* Herbert Xu | 2008-03-11 21:32:38 [+0800]: >> The error recovery could get quite complex here, so maybe a BUG() statement >> isn't that bad at all or? > >OK it seems that the only one that can really fail here is Geode. >At this point I don't think we want to make such an intrusive change >just for the Geode. That's what I though :) >Perhaps a better solution for it would be to convert it to the >async interface and use polling from a kernel thread? How fast >is it anyway? Something like 1.7 MB/sec on dm-crypt if I remember correctly. It was faster than software. I thing there is no need for polling because the geode has an interrupt. >Cheers, Sebastian -- To unsubscribe from this list: send the line "unsubscribe linux-crypto" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
