[PATCH v2 1/2 RESEND] sched/fair: take into account scheduling domain in select_idle_smt()

From: Keisuke Nishimura
Date: Wed Jan 10 2024 - 08:20:03 EST


When picking out a CPU on a task wakeup, select_idle_smt() has to take
into account the scheduling domain of @target. This is because the
"isolcpus" kernel command line option can remove CPUs from the domain to
isolate them from other SMT siblings.

This fix checks if the candidate CPU is in the target scheduling domain.

The commit df3cb4ea1fb6 ("sched/fair: Fix wrong cpu selecting from isolated
domain") originally proposed this fix by adding the check of the scheduling
domain in the loop. However, the commit 3e6efe87cd5cc ("sched/fair: Remove
redundant check in select_idle_smt()") accidentally removed the check.
This commit brings the check back.

Fixes: 3e6efe87cd5c ("sched/fair: Remove redundant check in select_idle_smt()")
Signed-off-by: Keisuke Nishimura <keisuke.nishimura@xxxxxxxx>
Signed-off-by: Julia Lawall <julia.lawall@xxxxxxxx>
---
v2: - Changed the log message to mention only isolcpus
- Moved the check in the loop according to the original fix

kernel/sched/fair.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 533547e3c90a..66457d4b8965 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7311,13 +7311,19 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
/*
* Scan the local SMT mask for idle CPUs.
*/
-static int select_idle_smt(struct task_struct *p, int target)
+static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
{
int cpu;

for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) {
if (cpu == target)
continue;
+ /*
+ * Check if the CPU is in the LLC scheduling domain of @target.
+ * Due to isolcpus, there is no guarantee that all the siblings are in the domain.
+ */
+ if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
+ continue;
if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
return cpu;
}
@@ -7341,7 +7347,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma
return __select_idle_cpu(core, p);
}

-static inline int select_idle_smt(struct task_struct *p, int target)
+static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
{
return -1;
}
@@ -7591,7 +7597,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
has_idle_core = test_idle_cores(target);

if (!has_idle_core && cpus_share_cache(prev, target)) {
- i = select_idle_smt(p, prev);
+ i = select_idle_smt(p, sd, prev);
if ((unsigned int)i < nr_cpumask_bits)
return i;
}
--
2.34.1