fanotify: allow userspace to override max marks

Some fanotify groups, especially those like AV scanners, will need to place
lots of marks, particularly ignore marks.  Since ignore marks do not pin
inodes in cache and are cleared if the inode is removed from core (usually
under memory pressure) we expose an interface for listeners, with
CAP_SYS_ADMIN, to override the maximum number of marks and be allowed to
set and 'unlimited' number of marks.  Programs which make use of this
feature will be able to OOM a machine.

Signed-off-by: Eric Paris <eparis@redhat.com>

fs/notify/fanotify/fanotify_user.c

@@ -707,7 +707,14 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS;
 	}
 
-	group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
+	if (flags & FAN_UNLIMITED_MARKS) {
+		fd = -EPERM;
+		if (!capable(CAP_SYS_ADMIN))
+			goto out_put_group;
+		group->fanotify_data.max_marks = UINT_MAX;
+	} else {
+		group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
+	}
 
 	fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
 	if (fd < 0)

include/linux/fanotify.h

@@ -32,9 +32,11 @@
 				 FAN_CLASS_PRE_CONTENT)
 
 #define FAN_UNLIMITED_QUEUE	0x00000010
+#define FAN_UNLIMITED_MARKS	0x00000020
 
 #define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK | \
-				 FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE)
+				 FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\
+				 FAN_UNLIMITED_MARKS)
 
 /* flags used for fanotify_modify_mark() */
 #define FAN_MARK_ADD		0x00000001