlock_t		sv_lock;
+	struct kref		sv_refcnt;
 	unsigned int		sv_nrthreads;	/* # of server threads */
 	unsigned int		sv_maxconn;	/* max connections allowed or
 						 * '0' causing max to be based
@@ -114,15 +114,43 @@ struct svc_serv {
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 };
 
-/*
- * We use sv_nrthreads as a reference count.  svc_destroy() drops
- * this refcount, so we need to bump it up around operations that
- * change the number of threads.  Horrible, but there it is.
- * Should be called with the "service mutex" held.
+/**
+ * svc_get() - increment reference count on a SUNRPC serv
+ * @serv:  the svc_serv to have count incremented
+ *
+ * Returns: the svc_serv that was passed in.
+ */
+static inline struct svc_serv *svc_get(struct svc_serv *serv)
+{
+	kref_get(&serv->sv_refcnt);
+	return serv;
+}
+
+void svc_destroy(struct kref *);
+
+/**
+ * svc_put - decrement reference count on a SUNRPC serv
+ * @serv:  the svc_serv to have count decremented
+ *
+ * When the reference count reaches zero, svc_destroy()
+ * is called to clean up and free the serv.
+ */
+static inline void svc_put(struct svc_serv *serv)
+{
+	kref_put(&serv->sv_refcnt, svc_destroy);
+}
+
+/**
+ * svc_put_not_last - decrement non-final reference count on SUNRPC serv
+ * @serv:  the svc_serv to have count decremented
+ *
+ * Returns: %true is refcount was decremented.
+ *
+ * If the refcount is 1, it is not decremented and instead failure is reported.
  */
-static inline void svc_get(struct svc_serv *serv)
+static inline bool svc_put_not_last(struct svc_serv *serv)
 {
-	serv->sv_nrthreads++;
+	return refcount_dec_not_one(&serv->sv_refcnt.refcount);
 }
 
 /*
@@ -469,29 +497,6 @@ 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);
@@ -501,20 +506,14 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int,
 			    const 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_replace_page(struct svc_rqst *rqstp,
 					 struct page *page);
 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,
 			const struct svc_serv_ops *);
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
-int		   svc_set_num_threads_sync(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 *);
 void		   svc_shutdown_net(struct svc_serv *, struct net *);
 int		   svc_process(struct svc_rqst *);
 int		   bc_svc_process(struct svc_serv *, struct rpc_rqst *,
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 3a99358c262b..1e566ac4b812 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1744,10 +1744,11 @@ TRACE_EVENT(svc_xprt_create_err,
 		const char *program,
 		const char *protocol,
 		struct sockaddr *sap,
+		size_t salen,
 		const struct svc_xprt *xprt
 	),
 
-	TP_ARGS(program, protocol, sap, xprt),
+	TP_ARGS(program, protocol, sap, salen, xprt),
 
 	TP_STRUCT__entry(
 		__field(long, error)
@@ -1760,7 +1761,7 @@ TRACE_EVENT(svc_xprt_create_err,
 		__entry->error = PTR_ERR(xprt);
 		__assign_str(program, program);
 		__assign_str(protocol, protocol);
-		memcpy(__entry->addr, sap, sizeof(__entry->addr));
+		memcpy(__entry->addr, sap, min(salen, sizeof(__entry->addr)));
 	),
 
 	TP_printk("addr=%pISpc program=%s protocol=%s error=%ld",
@@ -1768,7 +1769,7 @@ TRACE_EVENT(svc_xprt_create_err,
 		__entry->error)
 );
 
-TRACE_EVENT(svc_xprt_do_enqueue,
+TRACE_EVENT(svc_xprt_enqueue,
 	TP_PROTO(struct svc_xprt *xprt, struct svc_rqst *rqst),
 
 	TP_ARGS(xprt, rqst),
@@ -1815,7 +1816,6 @@ DECLARE_EVENT_CLASS(svc_xprt_event,
 			), \
 			TP_ARGS(xprt))
 
-DEFINE_SVC_XPRT_EVENT(received);
 DEFINE_SVC_XPRT_EVENT(no_write_space);
 DEFINE_SVC_XPRT_EVENT(close);
 DEFINE_SVC_XPRT_EVENT(detach);
@@ -1902,27 +1902,6 @@ TRACE_EVENT(svc_alloc_arg_err,
 	TP_printk("pages=%u", __entry->pages)
 );
 
-TRACE_EVENT(svc_handle_xprt,
-	TP_PROTO(struct svc_xprt *xprt, int len),
-
-	TP_ARGS(xprt, len),
-
-	TP_STRUCT__entry(
-		__field(int, len)
-		__field(unsigned long, flags)
-		__string(addr, xprt->xpt_remotebuf)
-	),
-
-	TP_fast_assign(
-		__entry->len = len;
-		__entry->flags = xprt->xpt_flags;
-		__assign_str(addr, xprt->xpt_remotebuf);
-	),
-
-	TP_printk("addr=%s len=%d flags=%s", __get_str(addr),
-		__entry->len, show_svc_xprt_flags(__entry->flags))
-);
-
 TRACE_EVENT(svc_stats_latency,
 	TP_PROTO(const struct svc_rqst *rqst),
 
@@ -2146,17 +2125,17 @@ DECLARE_EVENT_CLASS(svcsock_accept_class,
 	TP_STRUCT__entry(
 		__field(long, status)
 		__string(service, service)
-		__array(unsigned char, addr, sizeof(struct sockaddr_in6))
+		__field(unsigned int, netns_ino)
 	),
 
 	TP_fast_assign(
 		__entry->status = status;
 		__assign_str(service, service);
-		memcpy(__entry->addr, &xprt->xpt_local, sizeof(__entry->addr));
+		__entry->netns_ino = xprt->xpt_net->ns.inum;
 	),
 
-	TP_printk("listener=%pISpc service=%s status=%ld",
-		__entry->addr, __get_str(service), __entry->status
+	TP_printk("addr=listener service=%s status=%ld",
+		__get_str(service), __entry->status
 	)
 );