linux-kernel - Re: [PATCH v16 8/8] x86/smpboot: Allow parallel bringup for SEV-ES

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <2c3dd773-31ca-d4b1-78a2-b39f3785c7c5@amd.com>
Date:   Thu, 23 Mar 2023 08:16:49 -0500
From:   Tom Lendacky <thomas.lendacky@....com>
To:     Borislav Petkov <bp@...en8.de>,
        Usama Arif <usama.arif@...edance.com>
Cc:     dwmw2@...radead.org, tglx@...utronix.de, kim.phillips@....com,
        brgerst@...il.com, piotrgorski@...hyos.org,
        oleksandr@...alenko.name, arjan@...ux.intel.com, mingo@...hat.com,
        dave.hansen@...ux.intel.com, hpa@...or.com, x86@...nel.org,
        pbonzini@...hat.com, paulmck@...nel.org,
        linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
        rcu@...r.kernel.org, mimoja@...oja.de, hewenliang4@...wei.com,
        seanjc@...gle.com, pmenzel@...gen.mpg.de, fam.zheng@...edance.com,
        punit.agrawal@...edance.com, simon.evans@...edance.com,
        liangma@...ngbit.com, gpiccoli@...lia.com,
        David Woodhouse <dwmw@...zon.co.uk>,
        Sabin Rapan <sabrapan@...zon.com>
Subject: Re: [PATCH v16 8/8] x86/smpboot: Allow parallel bringup for SEV-ES

On 3/22/23 17:47, Borislav Petkov wrote:
> On Tue, Mar 21, 2023 at 07:40:08PM +0000, Usama Arif wrote:
>> From: David Woodhouse <dwmw@...zon.co.uk>
>>
>> Enable parallel bringup for SEV-ES guests. The APs can't actually
>> execute the CPUID instruction directly during early startup, but they
>> can make the GHCB call directly instead, just as the VC trap handler
>> would do.
>>
>> Thanks to Sabin for talking me through the way this works.
>>
>> Suggested-by: Sabin Rapan <sabrapan@...zon.com>
>> Signed-off-by: David Woodhouse <dwmw@...zon.co.uk>
>> Signed-off-by: Usama Arif <usama.arif@...edance.com>
>> Reviewed-by: Tom Lendacky <thomas.lendacky@....com>
>> ---
>>   arch/x86/coco/core.c              |  5 ++++
>>   arch/x86/include/asm/coco.h       |  1 +
>>   arch/x86/include/asm/sev-common.h |  3 +++
>>   arch/x86/include/asm/smp.h        |  5 +++-
>>   arch/x86/kernel/head_64.S         | 30 ++++++++++++++++++++++++
>>   arch/x86/kernel/smpboot.c         | 39 ++++++++++++++++++++++++++-----
>>   6 files changed, 76 insertions(+), 7 deletions(-)
> 
> How's the below (totally untested yet but it builds) instead after
> applying those two prerequisites:
> 
> https://lore.kernel.org/r/20230318115634.9392-1-bp@alien8.de
> 
> ---

...

> diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
> index ce371f62167b..96ff63cb5622 100644
> --- a/arch/x86/kernel/sev.c
> +++ b/arch/x86/kernel/sev.c
> @@ -1142,6 +1142,24 @@ void snp_set_wakeup_secondary_cpu(void)
>   	apic->wakeup_secondary_cpu = wakeup_cpu_via_vmgexit;
>   }
>   
> +u32 sev_get_cpuid_0b(void)

Maybe call this sev_early_get_cpuid_0b() or such to imply that the MSR 
protocol is being used and only retrieving / returning edx.

Also, since it is a function now and can be used at any point, the current 
GHCB MSR should be saved on entry and restored on exit.

Thanks,
Tom

> +{
> +	u32 eax, edx;
> +
> +	/* Request CPUID 0xB_EDX through GHCB protocol */
> +	native_wrmsr(MSR_AMD64_SEV_ES_GHCB,
> +		     (GHCB_CPUID_REQ_EDX << 30) | GHCB_MSR_CPUID_REQ,
> +		     0xb);
> +	VMGEXIT();
> +
> +	native_rdmsr(MSR_AMD64_SEV_ES_GHCB, eax, edx);
> +
> +	if ((eax & GHCB_MSR_INFO_MASK) == GHCB_MSR_CPUID_RESP)
> +		return edx;
> +
> +	return 0;
> +}
> +
>   int __init sev_es_setup_ap_jump_table(struct real_mode_header *rmh)
>   {
>   	u16 startup_cs, startup_ip;