From: Xunlei Pang <xlpang@xxxxxxxxxxxxxxxxx>
[ Upstream commit df3cb4ea1fb63ff326488efd671ba3c39034255e ]
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.
Steps to reproduce on my 31-CPU hyperthreads machine:
1. with boot parameter: "isolcpus=domain,2-31"
(thread lists: 0,16 and 1,17)
2. cgcreate -g cpu:test; cgexec -g cpu:test "test_threads"
3. some threads will be migrated to the isolated cpu16~17.
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.zy@xxxxxxxxxxxxxxxxx>
Signed-off-by: Xunlei Pang <xlpang@xxxxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Jiang Biao <benbjiang@xxxxxxxxxxx>
Reviewed-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Link: https://lkml.kernel.org/r/1600930127-76857-1-git-send-email-xlpang@xxxxxxxxxxxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
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 f71e8b0e0346a..60c5a80f325b6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6067,7 +6067,7 @@ 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;
@@ -6075,7 +6075,8 @@ 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;
@@ -6091,7 +6092,7 @@ 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;
}
@@ -6266,7 +6267,7 @@ 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;
--
2.25.1
