Re: [PATCH] sched_ext: serialize concurrent cpu.max writers in scx_group_set_bandwidth()

Hello,

On 8/22/26 4:13 AM, Tejun Heo wrote:
> On Fri, Aug 21, 2026 at 07:35:19PM +0900, Changwoo Min wrote:
>> Concurrent writes to a cgroup's cpu.max are not serialized by the cgroup or
>> kernfs layer -- cgroup_file_write() calls cft->write without cgroup_mutex, and
>> kernfs only serializes per open file -- so two writers to the same cgroup
>> through separate open files can reach tg_set_bandwidth() concurrently.
>>
>> tg_set_cfs_bandwidth() serializes the CFS side under cfs_constraints_mutex,
>> but scx_group_set_bandwidth() runs afterwards with only
>> percpu_down_read(&scx_cgroup_ops_rwsem) held, a read lock, so it does not
>> serialize concurrent writers.
>>
>> The ops.cgroup_set_bandwidth() callback and the cached tg->scx.bw_* stores can
>> then interleave between writers:
>>
>>    CPU1 (writer A)                 CPU2 (writer B)
>>    scx_group_set_bandwidth()
>>      SCX_CALL_OP(...)  /* A */
>>                                    scx_group_set_bandwidth()
>>                                      SCX_CALL_OP(...)  /* B */
>>                                      tg->scx.bw_* = B
>>      tg->scx.bw_* = A
>>
>> The scheduler's cgroup_set_bandwidth() op is invoked out of order and the cached
>> state is left inconsistent with the last writer; the 64-bit bw_* stores can also
>> tear on 32-bit.
>>
>> Serialize the SCX-side update with a new scx_cgroup_set_bw_mutex held across the
>> callback and the stores, so each writer applies its update atomically and in one
>> order -- the SCX counterpart to cfs_constraints_mutex on the CFS side.
>>
>> Reported-by: Sashiko <[email protected]>
>> Link: https://lore.kernel.org/sched-ext/[email protected]/
>> Signed-off-by: Changwoo Min <[email protected]>
> 
> I think the following is a better way to resolve this:
> 
>    http://lkml.kernel.org/r/[email protected]

Thanks for pointing this out. I missed the Michal's patch. Will take a look.

Regards,
Changwoo Min