1 files changed, 97 insertions, 68 deletions

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 305727ea0677..2c85c86b455f 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -6,9 +6,6 @@
  * (NOTE: these are not related to SCHED_IDLE batch scheduled
  *        tasks which are handled in sched/fair.c )
  */
-#include "sched.h"
-
-#include <trace/events/power.h>
 
 /* Linker adds these: start and end of __cpuidle functions */
 extern char __cpuidle_text_start[], __cpuidle_text_end[];
@@ -54,18 +51,22 @@ __setup("hlt", cpu_idle_nopoll_setup);
 
 static noinline int __cpuidle cpu_idle_poll(void)
 {
+	instrumentation_begin();
 	trace_cpu_idle(0, smp_processor_id());
 	stop_critical_timings();
-	rcu_idle_enter();
-	local_irq_enable();
+	ct_cpuidle_enter();
 
+	raw_local_irq_enable();
 	while (!tif_need_resched() &&
 	       (cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
+	raw_local_irq_disable();
 
-	rcu_idle_exit();
+	ct_cpuidle_exit();
 	start_critical_timings();
 	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+	local_irq_enable();
+	instrumentation_end();
 
 	return 1;
 }
@@ -74,13 +75,31 @@ static noinline int __cpuidle cpu_idle_poll(void)
 void __weak arch_cpu_idle_prepare(void) { }
 void __weak arch_cpu_idle_enter(void) { }
 void __weak arch_cpu_idle_exit(void) { }
-void __weak arch_cpu_idle_dead(void) { }
+void __weak __noreturn arch_cpu_idle_dead(void) { while (1); }
 void __weak arch_cpu_idle(void)
 {
 	cpu_idle_force_poll = 1;
-	raw_local_irq_enable();
 }
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE
+DEFINE_STATIC_KEY_FALSE(arch_needs_tick_broadcast);
+
+static inline void cond_tick_broadcast_enter(void)
+{
+	if (static_branch_unlikely(&arch_needs_tick_broadcast))
+		tick_broadcast_enter();
+}
+
+static inline void cond_tick_broadcast_exit(void)
+{
+	if (static_branch_unlikely(&arch_needs_tick_broadcast))
+		tick_broadcast_exit();
+}
+#else
+static inline void cond_tick_broadcast_enter(void) { }
+static inline void cond_tick_broadcast_exit(void) { }
+#endif
+
 /**
  * default_idle_call - Default CPU idle routine.
  *
@@ -88,44 +107,22 @@ void __weak arch_cpu_idle(void)
  */
 void __cpuidle default_idle_call(void)
 {
-	if (current_clr_polling_and_test()) {
-		local_irq_enable();
-	} else {
-
+	instrumentation_begin();
+	if (!current_clr_polling_and_test()) {
+		cond_tick_broadcast_enter();
 		trace_cpu_idle(1, smp_processor_id());
 		stop_critical_timings();
 
-		/*
-		 * arch_cpu_idle() is supposed to enable IRQs, however
-		 * we can't do that because of RCU and tracing.
-		 *
-		 * Trace IRQs enable here, then switch off RCU, and have
-		 * arch_cpu_idle() use raw_local_irq_enable(). Note that
-		 * rcu_idle_enter() relies on lockdep IRQ state, so switch that
-		 * last -- this is very similar to the entry code.
-		 */
-		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(_THIS_IP_);
-		rcu_idle_enter();
-		lockdep_hardirqs_on(_THIS_IP_);
-
+		ct_cpuidle_enter();
 		arch_cpu_idle();
-
-		/*
-		 * OK, so IRQs are enabled here, but RCU needs them disabled to
-		 * turn itself back on.. funny thing is that disabling IRQs
-		 * will cause tracing, which needs RCU. Jump through hoops to
-		 * make it 'work'.
-		 */
-		raw_local_irq_disable();
-		lockdep_hardirqs_off(_THIS_IP_);
-		rcu_idle_exit();
-		lockdep_hardirqs_on(_THIS_IP_);
-		raw_local_irq_enable();
+		ct_cpuidle_exit();
 
 		start_critical_timings();
 		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+		cond_tick_broadcast_exit();
 	}
+	local_irq_enable();
+	instrumentation_end();
 }
 
 static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
@@ -163,7 +160,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  *
  * NOTE: no locks or semaphores should be used here
  *
- * On archs that support TIF_POLLING_NRFLAG, is called with polling
+ * On architectures that support TIF_POLLING_NRFLAG, is called with polling
  * set, and it returns with polling set.  If it ever stops polling, it
  * must clear the polling bit.
  */
@@ -175,19 +172,13 @@ static void cpuidle_idle_call(void)
 
 	/*
 	 * Check if the idle task must be rescheduled. If it is the
-	 * case, exit the function after re-enabling the local irq.
+	 * case, exit the function after re-enabling the local IRQ.
 	 */
 	if (need_resched()) {
 		local_irq_enable();
 		return;
 	}
 
-	/*
-	 * The RCU framework needs to be told that we are entering an idle
-	 * section, so no more rcu read side critical sections and one more
-	 * step to the grace period
-	 */
-
 	if (cpuidle_not_available(drv, dev)) {
 		tick_nohz_idle_stop_tick();
 
@@ -199,7 +190,7 @@ static void cpuidle_idle_call(void)
 	 * Suspend-to-idle ("s2idle") is a system state in which all user space
 	 * has been frozen, all I/O devices have been suspended and the only
 	 * activity happens here and in interrupts (if any). In that case bypass
-	 * the cpuidle governor and go stratight for the deepest idle state
+	 * the cpuidle governor and go straight for the deepest idle state
 	 * available.  Possibly also suspend the local tick and the entire
 	 * timekeeping to prevent timer interrupts from kicking us out of idle
 	 * until a proper wakeup interrupt happens.
@@ -247,7 +238,7 @@ exit_idle:
 	__current_set_polling();
 
 	/*
-	 * It is up to the idle functions to reenable local interrupts
+	 * It is up to the idle functions to re-enable local interrupts
 	 */
 	if (WARN_ON_ONCE(irqs_disabled()))
 		local_irq_enable();
@@ -261,6 +252,12 @@ exit_idle:
 static void do_idle(void)
 {
 	int cpu = smp_processor_id();
+
+	/*
+	 * Check if we need to update blocked load
+	 */
+	nohz_run_idle_balance(cpu);
+
 	/*
 	 * If the arch has a polling bit, we maintain an invariant:
 	 *
@@ -274,20 +271,49 @@ static void do_idle(void)
 	tick_nohz_idle_enter();
 
 	while (!need_resched()) {
-		rmb();
 
+		/*
+		 * Interrupts shouldn't be re-enabled from that point on until
+		 * the CPU sleeping instruction is reached. Otherwise an interrupt
+		 * may fire and queue a timer that would be ignored until the CPU
+		 * wakes from the sleeping instruction. And testing need_resched()
+		 * doesn't tell about pending needed timer reprogram.
+		 *
+		 * Several cases to consider:
+		 *
+		 * - SLEEP-UNTIL-PENDING-INTERRUPT based instructions such as
+		 *   "wfi" or "mwait" are fine because they can be entered with
+		 *   interrupt disabled.
+		 *
+		 * - sti;mwait() couple is fine because the interrupts are
+		 *   re-enabled only upon the execution of mwait, leaving no gap
+		 *   in-between.
+		 *
+		 * - ROLLBACK based idle handlers with the sleeping instruction
+		 *   called with interrupts enabled are NOT fine. In this scheme
+		 *   when the interrupt detects it has interrupted an idle handler,
+		 *   it rolls back to its beginning which performs the
+		 *   need_resched() check before re-executing the sleeping
+		 *   instruction. This can leak a pending needed timer reprogram.
+		 *   If such a scheme is really mandatory due to the lack of an
+		 *   appropriate CPU sleeping instruction, then a FAST-FORWARD
+		 *   must instead be applied: when the interrupt detects it has
+		 *   interrupted an idle handler, it must resume to the end of
+		 *   this idle handler so that the generic idle loop is iterated
+		 *   again to reprogram the tick.
+		 */
 		local_irq_disable();
 
 		if (cpu_is_offline(cpu)) {
-			tick_nohz_idle_stop_tick();
 			cpuhp_report_idle_dead();
 			arch_cpu_idle_dead();
 		}
 
 		arch_cpu_idle_enter();
+		rcu_nocb_flush_deferred_wakeup();
 
