The slow path for waking tasks currently discards all potential targets
when no cookie-matching CPU is found, leading to suboptimal task placement.

Fall back to selecting the idlest CPU when no cookie-matching target is
available, ensuring better CPU utilization while maintaining the preference
for cookie-compatible placements.

Signed-off-by: Fernand Sieber <sieberf@amazon.com>
---
 kernel/sched/fair.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 43ddfc25af99..67746899809e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7335,7 +7335,8 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
  * sched_balance_find_dst_group_cpu - find the idlest CPU among the CPUs in the group.
  */
 static int
-sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+__sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p,
+				   int this_cpu, bool cookie_match)
 {
 	unsigned long load, min_load = ULONG_MAX;
 	unsigned int min_exit_latency = UINT_MAX;
@@ -7352,7 +7353,8 @@ sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *
 	for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
 		struct rq *rq = cpu_rq(i);
 
-		if (!sched_core_cookie_match(rq, p))
+		/* Only matching tasks if cookie_match, else only unmatching tasks */
+		if (cookie_match ^ sched_core_cookie_match(rq, p))
 			continue;
 
 		if (sched_idle_cpu(i))
@@ -7391,6 +7393,17 @@ sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
+/*
+ * sched_balance_find_dst_group_cpu - find the idlest CPU among the CPUs in the group.
+ */
+static inline int
+sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+{
+	int cpu = __sched_balance_find_dst_group_cpu(group, p, this_cpu, true);
+
+	return cpu >= 0 ? cpu : __sched_balance_find_dst_group_cpu(group, p, this_cpu, false);
+}
+
 static inline int sched_balance_find_dst_cpu(struct sched_domain *sd, struct task_struct *p,
 				  int cpu, int prev_cpu, int sd_flag)
 {
-- 
2.43.0




Amazon Development Centre (South Africa) (Proprietary) Limited
29 Gogosoa Street, Observatory, Cape Town, Western Cape, 7925, South Africa
Registration Number: 2004 / 034463 / 07

Hello Fernand,

On 9/22/2025 6:09 PM, Fernand Sieber wrote:
> @@ -7391,6 +7393,17 @@ sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *
>  	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;

Based on the above return in __sched_balance_find_dst_group_cpu(), it
should always return a valid CPU since "least_loaded_cpu" is initialized
to "this_cpu".

>  }
>  
> +/*
> + * sched_balance_find_dst_group_cpu - find the idlest CPU among the CPUs in the group.
> + */
> +static inline int
> +sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
> +{
> +	int cpu = __sched_balance_find_dst_group_cpu(group, p, this_cpu, true);
> +
> +	return cpu >= 0 ? cpu : __sched_balance_find_dst_group_cpu(group, p, this_cpu, false);

So, under what circumstance does "cpu" here turns out to be < 0?
Am I missing something?

> +}
> +
>  static inline int sched_balance_find_dst_cpu(struct sched_domain *sd, struct task_struct *p,
>  				  int cpu, int prev_cpu, int sd_flag)
>  {

-- 
Thanks and Regards,
Prateek

Hi Prateek,

On 9/23/2025 7:21 AM, K Prateek Nayak wrote:
> Based on the above return in __sched_balance_find_dst_group_cpu(), it
> should always return a valid CPU since "least_loaded_cpu" is initialized
> to "this_cpu".
>
> So, under what circumstance does "cpu" here turns out to be < 0?
> Am I missing something?

Hey Prateek. Thanks for the catch. I'll fix as follows for next rev:

+/*
+ * sched_balance_find_dst_group_cpu - find the idlest CPU among the CPUs in the group.
+ */
+static inline int
+sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+{
+	int cpu = __sched_balance_find_dst_group_cpu(group, p, -1, true);
+	return cpu >= 0 ? cpu : __sched_balance_find_dst_group_cpu(group, p, this_cpu, false);
+}
+

Thanks,
Fernand



Amazon Development Centre (South Africa) (Proprietary) Limited
29 Gogosoa Street, Observatory, Cape Town, Western Cape, 7925, South Africa
Registration Number: 2004 / 034463 / 07

On 9/23/2025 9:32 AM, Fernand Sieber wrote:
> Hey Prateek. Thanks for the catch. I'll fix as follows for next rev:
>
> +/*
> + * sched_balance_find_dst_group_cpu - find the idlest CPU among the CPUs in the group.
> + */
> +static inline int
> +sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
> +{
> +	int cpu = __sched_balance_find_dst_group_cpu(group, p, -1, true);
> +	return cpu >= 0 ? cpu : __sched_balance_find_dst_group_cpu(group, p, this_cpu, false);
> +}

On second thoughts, this doesn't work as it breaks the original fallback path.
A better modification would be this:

@@ -7341,7 +7341,7 @@ __sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct
        unsigned long load, min_load = ULONG_MAX;
        unsigned int min_exit_latency = UINT_MAX;
        u64 latest_idle_timestamp = 0;
-       int least_loaded_cpu = this_cpu;
+       int least_loaded_cpu = -1;
        int shallowest_idle_cpu = -1;
        int i;

@@ -7357,6 +7357,9 @@ __sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct
                if (cookie_match ^ sched_core_cookie_match(rq, p))
                        continue;

+               if (least_loaded_cpu < 0)
+                       least_loaded_cpu = this_cpu;
+
                if (sched_idle_cpu(i))
                        return i;

Thanks,
Fernand



Amazon Development Centre (South Africa) (Proprietary) Limited
29 Gogosoa Street, Observatory, Cape Town, Western Cape, 7925, South Africa
Registration Number: 2004 / 034463 / 07