Re: [RFC 1/2] sched/fair: Fix load_balance() affinity redo path

[Jeffrey Hugo <jhugo@codeaurora.org>]

On 5/12/2017 2:47 PM, Peter Zijlstra wrote:
> On Fri, May 12, 2017 at 11:01:37AM -0600, Jeffrey Hugo wrote:
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index d711093..8f783ba 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -8219,8 +8219,19 @@ static int load_balance(int this_cpu, struct rq *this_rq,
>>   
>>   		/* All tasks on this runqueue were pinned by CPU affinity */
>>   		if (unlikely(env.flags & LBF_ALL_PINNED)) {
>> +			struct cpumask tmp;
> 
> You cannot have cpumask's on stack.

Well, we need a temp variable to store the intermediate values since the 
cpumask_* operations are somewhat limited, and require a "storage" 
parameter.

Do you have any suggestions to meet all of these requirements?

> 
>> +
>> +			/* Cpumask of all initially possible busiest cpus. */
>> +			cpumask_copy(&tmp, sched_domain_span(env.sd));
>> +			cpumask_clear_cpu(env.dst_cpu, &tmp);
> 
> You forgot to mask with cpu_active_mask.

cpus == cpu_active_mask, which we compare against below in just a few 
lines with the cpumask_intersects check.  So, no, I don't think we did 
forget to mask with cpu_active_mask.

> 
>> +
>>   			cpumask_clear_cpu(cpu_of(busiest), cpus);
>> -			if (!cpumask_empty(cpus)) {
>> +			/*
>> +			 * Go back to "redo" iff the load-balance cpumask
>> +			 * contains other potential busiest cpus for the
>> +			 * current sched domain.
>> +			 */
>> +			if (cpumask_intersects(cpus, &tmp)) {
>>   				env.loop = 0;
>>   				env.loop_break = sched_nr_migrate_break;
>>   				goto redo;


-- 
Jeffrey Hugo
Qualcomm Datacenter Technologies as an affiliate of Qualcomm 
Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the
Code Aurora Forum, a Linux Foundation Collaborative Project.