Messages in this thread Patch in this message | | | Date | Sat, 10 Oct 2015 20:53:15 +0200 | From | Oleg Nesterov <> | Subject | [PATCH 3/3] sched: don't scan all-offline ->cpus_allowed twice if !CONFIG_CPUSETS |
| |
If CONFIG_CPUSETS=n then "case cpuset" changes the state and runs the already failed for_each_cpu() loop again for no reason.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> --- kernel/sched/core.c | 12 +++++++----- 1 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e4fa6be..b421e24 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1335,13 +1335,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p) goto out; } + /* No more Mr. Nice Guy. */ switch (state) { case cpuset: - /* No more Mr. Nice Guy. */ - cpuset_cpus_allowed_fallback(p); - state = possible; - break; - + if (IS_ENABLED(CONFIG_CPUSETS)) { + cpuset_cpus_allowed_fallback(p); + state = possible; + break; + } + /* fall-through */ case possible: do_set_cpus_allowed(p, cpu_possible_mask); state = fail; -- 1.5.5.1
| |