On 2021-08-27 15:38, Johannes Berg wrote:
On Fri, 2021-08-27 at 15:12 +0800, Wen Gong wrote:
On 2021-08-27 14:55, Johannes Berg wrote:
> On Fri, 2021-08-27 at 14:53 +0800, Wen Gong wrote:
> > >
> > > Well, there's an existing place in this function that uses
> > > cfg80211_find_ext_ie(), and various uses of ieee80211_bss_get_ie(), so
> > > it feels like if we're going to do the full parsing, we should switch
> > > all the existing "look up an element" to also use the parsed data
> > > instead.
>
> > ok.
> > so it ha 2 way to change, right?
> > 1.
> > change ieee802_11_parse_elems() to ieee80211_bss_get_ie()
>
> No why?
>
> I think we should make a first patch (that doesn't add TPE yet) that
> changes the function to ieee80211_parse_elems() and removes all the
> ieee80211_bss_get_ie() / cfg80211_find_ext_ie() calls in favour of just
> parsing once, and then looking at the elements there.
>
> Then your TPE patch becomes trivial since the elems are already there?
this patch still needed, because the lower driver need the info.
and this patch is save the info to "struct ieee80211_bss_conf
*bss_conf"
and
pass it to lower driver.
Of course, but you don't have to deal with parsing etc. in that patch
then.
yes.
then should I use "struct ieee802_11_elems elems = {0}" or "struct
ieee802_11_elems *elems = kzalloc(sizeof(*elems))"
in the parsing patch?
johannes
