On Sat, 2019-08-10 at 10:28 +0000, Guo Wei Lim wrote:
> Hi Johannes,
>
> Correct me if I am wrong.
> The problem is largely in net/mac80211/mesh_hwmp.c
> The macros
> #define PREQ_IE_ORIG_ADDR(x) (x + 7)
> #define PREP_IE_TARGET_ADDR(x) (x + 3)
>
> Almost guarantees the addresses will be odd when it hit the following
Oh, yeah, good point.
> if (ether_addr_equal(orig_addr, sdata->vif.addr)) {
>
> Results in unaligned memory access
Right.
> I have tested that replacing ether_addr_equal with
> ether_addr_equal_unaligned fixes the issue but this happens in many
> places as well as other functions like is_multicast_ether_addr(),
> is_broadcast_ether_addr() so it isn't the correct fix.
Unfortunately, I think it _is_ in fact the correct (and only possible)
fix, I can't think of anything other than making the code properly
handle unaligned addresses, as they do seem to happen here.
johannes
