Hi Arek, > > RSA padding information could be a xform entity rather than part of > > crypto op, as it seems associated with hashing algorithm used for the > > entire crypto session, where this algorithm is used in message digest > > itself. Even in virtIO standard spec, this info is associated in the > > asymmetric session creation. Hence, moving this info from crypto op into > xform structure. > > With the current approach in with-session mode, we set the key in the PMD > only once and use it in different configurations. > In the case where padding is a session parameter, we need to have a session > for all padding variations, duplicating the private key occurrences in memory > for this reason only. >
Even as per VirtIO asymmetric spec (below), padding info is per session as in virtio_crypto_rsa_session_para. https://github.com/oasis-tcs/virtio-spec/blob/master/device-types/crypto/description.tex#L736 To support VirtIO asymmetric op, this would be required. Thanks, Gowrishankar
