locks: implement delegations

Implement NFSv4 delegations at the vfs level using the new FL_DELEG lock
type.

Note nfsd is the only delegation user and is only using read
delegations.  Warn on any attempt to set a write delegation for now.
We'll come back to that case later.

Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

fs/locks.c

@@ -1292,28 +1292,40 @@ static void time_out_leases(struct inode *inode)
 	}
 }
 
+static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
+{
+	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE))
+		return false;
+	return locks_conflict(breaker, lease);
+}
+
 /**
  *	__break_lease	-	revoke all outstanding leases on file
  *	@inode: the inode of the file to return
- *	@mode: the open mode (read or write)
+ *	@mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR:
+ *	    break all leases
+ *	@type: FL_LEASE: break leases and delegations; FL_DELEG: break
+ *	    only delegations
  *
  *	break_lease (inlined for speed) has checked there already is at least
  *	some kind of lock (maybe a lease) on this file.  Leases are broken on
  *	a call to open() or truncate().  This function can sleep unless you
  *	specified %O_NONBLOCK to your open().
  */
-int __break_lease(struct inode *inode, unsigned int mode)
+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;
 	unsigned long break_time;
 	int i_have_this_lease = 0;
+	bool lease_conflict = false;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
 		return PTR_ERR(new_fl);
+	new_fl->fl_flags = type;
 
 	spin_lock(&inode->i_lock);
 
@@ -1323,12 +1335,15 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	if ((flock == NULL) || !IS_LEASE(flock))
 		goto out;
 
-	if (!locks_conflict(flock, new_fl))
+	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
-		goto out;
+		if (leases_conflict(fl, new_fl)) {
-
+			lease_conflict = true;
-	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next)
 			if (fl->fl_owner == current->files)
 				i_have_this_lease = 1;
+		}
+	}
+	if (!lease_conflict)
+		goto out;
 
 	break_time = 0;
 	if (lease_break_time > 0) {
@@ -1338,6 +1353,8 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	}
 
 	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (!leases_conflict(fl, new_fl))
+			continue;
 		if (want_write) {
 			if (fl->fl_flags & FL_UNLOCK_PENDING)
 				continue;
@@ -1379,7 +1396,7 @@ int __break_lease(struct inode *inode, unsigned int mode)
 		 */
 		for (flock = inode->i_flock; flock && IS_LEASE(flock);
 				flock = flock->fl_next) {
-			if (locks_conflict(new_fl, flock))
+			if (leases_conflict(new_fl, flock))
 				goto restart;
 		}
 		error = 0;
@@ -1460,9 +1477,26 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	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;
 
 	lease = *flp;
+	/*
+	 * In the delegation case we need mutual exclusion with
+	 * a number of operations that take the i_mutex.  We trylock
+	 * because delegations are an optional optimization, and if
+	 * there's some chance of a conflict--we'd rather not
+	 * bother, maybe that's a sign this just isn't a good file to
+	 * hand out a delegation on.
+	 */
+	if (is_deleg && !mutex_trylock(&inode->i_mutex))
+		return -EAGAIN;
+
+	if (is_deleg && arg == F_WRLCK) {
+		/* Write delegations are not currently supported: */
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
 
 	error = -EAGAIN;
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
@@ -1514,9 +1548,10 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 		goto out;
 
 	locks_insert_lock(before, lease);
-	return 0;
+	error = 0;
-
 out:
+	if (is_deleg)
+		mutex_unlock(&inode->i_mutex);
 	return error;
 }
 

include/linux/fs.h

@@ -1022,7 +1022,7 @@ extern int vfs_test_lock(struct file *, struct file_lock *);
 extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
 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);
+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 **);
@@ -1131,7 +1131,7 @@ static inline int flock_lock_file_wait(struct file *filp,
 	return -ENOLCK;
 }
 
-static inline int __break_lease(struct inode *inode, unsigned int mode)
+static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	return 0;
 }
@@ -1961,9 +1961,17 @@ static inline int locks_verify_truncate(struct inode *inode,
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	if (inode->i_flock)
-		return __break_lease(inode, mode);
+		return __break_lease(inode, mode, FL_LEASE);
 	return 0;
 }
+
+static inline int break_deleg(struct inode *inode, unsigned int mode)
+{
+	if (inode->i_flock)
+		return __break_lease(inode, mode, FL_DELEG);
+	return 0;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct inode *inode)
 {
@@ -2003,6 +2011,10 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 	return 0;
 }
 
+static inline int break_deleg(struct inode *inode, unsigned int mode)
+{
+	return 0;
+}
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */