1 files changed, 143 insertions, 108 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 84b9e076812..ec5f472bc5b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -75,6 +75,9 @@
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
 #include <asm/mutex.h>
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#endif
 
 #include "sched_cpupri.h"
 #include "workqueue_sched.h"
@@ -124,7 +127,7 @@
 
 static inline int rt_policy(int policy)
 {
-	if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
+	if (policy == SCHED_FIFO || policy == SCHED_RR)
 		return 1;
 	return 0;
 }
@@ -422,6 +425,7 @@ struct rt_rq {
  */
 struct root_domain {
 	atomic_t refcount;
+	atomic_t rto_count;
 	struct rcu_head rcu;
 	cpumask_var_t span;
 	cpumask_var_t online;
@@ -431,7 +435,6 @@ struct root_domain {
 	 * one runnable RT task.
 	 */
 	cpumask_var_t rto_mask;
-	atomic_t rto_count;
 	struct cpupri cpupri;
 };
 
@@ -528,6 +531,12 @@ struct rq {
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	u64 prev_irq_time;
 #endif
+#ifdef CONFIG_PARAVIRT
+	u64 prev_steal_time;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	u64 prev_steal_time_rq;
+#endif
 
 	/* calc_load related fields */
 	unsigned long calc_load_update;
@@ -581,7 +590,6 @@ static inline int cpu_of(struct rq *rq)
 
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
-			      rcu_read_lock_held() || \
 			      lockdep_is_held(&sched_domains_mutex))
 
 /*
@@ -1568,38 +1576,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 	return rq->avg_load_per_task;
 }
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-
-/*
- * Compute the cpu's hierarchical load factor for each task group.
- * This needs to be done in a top-down fashion because the load of a child
- * group is a fraction of its parents load.
- */
-static int tg_load_down(struct task_group *tg, void *data)
-{
-	unsigned long load;
-	long cpu = (long)data;
-
-	if (!tg->parent) {
-		load = cpu_rq(cpu)->load.weight;
-	} else {
-		load = tg->parent->cfs_rq[cpu]->h_load;
-		load *= tg->se[cpu]->load.weight;
-		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
-	}
-
-	tg->cfs_rq[cpu]->h_load = load;
-
-	return 0;
-}
-
-static void update_h_load(long cpu)
-{
-	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
-}
-
-#endif
-
 #ifdef CONFIG_PREEMPT
 
 static void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -1953,10 +1929,28 @@ void account_system_vtime(struct task_struct *curr)
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-static void update_rq_clock_task(struct rq *rq, s64 delta)
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#ifdef CONFIG_PARAVIRT
+static inline u64 steal_ticks(u64 steal)
 {
-	s64 irq_delta;
+	if (unlikely(steal > NSEC_PER_SEC))
+		return div_u64(steal, TICK_NSEC);
+
+	return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
+}
+#endif
 
+static void update_rq_clock_task(struct rq *rq, s64 delta)
+{
+/*
+ * In theory, the compile should just see 0 here, and optimize out the call
+ * to sched_rt_avg_update. But I don't trust it...
+ */
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	s64 steal = 0, irq_delta = 0;
+#endif
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
 
 	/*
@@ -1979,12 +1973,35 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->prev_irq_time += irq_delta;
 	delta -= irq_delta;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	if (static_branch((&paravirt_steal_rq_enabled))) {
+		u64 st;
+
+		steal = paravirt_steal_clock(cpu_of(rq));
+		steal -= rq->prev_steal_time_rq;
+
+		if (unlikely(steal > delta))
+			steal = delta;
+
+		st = steal_ticks(steal);
+		steal = st * TICK_NSEC;
+
+		rq->prev_steal_time_rq += steal;
+
+		delta -= steal;
+	}
+#endif
+
 	rq->clock_task += delta;
 
-	if (irq_delta && sched_feat(NONIRQ_POWER))
-		sched_rt_avg_update(rq, irq_delta);
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	if ((irq_delta + steal) && sched_feat(NONTASK_POWER))
+		sched_rt_avg_update(rq, irq_delta + steal);
+#endif
 }
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
 static int irqtime_account_hi_update(void)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
@@ -2019,12 +2036,7 @@ static int irqtime_account_si_update(void)
 
 #define sched_clock_irqtime	(0)
 
-static void update_rq_clock_task(struct rq *rq, s64 delta)
-{
-	rq->clock_task += delta;
-}
-
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+#endif
 
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -2497,7 +2509,7 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 	if (p->sched_class->task_woken)
 		p->sched_class->task_woken(rq, p);
 
-	if (unlikely(rq->idle_stamp)) {
+	if (rq->idle_stamp) {
 		u64 delta = rq->clock - rq->idle_stamp;
 		u64 max = 2*sysctl_sched_migration_cost;
 
