Merge tag 'locks-v3.18-1' of git://git.samba.org/jlayton/linux

Pull file locking related changes from Jeff Layton:
 "This release is a little more busy for file locking changes than the
  last:

   - a set of patches from Kinglong Mee to fix the lockowner handling in
     knfsd
   - a pile of cleanups to the internal file lease API.  This should get
     us a bit closer to allowing for setlease methods that can block.

  There are some dependencies between mine and Bruce's trees this cycle,
  and I based my tree on top of the requisite patches in Bruce's tree"

* tag 'locks-v3.18-1' of git://git.samba.org/jlayton/linux: (26 commits)
  locks: fix fcntl_setlease/getlease return when !CONFIG_FILE_LOCKING
  locks: flock_make_lock should return a struct file_lock (or PTR_ERR)
  locks: set fl_owner for leases to filp instead of current->files
  locks: give lm_break a return value
  locks: __break_lease cleanup in preparation of allowing direct removal of leases
  locks: remove i_have_this_lease check from __break_lease
  locks: move freeing of leases outside of i_lock
  locks: move i_lock acquisition into generic_*_lease handlers
  locks: define a lm_setup handler for leases
  locks: plumb a "priv" pointer into the setlease routines
  nfsd: don't keep a pointer to the lease in nfs4_file
  locks: clean up vfs_setlease kerneldoc comments
  locks: generic_delete_lease doesn't need a file_lock at all
  nfsd: fix potential lease memory leak in nfs4_setlease
  locks: close potential race in lease_get_mtime
  security: make security_file_set_fowner, f_setown and __f_setown void return
  locks: consolidate "nolease" routines
  locks: remove lock_may_read and lock_may_write
  lockd: rip out deferred lock handling from testlock codepath
  NFSD: Get reference of lockowner when coping file_lock
  ...

Documentation/filesystems/Locking

@@ -464,15 +464,12 @@ prototypes:
 			size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
 			size_t, unsigned int);
-	int (*setlease)(struct file *, long, struct file_lock **);
+	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int, loff_t, loff_t);
 };
 
 locking rules:
-	All may block except for ->setlease.
-	No VFS locks held on entry except for ->setlease.
-
-->setlease has the file_list_lock held and must not sleep.
+	All may block.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
@@ -496,6 +493,10 @@ components. And there are other reasons why the current interface is a mess...
 ->read on directories probably must go away - we should just enforce -EISDIR
 in sys_read() and friends.
 
+->setlease operations should call generic_setlease() before or after setting
+the lease within the individual filesystem to record the result of the
+operation
+
 --------------------------- dquot_operations -------------------------------
 prototypes:
 	int (*write_dquot) (struct dquot *);

Documentation/filesystems/vfs.txt

@@ -826,7 +826,7 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int);
-	int (*setlease)(struct file *, long arg, struct file_lock **);
+	int (*setlease)(struct file *, long arg, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len);
 	int (*show_fdinfo)(struct seq_file *m, struct file *f);
 };
@@ -895,8 +895,9 @@ otherwise noted.
   splice_read: called by the VFS to splice data from file to a pipe. This
 	       method is used by the splice(2) system call
 
-  setlease: called by the VFS to set or release a file lock lease.
-	    setlease has the file_lock_lock held and must not sleep.
+  setlease: called by the VFS to set or release a file lock lease. setlease
+	    implementations should call generic_setlease to record or remove
+	    the lease in the inode after setting it.
 
   fallocate: called by the VFS to preallocate blocks or punch a hole.
 

drivers/net/tun.c

@@ -2152,9 +2152,7 @@ static int tun_chr_fasync(int fd, struct file *file, int on)
 		goto out;
 
 	if (on) {
-		ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
-		if (ret)
-			goto out;
+		__f_setown(file, task_pid(current), PIDTYPE_PID, 0);
 		tfile->flags |= TUN_FASYNC;
 	} else
 		tfile->flags &= ~TUN_FASYNC;

drivers/tty/tty_io.c

@@ -2186,8 +2186,9 @@ static int __tty_fasync(int fd, struct file *filp, int on)
 		}
 		get_pid(pid);
 		spin_unlock_irqrestore(&tty->ctrl_lock, flags);
-		retval = __f_setown(filp, pid, type, 0);
+		__f_setown(filp, pid, type, 0);
 		put_pid(pid);
+		retval = 0;
 	}
 out:
 	return retval;

fs/cifs/cifsfs.c

@@ -813,7 +813,8 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence)
 	return generic_file_llseek(file, offset, whence);
 }
 
-static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
+static int
+cifs_setlease(struct file *file, long arg, struct file_lock **lease, void **priv)
 {
 	/*
 	 * Note that this is called by vfs setlease with i_lock held to
@@ -829,7 +830,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
 	if (arg == F_UNLCK ||
 	    ((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) ||
 	    ((arg == F_WRLCK) && CIFS_CACHE_WRITE(CIFS_I(inode))))
-		return generic_setlease(file, arg, lease);
+		return generic_setlease(file, arg, lease, priv);
 	else if (tlink_tcon(cfile->tlink)->local_lease &&
 		 !CIFS_CACHE_READ(CIFS_I(inode)))
 		/*
@@ -840,7 +841,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
 		 * knows that the file won't be changed on the server by anyone
 		 * else.
 		 */
-		return generic_setlease(file, arg, lease);
+		return generic_setlease(file, arg, lease, priv);
 	else
 		return -EAGAIN;
 }

fs/dlm/plock.c

@@ -30,7 +30,7 @@ struct plock_op {
 
 struct plock_xop {
 	struct plock_op xop;
-	void *callback;
+	int (*callback)(struct file_lock *fl, int result);
 	void *fl;
 	void *file;
 	struct file_lock flc;
@@ -190,7 +190,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	struct file *file;
 	struct file_lock *fl;
 	struct file_lock *flc;
-	int (*notify)(void *, void *, int) = NULL;
+	int (*notify)(struct file_lock *fl, int result) = NULL;
 	struct plock_xop *xop = (struct plock_xop *)op;
 	int rv = 0;
 
@@ -209,7 +209,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	notify = xop->callback;
 
 	if (op->info.rv) {
-		notify(fl, NULL, op->info.rv);
+		notify(fl, op->info.rv);
 		goto out;
 	}
 
@@ -228,7 +228,7 @@ static int dlm_plock_callback(struct plock_op *op)
 			  (unsigned long long)op->info.number, file, fl);
 	}
 
-	rv = notify(fl, NULL, 0);
+	rv = notify(fl, 0);
 	if (rv) {
 		/* XXX: We need to cancel the fs lock here: */
 		log_print("dlm_plock_callback: lock granted after lock request "

fs/fcntl.c

@@ -98,26 +98,19 @@ static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
 	write_unlock_irq(&filp->f_owner.lock);
 }
 
-int __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
+void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
 		int force)
 {
-	int err;
-
-	err = security_file_set_fowner(filp);
-	if (err)
-		return err;
-
+	security_file_set_fowner(filp);
 	f_modown(filp, pid, type, force);
-	return 0;
 }
 EXPORT_SYMBOL(__f_setown);
 
