Re: [Patch v4 01/22] sched/cache: Introduce infrastructure for cache-aware load balancing

["Chen, Yu C" <yu.c.chen@intel.com>]

On 4/15/2026 10:06 AM, Vern Hao wrote:
> Hi Tim,
> 

[ ... ]

>> +
>> +static inline
>> +void account_mm_sched(struct rq *rq, struct task_struct *p, s64 
>> delta_exec)
>> +{
>> +    struct sched_cache_time *pcpu_sched;
>> +    struct mm_struct *mm = p->mm;
>> +    unsigned long epoch;
>> +
>> +    if (!sched_cache_enabled())
>> +        return;
>> +
>> +    if (p->sched_class != &fair_sched_class)
>> +        return;
>> +    /*
>> +     * init_task, kthreads and user thread created
>> +     * by user_mode_thread() don't have mm.
>> +     */
>> +    if (!mm || !mm->sc_stat.pcpu_sched)
>> +        return;
>> +
>> +    pcpu_sched = per_cpu_ptr(p->mm->sc_stat.pcpu_sched, cpu_of(rq));
> 
> I do some test,  when i see many pids schedstat,  such as  cat proc/xxx/ 
> schedstat, there will cause a panic，maybe the 'p' is exit or others 
> reason,  sorry, i dont record these msg.  how about fix it like below.
> 
> pcpu_sched = per_cpu_ptr(mm->sc_stat.pcpu_sched, cpu_of(rq));
> 

Right, we have also received a report at
https://sashiko.dev/#/patchset/cover.1775065312.git.tim.c.chen%40linux.int.com
indicating that this issue needs to be fixed. We are working on it.
Thanks for the investigation.

thanks,
Chenyu