On 8/18/20 7:05 AM, Herbert Xu wrote:
On Tue, Aug 18, 2020 at 06:56:12AM -0700, Ben Greear wrote:
Herbert, thanks for working on this. If I apply the patches you posted,
that is expected to provide wifi aes decryption speedup similar to what
the original patch I sent does? Or, are additional patches needed?
It depends on whether the wifi code uses the async ahash interface,
if not it probably won't make much of an impact at all.
I just checked and if the code you're using is net/mac80211/aes_cmac.c
then it's using shash so it won't really benefit from this. However,
there's no reason why mac80211 can't be converted over to async as
we did for IPsec.
I think converting it to async is beyond what I have time to work on
and not sure if it would be accepted upstream anyway.
Is there any easy way to use your work to make shash fast for aesni? I
basically just want it to perform as well as it used to with my patch.
Thanks,
Ben
--
Ben Greear <greearb@xxxxxxxxxxxxxxx>
Candela Technologies Inc http://www.candelatech.com