-int f_setown(struct file *filp, unsigned long arg, int force)
+void f_setown(struct file *filp, unsigned long arg, int force)
 {
 	enum pid_type type;
 	struct pid *pid;
 	int who = arg;
-	int result;
 	type = PIDTYPE_PID;
 	if (who < 0) {
 		type = PIDTYPE_PGID;
@@ -125,9 +118,8 @@ int f_setown(struct file *filp, unsigned long arg, int force)
 	}
 	rcu_read_lock();
 	pid = find_vpid(who);
-	result = __f_setown(filp, pid, type, force);
+	__f_setown(filp, pid, type, force);
 	rcu_read_unlock();
-	return result;
 }
 EXPORT_SYMBOL(f_setown);
 
@@ -181,7 +173,7 @@ static int f_setown_ex(struct file *filp, unsigned long arg)
 	if (owner.pid && !pid)
 		ret = -ESRCH;
 	else
-		ret = __f_setown(filp, pid, type, 1);
+		 __f_setown(filp, pid, type, 1);
 	rcu_read_unlock();
 
 	return ret;
@@ -302,7 +294,8 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		force_successful_syscall_return();
 		break;
 	case F_SETOWN:
-		err = f_setown(filp, arg, 1);
+		f_setown(filp, arg, 1);
+		err = 0;
 		break;
 	case F_GETOWN_EX:
 		err = f_getown_ex(filp, arg);

fs/gfs2/file.c

@@ -913,26 +913,6 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
 
 #ifdef CONFIG_GFS2_FS_LOCKING_DLM
 
-/**
- * gfs2_setlease - acquire/release a file lease
- * @file: the file pointer
- * @arg: lease type
- * @fl: file lock
- *
- * We don't currently have a way to enforce a lease across the whole
- * cluster; until we do, disable leases (by just returning -EINVAL),
- * unless the administrator has requested purely local locking.
- *
- * Locking: called under i_lock
- *
- * Returns: errno
- */
-
-static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
-{
-	return -EINVAL;
-}
-
 /**
  * gfs2_lock - acquire/release a posix lock on a file
  * @file: the file pointer
@@ -1078,7 +1058,7 @@ const struct file_operations gfs2_file_fops = {
 	.flock		= gfs2_flock,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
-	.setlease	= gfs2_setlease,
+	.setlease	= simple_nosetlease,
 	.fallocate	= gfs2_fallocate,
 };
 

fs/libfs.c

@@ -1075,3 +1075,21 @@ struct inode *alloc_anon_inode(struct super_block *s)
 	return inode;
 }
 EXPORT_SYMBOL(alloc_anon_inode);
+
+/**
+ * simple_nosetlease - generic helper for prohibiting leases
+ * @filp: file pointer
+ * @arg: type of lease to obtain
+ * @flp: new lease supplied for insertion
+ * @priv: private data for lm_setup operation
+ *
+ * Generic helper for filesystems that do not wish to allow leases to be set.
+ * All arguments are ignored and it just returns -EINVAL.
+ */
+int
+simple_nosetlease(struct file *filp, long arg, struct file_lock **flp,
+		  void **priv)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(simple_nosetlease);

fs/lockd/svclock.c

@@ -245,7 +245,6 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host,
 	block->b_daemon = rqstp->rq_server;
 	block->b_host   = host;
 	block->b_file   = file;
-	block->b_fl = NULL;
 	file->f_count++;
 
 	/* Add to file's list of blocks */
@@ -295,7 +294,6 @@ static void nlmsvc_free_block(struct kref *kref)
 	nlmsvc_freegrantargs(block->b_call);
 	nlmsvc_release_call(block->b_call);
 	nlm_release_file(block->b_file);
-	kfree(block->b_fl);
 	kfree(block);
 }
 
@@ -508,7 +506,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		struct nlm_host *host, struct nlm_lock *lock,
 		struct nlm_lock *conflock, struct nlm_cookie *cookie)
 {
-	struct nlm_block 	*block = NULL;
 	int			error;
 	__be32			ret;
 
@@ -519,63 +516,26 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
-	/* Get existing block (in case client is busy-waiting) */
-	block = nlmsvc_lookup_block(file, lock);
-
-	if (block == NULL) {
-		struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-
-		if (conf == NULL)
-			return nlm_granted;
-		block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
-		if (block == NULL) {
-			kfree(conf);
-			return nlm_granted;
-		}
-		block->b_fl = conf;
-	}
-	if (block->b_flags & B_QUEUED) {
-		dprintk("lockd: nlmsvc_testlock deferred block %p flags %d fl %p\n",
-			block, block->b_flags, block->b_fl);
-		if (block->b_flags & B_TIMED_OUT) {
-			nlmsvc_unlink_block(block);
-			ret = nlm_lck_denied;
-			goto out;
-		}
-		if (block->b_flags & B_GOT_CALLBACK) {
-			nlmsvc_unlink_block(block);
-			if (block->b_fl != NULL
-					&& block->b_fl->fl_type != F_UNLCK) {
-				lock->fl = *block->b_fl;
-				goto conf_lock;
-			} else {
-				ret = nlm_granted;
-				goto out;
-			}
-		}
-		ret = nlm_drop_reply;
-		goto out;
-	}
-
 	if (locks_in_grace(SVC_NET(rqstp))) {
 		ret = nlm_lck_denied_grace_period;
 		goto out;
 	}
+
 	error = vfs_test_lock(file->f_file, &lock->fl);
-	if (error == FILE_LOCK_DEFERRED) {
-		ret = nlmsvc_defer_lock_rqst(rqstp, block);
-		goto out;
-	}
 	if (error) {
+		/* We can't currently deal with deferred test requests */
+		if (error == FILE_LOCK_DEFERRED)
+			WARN_ON_ONCE(1);
+
 		ret = nlm_lck_denied_nolocks;
 		goto out;
 	}
+
 	if (lock->fl.fl_type == F_UNLCK) {
 		ret = nlm_granted;
 		goto out;
 	}
 
-conf_lock:
 	dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
 		lock->fl.fl_type, (long long)lock->fl.fl_start,
 		(long long)lock->fl.fl_end);
@@ -586,10 +546,9 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 	conflock->fl.fl_type = lock->fl.fl_type;
 	conflock->fl.fl_start = lock->fl.fl_start;
 	conflock->fl.fl_end = lock->fl.fl_end;
+	locks_release_private(&lock->fl);
 	ret = nlm_lck_denied;
 out:
-	if (block)
-		nlmsvc_release_block(block);
 	return ret;
 }
 
@@ -660,29 +619,22 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l
  * This is a callback from the filesystem for VFS file lock requests.
  * It will be used if lm_grant is defined and the filesystem can not
  * respond to the request immediately.
- * For GETLK request it will copy the reply to the nlm_block.
  * For SETLK or SETLKW request it will get the local posix lock.
  * In all cases it will move the block to the head of nlm_blocked q where
  * nlmsvc_retry_blocked() can send back a reply for SETLKW or revisit the
  * deferred rpc for GETLK and SETLK.
  */
 static void
-nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
-			     int result)
+nlmsvc_update_deferred_block(struct nlm_block *block, int result)
 {
 	block->b_flags |= B_GOT_CALLBACK;
 	if (result == 0)
 		block->b_granted = 1;
 	else
 		block->b_flags |= B_TIMED_OUT;
-	if (conf) {
-		if (block->b_fl)
-			__locks_copy_lock(block->b_fl, conf);
-	}
 }
 
