More Linux Fixes/Cleanups Coming For AMD Inception/SRSO Mitigation Code
Earlier this month when the AMD Inception CPU vulnerability was disclosed the initial mitigation was merged to Linux kernel right away for what there is referred to as the Speculative Return Stack Overflow (SRSO). Within a day of that code being published there were already efforts to clean it up and merged last week for Linux 6.5-rc7 was that AMD Inception code cleaning. This week a new set of 22 patches were published for further improving the AMD Inception/SRSO mitigation code.
Linux kernel developer Josh Poimboeuf posted the set of 22 kernel patches to provide various fixes and clean-ups to the AMD Inception code beyond what's already been merged. Among the fixes are also adjusting the behavior when mitigations=off or spec_rstack_overflow=off as the two means of run-time disabling the mitigation on affected processors.
Arguably the most prominent change with this patch series is adding KVM support so that the IBPB_BRTYPE and SBPB CPUID bits are propagated to the guest virtual machine(s).
See this patch series for the latest AMD Inception fixes and clean-ups. None of the patches this round appear to have any impact on the overall performance of the mitigation: see my recent tests of the impact in Benchmarking The Performance Impact To AMD Inception Mitigations.
Linux kernel developer Josh Poimboeuf posted the set of 22 kernel patches to provide various fixes and clean-ups to the AMD Inception code beyond what's already been merged. Among the fixes are also adjusting the behavior when mitigations=off or spec_rstack_overflow=off as the two means of run-time disabling the mitigation on affected processors.
Arguably the most prominent change with this patch series is adding KVM support so that the IBPB_BRTYPE and SBPB CPUID bits are propagated to the guest virtual machine(s).
See this patch series for the latest AMD Inception fixes and clean-ups. None of the patches this round appear to have any impact on the overall performance of the mitigation: see my recent tests of the impact in Benchmarking The Performance Impact To AMD Inception Mitigations.
6 Comments