@@ -2886,7 +2898,7 @@ void sched_fork(struct task_struct *p)
 #if defined(CONFIG_SMP)
 	p->on_cpu = 0;
 #endif
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPT_COUNT
 	/* Want to start with kernel preemption disabled. */
 	task_thread_info(p)->preempt_count = 1;
 #endif
@@ -3053,7 +3065,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_disable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
-	perf_event_task_sched_in(current);
+	perf_event_task_sched_in(prev, current);
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_enable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
@@ -3877,6 +3889,25 @@ void account_idle_time(cputime_t cputime)
 		cpustat->idle = cputime64_add(cpustat->idle, cputime64);
 }
 
+static __always_inline bool steal_account_process_tick(void)
+{
+#ifdef CONFIG_PARAVIRT
+	if (static_branch(&paravirt_steal_enabled)) {
+		u64 steal, st = 0;
+
+		steal = paravirt_steal_clock(smp_processor_id());
+		steal -= this_rq()->prev_steal_time;
+
+		st = steal_ticks(steal);
+		this_rq()->prev_steal_time += st * TICK_NSEC;
+
+		account_steal_time(st);
+		return st;
+	}
+#endif
+	return false;
+}
+
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -3908,6 +3939,9 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 	cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 
+	if (steal_account_process_tick())
+		return;
+
 	if (irqtime_account_hi_update()) {
 		cpustat->irq = cputime64_add(cpustat->irq, tmp);
 	} else if (irqtime_account_si_update()) {
@@ -3961,6 +3995,9 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		return;
 	}
 
+	if (steal_account_process_tick())
+		return;
+
 	if (user_tick)
 		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
 	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
@@ -4242,9 +4279,9 @@ pick_next_task(struct rq *rq)
 }
 
 /*
- * schedule() is the main scheduler function.
+ * __schedule() is the main scheduler function.
  */
-asmlinkage void __sched schedule(void)
+static void __sched __schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
@@ -4285,16 +4322,6 @@ need_resched:
 				if (to_wakeup)
 					try_to_wake_up_local(to_wakeup);
 			}
-
-			/*
-			 * If we are going to sleep and we have plugged IO
-			 * queued, make sure to submit it to avoid deadlocks.
-			 */
-			if (blk_needs_flush_plug(prev)) {
-				raw_spin_unlock(&rq->lock);
-				blk_schedule_flush_plug(prev);
-				raw_spin_lock(&rq->lock);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -4332,17 +4359,34 @@ need_resched:
 	if (need_resched())
 		goto need_resched;
 }
+
+static inline void sched_submit_work(struct task_struct *tsk)
+{
+	if (!tsk->state)
+		return;
+	/*
+	 * If we are going to sleep and we have plugged IO queued,
+	 * make sure to submit it to avoid deadlocks.
+	 */
+	if (blk_needs_flush_plug(tsk))
+		blk_schedule_flush_plug(tsk);
+}
+
+asmlinkage void schedule(void)
+{
+	struct task_struct *tsk = current;
+
+	sched_submit_work(tsk);
+	__schedule();
+}
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 
 static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
 {
-	bool ret = false;
-
-	rcu_read_lock();
 	if (lock->owner != owner)
-		goto fail;
+		return false;
 
 	/*
 	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
@@ -4352,11 +4396,7 @@ static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
 	 */
 	barrier();
 
-	ret = owner->on_cpu;
-fail:
-	rcu_read_unlock();
-
-	return ret;
+	return owner->on_cpu;
 }
 
 /*
@@ -4368,21 +4408,21 @@ int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 	if (!sched_feat(OWNER_SPIN))
 		return 0;
 
+	rcu_read_lock();
 	while (owner_running(lock, owner)) {
 		if (need_resched())
-			return 0;
+			break;
 
 		arch_mutex_cpu_relax();
 	}
+	rcu_read_unlock();
 
 	/*
-	 * If the owner changed to another task there is likely
-	 * heavy contention, stop spinning.
+	 * We break out the loop above on need_resched() and when the
+	 * owner changed, which is a sign for heavy contention. Return
+	 * success only when lock->owner is NULL.
 	 */
-	if (lock->owner)
-		return 0;
-
-	return 1;
+	return lock->owner == NULL;
 }
 #endif
 
@@ -4405,7 +4445,7 @@ asmlinkage void __sched notrace preempt_schedule(void)
 
 	do {
 		add_preempt_count_notrace(PREEMPT_ACTIVE);
-		schedule();
+		__schedule();
 		sub_preempt_count_notrace(PREEMPT_ACTIVE);
 
 		/*
@@ -4433,7 +4473,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
-		schedule();
+		__schedule();
 		local_irq_disable();
 		sub_preempt_count(PREEMPT_ACTIVE);
 
@@ -5558,7 +5598,7 @@ static inline int should_resched(void)
 static void __cond_resched(void)
 {
 	add_preempt_count(PREEMPT_ACTIVE);
-	schedule();
+	__schedule();
 	sub_preempt_count(PREEMPT_ACTIVE);
 }
 