-static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
-					int result)
+static int nlmsvc_grant_deferred(struct file_lock *fl, int result)
 {
 	struct nlm_block *block;
 	int rc = -ENOENT;
@@ -697,7 +649,7 @@ static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
 					rc = -ENOLCK;
 					break;
 				}
-				nlmsvc_update_deferred_block(block, conf, result);
+				nlmsvc_update_deferred_block(block, result);
 			} else if (result == 0)
 				block->b_granted = 1;
 

fs/locks.c

@@ -230,8 +230,12 @@ void locks_release_private(struct file_lock *fl)
 			fl->fl_ops->fl_release_private(fl);
 		fl->fl_ops = NULL;
 	}
-	fl->fl_lmops = NULL;
 
+	if (fl->fl_lmops) {
+		if (fl->fl_lmops->lm_put_owner)
+			fl->fl_lmops->lm_put_owner(fl);
+		fl->fl_lmops = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(locks_release_private);
 
@@ -267,21 +271,10 @@ void locks_init_lock(struct file_lock *fl)
 
 EXPORT_SYMBOL(locks_init_lock);
 
-static void locks_copy_private(struct file_lock *new, struct file_lock *fl)
-{
-	if (fl->fl_ops) {
-		if (fl->fl_ops->fl_copy_lock)
-			fl->fl_ops->fl_copy_lock(new, fl);
-		new->fl_ops = fl->fl_ops;
-	}
-	if (fl->fl_lmops)
-		new->fl_lmops = fl->fl_lmops;
-}
-
 /*
  * Initialize a new lock from an existing file_lock structure.
  */
-void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
+void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	new->fl_owner = fl->fl_owner;
 	new->fl_pid = fl->fl_pid;
@@ -290,22 +283,30 @@ void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
 	new->fl_type = fl->fl_type;
 	new->fl_start = fl->fl_start;
 	new->fl_end = fl->fl_end;
+	new->fl_lmops = fl->fl_lmops;
 	new->fl_ops = NULL;
-	new->fl_lmops = NULL;
+
+	if (fl->fl_lmops) {
+		if (fl->fl_lmops->lm_get_owner)
+			fl->fl_lmops->lm_get_owner(new, fl);
+	}
 }
-EXPORT_SYMBOL(__locks_copy_lock);
+EXPORT_SYMBOL(locks_copy_conflock);
 
 void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
 {
 	/* "new" must be a freshly-initialized lock */
 	WARN_ON_ONCE(new->fl_ops);
 
-	__locks_copy_lock(new, fl);
+	locks_copy_conflock(new, fl);
+
 	new->fl_file = fl->fl_file;
 	new->fl_ops = fl->fl_ops;
-	new->fl_lmops = fl->fl_lmops;
 
-	locks_copy_private(new, fl);
+	if (fl->fl_ops) {
+		if (fl->fl_ops->fl_copy_lock)
+			fl->fl_ops->fl_copy_lock(new, fl);
+	}
 }
 
 EXPORT_SYMBOL(locks_copy_lock);
@@ -325,17 +326,18 @@ static inline int flock_translate_cmd(int cmd) {
 }
 
 /* Fill in a file_lock structure with an appropriate FLOCK lock. */
-static int flock_make_lock(struct file *filp, struct file_lock **lock,
-		unsigned int cmd)
+static struct file_lock *
+flock_make_lock(struct file *filp, unsigned int cmd)
 {
 	struct file_lock *fl;
 	int type = flock_translate_cmd(cmd);
+
 	if (type < 0)
-		return type;
+		return ERR_PTR(type);
 	
 	fl = locks_alloc_lock();
 	if (fl == NULL)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	fl->fl_file = filp;
 	fl->fl_owner = filp;
@@ -344,8 +346,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock,
 	fl->fl_type = type;
 	fl->fl_end = OFFSET_MAX;
 	
-	*lock = fl;
-	return 0;
+	return fl;
 }
 
 static int assign_type(struct file_lock *fl, long type)
@@ -426,14 +427,34 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
 }
 
 /* default lease lock manager operations */
-static void lease_break_callback(struct file_lock *fl)
+static bool
+lease_break_callback(struct file_lock *fl)
 {
 	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
+	return false;
+}
+
+static void
+lease_setup(struct file_lock *fl, void **priv)
+{
+	struct file *filp = fl->fl_file;
+	struct fasync_struct *fa = *priv;
+
+	/*
+	 * fasync_insert_entry() returns the old entry if any. If there was no
+	 * old entry, then it used "priv" and inserted it into the fasync list.
+	 * Clear the pointer to indicate that it shouldn't be freed.
+	 */
+	if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa))
+		*priv = NULL;
+
+	__f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
 }
 
 static const struct lock_manager_operations lease_manager_ops = {
 	.lm_break = lease_break_callback,
 	.lm_change = lease_modify,
+	.lm_setup = lease_setup,
 };
 
 /*
@@ -444,7 +465,7 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl)
 	if (assign_type(fl, type) != 0)
 		return -EINVAL;
 
-	fl->fl_owner = current->files;
+	fl->fl_owner = filp;
 	fl->fl_pid = current->tgid;
 
 	fl->fl_file = filp;
@@ -735,7 +756,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 			break;
 	}
 	if (cfl) {
-		__locks_copy_lock(fl, cfl);
+		locks_copy_conflock(fl, cfl);
 		if (cfl->fl_nspid)
 			fl->fl_pid = pid_vnr(cfl->fl_nspid);
 	} else
@@ -941,7 +962,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			if (!posix_locks_conflict(request, fl))
 				continue;
 			if (conflock)
-				__locks_copy_lock(conflock, fl);
+				locks_copy_conflock(conflock, fl);
 			error = -EAGAIN;
 			if (!(request->fl_flags & FL_SLEEP))
 				goto out;
@@ -1273,7 +1294,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 }
 
 /* We already had a lease on this file; just change its type */
-int lease_modify(struct file_lock **before, int arg)
+int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
 {
 	struct file_lock *fl = *before;
 	int error = assign_type(fl, arg);
@@ -1292,11 +1313,10 @@ int lease_modify(struct file_lock **before, int arg)
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock(before, NULL);
+		locks_delete_lock(before, dispose);
 	}
 	return 0;
 }
-
 EXPORT_SYMBOL(lease_modify);
 
 static bool past_time(unsigned long then)
@@ -1307,18 +1327,20 @@ static bool past_time(unsigned long then)
 	return time_after(jiffies, then);
 }
 
-static void time_out_leases(struct inode *inode)
+static void time_out_leases(struct inode *inode, struct list_head *dispose)
 {
 	struct file_lock **before;
 	struct file_lock *fl;
 
+	lockdep_assert_held(&inode->i_lock);
+
 	before = &inode->i_flock;
 	while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
-			lease_modify(before, F_RDLCK);
+			lease_modify(before, F_RDLCK, dispose);
 		if (past_time(fl->fl_break_time))
-			lease_modify(before, F_UNLCK);
+			lease_modify(before, F_UNLCK, dispose);
 		if (fl == *before)	/* lease_modify may have freed fl */
 			before = &fl->fl_next;
 	}
@@ -1331,6 +1353,20 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 	return locks_conflict(breaker, lease);
 }
 