 		/*
-		 * In poll mode we reenable interrupts and spin. Also if we
+		 * In poll mode we re-enable interrupts and spin. Also if we
 		 * detected in the wakeup from idle path that the tick
 		 * broadcast device expired for us, we don't want to go deep
 		 * idle as we know that the IPI is going to arrive right away.
@@ -323,7 +349,7 @@ static void do_idle(void)
 	 * RCU relies on this call to be done outside of an RCU read-side
 	 * critical section.
 	 */
-	flush_smp_call_function_from_idle();
+	flush_smp_call_function_queue();
 	schedule_idle();
 
 	if (unlikely(klp_patch_pending(current)))
@@ -372,10 +398,10 @@ void play_idle_precise(u64 duration_ns, u64 latency_ns)
 	cpuidle_use_deepest_state(latency_ns);
 
 	it.done = 0;
-	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	it.timer.function = idle_inject_timer_fn;
+	hrtimer_setup_on_stack(&it.timer, idle_inject_timer_fn, CLOCK_MONOTONIC,
+			       HRTIMER_MODE_REL_HARD);
 	hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
-		      HRTIMER_MODE_REL_PINNED);
+		      HRTIMER_MODE_REL_PINNED_HARD);
 
 	while (!READ_ONCE(it.done))
 		do_idle();
@@ -390,6 +416,7 @@ EXPORT_SYMBOL_GPL(play_idle_precise);
 
 void cpu_startup_entry(enum cpuhp_state state)
 {
+	current->flags |= PF_IDLE;
 	arch_cpu_idle_prepare();
 	cpuhp_online_idle(state);
 	while (1)
@@ -417,41 +444,43 @@ balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 /*
  * Idle tasks are unconditionally rescheduled:
  */
-static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
+static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 {
 	resched_curr(rq);
 }
 
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
+	dl_server_update_idle_time(rq, prev);
+	scx_update_idle(rq, false, true);
 }
 
 static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
 	update_idle_core(rq);
+	scx_update_idle(rq, true, true);
 	schedstat_inc(rq->sched_goidle);
+	next->se.exec_start = rq_clock_task(rq);
 }
 
-struct task_struct *pick_next_task_idle(struct rq *rq)
+struct task_struct *pick_task_idle(struct rq *rq)
 {
-	struct task_struct *next = rq->idle;
-
-	set_next_task_idle(rq, next, true);
-
-	return next;
+	scx_update_idle(rq, true, false);
+	return rq->idle;
 }
 
 /*
  * It is not legal to sleep in the idle task - print a warning
  * message if some code attempts to do it:
  */
-static void
+static bool
 dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 {
-	raw_spin_unlock_irq(&rq->lock);
+	raw_spin_rq_unlock_irq(rq);
 	printk(KERN_ERR "bad: scheduling from the idle thread!\n");
 	dump_stack();
-	raw_spin_lock_irq(&rq->lock);
+	raw_spin_rq_lock_irq(rq);
+	return true;
 }
 
 /*
@@ -491,9 +520,9 @@ DEFINE_SCHED_CLASS(idle) = {
 	/* dequeue is not valid, we print a debug message there: */
 	.dequeue_task		= dequeue_task_idle,
 
-	.check_preempt_curr	= check_preempt_curr_idle,
+	.wakeup_preempt		= wakeup_preempt_idle,
 
-	.pick_next_task		= pick_next_task_idle,
+	.pick_task		= pick_task_idle,
 	.put_prev_task		= put_prev_task_idle,
 	.set_next_task          = set_next_task_idle,