Re: [PATCH v2 1/2] sched: Use user_cpus_ptr for saving user provided cpumask in sched_setaffinity()

[Waiman Long <longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>]

On 8/1/22 12:45, Will Deacon wrote:
> On Mon, Aug 01, 2022 at 11:41:23AM -0400, Waiman Long wrote:
>> The user_cpus_ptr field is added by commit b90ca8badbd1 ("sched:
>> Introduce task_struct::user_cpus_ptr to track requested affinity"). It
>> is currently used only by arm64 arch due to possible asymmetric cpu
>> setup. This patch extends its usage to save user provided cpumask when
>> sched_setaffinity() is called for all arches.
>>
>> To preserve the existing arm64 use case, a new cpus_affinity_set flag is
>> added to differentiate if user_cpus_ptr is set up by sched_setaffinity()
>> or by force_compatible_cpus_allowed_ptr(). user_cpus_ptr
>> set by sched_setaffinity() has priority and won't be
>> overwritten by force_compatible_cpus_allowed_ptr() or
>> relax_compatible_cpus_allowed_ptr().
>>
>> As a call to sched_setaffinity() will no longer clear user_cpus_ptr
>> but set it instead, the SCA_USER flag is no longer necessary and can
>> be removed.
>>
>> Signed-off-by: Waiman Long <longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>> ---
>>   include/linux/sched.h |  1 +
>>   kernel/sched/core.c   | 71 +++++++++++++++++++++++++++++++------------
>>   kernel/sched/sched.h  |  1 -
>>   3 files changed, 52 insertions(+), 21 deletions(-)
>>
>> diff --git a/include/linux/sched.h b/include/linux/sched.h
>> index c46f3a63b758..60ae022fa842 100644
>> --- a/include/linux/sched.h
>> +++ b/include/linux/sched.h
>> @@ -815,6 +815,7 @@ struct task_struct {
>>   
>>   	unsigned int			policy;
>>   	int				nr_cpus_allowed;
>> +	int				cpus_affinity_set;
>>   	const cpumask_t			*cpus_ptr;
>>   	cpumask_t			*user_cpus_ptr;
>>   	cpumask_t			cpus_mask;
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index da0bf6fe9ecd..7757828c7422 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -2607,6 +2607,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
>>   		return -ENOMEM;
>>   
>>   	cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
>> +	dst->cpus_affinity_set = src->cpus_affinity_set;
> I haven't been through this thorougly, but it looks a bit suspicious to me
> to inherit this field directly across fork(). If a 64-bit task with this
> flag set forks and then exec's a 32-bit program, arm64 will be in trouble if
> we're not able to override the affinity forcefully.

I believe you can still override the affinity. What is in user_cpus_ptr 
is not the actual affinity which is in cpus_mask. It is just what the 
users desire. Its value has be masked off by the current cpuset as well 
as what is allowed in task_cpu_possible_mask().

Cheers,
Longman