+static bool
+any_leases_conflict(struct inode *inode, struct file_lock *breaker)
+{
+	struct file_lock *fl;
+
+	lockdep_assert_held(&inode->i_lock);
+
+	for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (leases_conflict(fl, breaker))
+			return true;
+	}
+	return false;
+}
+
 /**
  *	__break_lease	-	revoke all outstanding leases on file
  *	@inode: the inode of the file to return
@@ -1347,12 +1383,11 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
-	struct file_lock *new_fl, *flock;
-	struct file_lock *fl;
+	struct file_lock *new_fl;
+	struct file_lock *fl, **before;
 	unsigned long break_time;
-	int i_have_this_lease = 0;
-	bool lease_conflict = false;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
+	LIST_HEAD(dispose);
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
@@ -1361,20 +1396,9 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 
 	spin_lock(&inode->i_lock);
 
-	time_out_leases(inode);
-
-	flock = inode->i_flock;
-	if ((flock == NULL) || !IS_LEASE(flock))
-		goto out;
+	time_out_leases(inode, &dispose);
 
-	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
-		if (leases_conflict(fl, new_fl)) {
-			lease_conflict = true;
-			if (fl->fl_owner == current->files)
-				i_have_this_lease = 1;
-		}
-	}
-	if (!lease_conflict)
+	if (!any_leases_conflict(inode, new_fl))
 		goto out;
 
 	break_time = 0;
@@ -1384,7 +1408,9 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+	for (before = &inode->i_flock;
+			((fl = *before) != NULL) && IS_LEASE(fl);
+			before = &fl->fl_next) {
 		if (!leases_conflict(fl, new_fl))
 			continue;
 		if (want_write) {
@@ -1393,51 +1419,56 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			fl->fl_flags |= FL_UNLOCK_PENDING;
 			fl->fl_break_time = break_time;
 		} else {
-			if (lease_breaking(flock))
+			if (lease_breaking(inode->i_flock))
 				continue;
 			fl->fl_flags |= FL_DOWNGRADE_PENDING;
 			fl->fl_downgrade_time = break_time;
 		}
-		fl->fl_lmops->lm_break(fl);
+		if (fl->fl_lmops->lm_break(fl))
+			locks_delete_lock(before, &dispose);
 	}
 
-	if (i_have_this_lease || (mode & O_NONBLOCK)) {
+	fl = inode->i_flock;
+	if (!fl || !IS_LEASE(fl))
+		goto out;
+
+	if (mode & O_NONBLOCK) {
 		trace_break_lease_noblock(inode, new_fl);
 		error = -EWOULDBLOCK;
 		goto out;
 	}
 
 restart:
-	break_time = flock->fl_break_time;
+	break_time = inode->i_flock->fl_break_time;
 	if (break_time != 0)
 		break_time -= jiffies;
 	if (break_time == 0)
 		break_time++;
-	locks_insert_block(flock, new_fl);
+	locks_insert_block(inode->i_flock, new_fl);
 	trace_break_lease_block(inode, new_fl);
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
 						!new_fl->fl_next, break_time);
 	spin_lock(&inode->i_lock);
 	trace_break_lease_unblock(inode, new_fl);
 	locks_delete_block(new_fl);
 	if (error >= 0) {
-		if (error == 0)
-			time_out_leases(inode);
 		/*
 		 * Wait for the next conflicting lease that has not been
 		 * broken yet
 		 */
-		for (flock = inode->i_flock; flock && IS_LEASE(flock);
-				flock = flock->fl_next) {
-			if (leases_conflict(new_fl, flock))
-				goto restart;
-		}
+		if (error == 0)
+			time_out_leases(inode, &dispose);
+		if (any_leases_conflict(inode, new_fl))
+			goto restart;
+
 		error = 0;
 	}
 
 out:
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	locks_free_lock(new_fl);
 	return error;
 }
@@ -1455,8 +1486,18 @@ EXPORT_SYMBOL(__break_lease);
  */
 void lease_get_mtime(struct inode *inode, struct timespec *time)
 {
-	struct file_lock *flock = inode->i_flock;
-	if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK))
+	bool has_lease = false;
+	struct file_lock *flock;
+
+	if (inode->i_flock) {
+		spin_lock(&inode->i_lock);
+		flock = inode->i_flock;
+		if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK))
+			has_lease = true;
+		spin_unlock(&inode->i_lock);
+	}
+
+	if (has_lease)
 		*time = current_fs_time(inode->i_sb);
 	else
 		*time = inode->i_mtime;
@@ -1492,9 +1533,10 @@ int fcntl_getlease(struct file *filp)
 	struct file_lock *fl;
 	struct inode *inode = file_inode(filp);
 	int type = F_UNLCK;
+	LIST_HEAD(dispose);
 
 	spin_lock(&inode->i_lock);
-	time_out_leases(file_inode(filp));
+	time_out_leases(file_inode(filp), &dispose);
 	for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl);
 			fl = fl->fl_next) {
 		if (fl->fl_file == filp) {
@@ -1503,6 +1545,7 @@ int fcntl_getlease(struct file *filp)
 		}
 	}
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	return type;
 }
 
@@ -1532,13 +1575,15 @@ check_conflicting_open(const struct dentry *dentry, const long arg)
 	return ret;
 }
 
-static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp)
+static int
+generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv)
 {
 	struct file_lock *fl, **before, **my_before = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
+	LIST_HEAD(dispose);
 
 	lease = *flp;
 	trace_generic_add_lease(inode, lease);
@@ -1561,6 +1606,8 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 		return -EINVAL;
 	}
 
+	spin_lock(&inode->i_lock);
+	time_out_leases(inode, &dispose);
 	error = check_conflicting_open(dentry, arg);
 	if (error)
 		goto out;
@@ -1596,10 +1643,11 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	}
 
 	if (my_before != NULL) {
-		error = lease->fl_lmops->lm_change(my_before, arg);
-		if (!error)
-			*flp = *my_before;
-		goto out;
+		lease = *my_before;
+		error = lease->fl_lmops->lm_change(my_before, arg, &dispose);
+		if (error)
+			goto out;
+		goto out_setup;
 	}
 
 	error = -EINVAL;
@@ -1619,43 +1667,61 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	smp_mb();
 	error = check_conflicting_open(dentry, arg);
 	if (error)
-		locks_unlink_lock(before);
+		goto out_unlink;
+
+out_setup:
+	if (lease->fl_lmops->lm_setup)
+		lease->fl_lmops->lm_setup(lease, priv);
 out:
+	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
+	if (!error && !my_before)
+		*flp = NULL;
 	return error;
+out_unlink:
+	locks_unlink_lock(before);
+	goto out;
 }
 
-static int generic_delete_lease(struct file *filp, struct file_lock **flp)
+static int generic_delete_lease(struct file *filp)
 {
+	int error = -EAGAIN;
 	struct file_lock *fl, **before;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	LIST_HEAD(dispose);
 
-	trace_generic_delete_lease(inode, *flp);
-
+	spin_lock(&inode->i_lock);
+	time_out_leases(inode, &dispose);
 	for (before = &inode->i_flock;
 			((fl = *before) != NULL) && IS_LEASE(fl);
 			before = &fl->fl_next) {
-		if (fl->fl_file != filp)
-			continue;
-		return (*flp)->fl_lmops->lm_change(before, F_UNLCK);
+		if (fl->fl_file == filp)
+			break;
 	}
-	return -EAGAIN;
+	trace_generic_delete_lease(inode, fl);
+	if (fl)
+		error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
+	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
+	return error;
 }
 
