Merge branch 'timers/nohz-v3' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into timers/nohz

Pull nohz improvements from Frederic Weisbecker:

 " It mostly contains fixes and full dynticks off-case optimizations. I believe that
   distros want to enable this feature so it seems important to optimize the case
   where the "nohz_full=" parameter is empty. ie: I'm trying to remove any performance
   regression that comes with NO_HZ_FULL=y when the feature is not used.

   This patchset improves the current situation a lot (off-case appears to be around 11% faster
   with hackbench, although I guess it may vary depending on the configuration but it should be
   significantly faster in any case) now there is still some work to do: I can still observe a
   remaining loss of 1.6% throughput seen with hackbench compared to CONFIG_NO_HZ_FULL=n. "

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 17 insertions, 40 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7c32cb..3fb7ace 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2510,13 +2510,11 @@ void __sched schedule_preempt_disabled(void)
  */
 asmlinkage void __sched notrace preempt_schedule(void)
 {
-	struct thread_info *ti = current_thread_info();
-
 	/*
 	 * If there is a non-zero preempt_count or interrupts are disabled,
 	 * we do not want to preempt the current task. Just return..
 	 */
-	if (likely(ti->preempt_count || irqs_disabled()))
+	if (likely(!preemptible()))
 		return;
 
 	do {
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index a7959e0..c1d7493 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -378,11 +378,8 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 
 #ifndef __ARCH_HAS_VTIME_TASK_SWITCH
-void vtime_task_switch(struct task_struct *prev)
+void vtime_common_task_switch(struct task_struct *prev)
 {
-	if (!vtime_accounting_enabled())
-		return;
-
 	if (is_idle_task(prev))
 		vtime_account_idle(prev);
 	else
@@ -404,11 +401,8 @@ void vtime_task_switch(struct task_struct *prev)
  * vtime_account().
  */
 #ifndef __ARCH_HAS_VTIME_ACCOUNT
-void vtime_account_irq_enter(struct task_struct *tsk)
+void vtime_common_account_irq_enter(struct task_struct *tsk)
 {
-	if (!vtime_accounting_enabled())
-		return;
-
 	if (!in_interrupt()) {
 		/*
 		 * If we interrupted user, context_tracking_in_user()
@@ -428,7 +422,7 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 	}
 	vtime_account_system(tsk);
 }
-EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
+EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
@@ -559,12 +553,6 @@ static void cputime_adjust(struct task_cputime *curr,
 {
 	cputime_t rtime, stime, utime, total;
 
-	if (vtime_accounting_enabled()) {
-		*ut = curr->utime;
-		*st = curr->stime;
-		return;
-	}
-
 	stime = curr->stime;
 	total = stime + curr->utime;
 
@@ -664,23 +652,17 @@ static void __vtime_account_system(struct task_struct *tsk)
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	if (!vtime_accounting_enabled())
-		return;
-
 	write_seqlock(&tsk->vtime_seqlock);
 	__vtime_account_system(tsk);
 	write_sequnlock(&tsk->vtime_seqlock);
 }
 
-void vtime_account_irq_exit(struct task_struct *tsk)
+void vtime_gen_account_irq_exit(struct task_struct *tsk)
 {
-	if (!vtime_accounting_enabled())
-		return;
-
 	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
 	if (context_tracking_in_user())
 		tsk->vtime_snap_whence = VTIME_USER;
-	__vtime_account_system(tsk);
 	write_sequnlock(&tsk->vtime_seqlock);
 }
 
@@ -688,12 +670,8 @@ void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t delta_cpu;
 
-	if (!vtime_accounting_enabled())
-		return;
-
-	delta_cpu = get_vtime_delta(tsk);
-
 	write_seqlock(&tsk->vtime_seqlock);
+	delta_cpu = get_vtime_delta(tsk);
 	tsk->vtime_snap_whence = VTIME_SYS;
 	account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
 	write_sequnlock(&tsk->vtime_seqlock);
@@ -701,22 +679,27 @@ void vtime_account_user(struct task_struct *tsk)
 
 void vtime_user_enter(struct task_struct *tsk)
 {
-	if (!vtime_accounting_enabled())
-		return;
-
 	write_seqlock(&tsk->vtime_seqlock);
-	tsk->vtime_snap_whence = VTIME_USER;
 	__vtime_account_system(tsk);
+	tsk->vtime_snap_whence = VTIME_USER;
 	write_sequnlock(&tsk->vtime_seqlock);
 }
 
 void vtime_guest_enter(struct task_struct *tsk)
 {
+	/*
+	 * The flags must be updated under the lock with
+	 * the vtime_snap flush and update.
+	 * That enforces a right ordering and update sequence
+	 * synchronization against the reader (task_gtime())
+	 * that can thus safely catch up with a tickless delta.
+	 */
 	write_seqlock(&tsk->vtime_seqlock);
 	__vtime_account_system(tsk);
 	current->flags |= PF_VCPU;
 	write_sequnlock(&tsk->vtime_seqlock);
 }
+EXPORT_SYMBOL_GPL(vtime_guest_enter);
 
 void vtime_guest_exit(struct task_struct *tsk)
 {
@@ -725,6 +708,7 @@ void vtime_guest_exit(struct task_struct *tsk)
 	current->flags &= ~PF_VCPU;
 	write_sequnlock(&tsk->vtime_seqlock);
 }
+EXPORT_SYMBOL_GPL(vtime_guest_exit);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
@@ -733,11 +717,6 @@ void vtime_account_idle(struct task_struct *tsk)
 	account_idle_time(delta_cpu);
 }
 
-bool vtime_accounting_enabled(void)
-{
-	return context_tracking_active();
-}
-
 void arch_vtime_task_switch(struct task_struct *prev)
 {
 	write_seqlock(&prev->vtime_seqlock);