Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The biggest changes in this cycle were:

   - Make kcpustat vtime aware (Frederic Weisbecker)

   - Rework the CFS load_balance() logic (Vincent Guittot)

   - Misc cleanups, smaller enhancements, fixes.

  The load-balancing rework is the most intrusive change: it replaces
  the old heuristics that have become less meaningful after the
  introduction of the PELT metrics, with a grounds-up load-balancing
  algorithm.

  As such it's not really an iterative series, but replaces the old
  load-balancing logic with the new one. We hope there are no
  performance regressions left - but statistically it's highly probable
  that there *is* going to be some workload that is hurting from these
  chnages. If so then we'd prefer to have a look at that workload and
  fix its scheduling, instead of reverting the changes"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  rackmeter: Use vtime aware kcpustat accessor
  leds: Use all-in-one vtime aware kcpustat accessor
  cpufreq: Use vtime aware kcpustat accessors for user time
  procfs: Use all-in-one vtime aware kcpustat accessor
  sched/vtime: Bring up complete kcpustat accessor
  sched/cputime: Support other fields on kcpustat_field()
  sched/cpufreq: Move the cfs_rq_util_change() call to cpufreq_update_util()
  sched/fair: Add comments for group_type and balancing at SD_NUMA level
  sched/fair: Fix rework of find_idlest_group()
  sched/uclamp: Fix overzealous type replacement
  sched/Kconfig: Fix spelling mistake in user-visible help text
  sched/core: Further clarify sched_class::set_next_task()
  sched/fair: Use mul_u32_u32()
  sched/core: Simplify sched_class::pick_next_task()
  sched/core: Optimize pick_next_task()
  sched/core: Make pick_next_task_idle() more consistent
  sched/fair: Better document newidle_balance()
  leds: Use vtime aware kcpustat accessor to fetch CPUTIME_SYSTEM
  cpufreq: Use vtime aware kcpustat accessor to fetch CPUTIME_SYSTEM
  procfs: Use vtime aware kcpustat accessor to fetch CPUTIME_SYSTEM
  ...

arch/ia64/kernel/time.c

@@ -132,7 +132,7 @@ static __u64 vtime_delta(struct task_struct *tsk)
 	return delta_stime;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct thread_info *ti = task_thread_info(tsk);
 	__u64 stime = vtime_delta(tsk);
@@ -146,7 +146,7 @@ void vtime_account_system(struct task_struct *tsk)
 	else
 		ti->stime += stime;
 }
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 void vtime_account_idle(struct task_struct *tsk)
 {

arch/powerpc/kernel/time.c

@@ -338,7 +338,7 @@ static unsigned long vtime_delta(struct task_struct *tsk,
 	return stime;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_kernel(struct task_struct *tsk)
 {
 	unsigned long stime, stime_scaled, steal_time;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
@@ -366,7 +366,7 @@ void vtime_account_system(struct task_struct *tsk)
 #endif
 	}
 }
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
@@ -395,7 +395,7 @@ static void vtime_flush_scaled(struct task_struct *tsk,
 /*
  * Account the whole cputime accumulated in the paca
  * Must be called with interrupts disabled.
- * Assumes that vtime_account_system/idle() has been called
+ * Assumes that vtime_account_kernel/idle() has been called
  * recently (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */

arch/s390/kernel/vtime.c

@@ -247,9 +247,9 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_kernel(struct task_struct *tsk)
 __attribute__((alias("vtime_account_irq_enter")));
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 /*
  * Sorted add to a list. List is linear searched until first bigger

arch/x86/entry/calling.h

@@ -354,7 +354,7 @@ For 32-bit we have the following conventions - kernel is built with
 .macro CALL_enter_from_user_mode
 #ifdef CONFIG_CONTEXT_TRACKING
 #ifdef CONFIG_JUMP_LABEL
-	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_key, def=0
 #endif
 	call enter_from_user_mode
 .Lafter_call_\@:

drivers/cpufreq/cpufreq.c

@@ -113,18 +113,21 @@ EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
 
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
-	u64 idle_time;
+	struct kernel_cpustat kcpustat;
 	u64 cur_wall_time;
+	u64 idle_time;
 	u64 busy_time;
 
 	cur_wall_time = jiffies64_to_nsecs(get_jiffies_64());
 
