[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <b2cdf533-08f0-487b-998f-0d436be923f5@intel.com>
Date: Thu, 24 Oct 2024 23:34:02 +0800
From: Xiaoyao Li <xiaoyao.li@...el.com>
To: "Nikunj A. Dadhania" <nikunj@....com>, linux-kernel@...r.kernel.org,
thomas.lendacky@....com, bp@...en8.de, x86@...nel.org, kvm@...r.kernel.org
Cc: mingo@...hat.com, tglx@...utronix.de, dave.hansen@...ux.intel.com,
pgonda@...gle.com, seanjc@...gle.com, pbonzini@...hat.com
Subject: Re: [PATCH v13 05/13] x86/sev: Prevent RDTSC/RDTSCP interception for
Secure TSC enabled guests
On 10/24/2024 4:44 PM, Nikunj A. Dadhania wrote:
>
>
> On 10/24/2024 1:26 PM, Xiaoyao Li wrote:
>> On 10/21/2024 1:51 PM, Nikunj A Dadhania wrote:
>>> The hypervisor should not be intercepting RDTSC/RDTSCP when Secure TSC is
>>> enabled. A #VC exception will be generated if the RDTSC/RDTSCP instructions
>>> are being intercepted. If this should occur and Secure TSC is enabled,
>>> terminate guest execution.
>>
>> There is another option to ignore the interception and just return back to
>> guest execution.
>
> That is not correct, RDTSC/RDTSCP should return the timestamp counter value
> computed using the GUEST_TSC_SCALE and GUEST_TSC_OFFSET part of VMSA.
Ah, I missed this. Yes, if ignore the interception, guest needs to do
TSC scale itself with GUEST_TSC_SCALE and GUEST_TSC_OFFSET to get the
correct TSC. It's complicating things while making not intercepting
RDTSC/RDTSP a hard requirement is much simple.
I think it's worth adding it as the justification.
>> I think it better to add some justification on why make it> fatal and terminate the guest is better than ignoring the interception.
>
> How about the below updated commit message:
>
> The hypervisor should not be intercepting RDTSC/RDTSCP when Secure TSC is
> enabled. A #VC exception will be generated if the RDTSC/RDTSCP instructions
> are being intercepted. If this should occur and Secure TSC is enabled,
> terminate guest execution as the guest cannot rely on the TSC value provided
> by the hypervisor.
>
> Regards
> Nikunj
>
Powered by blists - more mailing lists