Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

[Jan Beulich <jbeulich@xxxxxxxx>]

On 15.01.2020 13:31, Igor Druzhinin wrote:
> On 15/01/2020 12:25, Igor Druzhinin wrote:
>> On 15/01/2020 11:40, Jan Beulich wrote:
>>> On 15.01.2020 10:47, Roger Pau Monné wrote:
>>>> On Tue, Jan 14, 2020 at 07:36:21PM +0000, Igor Druzhinin wrote:
>>>>> --- a/xen/arch/x86/time.c
>>>>> +++ b/xen/arch/x86/time.c
>>>>> @@ -955,10 +955,16 @@ u64 stime2tsc(s_time_t stime)
>>>>>  
>>>>>  void cstate_restore_tsc(void)
>>>>>  {
>>>>> +    struct cpu_time *t = &this_cpu(cpu_time);
>>>>> +
>>>>>      if ( boot_cpu_has(X86_FEATURE_NONSTOP_TSC) )
>>>>>          return;
>>>>>  
>>>>> -    write_tsc(stime2tsc(read_platform_stime(NULL)));
>>>>> +    t->stamp.master_stime = read_platform_stime(NULL);
>>>>> +    t->stamp.local_tsc = stime2tsc(t->stamp.master_stime);
>>>>> +    t->stamp.local_stime = t->stamp.master_stime;
>>>>> +
>>>>> +    write_tsc(t->stamp.local_tsc);
>>>>
>>>> In order to avoid the TSC write (and the likely associated vmexit),
>>>> could you instead do:
>>>>
>>>> t->stamp.local_stime = t->stamp.master_stime = read_platform_stime(NULL);
>>>> t->stamp.local_tsc = rdtsc_ordered();
>>>>
>>>> I think it should achieve the same as it syncs the local TSC stamp and
>>>> times, would avoid the TSC write and slightly simplifies the logic.
>>>
>>> Wouldn't this result in guests possibly observing the TSC moving
>>> backwards?
>>
>> Yes, I think so. Would restoring from TSC stamp if it's higher than
>> platform time better you think?
>>
> 
> Ignore my reply. I was thinking you're asking whether the original code
> would do such a thing. Although I'm concerned if what you say actually
> applies to the original code as well. Would you think the existing logic
> handles it already?

I think the original code won't guarantee to backwards move at
all, but it also wouldn't produce large backwards jumps. It's
large ones I was mainly thinking of when replying to Roger.
But let me also reply back to him...

Jan

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel