Re: [Xen-devel] [PATCH] x86/EPT: flush cache when (potentially) limiting cachability

["Jan Beulich" <jbeulich@xxxxxxxx>]

>>>> "Jan Beulich" <jbeulich@xxxxxxxx> 05/30/14 8:28 AM >>>
>>>> "Liu, SongtaoX" <songtaox.liu@xxxxxxxxx> 05/30/14 4:07 AM >>>
>>The following patch leads nested (Xen on Xen ,KVM on Xen) L2 guest failed
>>to boot up with default EPT option "hap=1". L2 guest with "hap=0" still works.
>
>That's way to vague a problem description. In what way does it fail? Are there
>any relevant log messages anywhere? Without suitable detail, how am I (or is
>anyone else) supposed to help with this?

I should have added that the patch here solely adding cache flushes, it can't
reasonable have affected correctness. Hence unless it introduces a live lock of
some sort, the only possibility I see is that it uncovered some other previously
latent/hidden problem.

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel