[PATCH] doc: announce cryptodev changes to offload RSA in VirtIO

[Kusztal, ArkadiuszX]

> -----Original Message-----
> From: Thomas Monjalon <thomas at monjalon.net>
> Sent: Wednesday, July 31, 2024 4:27 PM
> To: Gowrishankar Muthukrishnan <gmuthukrishn at marvell.com>
> Cc: dev at dpdk.org; Kusztal, ArkadiuszX <arkadiuszx.kusztal at intel.com>;
> dev at dpdk.org; Anoob Joseph <anoobj at marvell.com>; Richardson, Bruce
> <bruce.richardson at intel.com>; ciara.power at intel.com; Jerin Jacob
> <jerinj at marvell.com>; fanzhang.oss at gmail.com; Ji, Kai <kai.ji at intel.com>;
> jack.bond-preston at foss.arm.com; Marchand, David
> <david.marchand at redhat.com>; hemant.agrawal at nxp.com; De Lara Guarch,
> Pablo <pablo.de.lara.guarch at intel.com>; Trahe, Fiona
> <fiona.trahe at intel.com>; Doherty, Declan <declan.doherty at intel.com>;
> matan at nvidia.com; ruifeng.wang at arm.com; Gujjar, Abhinandan S
> <abhinandan.gujjar at intel.com>; maxime.coquelin at redhat.com;
> chenbox at nvidia.com; sunilprakashrao.uttarwar at amd.com;
> andrew.boyer at amd.com; ajit.khaparde at broadcom.com;
> raveendra.padasalagi at broadcom.com; vikas.gupta at broadcom.com;
> zhangfei.gao at linaro.org; g.singh at nxp.com; jianjay.zhou at huawei.com; Daly,
> Lee <lee.daly at intel.com>
> Subject: Re: [PATCH] doc: announce cryptodev changes to offload RSA in VirtIO
> 
> I'm not sure why we don't have a consensus on an idea proposed as RFC in
> September 2023.
> 
> Because there is not enough involvement outside of the Marvell team, I will
> keep a vague announce for the first item:
> 
> cryptodev: Some changes may happen to manage RSA padding for virtio-crypto.
> 
> The second item is applied verbatim, thanks.
> 
> 
> 31/07/2024 14:51, Thomas Monjalon:
> > 30/07/2024 16:39, Gowrishankar Muthukrishnan:
> > > Hi,
> > > We need to fix padding info in DPDK as per VirtIO specification in order to
> support RSA in virtio devices. VirtIO-crypto specification and DPDK specification
> differs in the way padding is handled.
> > > With current DPDK & virtio specification, it is impossible to support RSA in
> virtio-crypto. If you think DPDK spec should not be modified, we will try to
> amend the virtIO spec to match DPDK, but since we do not know if the virtIO
> community would accept, can we merge the deprecation notice?
> >
> > There is a long list of Cc but I see no support outside of Marvell.
> >
> >
> >
> > > >>> +* cryptodev: The struct rte_crypto_rsa_padding will be moved
> > > >>> +from
> > > >>> +  rte_crypto_rsa_op_param struct to rte_crypto_rsa_xform
> > > >>> +struct,
> > > >>> +  breaking ABI. The new location is recommended to comply with
> > > >>> +  virtio-crypto specification. Applications and drivers using
> > > >>> +  this struct will be updated.
> > > >>> +
> > >
> > >
> > > >> The problem here, I see is that there is one private key but multiple
> combinations of padding.
> > > >> Therefore, for every padding variation, we need to copy the same private
> key anew, duplicating it in memory.
> > > >> The only reason for me to keep a session-like struct in asymmetric crypto
> was exactly this.
> > > >
> > > > Each padding scheme in RSA has its own pros and cons (in terms of
> implementations as well).
> > > > When we share the same private key for Sign (and its public key in
> > > > case of Encryption) between multiple crypto ops (varying by
> > > > padding schemes among cops), a vulnerable attack against one
> > > > scheme could potentially open door to used private key in the session and
> hence take advantage on other crypto operations.
> > > >
> > > > I think, this could be one reason for why VirtIO spec mandates padding info
> as session parameter.
> > > > Hence, more than duplicating in memory, private and public keys
> > > > are secured and in catastrophe, only that session could be destroyed.

Hi Gowrishankar,

Sorry for the delayed response.

I do not have any particular security issues in mind here, and if PMD need to copy keys internally, for alignment or padding purposes, redundancy problems can be overcome. My concern was, that it is the more natural way of handling the API; we have one key, multiple padding schemes, so we reflect this logic in the API.

Both options are widely used; libcrypto, for example is setting padding within session, other languages like Go, Rust are setting it as an argument to the method of the key struct.

If this is that problematic with VirtIO compatibility, I say this change is okay.

> > >
> > >
> > > >>> +* cryptodev: The rte_crypto_rsa_xform struct member to hold
> > > >>> +private key
> > > >>> +  in either exponent or quintuple format is changed from union
> > > >>> +to struct
> > > >>> +  data type. This change is to support ASN.1 syntax (RFC 3447 Appendix
> A.1.2).
> > > >>> +  This change will not break existing applications.
> > > > >
> > > > > This one I agree. RFC 8017 obsoletes RFC 3447.
> 
>