Re: [PATCH] perf: Fix race in perf_mmap_close function

[Jiri Olsa]

On Thu, Sep 10, 2020 at 10:48:02PM +0900, Namhyung Kim wrote:

SNIP

> >   _do_fork+0x83/0x3a0
> >   __do_sys_wait4+0x83/0x90
> >   __do_sys_clone+0x85/0xa0
> >   do_syscall_64+0x5b/0x1e0
> >   entry_SYSCALL_64_after_hwframe+0x44/0xa9
> >
> > Using atomic decrease and check instead of separated calls.
> > This fixes CVE-2020-14351.
> >
> > Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
> > ---
> >  kernel/events/core.c | 4 +---
> >  1 file changed, 1 insertion(+), 3 deletions(-)
> >
> > diff --git a/kernel/events/core.c b/kernel/events/core.c
> > index 7ed5248f0445..29313cc54d9e 100644
> > --- a/kernel/events/core.c
> > +++ b/kernel/events/core.c
> > @@ -5903,8 +5903,6 @@ static void perf_mmap_close(struct vm_area_struct *vma)
> >                 mutex_unlock(&event->mmap_mutex);
> >         }
> >
> > -       atomic_dec(&rb->mmap_count);
> > -
> >         if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
> >                 goto out_put;
> 
> But when it takes the goto, rb->mmap_count won't decrement anymore..

event->mmap_count is per event, so if we have have race in here,
2 threads can go through with each event->mmap_count reaching zero

jirka