Re: [PATCH v2 4/8] x86/pti: Do not enable PTI on fixed Intel processors

[Borislav Petkov]

On Sun, Jan 21, 2018 at 09:49:05AM +0000, David Woodhouse wrote:
> When they advertise the IA32_ARCH_CAPABILITIES MSR and it has the RDCL_NO
> bit set, they don't need KPTI either.
> 
> Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
> ---
>  arch/x86/kernel/cpu/common.c | 9 +++++++--
>  1 file changed, 7 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
> index e5d66e9..80572ae 100644
> --- a/arch/x86/kernel/cpu/common.c
> +++ b/arch/x86/kernel/cpu/common.c
> @@ -900,8 +900,13 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
>  
>  	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
>  
> -	if (c->x86_vendor != X86_VENDOR_AMD)
> -		setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
> +	if (c->x86_vendor != X86_VENDOR_AMD) {
> +		unsigned long ia32_cap = 0;

WARNING: Missing a blank line after declarations
#36: FILE: arch/x86/kernel/cpu/common.c:905:
+               unsigned long ia32_cap = 0;
+               if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))

Yap, that thing seldom is right but this time it makes some sense.

Also,

	unsigned long long ia32_cap = 0;

for 32-bit.

-- 
Regards/Gruss,
    Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.