-	busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
+	kcpustat_cpu_fetch(&kcpustat, cpu);
+
+	busy_time = kcpustat.cpustat[CPUTIME_USER];
+	busy_time += kcpustat.cpustat[CPUTIME_SYSTEM];
+	busy_time += kcpustat.cpustat[CPUTIME_IRQ];
+	busy_time += kcpustat.cpustat[CPUTIME_SOFTIRQ];
+	busy_time += kcpustat.cpustat[CPUTIME_STEAL];
+	busy_time += kcpustat.cpustat[CPUTIME_NICE];
 
 	idle_time = cur_wall_time - busy_time;
 	if (wall)

drivers/cpufreq/cpufreq_governor.c

@@ -105,7 +105,7 @@ void gov_update_cpu_data(struct dbs_data *dbs_data)
 			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time,
 								  dbs_data->io_is_busy);
 			if (dbs_data->ignore_nice_load)
-				j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+				j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j);
 		}
 	}
 }
@@ -149,7 +149,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 		j_cdbs->prev_cpu_idle = cur_idle_time;
 
 		if (ignore_nice) {
-			u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+			u64 cur_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j);
 
 			idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC);
 			j_cdbs->prev_cpu_nice = cur_nice;
@@ -530,7 +530,7 @@ int cpufreq_dbs_governor_start(struct cpufreq_policy *policy)
 		j_cdbs->prev_load = 0;
 
 		if (ignore_nice)
-			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+			j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j);
 	}
 
 	gov->start(policy);

drivers/leds/trigger/ledtrig-activity.c

@@ -57,11 +57,15 @@ static void led_activity_function(struct timer_list *t)
 	curr_used = 0;
 
 	for_each_possible_cpu(i) {
-		curr_used += kcpustat_cpu(i).cpustat[CPUTIME_USER]
-			  +  kcpustat_cpu(i).cpustat[CPUTIME_NICE]
-			  +  kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]
-			  +  kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]
-			  +  kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
+		struct kernel_cpustat kcpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		curr_used += kcpustat.cpustat[CPUTIME_USER]
+			  +  kcpustat.cpustat[CPUTIME_NICE]
+			  +  kcpustat.cpustat[CPUTIME_SYSTEM]
+			  +  kcpustat.cpustat[CPUTIME_SOFTIRQ]
+			  +  kcpustat.cpustat[CPUTIME_IRQ];
 		cpus++;
 	}
 

drivers/macintosh/rack-meter.c

@@ -81,13 +81,14 @@ static int rackmeter_ignore_nice;
  */
 static inline u64 get_cpu_idle_time(unsigned int cpu)
 {
+	struct kernel_cpustat *kcpustat = &kcpustat_cpu(cpu);
 	u64 retval;
 
-	retval = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE] +
-		 kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
+	retval = kcpustat->cpustat[CPUTIME_IDLE] +
+		 kcpustat->cpustat[CPUTIME_IOWAIT];
 
 	if (rackmeter_ignore_nice)
-		retval += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
+		retval += kcpustat_field(kcpustat, CPUTIME_NICE, cpu);
 
 	return retval;
 }

fs/proc/stat.c

@@ -120,20 +120,23 @@ static int show_stat(struct seq_file *p, void *v)
 	getboottime64(&boottime);
 
