sched/preempt: Optimize preemption operations on __schedule() callers

__schedule() disables preemption and some of its callers
(the preempt_schedule*() family) also set PREEMPT_ACTIVE.

So we have two preempt_count() modifications that could be performed
at once.

Lets remove the preemption disablement from __schedule() and pull
this responsibility to its callers in order to optimize preempt_count()
operations in a single place.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1431441711-29753-5-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Author: fweisbec

include/linux/preempt.h

@@ -137,6 +137,18 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
+#define preempt_active_enter() \
+do { \
+	preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
+	barrier(); \
+} while (0)
+
+#define preempt_active_exit() \
+do { \
+	barrier(); \
+	preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
+} while (0)
+
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \

kernel/sched/core.c

@@ -2773,9 +2773,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
  *          - return from syscall or exception to user-space
  *          - return from interrupt-handler to user-space
  *
- * WARNING: all callers must re-check need_resched() afterward and reschedule
- * accordingly in case an event triggered the need for rescheduling (such as
- * an interrupt waking up a task) while preemption was disabled in __schedule().
+ * WARNING: must be called with preemption disabled!
  */
 static void __sched __schedule(void)
 {
@@ -2784,7 +2782,6 @@ static void __sched __schedule(void)
 	struct rq *rq;
 	int cpu;
 
-	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	rcu_note_context_switch();
@@ -2848,8 +2845,6 @@ static void __sched __schedule(void)
 		raw_spin_unlock_irq(&rq->lock);
 
 	post_schedule(rq);
-
-	sched_preempt_enable_no_resched();
 }
 
 static inline void sched_submit_work(struct task_struct *tsk)
@@ -2870,7 +2865,9 @@ asmlinkage __visible void __sched schedule(void)
 
 	sched_submit_work(tsk);
 	do {
+		preempt_disable();
 		__schedule();
+		sched_preempt_enable_no_resched();
 	} while (need_resched());
 }
 EXPORT_SYMBOL(schedule);
@@ -2909,15 +2906,14 @@ void __sched schedule_preempt_disabled(void)
 static void __sched notrace preempt_schedule_common(void)
 {
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		preempt_active_enter();
 		__schedule();
-		__preempt_count_sub(PREEMPT_ACTIVE);
+		preempt_active_exit();
 
 		/*
 		 * Check again in case we missed a preemption opportunity
 		 * between schedule and now.
 		 */
-		barrier();
 	} while (need_resched());
 }
 
@@ -2964,7 +2960,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 		return;
 
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		preempt_active_enter();
 		/*
 		 * Needs preempt disabled in case user_exit() is traced
 		 * and the tracer calls preempt_enable_notrace() causing
@@ -2974,8 +2970,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 		__schedule();
 		exception_exit(prev_ctx);
 
-		__preempt_count_sub(PREEMPT_ACTIVE);
-		barrier();
+		preempt_active_exit();
 	} while (need_resched());
 }
 EXPORT_SYMBOL_GPL(preempt_schedule_context);
@@ -2999,17 +2994,11 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	prev_state = exception_enter();
 
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		preempt_active_enter();
 		local_irq_enable();
 		__schedule();
 		local_irq_disable();
-		__preempt_count_sub(PREEMPT_ACTIVE);
-
-		/*
-		 * Check again in case we missed a preemption opportunity
-		 * between schedule and now.
-		 */
-		barrier();
+		preempt_active_exit();
 	} while (need_resched());
 
 	exception_exit(prev_state);