On Thu, Aug 9, 2018 at 1:52 AM, Vlastimil Babka <vbabka@xxxxxxx> wrote:
> In SLUB, prefetch_freepointer() is used when allocating an object from cache's
> freelist, to make sure the next object in the list is cache-hot, since it's
> probable it will be allocated soon.
>
> Commit 2482ddec670f ("mm: add SLUB free list pointer obfuscation") has
> unintentionally changed the prefetch in a way where the prefetch is turned to a
> real fetch, and only the next->next pointer is prefetched. In case there is not
> a stream of allocations that would benefit from prefetching, the extra real
> fetch might add a useless cache miss to the allocation. Restore the previous
> behavior.
>
> Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
> Cc: Kees Cook <keescook@xxxxxxxxxxxx>
> Cc: Daniel Micay <danielmicay@xxxxxxxxx>
> Cc: Eric Dumazet <edumazet@xxxxxxxxxx>
> Cc: Christoph Lameter <cl@xxxxxxxxx>
> Cc: Pekka Enberg <penberg@xxxxxxxxxx>
> Cc: David Rientjes <rientjes@xxxxxxxxxx>
> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
> ---
> While I don't expect this to be causing the bug at hand, it's worth fixing.
> For the bug it might mean that the page fault moves elsewhere.
>
> mm/slub.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/mm/slub.c b/mm/slub.c
> index 51258eff4178..ce2b9e5cea77 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -271,8 +271,7 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object)
>
> static void prefetch_freepointer(const struct kmem_cache *s, void *object)
> {
> - if (object)
> - prefetch(freelist_dereference(s, object + s->offset));
> + prefetch(object + s->offset);
Ah -- gotcha. I think I misunderstood the purpose here. You're not
prefetching what is being pointed at, you're literally prefetching
what is stored there. That wouldn't require dereferencing the freelist
pointer, no.
Thanks!
Acked-by: Kees Cook <keescook@xxxxxxxxxxxx>
> }
>
> static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
> --
> 2.18.0
>
--
Kees Cook
Pixel Security
