sched/core: Distinguish between idle_cpu() calls based on desired effect, introduce...

In the following commit:

  247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted vCPUs")

... we distinguish between idle_cpu() when the vCPU is not running for
scheduling threads.

However, the idle_cpu() function is used in other places for
actually checking whether the state of the CPU is idle or not.

Hence split the use of that function based on the desired return value,
by introducing the available_idle_cpu() function.

This fixes a (slight) regression in that initial vCPU commit, because
some code paths (like the load-balancer) don't care and shouldn't care
if the vCPU is preempted or not, they just want to know if there's any
tasks on the CPU.

Signed-off-by: Rohit Jain <rohit.k.jain@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dhaval.giani@oracle.com
Cc: linux-kernel@vger.kernel.org
Cc: matt@codeblueprint.co.uk
Cc: steven.sistare@oracle.com
Cc: subhra.mazumdar@oracle.com
Link: http://lkml.kernel.org/r/1525883988-10356-1-git-send-email-rohit.k.jain@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c2413703f45dcf005c7601b1e8c8c24c51d2a844..959a8588e3652e5884ef6806c6b46033d14817c0 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1504,6 +1504,7 @@ static inline int task_nice(const struct task_struct *p)
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
+extern int available_idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
 extern int sched_setattr(struct task_struct *, const struct sched_attr *);

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 102c36c317dc2983e613160123d8257d30f1c6ea..d1555185c054cab71025d9d86edf193ccec36c66 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4009,6 +4009,20 @@ int idle_cpu(int cpu)
                return 0;
 #endif
 
+       return 1;
+}
+
+/**
+ * available_idle_cpu - is a given CPU idle for enqueuing work.
+ * @cpu: the CPU in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
+ */
+int available_idle_cpu(int cpu)
+{
+       if (!idle_cpu(cpu))
+               return 0;
+
        if (vcpu_is_preempted(cpu))
                return 0;
 

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f32b97d4c63b5f6241694572e4f6401c77e43dba..748cb054fefd2e2e391fa29aacd004b58c5340fc 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5899,8 +5899,8 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
         * a cpufreq perspective, it's better to have higher utilisation
         * on one CPU.
         */
-       if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
-               return idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
+       if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
+               return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
 
        if (sync && cpu_rq(this_cpu)->nr_running == 1)
                return this_cpu;
@@ -6143,7 +6143,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 
        /* Traverse only the allowed CPUs */
        for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
-               if (idle_cpu(i)) {
+               if (available_idle_cpu(i)) {
                        struct rq *rq = cpu_rq(i);
                        struct cpuidle_state *idle = idle_get_state(rq);
                        if (idle && idle->exit_latency < min_exit_latency) {
@@ -6272,7 +6272,7 @@ void __update_idle_core(struct rq *rq)
                if (cpu == core)
                        continue;
 
-               if (!idle_cpu(cpu))
+               if (!available_idle_cpu(cpu))
                        goto unlock;
        }
 
@@ -6304,7 +6304,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 
                for_each_cpu(cpu, cpu_smt_mask(core)) {
                        cpumask_clear_cpu(cpu, cpus);
-                       if (!idle_cpu(cpu))
+                       if (!available_idle_cpu(cpu))
                                idle = false;
                }
 
@@ -6333,7 +6333,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
        for_each_cpu(cpu, cpu_smt_mask(target)) {
                if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
                        continue;
-               if (idle_cpu(cpu))
+               if (available_idle_cpu(cpu))
                        return cpu;
        }
 
@@ -6396,7 +6396,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
                        return -1;
                if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
                        continue;
-               if (idle_cpu(cpu))
+               if (available_idle_cpu(cpu))
                        break;
        }
 
@@ -6416,13 +6416,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
        struct sched_domain *sd;
        int i, recent_used_cpu;
 
-       if (idle_cpu(target))
+       if (available_idle_cpu(target))
                return target;
 
        /*
         * If the previous CPU is cache affine and idle, don't be stupid:
         */
-       if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
+       if (prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev))
                return prev;
 
        /* Check a recently used CPU as a potential idle candidate: */
@@ -6430,7 +6430,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
        if (recent_used_cpu != prev &&
            recent_used_cpu != target &&
            cpus_share_cache(recent_used_cpu, target) &&
-           idle_cpu(recent_used_cpu) &&
+           available_idle_cpu(recent_used_cpu) &&
            cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) {
                /*
                 * Replace recent_used_cpu with prev as it is a potential