 /**
  *	generic_setlease	-	sets a lease on an open file
- *	@filp: file pointer
- *	@arg: type of lease to obtain
- *	@flp: input - file_lock to use, output - file_lock inserted
+ *	@filp:	file pointer
+ *	@arg:	type of lease to obtain
+ *	@flp:	input - file_lock to use, output - file_lock inserted
+ *	@priv:	private data for lm_setup (may be NULL if lm_setup
+ *		doesn't require it)
  *
  *	The (input) flp->fl_lmops->lm_break function is required
  *	by break_lease().
- *
- *	Called with inode->i_lock held.
  */
-int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
+int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
+			void **priv)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -1669,83 +1735,52 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 	if (error)
 		return error;
 
-	time_out_leases(inode);
-
-	BUG_ON(!(*flp)->fl_lmops->lm_break);
-
 	switch (arg) {
 	case F_UNLCK:
-		return generic_delete_lease(filp, flp);
+		return generic_delete_lease(filp);
 	case F_RDLCK:
 	case F_WRLCK:
-		return generic_add_lease(filp, arg, flp);
+		if (!(*flp)->fl_lmops->lm_break) {
+			WARN_ON_ONCE(1);
+			return -ENOLCK;
+		}
+		return generic_add_lease(filp, arg, flp, priv);
 	default:
 		return -EINVAL;
 	}
 }
 EXPORT_SYMBOL(generic_setlease);
 
-static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
-{
-	if (filp->f_op->setlease)
-		return filp->f_op->setlease(filp, arg, lease);
-	else
-		return generic_setlease(filp, arg, lease);
-}
-
 /**
- *	vfs_setlease        -       sets a lease on an open file
- *	@filp: file pointer
- *	@arg: type of lease to obtain
- *	@lease: file_lock to use
- *
- *	Call this to establish a lease on the file.
- *	The (*lease)->fl_lmops->lm_break operation must be set; if not,
- *	break_lease will oops!
- *
- *	This will call the filesystem's setlease file method, if
- *	defined.  Note that there is no getlease method; instead, the
- *	filesystem setlease method should call back to setlease() to
- *	add a lease to the inode's lease list, where fcntl_getlease() can
- *	find it.  Since fcntl_getlease() only reports whether the current
- *	task holds a lease, a cluster filesystem need only do this for
- *	leases held by processes on this node.
- *
- *	There is also no break_lease method; filesystems that
- *	handle their own leases should break leases themselves from the
- *	filesystem's open, create, and (on truncate) setattr methods.
- *
- *	Warning: the only current setlease methods exist only to disable
- *	leases in certain cases.  More vfs changes may be required to
- *	allow a full filesystem lease implementation.
+ * vfs_setlease        -       sets a lease on an open file
+ * @filp:	file pointer
+ * @arg:	type of lease to obtain
+ * @lease:	file_lock to use when adding a lease
+ * @priv:	private info for lm_setup when adding a lease (may be
+ * 		NULL if lm_setup doesn't require it)
+ *
+ * Call this to establish a lease on the file. The "lease" argument is not
+ * used for F_UNLCK requests and may be NULL. For commands that set or alter
+ * an existing lease, the (*lease)->fl_lmops->lm_break operation must be set;
+ * if not, this function will return -ENOLCK (and generate a scary-looking
+ * stack trace).
+ *
+ * The "priv" pointer is passed directly to the lm_setup function as-is. It
+ * may be NULL if the lm_setup operation doesn't require it.
  */
-
-int vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
+int
+vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 {
-	struct inode *inode = file_inode(filp);
-	int error;
-
-	spin_lock(&inode->i_lock);
-	error = __vfs_setlease(filp, arg, lease);
-	spin_unlock(&inode->i_lock);
-
-	return error;
+	if (filp->f_op->setlease)
+		return filp->f_op->setlease(filp, arg, lease, priv);
+	else
+		return generic_setlease(filp, arg, lease, priv);
 }
 EXPORT_SYMBOL_GPL(vfs_setlease);
 
-static int do_fcntl_delete_lease(struct file *filp)
-{
-	struct file_lock fl, *flp = &fl;
-
-	lease_init(filp, F_UNLCK, flp);
-
-	return vfs_setlease(filp, F_UNLCK, &flp);
-}
-
 static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 {
-	struct file_lock *fl, *ret;
-	struct inode *inode = file_inode(filp);
+	struct file_lock *fl;
 	struct fasync_struct *new;
 	int error;
 
@@ -1758,26 +1793,9 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 		locks_free_lock(fl);
 		return -ENOMEM;
 	}
-	ret = fl;
-	spin_lock(&inode->i_lock);
-	error = __vfs_setlease(filp, arg, &ret);
-	if (error)
-		goto out_unlock;
-	if (ret == fl)
-		fl = NULL;
-
-	/*
-	 * fasync_insert_entry() returns the old entry if any.
-	 * If there was no old entry, then it used 'new' and
-	 * inserted it into the fasync list. Clear new so that
-	 * we don't release it here.
-	 */
-	if (!fasync_insert_entry(fd, filp, &ret->fl_fasync, new))
-		new = NULL;
+	new->fa_fd = fd;
 
-	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
-out_unlock:
-	spin_unlock(&inode->i_lock);
+	error = vfs_setlease(filp, arg, &fl, (void **)&new);
 	if (fl)
 		locks_free_lock(fl);
 	if (new)
@@ -1798,7 +1816,7 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
 	if (arg == F_UNLCK)
-		return do_fcntl_delete_lease(filp);
+		return vfs_setlease(filp, F_UNLCK, NULL, NULL);
 	return do_fcntl_add_lease(fd, filp, arg);
 }
 
@@ -1867,9 +1885,12 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
 	    !(f.file->f_mode & (FMODE_READ|FMODE_WRITE)))
 		goto out_putf;
 
-	error = flock_make_lock(f.file, &lock, cmd);
-	if (error)
+	lock = flock_make_lock(f.file, cmd);
+	if (IS_ERR(lock)) {
+		error = PTR_ERR(lock);
 		goto out_putf;
+	}
+
 	if (can_sleep)
 		lock->fl_flags |= FL_SLEEP;
 
@@ -1981,11 +2002,13 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l)
 	if (file_lock.fl_type != F_UNLCK) {
 		error = posix_lock_to_flock(&flock, &file_lock);
 		if (error)
-			goto out;
+			goto rel_priv;
 	}
 	error = -EFAULT;
 	if (!copy_to_user(l, &flock, sizeof(flock)))
 		error = 0;
+rel_priv:
+	locks_release_private(&file_lock);
 out:
 	return error;
 }
@@ -2206,7 +2229,8 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
 	error = -EFAULT;
 	if (!copy_to_user(l, &flock, sizeof(flock)))
 		error = 0;
-  
+
+	locks_release_private(&file_lock);
 out:
 	return error;
 }
@@ -2369,7 +2393,7 @@ void locks_remove_file(struct file *filp)
 	while ((fl = *before) != NULL) {
 		if (fl->fl_file == filp) {
 			if (IS_LEASE(fl)) {
-				lease_modify(before, F_UNLCK);
+				lease_modify(before, F_UNLCK, &dispose);
 				continue;
 			}
 
@@ -2593,86 +2617,6 @@ static int __init proc_locks_init(void)
 module_init(proc_locks_init);
 #endif
 
