sched/core: Fix rules for running on online && !active CPUs

As already enforced by the WARN() in __set_cpus_allowed_ptr(), the rules
for running on an online && !active CPU are stricter than just being a
kthread, you need to be a per-cpu kthread.

If you're not strictly per-CPU, you have better CPUs to run on and
don't need the partially booted one to get your work done.

The exception is to allow smpboot threads to bootstrap the CPU itself
and get kernel 'services' initialized before we allow userspace on it.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 955dbdf4ce87 ("sched: Allow migrating kthreads into online but inactive CPUs")
Link: http://lkml.kernel.org/r/20170725165821.cejhb7v2s3kecems@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 30 insertions, 12 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 092f7c4de903..1c58f54b9114 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -881,6 +881,33 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 }
 
 #ifdef CONFIG_SMP
+
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+        if (!(p->flags & PF_KTHREAD))
+                return false;
+
+        if (p->nr_cpus_allowed != 1)
+                return false;
+
+        return true;
+}
+
+/*
+ * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * __set_cpus_allowed_ptr() and select_fallback_rq().
+ */
+static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
+{
+        if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+                return false;
+
+        if (is_per_cpu_kthread(p))
+                return cpu_online(cpu);
+
+        return cpu_active(cpu);
+}
+
 /*
  * This is how migration works:
  *
@@ -938,16 +965,8 @@ struct migration_arg {
 static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
                                  struct task_struct *p, int dest_cpu)
 {
-        if (p->flags & PF_KTHREAD) {
-                if (unlikely(!cpu_online(dest_cpu)))
-                        return rq;
-        } else {
-                if (unlikely(!cpu_active(dest_cpu)))
-                        return rq;
-        }
-
         /* Affinity changed (again). */
-        if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+        if (!is_cpu_allowed(p, dest_cpu))
                 return rq;
 
         update_rq_clock(rq);
@@ -1476,10 +1495,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
         for (;;) {
                 /* Any allowed, online CPU? */
                 for_each_cpu(dest_cpu, &p->cpus_allowed) {
-                        if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
-                                continue;
-                        if (!cpu_online(dest_cpu))
+                        if (!is_cpu_allowed(p, dest_cpu))
                                 continue;
+
                         goto out;
                 }