Re: [PATCH v3 2/2] arm64: Turn on KPTI only on CPUs that need it

From: Will Deacon
Date: Mon Jan 22 2018 - 06:55:12 EST


On Mon, Jan 22, 2018 at 11:51:34AM +0000, Ard Biesheuvel wrote:
> On 22 January 2018 at 11:41, Will Deacon <will.deacon@xxxxxxx> wrote:
> > On Fri, Jan 19, 2018 at 04:22:48AM -0800, Jayachandran C wrote:
> >> Whitelist Broadcom Vulcan/Cavium ThunderX2 processors in
> >> unmap_kernel_at_el0(). These CPUs are not vulnerable to
> >> CVE-2017-5754 and do not need KPTI when KASLR is off.
> >>
> >> Signed-off-by: Jayachandran C <jnair@xxxxxxxxxxxxxxxxxx>
> >> ---
> >> arch/arm64/kernel/cpufeature.c | 7 +++++++
> >> 1 file changed, 7 insertions(+)
> >>
> >> diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
> >> index 647d44b..fb698ca 100644
> >> --- a/arch/arm64/kernel/cpufeature.c
> >> +++ b/arch/arm64/kernel/cpufeature.c
> >> @@ -866,6 +866,13 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
> >> if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
> >> return true;
> >>
> >> + /* Don't force KPTI for CPUs that are not vulnerable */
> >> + switch (read_cpuid_id() & MIDR_CPU_MODEL_MASK) {
> >> + case MIDR_CAVIUM_THUNDERX2:
> >> + case MIDR_BRCM_VULCAN:
> >> + return false;
> >> + }
> >> +
> >> /* Defer to CPU feature registers */
> >> return !cpuid_feature_extract_unsigned_field(pfr0,
> >> ID_AA64PFR0_CSV3_SHIFT);
> >
> > We'll need to re-jig this to work properly with big/little because this is
> > only called once, but that's ok for now:
> >
> > Acked-by: Will Deacon <will.deacon@xxxxxxx>
> >
> > Suzuki has a series reworking much of the cpufeatures code so that we can
> > do this properly for 4.17.
> >
>
> If we start adding opt outs here, we should at least include A53, and
> probably replace
>
> >> if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
> >> return true;
>
> with
>
> >> if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0)
> >> return true;
>
> so that adding 'nokaslr' to the command line also disables KPTI.

Yup, I was going to do this once we have the new cpufeatures code from
Suzuki and can safely whitelist cores that can appear in big/little
configurations.

Will