Merge branch 'sched/urgent' into sched/core, to avoid conflicts

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

11 files changed, 188 insertions, 110 deletions

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index b30a292..3ef6451 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -60,13 +60,14 @@
 #include <linux/sched.h>
 #include <linux/static_key.h>
 #include <linux/workqueue.h>
+#include <linux/compiler.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
  * This is default implementation.
  * Architectures and sub-architectures can override this.
  */
-unsigned long long __attribute__((weak)) sched_clock(void)
+unsigned long long __weak sched_clock(void)
 {
 	return (unsigned long long)(jiffies - INITIAL_JIFFIES)
 					* (NSEC_PER_SEC / HZ);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9cae286..13584f1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -73,6 +73,7 @@
 #include <linux/init_task.h>
 #include <linux/binfmts.h>
 #include <linux/context_tracking.h>
+#include <linux/compiler.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -2591,8 +2592,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 	if (likely(prev->sched_class == class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 		p = fair_sched_class.pick_next_task(rq, prev);
-		if (likely(p && p != RETRY_TASK))
-			return p;
+		if (unlikely(p == RETRY_TASK))
+			goto again;
+
+		/* assumes fair_sched_class->next == idle_sched_class */
+		if (unlikely(!p))
+			p = idle_sched_class.pick_next_task(rq, prev);
+
+		return p;
 	}
 
 again:
@@ -2845,52 +2852,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
 }
 EXPORT_SYMBOL(default_wake_function);
 
-static long __sched
-sleep_on_common(wait_queue_head_t *q, int state, long timeout)
-{
-	unsigned long flags;
-	wait_queue_t wait;
-
-	init_waitqueue_entry(&wait, current);
-
-	__set_current_state(state);
-
-	spin_lock_irqsave(&q->lock, flags);
-	__add_wait_queue(q, &wait);
-	spin_unlock(&q->lock);
-	timeout = schedule_timeout(timeout);
-	spin_lock_irq(&q->lock);
-	__remove_wait_queue(q, &wait);
-	spin_unlock_irqrestore(&q->lock, flags);
-
-	return timeout;
-}
-
-void __sched interruptible_sleep_on(wait_queue_head_t *q)
-{
-	sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-}
-EXPORT_SYMBOL(interruptible_sleep_on);
-
-long __sched
-interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
-	return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
-}
-EXPORT_SYMBOL(interruptible_sleep_on_timeout);
-
-void __sched sleep_on(wait_queue_head_t *q)
-{
-	sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-}
-EXPORT_SYMBOL(sleep_on);
-
-long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
-	return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
-}
-EXPORT_SYMBOL(sleep_on_timeout);
-
 #ifdef CONFIG_RT_MUTEXES
 
 /*
@@ -3169,6 +3130,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
 	dl_se->dl_throttled = 0;
 	dl_se->dl_new = 1;
+	dl_se->dl_yielded = 0;
 }
 
 static void __setscheduler_params(struct task_struct *p,
@@ -3684,6 +3646,7 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
  * sys_sched_setattr - same as above, but with extended sched_attr
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
+ * @flags: for future extension.
  */
 SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 			       unsigned int, flags)
@@ -3828,6 +3791,7 @@ err_size:
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
+ * @flags: for future extension.
  */
 SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		unsigned int, size, unsigned int, flags)
@@ -6062,6 +6026,8 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
 					,
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+		.max_newidle_lb_cost	= 0,
+		.next_decay_max_lb_cost	= jiffies,
 	};
 	SD_INIT_NAME(sd, NUMA);
 	sd->private = &tl->data;
@@ -6498,7 +6464,7 @@ static cpumask_var_t fallback_doms;
  * cpu core maps. It is supposed to return 1 if the topology changed
  * or 0 if it stayed the same.
  */
-int __attribute__((weak)) arch_update_cpu_topology(void)
+int __weak arch_update_cpu_topology(void)
 {
 	return 0;
 }
@@ -7230,7 +7196,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->put_prev_task(rq, tsk);
 
