Re: [PATCH] sched/numa, mm: Skip page promotion if cpu pid is valid

["Huang, Ying" <ying.huang@linux.alibaba.com>]

"David Hildenbrand (Arm)" <david@kernel.org> writes:

> On 3/31/26 10:33, Huang, Ying wrote:
>> Hi, Donet,
>> 
>> Donet Tom <donettom@linux.ibm.com> writes:
>> 
>>> On 3/26/26 3:59 PM, David Hildenbrand (Arm) wrote:
>>>> Is that measurable? Should we at least have a Fixes: ?
>>>>
>>>> /*
>>>>   * When ...
>>>>
>>>> IIUC, as timestamp we use jiffies_to_msecs(). So, soon after bootup,
>>>> we would no longer get false positives for cpupid_valid().
>>>> I suppose overflows are not a problem, correct?
>>>
>>> Thank you, David, for guiding me in the right direction.
>>>
>>> I initially thought that overflows would not occur, and therefore
>>> cpupid_valid() would not produce false positives. However,
>>> after looking into it further, it appears that overflow can
>>> happen when storing the access time.
>>>
>>> The last_cpupid field is used to store the last access time.
>>> From the code, it appears that 21 bits are used for this
>>> (#define LAST_CPUPID_SHIFT (LAST__PID_SHIFT + LAST__CPU_SHIFT)).
>>>
>>> With 21 bits, the maximum value that can be stored is
>> 
>> It can be less than 21 bits, if CONFIG_NR_CPUS is small.
>> 
>> 	DEFINE(NR_CPUS_BITS, order_base_2(CONFIG_NR_CPUS));
>> 
>>> 2097151ms (35Hrs) . If the access time exceeds this
>>> range, it can overflow, which may lead to cpupid_valid()
>>> returning false positives.
>>>
>>> I think we need a reliable way to determine cpupid_valid() that
>>> does not produce false positives.
>> 
>> Yes.  IMHO, false positives is unavoidable.  So, the patch fixes a
>> temporal performance issue at the cost of a longstanding performance
>> issue.  Right?
>
>
> Could we set aside a bit to indicate "cpuid vs. time" ? We'd lose one
> bit for time, to we care?

Do we need one more bit for time and cpupid?  However, page flags are
precious resources.

> Would make it all easier to get ...

---
Best Regards,
Huang, Ying