diff options
| author | Xunlei Pang <xlpang@linux.alibaba.com> | 2020-09-24 14:48:47 +0800 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2020-10-29 10:11:01 +0100 |
| commit | b4e623ddf50614efebdd65f72068820e6b6ae9fc (patch) | |
| tree | a8107d781b2deb2ce746a79183b8f9e93e16d50c /kernel | |
| parent | 797f596715c71f47cc85b0a19ad286da2fd0c9cf (diff) | |
| download | linux-stable-b4e623ddf50614efebdd65f72068820e6b6ae9fc.tar.gz linux-stable-b4e623ddf50614efebdd65f72068820e6b6ae9fc.tar.bz2 linux-stable-b4e623ddf50614efebdd65f72068820e6b6ae9fc.zip | |
sched/fair: Fix wrong cpu selecting from isolated domain
[ 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@linux.alibaba.com>
Signed-off-by: Xunlei Pang <xlpang@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/1600930127-76857-1-git-send-email-xlpang@linux.alibaba.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/sched/fair.c | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 51408ebd76c2..ea3d20be3e75 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 @@ symmetric: 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; |