-	tg = container_of(task_css_check(tsk, cpu_cgroup_subsys_id,
+	tg = container_of(task_css_check(tsk, cpu_cgrp_id,
 				lockdep_is_held(&tsk->sighand->siglock)),
 			  struct task_group, css);
 	tg = autogroup_task_group(tsk, tg);
@@ -7657,7 +7623,7 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 {
 	struct task_struct *task;
 
-	cgroup_taskset_for_each(task, css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
@@ -7675,7 +7641,7 @@ static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
 {
 	struct task_struct *task;
 
-	cgroup_taskset_for_each(task, css, tset)
+	cgroup_taskset_for_each(task, tset)
 		sched_move_task(task);
 }
 
@@ -8014,8 +7980,7 @@ static struct cftype cpu_files[] = {
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys cpu_cgroup_subsys = {
-	.name		= "cpu",
+struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_alloc	= cpu_cgroup_css_alloc,
 	.css_free	= cpu_cgroup_css_free,
 	.css_online	= cpu_cgroup_css_online,
@@ -8023,7 +7988,6 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
-	.subsys_id	= cpu_cgroup_subsys_id,
 	.base_cftypes	= cpu_files,
 	.early_init	= 1,
 };
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 622e081..c143ee3 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -41,7 +41,7 @@ static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
 /* return cpu accounting group to which this task belongs */
 static inline struct cpuacct *task_ca(struct task_struct *tsk)
 {
-	return css_ca(task_css(tsk, cpuacct_subsys_id));
+	return css_ca(task_css(tsk, cpuacct_cgrp_id));
 }
 
 static inline struct cpuacct *parent_ca(struct cpuacct *ca)
@@ -275,11 +275,9 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val)
 	rcu_read_unlock();
 }
 
-struct cgroup_subsys cpuacct_subsys = {
-	.name		= "cpuacct",
+struct cgroup_subsys cpuacct_cgrp_subsys = {
 	.css_alloc	= cpuacct_css_alloc,
 	.css_free	= cpuacct_css_free,
-	.subsys_id	= cpuacct_subsys_id,
 	.base_cftypes	= files,
 	.early_init	= 1,
 };
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5b9bb42..ab001b5 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -210,7 +210,5 @@ int cpudl_init(struct cpudl *cp)
  */
 void cpudl_cleanup(struct cpudl *cp)
 {
-	/*
-	 * nothing to do for the moment
-	 */
+	free_cpumask_var(cp->free_cpus);
 }
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 8b836b3..3031bac 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -70,8 +70,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 	int idx = 0;
 	int task_pri = convert_prio(p->prio);
 
-	if (task_pri >= MAX_RT_PRIO)
-		return 0;
+	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
 
 	for (idx = 0; idx < task_pri; idx++) {
 		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index a95097c..72fdf06 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -332,50 +332,50 @@ out:
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq)
+					 struct rq *rq, int ticks)
 {
-	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+	u64 cputime = (__force u64) cputime_one_jiffy;
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 
 	if (steal_account_process_tick())
 		return;
 
+	cputime *= ticks;
+	scaled *= ticks;
+
 	if (irqtime_account_hi_update()) {
-		cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_IRQ] += cputime;
 	} else if (irqtime_account_si_update()) {
-		cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_SOFTIRQ] += cputime;
 	} else if (this_cpu_ksoftirqd() == p) {
 		/*
 		 * ksoftirqd time do not get accounted in cpu_softirq_time.
 		 * So, we have to handle it separately here.
 		 * Also, p->stime needs to be updated for ksoftirqd.
 		 */
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SOFTIRQ);
+		__account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
-		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_user_time(p, cputime, scaled);
 	} else if (p == rq->idle) {
-		account_idle_time(cputime_one_jiffy);
+		account_idle_time(cputime);
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
-		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_guest_time(p, cputime, scaled);
 	} else {
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SYSTEM);
+		__account_system_time(p, cputime, scaled,	CPUTIME_SYSTEM);
 	}
 }
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-	int i;
 	struct rq *rq = this_rq();
 
