On Tue, Sep 22, 2020 at 10:29:18AM +0200, Borislav Petkov wrote: > On Mon, Sep 21, 2020 at 12:17:00PM -0700, Sean Christopherson wrote: > > That was effectively my original suggestion as well, check for a stale cache > > and retry indefinitely. I capitulated because it did feel like I was being > > overly paranoid. I'm obviously ok going the retry indefinitely route :-). > > > > https://lkml.kernel.org/r/20180904163546.ga5...@linux.intel.com > > Right, so if EINIT is so expensive, why does it matter how many cyccles > WRMSR has? I.e., you don't really need to cache - you simply write the 4 > MSRs and you're done. Simple. > > As to "indefinitely" - caller can increment a counter which counts > how many times it returned SGX_INVALID_EINITTOKEN. I guess when it > reaches some too high number which should not be reached during normal > usage patterns, you can give up and issue a message to say that counter > reached max retries or so but other than that, you should be ok. That > thing is running interruptible in a loop anyway...
The way I see it after reading the thread is: 1. Start with simpler always-update-MSRs in this patch set. 2. If this ever causes a bottleneck, then we will fix it. > Thx. > > -- > Regards/Gruss, > Boris. > > https://people.kernel.org/tglx/notes-about-netiquette /Jarkko