@@ -7413,6 +7453,7 @@ static void __sdt_free(const struct cpumask *cpu_map)
 			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
 			if (sd && (sd->flags & SD_OVERLAP))
 				free_sched_groups(sd->groups, 0);
+			kfree(*per_cpu_ptr(sdd->sd, j));
 			kfree(*per_cpu_ptr(sdd->sg, j));
 			kfree(*per_cpu_ptr(sdd->sgp, j));
 		}
@@ -7898,17 +7939,10 @@ int in_sched_functions(unsigned long addr)
 		&& addr < (unsigned long)__sched_text_end);
 }
 
-static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
+static void init_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	cfs_rq->tasks_timeline = RB_ROOT;
 	INIT_LIST_HEAD(&cfs_rq->tasks);
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	cfs_rq->rq = rq;
-	/* allow initial update_cfs_load() to truncate */
-#ifdef CONFIG_SMP
-	cfs_rq->load_stamp = 1;
-#endif
-#endif
 	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
 #ifndef CONFIG_64BIT
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
@@ -7928,13 +7962,9 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 	/* delimiter for bitsearch: */
 	__set_bit(MAX_RT_PRIO, array->bitmap);
 
-#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
+#if defined CONFIG_SMP
 	rt_rq->highest_prio.curr = MAX_RT_PRIO;
-#ifdef CONFIG_SMP
 	rt_rq->highest_prio.next = MAX_RT_PRIO;
-#endif
-#endif
-#ifdef CONFIG_SMP
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
 	plist_head_init(&rt_rq->pushable_tasks);
@@ -7944,11 +7974,6 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 	rt_rq->rt_throttled = 0;
 	rt_rq->rt_runtime = 0;
 	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
-
-#ifdef CONFIG_RT_GROUP_SCHED
-	rt_rq->rt_nr_boosted = 0;
-	rt_rq->rq = rq;
-#endif
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -7957,11 +7982,17 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 				struct sched_entity *parent)
 {
 	struct rq *rq = cpu_rq(cpu);
-	tg->cfs_rq[cpu] = cfs_rq;
-	init_cfs_rq(cfs_rq, rq);
+
 	cfs_rq->tg = tg;
+	cfs_rq->rq = rq;
+#ifdef CONFIG_SMP
+	/* allow initial update_cfs_load() to truncate */
+	cfs_rq->load_stamp = 1;
+#endif
 
+	tg->cfs_rq[cpu] = cfs_rq;
 	tg->se[cpu] = se;
+
 	/* se could be NULL for root_task_group */
 	if (!se)
 		return;
@@ -7984,12 +8015,14 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 {
 	struct rq *rq = cpu_rq(cpu);
 
-	tg->rt_rq[cpu] = rt_rq;
-	init_rt_rq(rt_rq, rq);
+	rt_rq->highest_prio.curr = MAX_RT_PRIO;
+	rt_rq->rt_nr_boosted = 0;
+	rt_rq->rq = rq;
 	rt_rq->tg = tg;
-	rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
 
+	tg->rt_rq[cpu] = rt_rq;
 	tg->rt_se[cpu] = rt_se;
+
 	if (!rt_se)
 		return;
 
@@ -8071,7 +8104,7 @@ void __init sched_init(void)
 		rq->nr_running = 0;
 		rq->calc_load_active = 0;
 		rq->calc_load_update = jiffies + LOAD_FREQ;
-		init_cfs_rq(&rq->cfs, rq);
+		init_cfs_rq(&rq->cfs);
 		init_rt_rq(&rq->rt, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		root_task_group.shares = root_task_group_load;
@@ -8185,7 +8218,7 @@ void __init sched_init(void)
 	scheduler_running = 1;
 }
 
-#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 static inline int preempt_count_equals(int preempt_offset)
 {
 	int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
@@ -8195,7 +8228,6 @@ static inline int preempt_count_equals(int preempt_offset)
 
 void __might_sleep(const char *file, int line, int preempt_offset)
 {
-#ifdef in_atomic
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
@@ -8217,7 +8249,6 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 	if (irqs_disabled())
 		print_irqtrace_events(current);
 	dump_stack();
-#endif
 }
 EXPORT_SYMBOL(__might_sleep);
 #endif
@@ -8376,6 +8407,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		if (!se)
 			goto err_free_rq;
 
+		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 	}
 
@@ -8403,7 +8435,7 @@ static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
 	list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
-#else /* !CONFG_FAIR_GROUP_SCHED */
+#else /* !CONFIG_FAIR_GROUP_SCHED */
 static inline void free_fair_sched_group(struct task_group *tg)
 {
 }
@@ -8424,7 +8456,8 @@ static void free_rt_sched_group(struct task_group *tg)
 {
 	int i;
 
-	destroy_rt_bandwidth(&tg->rt_bandwidth);
+	if (tg->rt_se)
+		destroy_rt_bandwidth(&tg->rt_bandwidth);
 
 	for_each_possible_cpu(i) {
 		if (tg->rt_rq)
@@ -8465,6 +8498,8 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 		if (!rt_se)
 			goto err_free_rq;
 
+		init_rt_rq(rt_rq, cpu_rq(i));
+		rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
 		init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
 	}