-	for (i = 0; i < ticks; i++)
-		irqtime_account_process_tick(current, 0, rq);
+	irqtime_account_process_tick(current, 0, rq, ticks);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 static inline void irqtime_account_idle_ticks(int ticks) {}
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq) {}
+						struct rq *rq, int nr_ticks) {}
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
@@ -464,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		return;
 
 	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq);
+		irqtime_account_process_tick(p, user_tick, rq, 1);
 		return;
 	}
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b080957..800e99b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -528,6 +528,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	sched_clock_tick();
 	update_rq_clock(rq);
 	dl_se->dl_throttled = 0;
+	dl_se->dl_yielded = 0;
 	if (p->on_rq) {
 		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
 		if (task_has_dl_policy(rq->curr))
@@ -893,10 +894,10 @@ static void yield_task_dl(struct rq *rq)
 	 * We make the task go to sleep until its current deadline by
 	 * forcing its runtime to zero. This way, update_curr_dl() stops
 	 * it and the bandwidth timer will wake it up and will give it
-	 * new scheduling parameters (thanks to dl_new=1).
+	 * new scheduling parameters (thanks to dl_yielded=1).
 	 */
 	if (p->dl.runtime > 0) {
-		rq->curr->dl.dl_new = 1;
+		rq->curr->dl.dl_yielded = 1;
 		p->dl.runtime = 0;
 	}
 	update_curr_dl(rq);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index f3344c3..695f977 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -111,8 +111,7 @@ static char *task_group_path(struct task_group *tg)
 	if (autogroup_path(tg, group_path, PATH_MAX))
 		return group_path;
 
-	cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
-	return group_path;
+	return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
 }
 #endif
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 43232b8..5d859ec 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6658,6 +6658,7 @@ static int idle_balance(struct rq *this_rq)
 	int this_cpu = this_rq->cpu;
 
 	idle_enter_fair(this_rq);
+
 	/*
 	 * We must set idle_stamp _before_ calling idle_balance(), such that we
 	 * measure the duration of idle_balance() as idle time.
@@ -6710,14 +6711,16 @@ static int idle_balance(struct rq *this_rq)
 
 	raw_spin_lock(&this_rq->lock);
 
+	if (curr_cost > this_rq->max_idle_balance_cost)
+		this_rq->max_idle_balance_cost = curr_cost;
+
 	/*
-	 * While browsing the domains, we released the rq lock.
-	 * A task could have be enqueued in the meantime
+	 * While browsing the domains, we released the rq lock, a task could
+	 * have been enqueued in the meantime. Since we're not going idle,
+	 * pretend we pulled a task.
 	 */
-	if (this_rq->cfs.h_nr_running && !pulled_task) {
+	if (this_rq->cfs.h_nr_running && !pulled_task)
 		pulled_task = 1;
-		goto out;
-	}
 
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
@@ -6727,9 +6730,6 @@ static int idle_balance(struct rq *this_rq)
 		this_rq->next_balance = next_balance;
 	}
 
-	if (curr_cost > this_rq->max_idle_balance_cost)
-		this_rq->max_idle_balance_cost = curr_cost;
-
 out:
 	/* Is there a task of a high priority class? */
 	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index b7976a1..8f4390a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -63,6 +63,136 @@ void __weak arch_cpu_idle(void)
 	local_irq_enable();
 }
 
