cpuidle: Ensure ct_cpuidle_enter() is always called from noinstr/__cpuidle

Tracing (kprobes included) and other compiler instrumentation relies
on a normal kernel runtime. Therefore all functions that disable RCU
should be noinstr, as should all functions that are called while RCU
is disabled.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230112195542.212914195@infradead.org

1 files changed, 28 insertions, 9 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 08374c7935ce..73f7d8b763c6 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -137,11 +137,13 @@ int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 }
 
 #ifdef CONFIG_SUSPEND
-static void enter_s2idle_proper(struct cpuidle_driver *drv,
-				struct cpuidle_device *dev, int index)
+static noinstr void enter_s2idle_proper(struct cpuidle_driver *drv,
+					 struct cpuidle_device *dev, int index)
 {
-	ktime_t time_start, time_end;
 	struct cpuidle_state *target_state = &drv->states[index];
+	ktime_t time_start, time_end;
+
+	instrumentation_begin();
 
 	time_start = ns_to_ktime(local_clock());
 
@@ -152,13 +154,18 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
 	 * suspended is generally unsafe.
 	 */
 	stop_critical_timings();
-	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
 		ct_cpuidle_enter();
+		/* Annotate away the indirect call */
+		instrumentation_begin();
+	}
 	target_state->enter_s2idle(dev, drv, index);
 	if (WARN_ON_ONCE(!irqs_disabled()))
 		raw_local_irq_disable();
-	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
+		instrumentation_end();
 		ct_cpuidle_exit();
+	}
 	tick_unfreeze();
 	start_critical_timings();
 
@@ -166,6 +173,7 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
 
 	dev->states_usage[index].s2idle_time += ktime_us_delta(time_end, time_start);
 	dev->states_usage[index].s2idle_usage++;
+	instrumentation_end();
 }
 
 /**
@@ -200,8 +208,9 @@ int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev)
  * @drv: cpuidle driver for this cpu
  * @index: index into the states table in @drv of the state to enter
  */
-int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
-			int index)
+noinstr int cpuidle_enter_state(struct cpuidle_device *dev,
+				 struct cpuidle_driver *drv,
+				 int index)
 {
 	int entered_state;
 
@@ -209,6 +218,8 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
 	ktime_t time_start, time_end;
 
+	instrumentation_begin();
+
 	/*
 	 * Tell the time framework to switch to a broadcast timer because our
 	 * local timer will be shut down.  If a local timer is used from another
@@ -235,15 +246,21 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	time_start = ns_to_ktime(local_clock());
 
 	stop_critical_timings();
-	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
 		ct_cpuidle_enter();
+		/* Annotate away the indirect call */
+		instrumentation_begin();
+	}
 
 	entered_state = target_state->enter(dev, drv, index);
+
 	if (WARN_ONCE(!irqs_disabled(), "%ps leaked IRQ state", target_state->enter))
 		raw_local_irq_disable();
 
-	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
+		instrumentation_end();
 		ct_cpuidle_exit();
+	}
 	start_critical_timings();
 
 	sched_clock_idle_wakeup_event();
@@ -306,6 +323,8 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		dev->states_usage[index].rejected++;
 	}
 
+	instrumentation_end();
+
 	return entered_state;
 }