Merge tag 'sched-cputime-for-mingo' of...

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

Pull more cputime cleanups from Frederic Weisbecker:

 * Get rid of underscores polluting the vtime namespace

 * Consolidate context switch and tick handling

 * Improve debuggability by detecting irq unsafe callers
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/ia64/include/asm/cputime.h

@@ -103,5 +103,7 @@ static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
 #define cputime64_to_clock_t(__ct)	\
 	cputime_to_clock_t((__force cputime_t)__ct)
 
+extern void arch_vtime_task_switch(struct task_struct *tsk);
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 #endif /* __IA64_CPUTIME_H */

arch/ia64/kernel/time.c

@@ -83,7 +83,7 @@ static struct clocksource *itc_clocksource;
 
 extern cputime_t cycle_to_cputime(u64 cyc);
 
-static void vtime_account_user(struct task_struct *tsk)
+void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t delta_utime;
 	struct thread_info *ti = task_thread_info(tsk);
@@ -100,18 +100,11 @@ static void vtime_account_user(struct task_struct *tsk)
  * accumulated times to the current process, and to prepare accounting on
  * the next process.
  */
-void vtime_task_switch(struct task_struct *prev)
+void arch_vtime_task_switch(struct task_struct *prev)
 {
 	struct thread_info *pi = task_thread_info(prev);
 	struct thread_info *ni = task_thread_info(current);
 
-	if (idle_task(smp_processor_id()) != prev)
-		__vtime_account_system(prev);
-	else
-		__vtime_account_idle(prev);
-
-	vtime_account_user(prev);
-
 	pi->ac_stamp = ni->ac_stamp;
 	ni->ac_stime = ni->ac_utime = 0;
 }
@@ -126,6 +119,8 @@ static cputime_t vtime_delta(struct task_struct *tsk)
 	cputime_t delta_stime;
 	__u64 now;
 
+	WARN_ON_ONCE(!irqs_disabled());
+
 	now = ia64_get_itc();
 
 	delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
@@ -135,27 +130,18 @@ 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));
 }
 
-/*
- * Called from the timer interrupt handler to charge accumulated user time
- * to the current process.  Must be called with interrupts disabled.
- */
-void account_process_tick(struct task_struct *p, int user_tick)
-{
-	vtime_account_user(p);
-}
-
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
 static irqreturn_t

arch/powerpc/include/asm/cputime.h

@@ -228,6 +228,8 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 
 #define cputime64_to_clock_t(ct)	cputime_to_clock_t((cputime_t)(ct))
 
+static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
+
 #endif /* __KERNEL__ */
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 #endif /* __POWERPC_CPUTIME_H */

arch/powerpc/kernel/time.c

@@ -297,6 +297,8 @@ static u64 vtime_delta(struct task_struct *tsk,
 	u64 now, nowscaled, deltascaled;
 	u64 udelta, delta, user_scaled;
 
+	WARN_ON_ONCE(!irqs_disabled());
+
 	now = mftb();
 	nowscaled = read_spurr(now);
 	get_paca()->system_time += now - get_paca()->starttime;
@@ -336,7 +338,7 @@ 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 +348,7 @@ 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;
 
@@ -355,15 +357,15 @@ void __vtime_account_idle(struct task_struct *tsk)
 }
 
 /*
- * Transfer the user and system times accumulated in the paca
- * by the exception entry and exit code to the generic process
- * user and system time records.
+ * Transfer the user time accumulated in the paca
+ * by the exception entry and exit code to the generic
+ * process user time records.
  * Must be called with interrupts disabled.
- * Assumes that vtime_account() has been called recently
- * (i.e. since the last entry from usermode) so that
+ * Assumes that vtime_account_system/idle() has been called
+ * recently (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
-void account_process_tick(struct task_struct *tsk, int user_tick)
+void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t utime, utimescaled;
 
@@ -375,12 +377,6 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 	account_user_time(tsk, utime, utimescaled);
 }
 
-void vtime_task_switch(struct task_struct *prev)
-{
-	vtime_account(prev);
-	account_process_tick(prev, 0);
-}
-
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
 #define calc_cputime_factors()
 #endif

arch/s390/include/asm/cputime.h

@@ -14,6 +14,7 @@
 
 
 #define __ARCH_HAS_VTIME_ACCOUNT
+#define __ARCH_HAS_VTIME_TASK_SWITCH
 
 /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
 

arch/s390/kernel/vtime.c

@@ -112,7 +112,12 @@ void vtime_task_switch(struct task_struct *prev)
 	S390_lowcore.system_timer = ti->system_timer;
 }
 