 	for_each_possible_cpu(i) {
-		struct kernel_cpustat *kcs = &kcpustat_cpu(i);
-
-		user += kcs->cpustat[CPUTIME_USER];
-		nice += kcs->cpustat[CPUTIME_NICE];
-		system += kcs->cpustat[CPUTIME_SYSTEM];
-		idle += get_idle_time(kcs, i);
-		iowait += get_iowait_time(kcs, i);
-		irq += kcs->cpustat[CPUTIME_IRQ];
-		softirq += kcs->cpustat[CPUTIME_SOFTIRQ];
-		steal += kcs->cpustat[CPUTIME_STEAL];
-		guest += kcs->cpustat[CPUTIME_GUEST];
-		guest_nice += kcs->cpustat[CPUTIME_GUEST_NICE];
-		sum += kstat_cpu_irqs_sum(i);
-		sum += arch_irq_stat_cpu(i);
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		user		+= cpustat[CPUTIME_USER];
+		nice		+= cpustat[CPUTIME_NICE];
+		system		+= cpustat[CPUTIME_SYSTEM];
+		idle		+= get_idle_time(&kcpustat, i);
+		iowait		+= get_iowait_time(&kcpustat, i);
+		irq		+= cpustat[CPUTIME_IRQ];
+		softirq		+= cpustat[CPUTIME_SOFTIRQ];
+		steal		+= cpustat[CPUTIME_STEAL];
+		guest		+= cpustat[CPUTIME_GUEST];
+		guest_nice	+= cpustat[CPUTIME_USER];
+		sum		+= kstat_cpu_irqs_sum(i);
+		sum		+= arch_irq_stat_cpu(i);
 
 		for (j = 0; j < NR_SOFTIRQS; j++) {
 			unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
@@ -157,19 +160,22 @@ static int show_stat(struct seq_file *p, void *v)
 	seq_putc(p, '\n');
 
 	for_each_online_cpu(i) {
-		struct kernel_cpustat *kcs = &kcpustat_cpu(i);
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
 
 		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
-		user = kcs->cpustat[CPUTIME_USER];
-		nice = kcs->cpustat[CPUTIME_NICE];
-		system = kcs->cpustat[CPUTIME_SYSTEM];
-		idle = get_idle_time(kcs, i);
-		iowait = get_iowait_time(kcs, i);
-		irq = kcs->cpustat[CPUTIME_IRQ];
-		softirq = kcs->cpustat[CPUTIME_SOFTIRQ];
-		steal = kcs->cpustat[CPUTIME_STEAL];
-		guest = kcs->cpustat[CPUTIME_GUEST];
-		guest_nice = kcs->cpustat[CPUTIME_GUEST_NICE];
+		user		= cpustat[CPUTIME_USER];
+		nice		= cpustat[CPUTIME_NICE];
+		system		= cpustat[CPUTIME_SYSTEM];
+		idle		= get_idle_time(&kcpustat, i);
+		iowait		= get_iowait_time(&kcpustat, i);
+		irq		= cpustat[CPUTIME_IRQ];
+		softirq		= cpustat[CPUTIME_SOFTIRQ];
+		steal		= cpustat[CPUTIME_STEAL];
+		guest		= cpustat[CPUTIME_GUEST];
+		guest_nice	= cpustat[CPUTIME_USER];
 		seq_printf(p, "cpu%d", i);
 		seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
 		seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));

include/linux/context_tracking.h

@@ -22,34 +22,34 @@ extern void context_tracking_user_exit(void);
 
 static inline void user_enter(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		context_tracking_enter(CONTEXT_USER);
 
 }
 static inline void user_exit(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		context_tracking_exit(CONTEXT_USER);
 }
 
 /* Called with interrupts disabled.  */
 static inline void user_enter_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_enter(CONTEXT_USER);
 
 }
 static inline void user_exit_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_exit(CONTEXT_USER);
 }
 
 static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
 
-	if (!context_tracking_is_enabled())
+	if (!context_tracking_enabled())
 		return 0;
 
 	prev_ctx = this_cpu_read(context_tracking.state);
@@ -61,7 +61,7 @@ static inline enum ctx_state exception_enter(void)
 
 static inline void exception_exit(enum ctx_state prev_ctx)
 {
-	if (context_tracking_is_enabled()) {
+	if (context_tracking_enabled()) {
 		if (prev_ctx != CONTEXT_KERNEL)
 			context_tracking_enter(prev_ctx);
 	}
@@ -77,7 +77,7 @@ static inline void exception_exit(enum ctx_state prev_ctx)
  */
 static inline enum ctx_state ct_state(void)
 {
-	return context_tracking_is_enabled() ?
+	return context_tracking_enabled() ?
 		this_cpu_read(context_tracking.state) : CONTEXT_DISABLED;
 }
 #else
@@ -90,7 +90,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; }
 #endif /* !CONFIG_CONTEXT_TRACKING */
 
