Re: [PATCH v5 02/12] x86/retpoline: Add initial retpoline support

[Andrew Cooper]

On 06/01/18 11:49, David Woodhouse wrote:
> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
> index 372ba3f..40e6e54 100644
> --- a/arch/x86/kernel/cpu/common.c
> +++ b/arch/x86/kernel/cpu/common.c
> @@ -904,6 +904,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
>  
>  	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
>  	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
> +#ifdef CONFIG_RETPOLINE
> +	setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
> +	if (c->x86_vendor == X86_VENDOR_AMD)
> +		setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);

This isn't safe. It needs to be dependant on finding that LFENCEs are
actually dispatch serialising.

In particular, when virtualised, you'll most likely be saddled with the
hypervisors choice of setting, in which case you need to use retpoline
as a fallback.

~Andrew

> +#endif
>  
>  	fpu__init_system(c);
>  
>