-void account_process_tick(struct task_struct *tsk, int user_tick)
+/*
+ * In s390, accounting pending user time also implies
+ * accounting system time in order to correctly compute
+ * the stolen time accounting.
+ */
+void vtime_account_user(struct task_struct *tsk)
 {
 	if (do_account_vtime(tsk, HARDIRQ_OFFSET))
 		virt_timer_expire();
@@ -127,6 +132,8 @@ void vtime_account(struct task_struct *tsk)
 	struct thread_info *ti = task_thread_info(tsk);
 	u64 timer, system;
 
+	WARN_ON_ONCE(!irqs_disabled());
+
 	timer = S390_lowcore.last_update_timer;
 	S390_lowcore.last_update_timer = get_vtimer();
 	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
@@ -140,9 +147,9 @@ void vtime_account(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_account);
 
-void __vtime_account_system(struct task_struct *tsk)
+void vtime_account_system(struct task_struct *tsk)
 __attribute__((alias("vtime_account")));
-EXPORT_SYMBOL_GPL(__vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void __kprobes vtime_stop_cpu(void)
 {

include/linux/kernel_stat.h

@@ -127,7 +127,15 @@ extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t)
 extern void account_steal_time(cputime_t);
 extern void account_idle_time(cputime_t);
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+static inline void account_process_tick(struct task_struct *tsk, int user)
+{
+	vtime_account_user(tsk);
+}
+#else
 extern void account_process_tick(struct task_struct *, int user);
+#endif
+
 extern void account_steal_ticks(unsigned long ticks);
 extern void account_idle_ticks(unsigned long ticks);
 

include/linux/kvm_host.h

@@ -730,7 +730,7 @@ static inline void kvm_guest_enter(void)
 	 * This is running in ioctl context so we can avoid
 	 * the call to vtime_account() with its unnecessary idle check.
 	 */
-	vtime_account_system(current);
+	vtime_account_system_irqsafe(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
@@ -748,7 +748,7 @@ static inline void kvm_guest_exit(void)
 	 * This is running in ioctl context so we can avoid
 	 * the call to vtime_account() with its unnecessary idle check.
 	 */
-	vtime_account_system(current);
+	vtime_account_system_irqsafe(current);
 	current->flags &= ~PF_VCPU;
 }
 

include/linux/vtime.h

@@ -5,14 +5,15 @@ 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_system_irqsafe(struct task_struct *tsk);
+extern void vtime_account_idle(struct task_struct *tsk);
+extern void vtime_account_user(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_system_irqsafe(struct task_struct *tsk) { }
 static inline void vtime_account(struct task_struct *tsk) { }
 #endif
 
@@ -40,7 +41,7 @@ static inline void vtime_account_irq_enter(struct task_struct *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);
+	vtime_account_system(tsk);
 	irqtime_account_irq(tsk);
 }
 

kernel/sched/cputime.c

@@ -461,20 +461,33 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime
 	*st = cputime.stime;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_system_irqsafe(struct task_struct *tsk)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__vtime_account_system(tsk);
+	vtime_account_system(tsk);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe);
+
+#ifndef __ARCH_HAS_VTIME_TASK_SWITCH
+void vtime_task_switch(struct task_struct *prev)
+{
+	if (is_idle_task(prev))
+		vtime_account_idle(prev);
+	else
+		vtime_account_system(prev);
+
+	vtime_account_user(prev);
+	arch_vtime_task_switch(prev);
+}
+#endif
 
 /*
  * 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().
@@ -482,16 +495,10 @@ EXPORT_SYMBOL_GPL(vtime_account_system);
 #ifndef __ARCH_HAS_VTIME_ACCOUNT
 void vtime_account(struct task_struct *tsk)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-
 	if (in_interrupt() || !is_idle_task(tsk))
-		__vtime_account_system(tsk);
+		vtime_account_system(tsk);
 	else
-		__vtime_account_idle(tsk);
-
-	local_irq_restore(flags);
+		vtime_account_idle(tsk);
 }
 EXPORT_SYMBOL_GPL(vtime_account);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */