> > This adds an opt-in flag to the perf_event_open() syscall to retain > > sibling events after their file descriptors are closed. In this case, the > > actual events will be closed with the group leader. > > So having the 1:1 relation with filedesc imposes a resource limit on > userspace. > > This patch breaks that and enables a user to basically DoS the system by > creating unbound events.
The idea was to account the events in the locked memory allocation too. Not sure that made it into the patch though. It has a minor issue that it might break some existing setups that rely on the mmap fitting exactly into the mmap allocation, but that could be solved by allowing a little slack, since the existing setups likely don't have that many events. There's also a secondary issue of DoS the kernel by creating very long lists to iterate, but I suppose this is already quite possible, so probably not a new issue. -Andi
