Introduce a new migration type, migrate_llc_task, to support
cache-aware load balancing.

After identifying the busiest sched_group (having the most tasks
preferring the destination LLC), mark migrations with this type.
During load balancing, each runqueue in the busiest sched_group is
examined, and the runqueue with the highest number of tasks preferring
the destination CPU is selected as the busiest runqueue.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---

Notes:
    v1->v2: Remove unnecessary cpus_share_cache() check in
            sched_balance_find_src_rq() (K Prateek Nayak)

 kernel/sched/fair.c | 32 +++++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index db555c11b5b8..529adf342ce0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9547,7 +9547,8 @@ enum migration_type {
 	migrate_load = 0,
 	migrate_util,
 	migrate_task,
-	migrate_misfit
+	migrate_misfit,
+	migrate_llc_task
 };
 
 #define LBF_ALL_PINNED	0x01
@@ -10134,6 +10135,10 @@ static int detach_tasks(struct lb_env *env)
 			env->imbalance -= util;
 			break;
 
+		case migrate_llc_task:
+			env->imbalance--;
+			break;
+
 		case migrate_task:
 			env->imbalance--;
 			break;
@@ -11766,6 +11771,15 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		return;
 	}
 
+#ifdef CONFIG_SCHED_CACHE
+	if (busiest->group_type == group_llc_balance) {
+		/* Move a task that prefer local LLC */
+		env->migration_type = migrate_llc_task;
+		env->imbalance = 1;
+		return;
+	}
+#endif
+
 	if (busiest->group_type == group_imbalanced) {
 		/*
 		 * In the group_imb case we cannot rely on group-wide averages
@@ -12073,6 +12087,10 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env,
 	struct rq *busiest = NULL, *rq;
 	unsigned long busiest_util = 0, busiest_load = 0, busiest_capacity = 1;
 	unsigned int busiest_nr = 0;
+#ifdef CONFIG_SCHED_CACHE
+	unsigned int busiest_pref_llc = 0;
+	int dst_llc;
+#endif
 	int i;
 
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
@@ -12181,6 +12199,16 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env,
 			}
 			break;
 
+		case migrate_llc_task:
+#ifdef CONFIG_SCHED_CACHE
+			dst_llc = llc_id(env->dst_cpu);
+			if (dst_llc >= 0 &&
+			    busiest_pref_llc < rq->nr_pref_llc[dst_llc]) {
+				busiest_pref_llc = rq->nr_pref_llc[dst_llc];
+				busiest = rq;
+			}
+#endif
+			break;
 		case migrate_task:
 			if (busiest_nr < nr_running) {
 				busiest_nr = nr_running;
@@ -12363,6 +12391,8 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd
 	case migrate_misfit:
 		__schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance);
 		break;
+	case migrate_llc_task:
+		break;
 	}
 }
 
-- 
2.32.0

On Wed, Dec 03, 2025 at 03:07:31PM -0800, Tim Chen wrote:
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index db555c11b5b8..529adf342ce0 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -9547,7 +9547,8 @@ enum migration_type {
>  	migrate_load = 0,
>  	migrate_util,
>  	migrate_task,
> -	migrate_misfit
> +	migrate_misfit,
> +	migrate_llc_task
>  };
>  
>  #define LBF_ALL_PINNED	0x01
> @@ -10134,6 +10135,10 @@ static int detach_tasks(struct lb_env *env)
>  			env->imbalance -= util;
>  			break;
>  
> +		case migrate_llc_task:
> +			env->imbalance--;
> +			break;
> +
>  		case migrate_task:
>  			env->imbalance--;
>  			break;

> @@ -12181,6 +12199,16 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env,
>  			}
>  			break;
>  
> +		case migrate_llc_task:
> +#ifdef CONFIG_SCHED_CACHE
> +			dst_llc = llc_id(env->dst_cpu);
> +			if (dst_llc >= 0 &&
> +			    busiest_pref_llc < rq->nr_pref_llc[dst_llc]) {
> +				busiest_pref_llc = rq->nr_pref_llc[dst_llc];
> +				busiest = rq;
> +			}
> +#endif
> +			break;
>  		case migrate_task:
>  			if (busiest_nr < nr_running) {
>  				busiest_nr = nr_running;
> @@ -12363,6 +12391,8 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd
>  	case migrate_misfit:
>  		__schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance);
>  		break;
> +	case migrate_llc_task:
> +		break;
>  	}
>  }

The enum and all switch statements had the same order; you wrecked it!

On 12/10/2025 9:32 PM, Peter Zijlstra wrote:
> On Wed, Dec 03, 2025 at 03:07:31PM -0800, Tim Chen wrote:
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index db555c11b5b8..529adf342ce0 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -9547,7 +9547,8 @@ enum migration_type {
>>   	migrate_load = 0,
>>   	migrate_util,
>>   	migrate_task,
>> -	migrate_misfit
>> +	migrate_misfit,
>> +	migrate_llc_task
>>   };
>>   
>>   #define LBF_ALL_PINNED	0x01
>> @@ -10134,6 +10135,10 @@ static int detach_tasks(struct lb_env *env)
>>   			env->imbalance -= util;
>>   			break;
>>   
>> +		case migrate_llc_task:
>> +			env->imbalance--;
>> +			break;
>> +
>>   		case migrate_task:
>>   			env->imbalance--;
>>   			break;
> 
>> @@ -12181,6 +12199,16 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env,
>>   			}
>>   			break;
>>   
>> +		case migrate_llc_task:
>> +#ifdef CONFIG_SCHED_CACHE
>> +			dst_llc = llc_id(env->dst_cpu);
>> +			if (dst_llc >= 0 &&
>> +			    busiest_pref_llc < rq->nr_pref_llc[dst_llc]) {
>> +				busiest_pref_llc = rq->nr_pref_llc[dst_llc];
>> +				busiest = rq;
>> +			}
>> +#endif
>> +			break;
>>   		case migrate_task:
>>   			if (busiest_nr < nr_running) {
>>   				busiest_nr = nr_running;
>> @@ -12363,6 +12391,8 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd
>>   	case migrate_misfit:
>>   		__schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance);
>>   		break;
>> +	case migrate_llc_task:
>> +		break;
>>   	}
>>   }
> 
> The enum and all switch statements had the same order; you wrecked it!

OK, will fix the order.

Thanks,
Chenyu