On Fri, May 5, 2017 at 1:23 AM, Daniel Gruss <[email protected]> wrote: > > On 04.05.2017 17:28, Thomas Garnier wrote: >> >> Please read the documentation on submitting patches [1] and coding style [2]. > > > I will have a closer look at that. > >> - How this approach prevent the hardware attacks you mentioned? You >> still have to keep a part of _text in the pagetable and an attacker >> could discover it no? (and deduce the kernel base address). > > > These parts are moved to a different section (.user_mapped) which is at a > possibly predictable location - the location of the randomized parts of the > kernel is independent of the location of .user_mapped. > The code/data footprint for .user_mapped is quite small, helping to reduce or > eliminate the attack surface... >
If I get it right, it means you can leak the per-cpu address instead of the kernel. Correct? That would be a problem because you can elevate privilege by overwriting per-cpu variables. Leaking this address means also defeating KASLR memory randomization [3] (cf paper in the commit). In theory you could put the code in the fixmap but you still have the per-cpu variables and changing that is hard. [3] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=021182e52fe01c1f7b126f97fd6ba048dc4234fd >> You also need to make it clear that btb attacks are still possible. > > > By just increasing the KASLR randomization range, btb attacks can be > mitigated (for free). Correct, I hope we can do that. > >> - What is the perf impact? > > > It will vary for different machines. We have promising results (<1%) for an > i7-6700K with representative benchmarks. However, for older systems or for > workloads with a lot of pressure on some TLB levels, the performance may be > much worse. I think including performance data in both cases would be useful. -- Thomas
