Thank you very much for your information.
I'm looking forward to seeing your results.
Cheers,
Keisuke Mera
Herbert Xu wrote:
On Wed, Nov 02, 2005 at 01:35:05PM +0900, MERA Keisuke wrote:
Could you give some informations about these, or can I have some
materials or pointers (for example, a url of your git tree) ?
Maybe I can help your developments.
Here is the plan:
: 1) Add support for multiple implementations for the same algorithm.
:
: For example, this lets you have both aes/aes-i586/aes-via_padlock
: registered and the one with the highest priority will be used.
: The priority will be set by the module with an override option
: for the user.
:
: 2) Extend the interface between crypto API and the underlying
: implementations to use scatterlists.
:
: Wrappers will be provided to extend implementations with existing
: single-block interfaces to provide scatterlists. Essentially
: it'll be the same as the current scatterlist walking function,
: albeit executed conceptually at a lower layer.
:
: 3) Add support for (raw, as in no scheduler/fail-over) async
: implementations through the addition of a callback function
: to crypto_tfm and a callback data argument to the existing
: top-level crypto entry point functions (encrypt/decrypt/etc).
:
: 4) Implement implementation registration notification.
:
: 5) Implement at least one scheduler using the same scatterlist
: interface used by async drivers and software implementations.
:
: It'll work in the manner which I described previously. For
: this particular scheduler, there will be one instantiation
: that listens for the registration events of underlying
: implementations and then reconfigures itself appropriately.
: For example, it could simply utilise the hard-coded method
: used by OpenBSD.
We're still at step 1 at the moment I'm afraid. I did have a set
of patches before the release of 2.6.14 that did step 1. However,
I've now decided to replace them with a set that uses a flat name
space. That is, to find aes-i586 you only need to give the string
aes-i586 instead of aes-i586 in addition to the algorithm type
"aes".
Cheers,
-
To unsubscribe from this list: send the line "unsubscribe linux-crypto" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
