Merge commit 'cputime/cputime'

Conflicts:

	kernel/sched.c

9 files changed, 102 insertions, 66 deletions

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 65c10a42c88f..f0ebb342409d 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -93,13 +93,14 @@ void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next)
 	now = ia64_get_itc();
 
 	delta_stime = cycle_to_cputime(pi->ac_stime + (now - pi->ac_stamp));
-	account_system_time(prev, 0, delta_stime);
-	account_system_time_scaled(prev, delta_stime);
+	if (idle_task(smp_processor_id()) != prev)
+		account_system_time(prev, 0, delta_stime, delta_stime);
+	else
+		account_idle_time(delta_stime);
 
 	if (pi->ac_utime) {
 		delta_utime = cycle_to_cputime(pi->ac_utime);
-		account_user_time(prev, delta_utime);
-		account_user_time_scaled(prev, delta_utime);
+		account_user_time(prev, delta_utime, delta_utime);
 	}
 
 	pi->ac_stamp = ni->ac_stamp = now;
@@ -122,8 +123,10 @@ void account_system_vtime(struct task_struct *tsk)
 	now = ia64_get_itc();
 
 	delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
-	account_system_time(tsk, 0, delta_stime);
-	account_system_time_scaled(tsk, delta_stime);
+	if (irq_count() || idle_task(smp_processor_id()) != tsk)
+		account_system_time(tsk, 0, delta_stime, delta_stime);
+	else
+		account_idle_time(delta_stime);
 	ti->ac_stime = 0;
 
 	ti->ac_stamp = now;
@@ -143,8 +146,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 
 	if (ti->ac_utime) {
 		delta_utime = cycle_to_cputime(ti->ac_utime);
-		account_user_time(p, delta_utime);
-		account_user_time_scaled(p, delta_utime);
+		account_user_time(p, delta_utime, delta_utime);
 		ti->ac_utime = 0;
 	}
 }
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 51b201ddf9a1..fb7049c054c0 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -33,6 +33,7 @@
 #include <linux/mqueue.h>
 #include <linux/hardirq.h>
 #include <linux/utsname.h>
+#include <linux/kernel_stat.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 99f1ddd68582..c9564031a2a9 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -256,8 +256,10 @@ void account_system_vtime(struct task_struct *tsk)
 		delta += sys_time;
 		get_paca()->system_time = 0;
 	}
-	account_system_time(tsk, 0, delta);
-	account_system_time_scaled(tsk, deltascaled);
+	if (in_irq() || idle_task(smp_processor_id()) != tsk)
+		account_system_time(tsk, 0, delta, deltascaled);
+	else
+		account_idle_time(delta);
 	per_cpu(cputime_last_delta, smp_processor_id()) = delta;
 	per_cpu(cputime_scaled_last_delta, smp_processor_id()) = deltascaled;
 	local_irq_restore(flags);
@@ -275,10 +277,8 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 
 	utime = get_paca()->user_time;
 	get_paca()->user_time = 0;
-	account_user_time(tsk, utime);
-
 	utimescaled = cputime_to_scaled(utime);
-	account_user_time_scaled(tsk, utimescaled);
+	account_user_time(tsk, utime, utimescaled);
 }
 
 /*
@@ -338,8 +338,12 @@ void calculate_steal_time(void)
 	tb = mftb();
 	purr = mfspr(SPRN_PURR);
 	stolen = (tb - pme->tb) - (purr - pme->purr);
-	if (stolen > 0)
-		account_steal_time(current, stolen);
+	if (stolen > 0) {
+		if (idle_task(smp_processor_id()) != current)
+			account_steal_time(stolen);
+		else
+			account_idle_time(stolen);
+	}
 	pme->tb = tb;
 	pme->purr = purr;
 }
diff --git a/arch/s390/include/asm/cpu.h b/arch/s390/include/asm/cpu.h
index e5a6a9ba3adf..a6f6ac397b06 100644
--- a/arch/s390/include/asm/cpu.h
+++ b/arch/s390/include/asm/cpu.h
@@ -14,8 +14,8 @@
 
 struct s390_idle_data {
 	spinlock_t lock;
-	unsigned int in_idle;
 	unsigned long long idle_count;
+	unsigned long long idle_delta;
 	unsigned long long idle_enter;
 	unsigned long long idle_time;
 };
@@ -26,7 +26,7 @@ void s390_idle_leave(void);
 
 static inline void s390_idle_check(void)
 {
-	if ((&__get_cpu_var(s390_idle))->in_idle)
+	if ((&__get_cpu_var(s390_idle))->idle_enter != 0ULL)
 		s390_idle_leave();
 }
 
