Re: [PATCH] x86: suppress KMSAN reports in arch_within_stack_frames()

[Alexander Potapenko]

On Mon, Nov 21, 2022 at 11:23 AM Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
>
> On Fri, Nov 18, 2022 at 06:23:05PM +0100, Alexander Potapenko wrote:
> > arch_within_stack_frames() performs stack walking and may confuse
> > KMSAN by stepping on stale shadow values. To prevent false positive
> > reports, disable KMSAN checks in this function.
> >
> > This fixes KMSAN's interoperability with CONFIG_HARDENED_USERCOPY.
> >
> > Link: https://github.com/google/kmsan/issues/89
> > Link: https://lore.kernel.org/lkml/Y3b9AAEKp2Vr3e6O@sol.localdomain/
> > Cc: Eric Biggers <ebiggers@xxxxxxxxxx>
> > Signed-off-by: Alexander Potapenko <glider@xxxxxxxxxx>
> > ---
> >  arch/x86/include/asm/thread_info.h | 5 +++++
> >  1 file changed, 5 insertions(+)
> >
> > diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
> > index f0cb881c1d690..f1cccba52eb97 100644
> > --- a/arch/x86/include/asm/thread_info.h
> > +++ b/arch/x86/include/asm/thread_info.h
> > @@ -163,7 +163,12 @@ struct thread_info {
> >   *   GOOD_FRAME      if within a frame
> >   *   BAD_STACK       if placed across a frame boundary (or outside stack)
> >   *   NOT_STACK       unable to determine (no frame pointers, etc)
> > + *
> > + * This function reads pointers from the stack and dereferences them. The
> > + * pointers may not have their KMSAN shadow set up properly, which may result
> > + * in false positive reports. Disable instrumentation to avoid those.
> >   */
> > +__no_kmsan_checks
> >  static inline int arch_within_stack_frames(const void * const stack,
> >                                          const void * const stackend,
> >                                          const void *obj, unsigned long len)
>
> Seems OK; but now I'm confused as to the exact distinction between
> __no_sanitize_memory and __no_kmsan_checks.
>
> The comments there about seem to suggest __no_sanitize_memory ensures no
> instrumentation at all, and __no_kmsan_checks some instrumentation but
> doesn't actually check anything -- so what's left then?

__no_sanitize_memory prohibits all instrumentation whatsoever, whereas
__no_kmsan_checks adds instrumentation that suppresses potential false
positives around this function.

Quoting include/linux/compiler-clang.h:

/*
 * The __no_kmsan_checks attribute ensures that a function does not produce
 * false positive reports by:
 *  - initializing all local variables and memory stores in this function;
 *  - skipping all shadow checks;
 *  - passing initialized arguments to this function's callees.
 */

Does this answer your question?

-- 
Alexander Potapenko
Software Engineer

Google Germany GmbH
Erika-Mann-Straße, 33
80636 München

Geschäftsführer: Paul Manicle, Liana Sebastian
Registergericht und -nummer: Hamburg, HRB 86891
Sitz der Gesellschaft: Hamburg