On Sat, Apr 25, 2009 at 02:10:19PM +0400, Evgeniy Polyakov wrote:
>
> What's the deal PCI drivers have with CPUs data comes from/to?
> They do not touch cache, just run DMA transfer and complete the request.
It's the same as NICs. To set things up and to reap the result
you need to synchronise.
On Sat, Apr 25, 2009 at 05:21:42PM +0800, Herbert Xu
(herb...@gondor.apana.org.au) wrote:
> > Why can't it be used by default for all crypto operations instead of
> > synchronous one?
>
> PCI-based drivers will not benefit from spreading the requests
> across CPUs. If anything they will suffer f
On Sat, Apr 25, 2009 at 12:38:49PM +0400, Evgeniy Polyakov wrote:
> Hi.
>
> On Fri, Apr 24, 2009 at 12:24:51PM +0200, Steffen Klassert
> (steffen.klass...@secunet.com) wrote:
> > This patchset adds the 'pcrypt' parallel crypto template. With this
> > template it
> > is possible to process the cr
Hi.
On Fri, Apr 24, 2009 at 12:24:51PM +0200, Steffen Klassert
(steffen.klass...@secunet.com) wrote:
> This patchset adds the 'pcrypt' parallel crypto template. With this template
> it
> is possible to process the crypto requests of a transform in parallel without
> getting request reorder. This
This patchset adds the 'pcrypt' parallel crypto template. With this template it
is possible to process the crypto requests of a transform in parallel without
getting request reorder. This is in particular interesting for IPsec.
The parallel crypto template is based on a generic parallelization/ser