sched: Let the scheduler see CPU idle states

When the cpu enters idle, it stores the cpuidle state pointer in its
struct rq instance which in turn could be used to make a better decision
when balancing tasks.

As soon as the cpu exits its idle state, the struct rq reference is
cleared.

There are a couple of situations where the idle state pointer could be changed
while it is being consulted:

1. For x86/acpi with dynamic c-states, when a laptop switches from battery
   to AC that could result on removing the deeper idle state. The acpi driver
   triggers:
	'acpi_processor_cst_has_changed'
		'cpuidle_pause_and_lock'
			'cpuidle_uninstall_idle_handler'
				'kick_all_cpus_sync'.

All cpus will exit their idle state and the pointed object will be set to
NULL.

2. The cpuidle driver is unloaded. Logically that could happen but not
in practice because the drivers are always compiled in and 95% of them are
not coded to unregister themselves.  In any case, the unloading code must
call 'cpuidle_unregister_device', that calls 'cpuidle_pause_and_lock'
leading to 'kick_all_cpus_sync' as mentioned above.

A race can happen if we use the pointer and then one of these two scenarios
occurs at the same moment.

In order to be safe, the idle state pointer stored in the rq must be
used inside a rcu_read_lock section where we are protected with the
'rcu_barrier' in the 'cpuidle_uninstall_idle_handler' function. The
idle_get_state() and idle_put_state() accessors should be used to that
effect.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: linux-pm@vger.kernel.org
Cc: linaro-kernel@lists.linaro.org
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 36 insertions, 0 deletions

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 11e7bc434f43..c47fce75e666 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -147,6 +147,9 @@ use_default:
             clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
                 goto use_default;
 
+        /* Take note of the planned idle state. */
+        idle_set_state(this_rq(), &drv->states[next_state]);
+
         /*
          * Enter the idle state previously returned by the governor decision.
          * This function will block until an interrupt occurs and will take
@@ -154,6 +157,9 @@ use_default:
          */
         entered_state = cpuidle_enter(drv, dev, next_state);
 
+        /* The cpu is no longer idle or about to enter idle. */
+        idle_set_state(this_rq(), NULL);
+
         if (broadcast)
                 clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 76f3a38a401c..16e1ca9cb7e8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -14,6 +14,7 @@
 #include "cpuacct.h"
 
 struct rq;
+struct cpuidle_state;
 
 /* task_struct::on_rq states: */
 #define TASK_ON_RQ_QUEUED       1
@@ -643,6 +644,11 @@ struct rq {
 #ifdef CONFIG_SMP
         struct llist_head wake_list;
 #endif
+
+#ifdef CONFIG_CPU_IDLE
+        /* Must be inspected within a rcu lock section */
+        struct cpuidle_state *idle_state;
+#endif
 };
 
 static inline int cpu_of(struct rq *rq)
@@ -1196,6 +1202,30 @@ static inline void idle_exit_fair(struct rq *rq) { }
 
 #endif
 
+#ifdef CONFIG_CPU_IDLE
+static inline void idle_set_state(struct rq *rq,
+                                  struct cpuidle_state *idle_state)
+{
+        rq->idle_state = idle_state;
+}
+
+static inline struct cpuidle_state *idle_get_state(struct rq *rq)
+{
+        WARN_ON(!rcu_read_lock_held());
+        return rq->idle_state;
+}
+#else
+static inline void idle_set_state(struct rq *rq,
+                                  struct cpuidle_state *idle_state)
+{
+}
+
+static inline struct cpuidle_state *idle_get_state(struct rq *rq)
+{
+        return NULL;
+}
+#endif
+
 extern void sysrq_sched_debug_show(void);
 extern void sched_init_granularity(void);
 extern void update_max_interval(void);