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 04f8c67a6101..b6bc20862221 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -38,6 +38,7 @@
 #include <linux/utsname.h>
 #include <linux/tick.h>
 #include <linux/elfcore.h>
+#include <linux/kernel_stat.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -79,30 +80,26 @@ DEFINE_PER_CPU(struct s390_idle_data, s390_idle) = {
 	.lock = __SPIN_LOCK_UNLOCKED(s390_idle.lock)
 };
 
-static int s390_idle_enter(void)
+void s390_idle_leave(void)
 {
 	struct s390_idle_data *idle;
+	unsigned long long idle_time;
 
 	idle = &__get_cpu_var(s390_idle);
+	idle_time = S390_lowcore.int_clock - idle->idle_enter;
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	idle_time += idle->idle_delta;
+	idle->idle_delta = idle_time & 4095;
+	idle_time -= idle->idle_delta;
+	account_idle_time(idle_time >> 12);
+	S390_lowcore.last_update_clock = S390_lowcore.int_clock;
+#endif
 	spin_lock(&idle->lock);
+	idle->idle_time += idle_time;
+	idle->idle_enter = 0ULL;
 	idle->idle_count++;
-	idle->in_idle = 1;
-	idle->idle_enter = get_clock();
 	spin_unlock(&idle->lock);
-	vtime_stop_cpu_timer();
-	return NOTIFY_OK;
-}
-
-void s390_idle_leave(void)
-{
-	struct s390_idle_data *idle;
-
 	vtime_start_cpu_timer();
-	idle = &__get_cpu_var(s390_idle);
-	spin_lock(&idle->lock);
-	idle->idle_time += get_clock() - idle->idle_enter;
-	idle->in_idle = 0;
-	spin_unlock(&idle->lock);
 }
 
 extern void s390_handle_mcck(void);
@@ -111,16 +108,16 @@ extern void s390_handle_mcck(void);
  */
 static void default_idle(void)
 {
+	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
+	unsigned long addr;
+	psw_t psw;
+
 	/* CPU is going idle. */
 	local_irq_disable();
 	if (need_resched()) {
 		local_irq_enable();
 		return;
 	}
-	if (s390_idle_enter() == NOTIFY_BAD) {
-		local_irq_enable();
-		return;
-	}
 #ifdef CONFIG_HOTPLUG_CPU
 	if (cpu_is_offline(smp_processor_id())) {
 		preempt_enable_no_resched();
@@ -138,9 +135,42 @@ static void default_idle(void)
 	trace_hardirqs_on();
 	/* Don't trace preempt off for idle. */
 	stop_critical_timings();
+	vtime_stop_cpu_timer();
+
+	/*
+	 * The inline assembly is equivalent to
+	 * 	idle->idle_enter = get_clock();
+	 * 	__load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT |
+	 *			   PSW_MASK_IO | PSW_MASK_EXT);
+	 * The difference is that the inline assembly makes sure that
+	 * the stck instruction is right before the lpsw instruction.
+	 * This is done to increase the precision.
+	 */
+
 	/* Wait for external, I/O or machine check interrupt. */
-	__load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT |
-			PSW_MASK_IO | PSW_MASK_EXT);
+	psw.mask = psw_kernel_bits|PSW_MASK_WAIT|PSW_MASK_IO|PSW_MASK_EXT;
+#ifndef __s390x__
+	asm volatile(
+		"	basr	%0,0\n"
+		"0:	ahi	%0,1f-0b\n"
+		"	st	%0,4(%2)\n"
+		"	stck	0(%3)\n"
+		"	lpsw	0(%2)\n"
+		"1:"
+		: "=&d" (addr), "=m" (idle->idle_enter)
+		: "a" (&psw), "a" (&idle->idle_enter), "m" (psw)
+		: "memory", "cc");
+#else /* __s390x__ */
+	asm volatile(
+		"	larl	%0,1f\n"
+		"	stg	%0,8(%2)\n"
+		"	stck	0(%3)\n"
+		"	lpswe	0(%2)\n"
+		"1:"
+		: "=&d" (addr), "=m" (idle->idle_enter)
+		: "a" (&psw), "a" (&idle->idle_enter), "m" (psw)
+		: "memory", "cc");
+#endif /* __s390x__ */
 	start_critical_timings();
 }
 
diff --git a/arch/s390/kernel/s390_ext.c b/arch/s390/kernel/s390_ext.c
index e019b419efc6..a0d2d55d7fb3 100644
--- a/arch/s390/kernel/s390_ext.c
+++ b/arch/s390/kernel/s390_ext.c
@@ -119,8 +119,8 @@ void do_extint(struct pt_regs *regs, unsigned short code)
 	struct pt_regs *old_regs;
 
 	old_regs = set_irq_regs(regs);
-	irq_enter();
 	s390_idle_check();
+	irq_enter();
 	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
 		/* Serve timer interrupts first. */
 		clock_comparator_work();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index e26c2782c775..179732fca7ee 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -850,9 +850,11 @@ static ssize_t show_idle_count(struct sys_device *dev,
 	unsigned long long idle_count;
 
