Merge tag 'nfsd-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "We introduce 'courteous server' in this release. Previously NFSD would
  purge open and lock state for an unresponsive client after one lease
  period (typically 90 seconds). Now, after one lease period, another
  client can open and lock those files and the unresponsive client's
  lease is purged; otherwise if the unresponsive client's open and lock
  state is uncontended, the server retains that open and lock state for
  up to 24 hours, allowing the client's workload to resume after a
  lengthy network partition.

  A longstanding issue with NFSv4 file creation is also addressed.
  Previously a file creation can fail internally, returning an error to
  the client, but leave the newly created file in place as an artifact.
  The file creation code path has been reorganized so that internal
  failures and race conditions are less likely to result in an unwanted
  file creation.

  A fault injector has been added to help exercise paths that are run
  during kernel metadata cache invalidation. These caches contain
  information maintained by user space about exported filesystems. Many
  of our test workloads do not trigger cache invalidation.

  There is one patch that is needed to support PREEMPT_RT and a fix for
  an ancient 'sleep while spin-locked' splat that seems to have become
  easier to hit since v5.18-rc3"

* tag 'nfsd-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (36 commits)
  NFSD: nfsd_file_put() can sleep
  NFSD: Add documenting comment for nfsd4_release_lockowner()
  NFSD: Modernize nfsd4_release_lockowner()
  NFSD: Fix possible sleep during nfsd4_release_lockowner()
  nfsd: destroy percpu stats counters after reply cache shutdown
  nfsd: Fix null-ptr-deref in nfsd_fill_super()
  nfsd: Unregister the cld notifier when laundry_wq create failed
  SUNRPC: Use RMW bitops in single-threaded hot paths
  NFSD: Clean up the show_nf_flags() macro
  NFSD: Trace filecache opens
  NFSD: Move documenting comment for nfsd4_process_open2()
  NFSD: Fix whitespace
  NFSD: Remove dprintk call sites from tail of nfsd4_open()
  NFSD: Instantiate a struct file when creating a regular NFSv4 file
  NFSD: Clean up nfsd_open_verified()
  NFSD: Remove do_nfsd_create()
  NFSD: Refactor NFSv4 OPEN(CREATE)
  NFSD: Refactor NFSv3 CREATE
  NFSD: Refactor nfsd_create_setattr()
  NFSD: Avoid calling fh_drop_write() twice in do_nfsd_create()
  ...

4 files changed, 22 insertions, 14 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1225f8c75650..01403e637271 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1022,6 +1022,7 @@ struct file_lock_operations {
 };
 
 struct lock_manager_operations {
+	void *lm_mod_owner;
 	fl_owner_t (*lm_get_owner)(fl_owner_t);
 	void (*lm_put_owner)(fl_owner_t);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
@@ -1030,6 +1031,8 @@ struct lock_manager_operations {
 	int (*lm_change)(struct file_lock *, int, struct list_head *);
 	void (*lm_setup)(struct file_lock *, void **);
 	bool (*lm_breaker_owns_lease)(struct file_lock *);
+	bool (*lm_lock_expirable)(struct file_lock *cfl);
+	void (*lm_expire_lock)(void);
 };
 
 struct lock_manager {
@@ -1167,6 +1170,8 @@ extern void lease_unregister_notifier(struct notifier_block *);
 struct files_struct;
 extern void show_fd_locks(struct seq_file *f,
 			 struct file *filp, struct files_struct *files);
+extern bool locks_owner_has_blockers(struct file_lock_context *flctx,
+			fl_owner_t owner);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1302,6 +1307,11 @@ static inline int lease_modify(struct file_lock *fl, int arg,
 struct files_struct;
 static inline void show_fd_locks(struct seq_file *f,
 			struct file *filp, struct files_struct *files) {}
+static inline bool locks_owner_has_blockers(struct file_lock_context *flctx,
+			fl_owner_t owner)
+{
+	return false;
+}
 #endif /* !CONFIG_FILE_LOCKING */
 
 static inline struct inode *file_inode(const struct file *f)
@@ -2630,6 +2640,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
 			      name, flags, mode);
 }
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
+extern struct file *dentry_create(const struct path *path, int flags,
+				  umode_t mode, const struct cred *cred);
 extern struct file * open_with_fake_path(const struct path *, int,
 					 struct inode*, const struct cred *);
 static inline struct file *file_clone_open(struct file *file)
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index b134b2b3371c..ec5a555df96f 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -121,17 +121,17 @@ struct cache_detail {
 	struct net		*net;
 };
 
-
 /* this must be embedded in any request structure that
  * identifies an object that will want a callback on
  * a cache fill
  */
 struct cache_req {
 	struct cache_deferred_req *(*defer)(struct cache_req *req);
-	int thread_wait;  /* How long (jiffies) we can block the
-			   * current thread to wait for updates.
-			   */
+	unsigned long	thread_wait;	/* How long (jiffies) we can block the
+					 * current thread to wait for updates.
+					 */
 };
+
 /* this must be embedded in a deferred_request that is being
  * delayed awaiting cache-fill
  */
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 217711fc9cac..daecb009c05b 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -257,7 +257,6 @@ struct svc_rqst {
 	void *			rq_xprt_ctxt;	/* transport specific context ptr */
 	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */
 
-	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
 	struct xdr_stream	rq_arg_stream;
 	struct xdr_stream	rq_res_stream;
@@ -397,7 +396,6 @@ struct svc_deferred_req {
 	size_t			daddrlen;
 	void			*xprt_ctxt;
 	struct cache_deferred_req handle;
-	size_t			xprt_hlen;
 	int			argslen;
 	__be32			args[];
 };
@@ -506,7 +504,7 @@ int		   svc_register(const struct svc_serv *, struct net *, const int,
 
 void		   svc_wake_up(struct svc_serv *);
 void		   svc_reserve(struct svc_rqst *rqstp, int space);
-struct svc_pool *  svc_pool_for_cpu(struct svc_serv *serv, int cpu);
+struct svc_pool   *svc_pool_for_cpu(struct svc_serv *serv);
 char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
 const char *	   svc_proc_name(const struct svc_rqst *rqstp);
 int		   svc_encode_result_payload(struct svc_rqst *rqstp,
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 3995c58a1c51..b61d9c90fa26 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -2015,19 +2015,17 @@ DECLARE_EVENT_CLASS(svc_deferred_event,
 	TP_STRUCT__entry(
 		__field(const void *, dr)
 		__field(u32, xid)
-		__array(__u8, addr, INET6_ADDRSTRLEN + 10)
+		__sockaddr(addr, dr->addrlen)
 	),
 
 	TP_fast_assign(
 		__entry->dr = dr;
-		__entry->xid = be32_to_cpu(*(__be32 *)(dr->args +
-						       (dr->xprt_hlen>>2)));
-		snprintf(__entry->addr, sizeof(__entry->addr) - 1,
-			 "%pISpc", (struct sockaddr *)&dr->addr);
+		__entry->xid = be32_to_cpu(*(__be32 *)dr->args);
+		__assign_sockaddr(addr, &dr->addr, dr->addrlen);
 	),
 
-	TP_printk("addr=%s dr=%p xid=0x%08x", __entry->addr, __entry->dr,
-		__entry->xid)
+	TP_printk("addr=%pISpc dr=%p xid=0x%08x", __get_sockaddr(addr),
+		__entry->dr, __entry->xid)
 );
 
 #define DEFINE_SVC_DEFERRED_EVENT(name) \