sched/core: Optimize __schedule()

Oleg noted that by making do_exit() use __schedule() for the TASK_DEAD
context switch, we can avoid the TASK_DEAD special case currently in
__schedule() because that avoids the extra preempt_disable() from
schedule().

In order to facilitate this, create a do_task_dead() helper which we
place in the scheduler code, such that it can access __schedule().

Also add some __noreturn annotations to the functions, there's no
coming back from do_exit().

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Cheng Chao <cs.os.kernel@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akpm@linux-foundation.org
Cc: chris@chris-wilson.co.uk
Cc: tj@kernel.org
Link: http://lkml.kernel.org/r/20160913163729.GB5012@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/kernel.h

@@ -259,17 +259,14 @@ static inline void might_fault(void) { }
 extern struct atomic_notifier_head panic_notifier_list;
 extern long (*panic_blink)(int state);
 __printf(1, 2)
-void panic(const char *fmt, ...)
+void panic(const char *fmt, ...) __noreturn __cold;
-	__noreturn __cold;
 void nmi_panic(struct pt_regs *regs, const char *msg);
 extern void oops_enter(void);
 extern void oops_exit(void);
 void print_oops_end_marker(void);
 extern int oops_may_print(void);
-void do_exit(long error_code)
+void do_exit(long error_code) __noreturn;
-	__noreturn;
+void complete_and_exit(struct completion *, long) __noreturn;
-void complete_and_exit(struct completion *, long)
-	__noreturn;
 
 /* Internal, do not use. */
 int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);

include/linux/sched.h

@@ -448,6 +448,8 @@ static inline void io_schedule(void)
 	io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
 }
 
+void __noreturn do_task_dead(void);
+
 struct nsproxy;
 struct user_namespace;
 

kernel/exit.c

@@ -725,7 +725,7 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
-void do_exit(long code)
+void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
@@ -882,29 +882,7 @@ void do_exit(long code)
 	exit_rcu();
 	TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i));
 
-	/*
+	do_task_dead();
-	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
-	 * when the following two conditions become true.
-	 *   - There is race condition of mmap_sem (It is acquired by
-	 *     exit_mm()), and
-	 *   - SMI occurs before setting TASK_RUNINNG.
-	 *     (or hypervisor of virtual machine switches to other guest)
-	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
-	 *
-	 * To avoid it, we have to wait for releasing tsk->pi_lock which
-	 * is held by try_to_wake_up()
-	 */
-	smp_mb();
-	raw_spin_unlock_wait(&tsk->pi_lock);
-
-	/* causes final put_task_struct in finish_task_switch(). */
-	tsk->state = TASK_DEAD;
-	tsk->flags |= PF_NOFREEZE;	/* tell freezer to ignore us */
-	schedule();
-	BUG();
-	/* Avoid "noreturn function does return".  */
-	for (;;)
-		cpu_relax();	/* For when BUG is null */
 }
 EXPORT_SYMBOL_GPL(do_exit);
 

kernel/sched/core.c

@@ -3331,17 +3331,6 @@ static void __sched notrace __schedule(bool preempt)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	/*
-	 * do_exit() calls schedule() with preemption disabled as an exception;
-	 * however we must fix that up, otherwise the next task will see an
-	 * inconsistent (higher) preempt count.
-	 *
-	 * It also avoids the below schedule_debug() test from complaining
-	 * about this.
-	 */
-	if (unlikely(prev->state == TASK_DEAD))
-		preempt_enable_no_resched_notrace();
-
 	schedule_debug(prev);
 
 	if (sched_feat(HRTICK))
@@ -3409,6 +3398,33 @@ static void __sched notrace __schedule(bool preempt)
 }
 STACK_FRAME_NON_STANDARD(__schedule); /* switch_to() */
 
+void __noreturn do_task_dead(void)
+{
+	/*
+	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
+	 * when the following two conditions become true.
+	 *   - There is race condition of mmap_sem (It is acquired by
+	 *     exit_mm()), and
+	 *   - SMI occurs before setting TASK_RUNINNG.
+	 *     (or hypervisor of virtual machine switches to other guest)
+	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
+	 *
+	 * To avoid it, we have to wait for releasing tsk->pi_lock which
+	 * is held by try_to_wake_up()
+	 */
+	smp_mb();
+	raw_spin_unlock_wait(&current->pi_lock);
+
+	/* causes final put_task_struct in finish_task_switch(). */
+	__set_current_state(TASK_DEAD);
+	current->flags |= PF_NOFREEZE;	/* tell freezer to ignore us */
+	__schedule(false);
+	BUG();
+	/* Avoid "noreturn function does return".  */
+	for (;;)
+		cpu_relax();	/* For when BUG is null */
+}
+
 static inline void sched_submit_work(struct task_struct *tsk)
 {
 	if (!tsk->state || tsk_is_pi_blocked(tsk))