+/**
+ * cpuidle_idle_call - the main idle function
+ *
+ * NOTE: no locks or semaphores should be used here
+ * return non-zero on failure
+ */
+static int cpuidle_idle_call(void)
+{
+	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int next_state, entered_state, ret;
+	bool broadcast;
+
+	/*
+	 * Check if the idle task must be rescheduled. If it is the
+	 * case, exit the function after re-enabling the local irq and
+	 * set again the polling flag
+	 */
+	if (current_clr_polling_and_test()) {
+		local_irq_enable();
+		__current_set_polling();
+		return 0;
+	}
+
+	/*
+	 * During the idle period, stop measuring the disabled irqs
+	 * critical sections latencies
+	 */
+	stop_critical_timings();
+
+	/*
+	 * Tell the RCU framework we are entering an idle section,
+	 * so no more rcu read side critical sections and one more
+	 * step to the grace period
+	 */
+	rcu_idle_enter();
+
+	/*
+	 * Check if the cpuidle framework is ready, otherwise fallback
+	 * to the default arch specific idle method
+	 */
+	ret = cpuidle_enabled(drv, dev);
+
+	if (!ret) {
+		/*
+		 * Ask the governor to choose an idle state it thinks
+		 * it is convenient to go to. There is *always* a
+		 * convenient idle state
+		 */
+		next_state = cpuidle_select(drv, dev);
+
+		/*
+		 * The idle task must be scheduled, it is pointless to
+		 * go to idle, just update no idle residency and get
+		 * out of this function
+		 */
+		if (current_clr_polling_and_test()) {
+			dev->last_residency = 0;
+			entered_state = next_state;
+			local_irq_enable();
+		} else {
+			broadcast = !!(drv->states[next_state].flags &
+				       CPUIDLE_FLAG_TIMER_STOP);
+
+			if (broadcast)
+				/*
+				 * Tell the time framework to switch
+				 * to a broadcast timer because our
+				 * local timer will be shutdown. If a
+				 * local timer is used from another
+				 * cpu as a broadcast timer, this call
+				 * may fail if it is not available
+				 */
+				ret = clockevents_notify(
+					CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
+					&dev->cpu);
+
+			if (!ret) {
+				trace_cpu_idle_rcuidle(next_state, dev->cpu);
+
+				/*
+				 * Enter the idle state previously
+				 * returned by the governor
+				 * decision. This function will block
+				 * until an interrupt occurs and will
+				 * take care of re-enabling the local
+				 * interrupts
+				 */
+				entered_state = cpuidle_enter(drv, dev,
+							      next_state);
+
+				trace_cpu_idle_rcuidle(PWR_EVENT_EXIT,
+						       dev->cpu);
+
+				if (broadcast)
+					clockevents_notify(
+						CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
+						&dev->cpu);
+
+				/*
+				 * Give the governor an opportunity to reflect on the
+				 * outcome
+				 */
+				cpuidle_reflect(dev, entered_state);
+			}
+		}
+	}
+
+	/*
+	 * We can't use the cpuidle framework, let's use the default
+	 * idle routine
+	 */
+	if (ret)
+		arch_cpu_idle();
+
+	__current_set_polling();
+
+	/*
+	 * It is up to the idle functions to enable back the local
+	 * interrupt
+	 */
+	if (WARN_ON_ONCE(irqs_disabled()))
+		local_irq_enable();
+
+	rcu_idle_exit();
+	start_critical_timings();
+
+	return 0;
+}
+
 /*
  * Generic idle loop implementation
  */
@@ -90,23 +220,11 @@ static void cpu_idle_loop(void)
 			 * know that the IPI is going to arrive right
 			 * away
 			 */
-			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
+			if (cpu_idle_force_poll || tick_check_broadcast_expired())
 				cpu_idle_poll();
-			} else {
-				if (!current_clr_polling_and_test()) {
-					stop_critical_timings();
-					rcu_idle_enter();
-					if (cpuidle_idle_call())
-						arch_cpu_idle();
-					if (WARN_ON_ONCE(irqs_disabled()))
-						local_irq_enable();
-					rcu_idle_exit();
-					start_critical_timings();
-				} else {
-					local_irq_enable();
-				}
-				__current_set_polling();
-			}
+			else
+				cpuidle_idle_call();
+
 			arch_cpu_idle_exit();
 		}
 
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index da98af3..a476bea 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -142,4 +142,4 @@ static int __init proc_schedstat_init(void)
 	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
 	return 0;
 }
-module_init(proc_schedstat_init);
+subsys_initcall(proc_schedstat_init);