-#define CT_WARN_ON(cond) WARN_ON(context_tracking_is_enabled() && (cond))
+#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond))
 
 #ifdef CONFIG_CONTEXT_TRACKING_FORCE
 extern void context_tracking_init(void);
@@ -103,12 +103,12 @@ static inline void context_tracking_init(void) { }
 /* must be called with irqs disabled */
 static inline void guest_enter_irqoff(void)
 {
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		vtime_guest_enter(current);
 	else
 		current->flags |= PF_VCPU;
 
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_enter(CONTEXT_GUEST);
 
 	/* KVM does not hold any references to rcu protected data when it
@@ -118,16 +118,16 @@ static inline void guest_enter_irqoff(void)
 	 * one time slice). Lets treat guest mode as quiescent state, just like
 	 * we do with user-mode execution.
 	 */
-	if (!context_tracking_cpu_is_enabled())
+	if (!context_tracking_enabled_this_cpu())
 		rcu_virt_note_context_switch(smp_processor_id());
 }
 
 static inline void guest_exit_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_exit(CONTEXT_GUEST);
 
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		vtime_guest_exit(current);
 	else
 		current->flags &= ~PF_VCPU;
@@ -141,15 +141,15 @@ static inline void guest_enter_irqoff(void)
 	 * to assume that it's the stime pending cputime
 	 * to flush.
 	 */
-	vtime_account_system(current);
+	vtime_account_kernel(current);
 	current->flags |= PF_VCPU;
 	rcu_virt_note_context_switch(smp_processor_id());
 }
 
 static inline void guest_exit_irqoff(void)
 {
 	/* Flush the guest cputime we spent on the guest */
-	vtime_account_system(current);
+	vtime_account_kernel(current);
 	current->flags &= ~PF_VCPU;
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */

include/linux/context_tracking_state.h

@@ -23,17 +23,22 @@ struct context_tracking {
 };
 
 #ifdef CONFIG_CONTEXT_TRACKING
-extern struct static_key_false context_tracking_enabled;
+extern struct static_key_false context_tracking_key;
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
-static inline bool context_tracking_is_enabled(void)
+static inline bool context_tracking_enabled(void)
 {
-	return static_branch_unlikely(&context_tracking_enabled);
+	return static_branch_unlikely(&context_tracking_key);
 }
 
-static inline bool context_tracking_cpu_is_enabled(void)
+static inline bool context_tracking_enabled_cpu(int cpu)
 {
-	return __this_cpu_read(context_tracking.active);
+	return context_tracking_enabled() && per_cpu(context_tracking.active, cpu);
+}
+
+static inline bool context_tracking_enabled_this_cpu(void)
+{
+	return context_tracking_enabled() && __this_cpu_read(context_tracking.active);
 }
 
 static inline bool context_tracking_in_user(void)
@@ -42,9 +47,9 @@ static inline bool context_tracking_in_user(void)
 }
 #else
 static inline bool context_tracking_in_user(void) { return false; }
-static inline bool context_tracking_active(void) { return false; }
-static inline bool context_tracking_is_enabled(void) { return false; }
-static inline bool context_tracking_cpu_is_enabled(void) { return false; }
+static inline bool context_tracking_enabled(void) { return false; }
+static inline bool context_tracking_enabled_cpu(int cpu) { return false; }
+static inline bool context_tracking_enabled_this_cpu(void) { return false; }
 #endif /* CONFIG_CONTEXT_TRACKING */
 
 #endif