> > Ok, so this is where the host PT is disabled. > > > > So, my recommendation for this patchset is: we need to address the > > fact that we are disabling host PT without telling the host. We need > > to either stop doing it or inform the host. I don't think there need > > to be any more versions of this patchset until this issue is addressed. > > If you don't want that effect, do not enable host-guest mode. The default is "off" in fact. > > I agree that it would be better to inform the host, but I think it's acceptable to proceed with these patches since the mode is strictly > opt in (kvm_intel.pt_mode=1). Perfect is the enemy of good, and I'd like to get the "boring" code in first. > > Luwei, can you document this in patch 4 as requested by Alexander? > Sorry for a delay reply due to holiday of PRC. I will add more detail description in the patch of Intel PT virtualization mode. Thanks, Luwei Kang