-/**
- *	lock_may_read - checks that the region is free of locks
- *	@inode: the inode that is being read
- *	@start: the first byte to read
- *	@len: the number of bytes to read
- *
- *	Emulates Windows locking requirements.  Whole-file
- *	mandatory locks (share modes) can prohibit a read and
- *	byte-range POSIX locks can prohibit a read if they overlap.
- *
- *	N.B. this function is only ever called
- *	from knfsd and ownership of locks is never checked.
- */
-int lock_may_read(struct inode *inode, loff_t start, unsigned long len)
-{
-	struct file_lock *fl;
-	int result = 1;
-
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (IS_POSIX(fl)) {
-			if (fl->fl_type == F_RDLCK)
-				continue;
-			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
-				continue;
-		} else if (IS_FLOCK(fl)) {
-			if (!(fl->fl_type & LOCK_MAND))
-				continue;
-			if (fl->fl_type & LOCK_READ)
-				continue;
-		} else
-			continue;
-		result = 0;
-		break;
-	}
-	spin_unlock(&inode->i_lock);
-	return result;
-}
-
-EXPORT_SYMBOL(lock_may_read);
-
-/**
- *	lock_may_write - checks that the region is free of locks
- *	@inode: the inode that is being written
- *	@start: the first byte to write
- *	@len: the number of bytes to write
- *
- *	Emulates Windows locking requirements.  Whole-file
- *	mandatory locks (share modes) can prohibit a write and
- *	byte-range POSIX locks can prohibit a write if they overlap.
- *
- *	N.B. this function is only ever called
- *	from knfsd and ownership of locks is never checked.
- */
-int lock_may_write(struct inode *inode, loff_t start, unsigned long len)
-{
-	struct file_lock *fl;
-	int result = 1;
-
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (IS_POSIX(fl)) {
-			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
-				continue;
-		} else if (IS_FLOCK(fl)) {
-			if (!(fl->fl_type & LOCK_MAND))
-				continue;
-			if (fl->fl_type & LOCK_WRITE)
-				continue;
-		} else
-			continue;
-		result = 0;
-		break;
-	}
-	spin_unlock(&inode->i_lock);
-	return result;
-}
-
-EXPORT_SYMBOL(lock_may_write);
-
 static int __init filelock_init(void)
 {
 	int i;

fs/nfs/file.c

@@ -919,17 +919,6 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 }
 EXPORT_SYMBOL_GPL(nfs_flock);
 
-/*
- * There is no protocol support for leases, so we have no way to implement
- * them correctly in the face of opens by other clients.
- */
-int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
-{
-	dprintk("NFS: setlease(%pD2, arg=%ld)\n", file, arg);
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(nfs_setlease);
-
 const struct file_operations nfs_file_operations = {
 	.llseek		= nfs_file_llseek,
 	.read		= new_sync_read,
@@ -946,6 +935,6 @@ const struct file_operations nfs_file_operations = {
 	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
+	.setlease	= simple_nosetlease,
 };
 EXPORT_SYMBOL_GPL(nfs_file_operations);

fs/nfs/internal.h

@@ -339,7 +339,6 @@ int nfs_file_release(struct inode *, struct file *);
 int nfs_lock(struct file *, int, struct file_lock *);
 int nfs_flock(struct file *, int, struct file_lock *);
 int nfs_check_flags(int);
-int nfs_setlease(struct file *, long, struct file_lock **);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;

fs/nfs/nfs4file.c

@@ -131,5 +131,5 @@ const struct file_operations nfs4_file_operations = {
 	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
+	.setlease	= simple_nosetlease,
 };

fs/nfsd/nfs4state.c

@@ -218,6 +218,13 @@ static void nfsd4_put_session(struct nfsd4_session *ses)
 	spin_unlock(&nn->client_lock);
 }
 
+static inline struct nfs4_stateowner *
+nfs4_get_stateowner(struct nfs4_stateowner *sop)
+{
+	atomic_inc(&sop->so_count);
+	return sop;
+}
+
 static int
 same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner)
 {
@@ -237,10 +244,8 @@ find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
 			    so_strhash) {
 		if (!so->so_is_open_owner)
 			continue;
-		if (same_owner_str(so, &open->op_owner)) {
-			atomic_inc(&so->so_count);
-			return openowner(so);
-		}
+		if (same_owner_str(so, &open->op_owner))
+			return openowner(nfs4_get_stateowner(so));
 	}
 	return NULL;
 }
@@ -678,18 +683,14 @@ nfs4_put_stid(struct nfs4_stid *s)
 static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 {
 	struct file *filp = NULL;
-	struct file_lock *fl;
 
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_lease && atomic_dec_and_test(&fp->fi_delegees)) {
+	if (fp->fi_deleg_file && atomic_dec_and_test(&fp->fi_delegees))
 		swap(filp, fp->fi_deleg_file);
-		fl = fp->fi_lease;
-		fp->fi_lease = NULL;
-	}
 	spin_unlock(&fp->fi_lock);
 
 	if (filp) {
-		vfs_setlease(filp, F_UNLCK, &fl);
+		vfs_setlease(filp, F_UNLCK, NULL, NULL);
 		fput(filp);
 	}
 }
@@ -1655,7 +1656,7 @@ __destroy_client(struct nfs4_client *clp)
 	}
 	while (!list_empty(&clp->cl_openowners)) {
 		oo = list_entry(clp->cl_openowners.next, struct nfs4_openowner, oo_perclient);
-		atomic_inc(&oo->oo_owner.so_count);
+		nfs4_get_stateowner(&oo->oo_owner);
 		release_openowner(oo);
 	}
 	nfsd4_shutdown_callback(clp);
@@ -3067,8 +3068,8 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct knfsd_fh *fh)
 	INIT_LIST_HEAD(&fp->fi_stateids);
 	INIT_LIST_HEAD(&fp->fi_delegations);
 	fh_copy_shallow(&fp->fi_fhandle, fh);
+	fp->fi_deleg_file = NULL;
 	fp->fi_had_conflict = false;
-	fp->fi_lease = NULL;
 	fp->fi_share_deny = 0;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
@@ -3136,8 +3137,7 @@ static void nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
 {
 	if (!nfsd4_has_session(cstate)) {
 		mutex_lock(&so->so_replay.rp_mutex);
-		cstate->replay_owner = so;
-		atomic_inc(&so->so_count);
+		cstate->replay_owner = nfs4_get_stateowner(so);
 	}
 }
 
@@ -3236,8 +3236,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	atomic_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_OPEN_STID;
 	INIT_LIST_HEAD(&stp->st_locks);
-	stp->st_stateowner = &oo->oo_owner;
-	atomic_inc(&stp->st_stateowner->so_count);
+	stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner);
 	get_nfs4_file(fp);
 	stp->st_stid.sc_file = fp;
 	stp->st_access_bmap = 0;
@@ -3434,18 +3433,20 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 }
 
 /* Called from break_lease() with i_lock held. */
-static void nfsd_break_deleg_cb(struct file_lock *fl)
+static bool
+nfsd_break_deleg_cb(struct file_lock *fl)
 {
+	bool ret = false;
 	struct nfs4_file *fp = (struct nfs4_file *)fl->fl_owner;
 	struct nfs4_delegation *dp;
 
 	if (!fp) {
 		WARN(1, "(%p)->fl_owner NULL\n", fl);
-		return;
+		return ret;
 	}
 	if (fp->fi_had_conflict) {
 		WARN(1, "duplicate break on %p\n", fp);
-		return;
+		return ret;
 	}
 	/*
 	 * We don't want the locks code to timeout the lease for us;
@@ -3457,24 +3458,23 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
 	spin_lock(&fp->fi_lock);
 	fp->fi_had_conflict = true;
 	/*
-	 * If there are no delegations on the list, then we can't count on this
-	 * lease ever being cleaned up. Set the fl_break_time to jiffies so that
-	 * time_out_leases will do it ASAP. The fact that fi_had_conflict is now
-	 * true should keep any new delegations from being hashed.
+	 * If there are no delegations on the list, then return true
+	 * so that the lease code will go ahead and delete it.
 	 */
 	if (list_empty(&fp->fi_delegations))
-		fl->fl_break_time = jiffies;
+		ret = true;
 	else
 		list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
 			nfsd_break_one_deleg(dp);
 	spin_unlock(&fp->fi_lock);
+	return ret;
 }
 
-static
-int nfsd_change_deleg_cb(struct file_lock **onlist, int arg)
+static int
+nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose)
 {
 	if (arg & F_UNLCK)
-		return lease_modify(onlist, arg);
+		return lease_modify(onlist, arg, dispose);
 	else
 		return -EAGAIN;
 }
@@ -3820,7 +3820,7 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag)
 static int nfs4_setlease(struct nfs4_delegation *dp)
 {
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
-	struct file_lock *fl;
+	struct file_lock *fl, *ret;
 	struct file *filp;
 	int status = 0;
 
@@ -3834,11 +3834,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 		return -EBADF;
 	}
 	fl->fl_file = filp;
-	status = vfs_setlease(filp, fl->fl_type, &fl);
-	if (status) {
+	ret = fl;
+	status = vfs_setlease(filp, fl->fl_type, &fl, NULL);
+	if (fl)
 		locks_free_lock(fl);
+	if (status)
 		goto out_fput;
-	}
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
 	/* Did the lease get broken before we took the lock? */
@@ -3846,13 +3847,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	if (fp->fi_had_conflict)
 		goto out_unlock;
 	/* Race breaker */
-	if (fp->fi_lease) {
+	if (fp->fi_deleg_file) {
 		status = 0;
 		atomic_inc(&fp->fi_delegees);
 		hash_delegation_locked(dp, fp);
 		goto out_unlock;
 	}
-	fp->fi_lease = fl;
 	fp->fi_deleg_file = filp;
 	atomic_set(&fp->fi_delegees, 1);
 	hash_delegation_locked(dp, fp);
@@ -3885,7 +3885,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
 	dp->dl_stid.sc_file = fp;
-	if (!fp->fi_lease) {
+	if (!fp->fi_deleg_file) {
 		spin_unlock(&fp->fi_lock);
 		spin_unlock(&state_lock);
 		status = nfs4_setlease(dp);
@@ -4929,9 +4929,25 @@ nfs4_transform_lock_offset(struct file_lock *lock)
 		lock->fl_end = OFFSET_MAX;
 }
 
-/* Hack!: For now, we're defining this just so we can use a pointer to it
- * as a unique cookie to identify our (NFSv4's) posix locks. */
+static void nfsd4_fl_get_owner(struct file_lock *dst, struct file_lock *src)
+{
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)src->fl_owner;
+	dst->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lo->lo_owner));
+}
+
+static void nfsd4_fl_put_owner(struct file_lock *fl)
+{
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)fl->fl_owner;
+
+	if (lo) {
+		nfs4_put_stateowner(&lo->lo_owner);
+		fl->fl_owner = NULL;
+	}
+}
+
 static const struct lock_manager_operations nfsd_posix_mng_ops  = {
+	.lm_get_owner = nfsd4_fl_get_owner,
+	.lm_put_owner = nfsd4_fl_put_owner,
 };
 
 static inline void
@@ -4977,10 +4993,8 @@ find_lockowner_str_locked(clientid_t *clid, struct xdr_netobj *owner,
 			    so_strhash) {
 		if (so->so_is_open_owner)
 			continue;
-		if (!same_owner_str(so, owner))
-			continue;
-		atomic_inc(&so->so_count);
-		return lockowner(so);
+		if (same_owner_str(so, owner))
+			return lockowner(nfs4_get_stateowner(so));
 	}
 	return NULL;
 }
@@ -5059,8 +5073,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 
 	atomic_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_LOCK_STID;
-	stp->st_stateowner = &lo->lo_owner;
-	atomic_inc(&lo->lo_owner.so_count);
+	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
 	get_nfs4_file(fp);
 	stp->st_stid.sc_file = fp;
 	stp->st_stid.sc_free = nfs4_free_lock_stateid;
@@ -5299,7 +5312,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_openmode;
 		goto out;
 	}
-	file_lock->fl_owner = (fl_owner_t)lock_sop;
+
+	file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner));
 	file_lock->fl_pid = current->tgid;
 	file_lock->fl_file = filp;
 	file_lock->fl_flags = FL_POSIX;
@@ -5495,7 +5509,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 	file_lock->fl_type = F_UNLCK;
-	file_lock->fl_owner = (fl_owner_t)lockowner(stp->st_stateowner);
+	file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner));
 	file_lock->fl_pid = current->tgid;
 	file_lock->fl_file = filp;
 	file_lock->fl_flags = FL_POSIX;
@@ -5602,7 +5616,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 			}
 		}
 
-		atomic_inc(&sop->so_count);
+		nfs4_get_stateowner(sop);
 		break;
 	}
 	spin_unlock(&clp->cl_lock);

fs/nfsd/state.h

@@ -486,7 +486,6 @@ struct nfs4_file {
 	atomic_t		fi_access[2];
 	u32			fi_share_deny;
 	struct file		*fi_deleg_file;
-	struct file_lock	*fi_lease;
 	atomic_t		fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;

fs/notify/dnotify/dnotify.c

@@ -346,13 +346,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 		goto out;
 	}
 
-	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
-	if (error) {
-		/* if we added, we must shoot */
-		if (dn_mark == new_dn_mark)
-			destroy = 1;
-		goto out;
-	}
+	__f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
 
 	error = attach_dn(dn, dn_mark, id, fd, filp, mask);
 	/* !error means that we attached the dn to the dn_mark, so don't free it */

include/linux/fs.h

@@ -851,13 +851,7 @@ static inline struct file *get_file(struct file *f)
  */
 #define FILE_LOCK_DEFERRED 1
 
