Messages in this thread | | | Date | Wed, 29 May 2013 09:44:33 +0200 | From | Peter Zijlstra <> | Subject | Re: OOPS in perf_mmap_close() |
| |
On Tue, May 28, 2013 at 02:22:11PM -0400, Vince Weaver wrote: > On Tue, 28 May 2013, Vince Weaver wrote: > > > It looks like this is already in tip, but I can confirm that this > > patch seems to fix things on my machine and holds up against longer > > fuzzing runs. > > OK, I take it back. Even with the new patch applied, my fuzzer can still > make the kernel leak user->locked_vm > > I assume that the locked_vm value should go back to 0 once a process that > has a bunch of mmap'd perf_events opened exits?
Yep.
> I admit this is sort of an obscure corner case, but it does mean that a > user can leak user->locked_vm to the point that "perf record" no longer > works.
Hurm.. I don't suppose you have an easy reproducer handy eh? I'll go stare at it. At least the current state is better than before, but clearly we're not quite there yet.
| |