 	idle = &per_cpu(s390_idle, dev->id);
-	spin_lock_irq(&idle->lock);
+	spin_lock(&idle->lock);
 	idle_count = idle->idle_count;
-	spin_unlock_irq(&idle->lock);
+	if (idle->idle_enter)
+		idle_count++;
+	spin_unlock(&idle->lock);
 	return sprintf(buf, "%llu\n", idle_count);
 }
 static SYSDEV_ATTR(idle_count, 0444, show_idle_count, NULL);
@@ -861,18 +863,17 @@ static ssize_t show_idle_time(struct sys_device *dev,
 				struct sysdev_attribute *attr, char *buf)
 {
 	struct s390_idle_data *idle;
-	unsigned long long new_time;
+	unsigned long long now, idle_time, idle_enter;
 
 	idle = &per_cpu(s390_idle, dev->id);
-	spin_lock_irq(&idle->lock);
-	if (idle->in_idle) {
-		new_time = get_clock();
-		idle->idle_time += new_time - idle->idle_enter;
-		idle->idle_enter = new_time;
-	}
-	new_time = idle->idle_time;
-	spin_unlock_irq(&idle->lock);
-	return sprintf(buf, "%llu\n", new_time >> 12);
+	spin_lock(&idle->lock);
+	now = get_clock();
+	idle_time = idle->idle_time;
+	idle_enter = idle->idle_enter;
+	if (idle_enter != 0ULL && idle_enter < now)
+		idle_time += now - idle_enter;
+	spin_unlock(&idle->lock);
+	return sprintf(buf, "%llu\n", idle_time >> 12);
 }
 static SYSDEV_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 0fa5dc5d68e1..bda56ef4a014 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -51,18 +51,18 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 	rcu_user_flag = cputime != 0;
 	S390_lowcore.user_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_user_time(tsk, cputime);
+	account_user_time(tsk, cputime, cputime);
 
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, HARDIRQ_OFFSET, cputime);
+	account_system_time(tsk, HARDIRQ_OFFSET, cputime, cputime);
 
 	cputime = S390_lowcore.steal_clock;
 	if ((__s64) cputime > 0) {
 		cputime >>= 12;
 		S390_lowcore.steal_clock -= cputime << 12;
-		account_steal_time(tsk, cputime);
+		account_steal_time(cputime);
 	}
 }
 
@@ -83,12 +83,12 @@ void account_vtime(struct task_struct *tsk)
 	cputime = S390_lowcore.user_timer >> 12;
 	S390_lowcore.user_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_user_time(tsk, cputime);
+	account_user_time(tsk, cputime, cputime);
 
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, 0, cputime);
+	account_system_time(tsk, 0, cputime, cputime);
 }
 
 /*
@@ -108,7 +108,7 @@ void account_system_vtime(struct task_struct *tsk)
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, 0, cputime);
+	account_system_time(tsk, 0, cputime, cputime);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
@@ -146,8 +146,8 @@ void vtime_start_cpu_timer(void)
 	if (vt_list->idle & 1LL<<63)
 		return;
 
-	if (!list_empty(&vt_list->list))
-		set_vtimer(vt_list->idle);
+	S390_lowcore.last_update_timer = S390_lowcore.async_enter_timer;
+	set_vtimer(vt_list->idle);
 }
 
 void vtime_stop_cpu_timer(void)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 65d75a6be0ba..14f240623497 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -132,8 +132,7 @@ static void do_stolen_accounting(void)
 	*snap = state;
 
 	/* Add the appropriate number of ticks of stolen time,
-	   including any left-overs from last time.  Passing NULL to
-	   account_steal_time accounts the time as stolen. */
+	   including any left-overs from last time. */
 	stolen = runnable + offline + __get_cpu_var(residual_stolen);
 
 	if (stolen < 0)
@@ -141,11 +140,10 @@ static void do_stolen_accounting(void)
 
 	ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
 	__get_cpu_var(residual_stolen) = stolen;
-	account_steal_time(NULL, ticks);
+	account_steal_ticks(ticks);
 
 	/* Add the appropriate number of ticks of blocked time,
-	   including any left-overs from last time.  Passing idle to
-	   account_steal_time accounts the time as idle/wait. */
+	   including any left-overs from last time. */
 	blocked += __get_cpu_var(residual_blocked);
 
 	if (blocked < 0)
@@ -153,7 +151,7 @@ static void do_stolen_accounting(void)
 
 	ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
 	__get_cpu_var(residual_blocked) = blocked;
-	account_steal_time(idle_task(smp_processor_id()), ticks);
+	account_idle_ticks(ticks);
 }
 
 /*