Merge tag 'cputime-cleanups-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into sched/core

Pull cputime cleanups and optimizations from Frederic Weisbecker:

 * Gather vtime headers that were a bit scattered around

 * Separate irqtime and vtime namespaces that were
   colliding, resulting in useless calls to irqtime accounting.

 * Slightly optimize irq and guest vtime accounting.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/ia64/kernel/time.c

@@ -106,9 +106,9 @@ void vtime_task_switch(struct task_struct *prev)
 	struct thread_info *ni = task_thread_info(current);
 
 	if (idle_task(smp_processor_id()) != prev)
-		vtime_account_system(prev);
+		__vtime_account_system(prev);
 	else
-		vtime_account_idle(prev);
+		__vtime_account_idle(prev);
 
 	vtime_account_user(prev);
 
@@ -135,14 +135,14 @@ static cputime_t vtime_delta(struct task_struct *tsk)
 	return delta_stime;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void __vtime_account_system(struct task_struct *tsk)
 {
 	cputime_t delta = vtime_delta(tsk);
 
 	account_system_time(tsk, 0, delta, delta);
 }
 
-void vtime_account_idle(struct task_struct *tsk)
+void __vtime_account_idle(struct task_struct *tsk)
 {
 	account_idle_time(vtime_delta(tsk));
 }

arch/powerpc/kernel/time.c

@@ -336,7 +336,7 @@ static u64 vtime_delta(struct task_struct *tsk,
 	return delta;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void __vtime_account_system(struct task_struct *tsk)
 {
 	u64 delta, sys_scaled, stolen;
 
@@ -346,7 +346,7 @@ void vtime_account_system(struct task_struct *tsk)
 		account_steal_time(stolen);
 }
 
-void vtime_account_idle(struct task_struct *tsk)
+void __vtime_account_idle(struct task_struct *tsk)
 {
 	u64 delta, sys_scaled, stolen;
 

arch/s390/kernel/vtime.c

@@ -140,6 +140,10 @@ void vtime_account(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_account);
 
+void __vtime_account_system(struct task_struct *tsk)
+__attribute__((alias("vtime_account")));
+EXPORT_SYMBOL_GPL(__vtime_account_system);
+
 void __kprobes vtime_stop_cpu(void)
 {
 	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);

arch/s390/kvm/kvm-s390.c

@@ -608,9 +608,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		kvm_s390_deliver_pending_interrupts(vcpu);
 
 	vcpu->arch.sie_block->icptcode = 0;
-	local_irq_disable();
 	kvm_guest_enter();
-	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	trace_kvm_s390_sie_enter(vcpu,
@@ -629,9 +627,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
 	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
-	local_irq_disable();
 	kvm_guest_exit();
-	local_irq_enable();
 
 	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
 	return rc;

include/linux/hardirq.h

@@ -4,6 +4,7 @@
 #include <linux/preempt.h>
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
+#include <linux/vtime.h>
 #include <asm/hardirq.h>
 
 /*
@@ -129,16 +130,6 @@ extern void synchronize_irq(unsigned int irq);
 # define synchronize_irq(irq)	barrier()
 #endif
 
-struct task_struct;
-
-#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
-static inline void vtime_account(struct task_struct *tsk)
-{
-}
-#else
-extern void vtime_account(struct task_struct *tsk);
-#endif
-
 #if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
 
 static inline void rcu_nmi_enter(void)
@@ -162,7 +153,7 @@ extern void rcu_nmi_exit(void);
  */
 #define __irq_enter()					\
 	do {						\
-		vtime_account(current);		\
+		vtime_account_irq_enter(current);	\
 		add_preempt_count(HARDIRQ_OFFSET);	\
 		trace_hardirq_enter();			\
 	} while (0)
@@ -178,7 +169,7 @@ extern void irq_enter(void);
 #define __irq_exit()					\
 	do {						\
 		trace_hardirq_exit();			\
-		vtime_account(current);		\
+		vtime_account_irq_exit(current);	\
 		sub_preempt_count(HARDIRQ_OFFSET);	\
 	} while (0)
 

include/linux/kernel_stat.h

@@ -7,6 +7,7 @@
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/vtime.h>
 #include <asm/irq.h>
 #include <asm/cputime.h>
 
@@ -130,12 +131,4 @@ extern void account_process_tick(struct task_struct *, int user);
 extern void account_steal_ticks(unsigned long ticks);
 extern void account_idle_ticks(unsigned long ticks);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void vtime_task_switch(struct task_struct *prev);
-extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
-#else
-static inline void vtime_task_switch(struct task_struct *prev) { }
-#endif
-
 #endif /* _LINUX_KERNEL_STAT_H */

include/linux/kvm_host.h

@@ -737,7 +737,11 @@ static inline int kvm_deassign_device(struct kvm *kvm,
 static inline void kvm_guest_enter(void)
 {
 	BUG_ON(preemptible());
-	vtime_account(current);
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
 	current->flags |= PF_VCPU;
 	/* KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode
@@ -751,7 +755,11 @@ static inline void kvm_guest_enter(void)
 
 static inline void kvm_guest_exit(void)
 {
-	vtime_account(current);
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
 	current->flags &= ~PF_VCPU;
 }
 

include/linux/vtime.h

@@ -0,0 +1,47 @@
+#ifndef _LINUX_KERNEL_VTIME_H
+#define _LINUX_KERNEL_VTIME_H
+
+struct task_struct;
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void vtime_task_switch(struct task_struct *prev);
+extern void __vtime_account_system(struct task_struct *tsk);
+extern void vtime_account_system(struct task_struct *tsk);
+extern void __vtime_account_idle(struct task_struct *tsk);
+extern void vtime_account(struct task_struct *tsk);
+#else
+static inline void vtime_task_switch(struct task_struct *prev) { }
+static inline void __vtime_account_system(struct task_struct *tsk) { }
+static inline void vtime_account_system(struct task_struct *tsk) { }
+static inline void vtime_account(struct task_struct *tsk) { }
+#endif
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+extern void irqtime_account_irq(struct task_struct *tsk);
+#else
+static inline void irqtime_account_irq(struct task_struct *tsk) { }
+#endif
+
+static inline void vtime_account_irq_enter(struct task_struct *tsk)
+{
+	/*
+	 * Hardirq can interrupt idle task anytime. So we need vtime_account()
+	 * that performs the idle check in CONFIG_VIRT_CPU_ACCOUNTING.
+	 * Softirq can also interrupt idle task directly if it calls
+	 * local_bh_enable(). Such case probably don't exist but we never know.
+	 * Ksoftirqd is not concerned because idle time is flushed on context
+	 * switch. Softirqs in the end of hardirqs are also not a problem because
+	 * the idle time is flushed on hardirq time already.
+	 */
+	vtime_account(tsk);
+	irqtime_account_irq(tsk);
+}
+
+static inline void vtime_account_irq_exit(struct task_struct *tsk)
+{
+	/* On hard|softirq exit we always account to hard|softirq cputime */
+	__vtime_account_system(tsk);
+	irqtime_account_irq(tsk);
+}
+
+#endif /* _LINUX_KERNEL_VTIME_H */

kernel/sched/cputime.c

@@ -43,7 +43,7 @@ DEFINE_PER_CPU(seqcount_t, irq_time_seq);
  * Called before incrementing preempt_count on {soft,}irq_enter
  * and before decrementing preempt_count on {soft,}irq_exit.
  */
-void vtime_account(struct task_struct *curr)
+void irqtime_account_irq(struct task_struct *curr)
 {
 	unsigned long flags;
 	s64 delta;
@@ -73,7 +73,7 @@ void vtime_account(struct task_struct *curr)
 	irq_time_write_end();
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(vtime_account);
+EXPORT_SYMBOL_GPL(irqtime_account_irq);
 
 static int irqtime_account_hi_update(void)
 {
@@ -433,10 +433,20 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	*st = cputime.stime;
 }
 
+void vtime_account_system(struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__vtime_account_system(tsk);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(vtime_account_system);
+
 /*
  * Archs that account the whole time spent in the idle task
  * (outside irq) as idle time can rely on this and just implement
- * vtime_account_system() and vtime_account_idle(). Archs that
+ * __vtime_account_system() and __vtime_account_idle(). Archs that
  * have other meaning of the idle time (s390 only includes the
  * time spent by the CPU when it's in low power mode) must override
  * vtime_account().
@@ -449,9 +459,9 @@ void vtime_account(struct task_struct *tsk)
 	local_irq_save(flags);
 
 	if (in_interrupt() || !is_idle_task(tsk))
-		vtime_account_system(tsk);
+		__vtime_account_system(tsk);
 	else
-		vtime_account_idle(tsk);
+		__vtime_account_idle(tsk);
 
 	local_irq_restore(flags);
 }

kernel/softirq.c

@@ -221,7 +221,7 @@ asmlinkage void __do_softirq(void)
 	current->flags &= ~PF_MEMALLOC;
 
 	pending = local_softirq_pending();
-	vtime_account(current);
+	vtime_account_irq_enter(current);
 
 	__local_bh_disable((unsigned long)__builtin_return_address(0),
 				SOFTIRQ_OFFSET);
@@ -272,7 +272,7 @@ restart:
 
 	lockdep_softirq_exit();
 
-	vtime_account(current);
+	vtime_account_irq_exit(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
@@ -341,7 +341,7 @@ static inline void invoke_softirq(void)
  */
 void irq_exit(void)
 {
-	vtime_account(current);
+	vtime_account_irq_exit(current);
 	trace_hardirq_exit();
 	sub_preempt_count(IRQ_EXIT_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())