-/*
- * The POSIX file lock owner is determined by
- * the "struct files_struct" in the thread group
- * (or NULL for no owner - BSD locks).
- *
- * Lockd stuffs a "host" pointer into this.
- */
+/* legacy typedef, should eventually be removed */
 typedef void *fl_owner_t;
 
 struct file_lock_operations {
@@ -868,10 +862,13 @@ struct file_lock_operations {
 struct lock_manager_operations {
 	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
 	unsigned long (*lm_owner_key)(struct file_lock *);
+	void (*lm_get_owner)(struct file_lock *, struct file_lock *);
+	void (*lm_put_owner)(struct file_lock *);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
-	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
-	void (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock **, int);
+	int (*lm_grant)(struct file_lock *, int);
+	bool (*lm_break)(struct file_lock *);
+	int (*lm_change)(struct file_lock **, int, struct list_head *);
+	void (*lm_setup)(struct file_lock *, void **);
 };
 
 struct lock_manager {
@@ -966,7 +963,7 @@ void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
 extern struct file_lock * locks_alloc_lock(void);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
-extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
+extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
 extern void locks_remove_file(struct file *);
 extern void locks_release_private(struct file_lock *);
@@ -980,11 +977,9 @@ extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
 extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 extern void lease_get_mtime(struct inode *, struct timespec *time);
-extern int generic_setlease(struct file *, long, struct file_lock **);
-extern int vfs_setlease(struct file *, long, struct file_lock **);
-extern int lease_modify(struct file_lock **, int);
-extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
-extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
+extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
+extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
+extern int lease_modify(struct file_lock **, int, struct list_head *);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1013,12 +1008,12 @@ static inline int fcntl_setlk64(unsigned int fd, struct file *file,
 #endif
 static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
-	return 0;
+	return -EINVAL;
 }
 
 static inline int fcntl_getlease(struct file *filp)
 {
-	return 0;
+	return F_UNLCK;
 }
 
 static inline void locks_init_lock(struct file_lock *fl)
@@ -1026,7 +1021,7 @@ static inline void locks_init_lock(struct file_lock *fl)
 	return;
 }
 
-static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl)
+static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	return;
 }
@@ -1100,33 +1095,22 @@ static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
 }
 
 static inline int generic_setlease(struct file *filp, long arg,
-				    struct file_lock **flp)
+				    struct file_lock **flp, void **priv)
 {
 	return -EINVAL;
 }
 
 static inline int vfs_setlease(struct file *filp, long arg,
-			       struct file_lock **lease)
+			       struct file_lock **lease, void **priv)
 {
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock **before, int arg)
+static inline int lease_modify(struct file_lock **before, int arg,
+			       struct list_head *dispose)
 {
 	return -EINVAL;
 }
-
-static inline int lock_may_read(struct inode *inode, loff_t start,
-				unsigned long len)
-{
-	return 1;
-}
-
-static inline int lock_may_write(struct inode *inode, loff_t start,
-				 unsigned long len)
-{
-	return 1;
-}
 #endif /* !CONFIG_FILE_LOCKING */
 
 
@@ -1151,8 +1135,8 @@ extern void fasync_free(struct fasync_struct *);
 /* can be called from interrupts */
 extern void kill_fasync(struct fasync_struct **, int, int);
 
-extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
-extern int f_setown(struct file *filp, unsigned long arg, int force);
+extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
+extern void f_setown(struct file *filp, unsigned long arg, int force);
 extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
@@ -1506,7 +1490,7 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
-	int (*setlease)(struct file *, long, struct file_lock **);
+	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	int (*show_fdinfo)(struct seq_file *m, struct file *f);
@@ -2611,6 +2595,7 @@ extern int simple_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata);
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
+extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);

include/linux/lockd/lockd.h

@@ -178,7 +178,6 @@ struct nlm_block {
 	unsigned char		b_granted;	/* VFS granted lock */
 	struct nlm_file *	b_file;		/* file in question */
 	struct cache_req *	b_cache_req;	/* deferred request handling */
-	struct file_lock *	b_fl;		/* set for GETLK */
 	struct cache_deferred_req * b_deferred_req;
 	unsigned int		b_flags;	/* block flags */
 #define B_QUEUED		1	/* lock queued */

include/linux/security.h

@@ -1559,7 +1559,7 @@ struct security_operations {
 	int (*file_lock) (struct file *file, unsigned int cmd);
 	int (*file_fcntl) (struct file *file, unsigned int cmd,
 			   unsigned long arg);
-	int (*file_set_fowner) (struct file *file);
+	void (*file_set_fowner) (struct file *file);
 	int (*file_send_sigiotask) (struct task_struct *tsk,
 				    struct fown_struct *fown, int sig);
 	int (*file_receive) (struct file *file);
@@ -1834,7 +1834,7 @@ int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
 			   unsigned long prot);
 int security_file_lock(struct file *file, unsigned int cmd);
 int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
-int security_file_set_fowner(struct file *file);
+void security_file_set_fowner(struct file *file);
 int security_file_send_sigiotask(struct task_struct *tsk,
 				 struct fown_struct *fown, int sig);
 int security_file_receive(struct file *file);
@@ -2312,9 +2312,9 @@ static inline int security_file_fcntl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
-static inline int security_file_set_fowner(struct file *file)
+static inline void security_file_set_fowner(struct file *file)
 {
-	return 0;
+	return;
 }
 
 static inline int security_file_send_sigiotask(struct task_struct *tsk,

include/trace/events/filelock.h

@@ -53,15 +53,15 @@ DECLARE_EVENT_CLASS(filelock_lease,
 	),
 
 	TP_fast_assign(
-		__entry->fl = fl;
+		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_next = fl->fl_next;
-		__entry->fl_owner = fl->fl_owner;
-		__entry->fl_flags = fl->fl_flags;
-		__entry->fl_type = fl->fl_type;
-		__entry->fl_break_time = fl->fl_break_time;
-		__entry->fl_downgrade_time = fl->fl_downgrade_time;
+		__entry->fl_next = fl ? fl->fl_next : NULL;
+		__entry->fl_owner = fl ? fl->fl_owner : NULL;
+		__entry->fl_flags = fl ? fl->fl_flags : 0;
+		__entry->fl_type = fl ? fl->fl_type : 0;
+		__entry->fl_break_time = fl ? fl->fl_break_time : 0;
+		__entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0;
 	),
 
 	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_next=0x%p fl_owner=0x%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",

net/socket.c

@@ -1065,7 +1065,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			err = -EFAULT;
 			if (get_user(pid, (int __user *)argp))
 				break;
-			err = f_setown(sock->file, pid, 1);
+			f_setown(sock->file, pid, 1);
+			err = 0;
 			break;
 		case FIOGETOWN:
 		case SIOCGPGRP:

security/capability.c

@@ -343,9 +343,9 @@ static int cap_file_fcntl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
-static int cap_file_set_fowner(struct file *file)
+static void cap_file_set_fowner(struct file *file)
 {
-	return 0;
+	return;
 }
 
 static int cap_file_send_sigiotask(struct task_struct *tsk,

security/security.c

@@ -775,9 +775,9 @@ int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 	return security_ops->file_fcntl(file, cmd, arg);
 }
 
-int security_file_set_fowner(struct file *file)
+void security_file_set_fowner(struct file *file)
 {
-	return security_ops->file_set_fowner(file);
+	security_ops->file_set_fowner(file);
 }
 
 int security_file_send_sigiotask(struct task_struct *tsk,

security/selinux/hooks.c

@@ -3346,14 +3346,12 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd,
 	return err;
 }
 
-static int selinux_file_set_fowner(struct file *file)
+static void selinux_file_set_fowner(struct file *file)
 {
 	struct file_security_struct *fsec;
 
 	fsec = file->f_security;
 	fsec->fown_sid = current_sid();
-
-	return 0;
 }
 
 static int selinux_file_send_sigiotask(struct task_struct *tsk,

security/smack/smack_lsm.c

@@ -1390,12 +1390,11 @@ static int smack_mmap_file(struct file *file,
  * Returns 0
  * Further research may be required on this one.
  */
-static int smack_file_set_fowner(struct file *file)
+static void smack_file_set_fowner(struct file *file)
 {
 	struct smack_known *skp = smk_of_current();
 
 	file->f_security = skp->smk_known;
-	return 0;
 }
 
 /**