We've met problems that occasionally tasks with full cpumask
(e.g. by putting it into a cpuset or setting to full affinity)
were migrated to our isolated cpus in production environment.
After some analysis, we found that it is due to the current
select_idle_smt() not considering the sched_domain mask.
Fix it by checking the valid domain mask in select_idle_smt().
Fixes: 10e2f1acd010 ("sched/core: Rewrite and improve select_idle_siblings())
Reported-by: Wetp Zhang <wetp...@linux.alibaba.com>
Signed-off-by: Xunlei Pang <xlp...@linux.alibaba.com>
---
kernel/sched/fair.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1a68a05..fa942c4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6075,7 +6075,7 @@ static int select_idle_core(struct task_struct *p, struct
sched_domain *sd, int
/*
* 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;
@@ -6083,7 +6083,8 @@ static int select_idle_smt(struct task_struct *p, int
target)
return -1;
for_each_cpu(cpu, cpu_smt_mask(target)) {
- if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr) ||
+ !cpumask_test_cpu(cpu, sched_domain_span(sd)))
continue;
if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
return cpu;
@@ -6099,7 +6100,7 @@ static inline int select_idle_core(struct task_struct *p,
struct sched_domain *s
return -1;
}
-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;
}
@@ -6274,7 +6275,7 @@ static int select_idle_sibling(struct task_struct *p, int
prev, int target)
if ((unsigned)i < nr_cpumask_bits)
return i;
- i = select_idle_smt(p, target);
+ i = select_idle_smt(p, sd, target);
if ((unsigned)i < nr_cpumask_bits)
return i;
--
1.8.3.1
