Hi Cristian,

On Wed, Jan 20, 2016 at 02:06:49PM +0000, Cristian Stoica wrote:
> > I really have no idea where you're heading at with this. But without further
> > context, it doesn't make any sense to me. If you have a functional
> > enhancement up your sleeve, I suggest submitting that along with this
> > change so I get an idea of what this is all about.
> > 
> Of course, these patches have some context.
> I'm playing with the code to speed up hashing operations.
> For now I want to see if there is a simple design that will make better use 
> of the Linux Crypto API which has both 
> 'init-update-final' and 'digest' operations.
> One objective is to have less ioctl calls and avoid unnecessary init-updates 
> where a single digest will do.

Ah, this explains things a bit.

> Currently I have a CIOCHASH ioctl that is identical to CIOCCRYPT but only for 
> hashing. In the current form it is faster for my test cases but needs some 
> clarifications on API.
> I can send some code to discuss design ideas if you are interested.

Sure, just send them as RFC to the list and we'll figure things out
together. :)

Thanks, Phil

Cryptodev-linux-devel mailing list

Reply via email to