Re:CPU Usage Differences After Applying Meltdown Patch at Ep...
by sigmar on Saturday January 06, 2018 @01:12PM
(#16086599)
>There's no point adding another padlock to the outside wall of Fort Knox.
Strongly disagree. No single defense measure is infallible and defense in depth has proven one of the most important topics in computer security.
Re:CPU Usage Differences After Applying Meltdown Patch at Ep...
by pixl97 on Saturday January 06, 2018 @08:56PM
(#16088631)
In the past if you had a RCE that only got user level access and that user was very locked down there was only a limited amount of damage they could have done. Now with meltdown, every RCE is a full information loss at system level exploit.
I also think that we need more information before we really see the long-term performance impact here. First, the patches will likely be optimized over time. Second, I am not sure that PTI needs to be run within guest kernels if the host already has the mitigation (effectively creating a double-hit from PTI in both the guest and host kernel), or that even if PTI is needed in both kernels now, that it will be needed long-term. We also need to figure out what type of Spectre mitigations need to be performed within the guest if the host system has the new microcode that selectively disables branch prediction.
The short answer is that it's going to take another 4-6 weeks before even the kernel devs have a firm grasp of what's useful/necessary to mitigate this and for things to settle into place, as Greg K-H blogged about earlier. At that point, we should have a more realistic perspective on the long-term performance impact.