1 files changed, 304 insertions, 36 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7b34c7826ca5..eeef1a3086d1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1,9 +1,27 @@
 
 #include <linux/sched.h>
+#include <linux/sched/autogroup.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/topology.h>
 #include <linux/sched/rt.h>
-#include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
+#include <linux/sched/clock.h>
+#include <linux/sched/wake_q.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/numa_balancing.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/cpufreq.h>
+#include <linux/sched/stat.h>
+#include <linux/sched/nohz.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/hotplug.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
+#include <linux/sched/init.h>
+
+#include <linux/u64_stats_sync.h>
+#include <linux/kernel_stat.h>
 #include <linux/binfmts.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
@@ -12,14 +30,18 @@
 #include <linux/tick.h>
 #include <linux/slab.h>
 
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#endif
+
 #include "cpupri.h"
 #include "cpudeadline.h"
 #include "cpuacct.h"
 
 #ifdef CONFIG_SCHED_DEBUG
-#define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
+# define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
-#define SCHED_WARN_ON(x)	((void)(x))
+# define SCHED_WARN_ON(x)	({ (void)(x), 0; })
 #endif
 
 struct rq;
@@ -196,23 +218,25 @@ static inline int dl_bandwidth_enabled(void)
 	return sysctl_sched_rt_runtime >= 0;
 }
 
-extern struct dl_bw *dl_bw_of(int i);
-
 struct dl_bw {
 	raw_spinlock_t lock;
 	u64 bw, total_bw;
 };
 
+static inline void __dl_update(struct dl_bw *dl_b, s64 bw);
+
 static inline
-void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
 {
 	dl_b->total_bw -= tsk_bw;
+	__dl_update(dl_b, (s32)tsk_bw / cpus);
 }
 
 static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
 {
 	dl_b->total_bw += tsk_bw;
+	__dl_update(dl_b, -((s32)tsk_bw / cpus));
 }
 
 static inline
@@ -222,7 +246,22 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
 	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
 }
 
-extern struct mutex sched_domains_mutex;
+void dl_change_utilization(struct task_struct *p, u64 new_bw);
+extern void init_dl_bw(struct dl_bw *dl_b);
+extern int sched_dl_global_validate(void);
+extern void sched_dl_do_global(void);
+extern int sched_dl_overflow(struct task_struct *p, int policy,
+			     const struct sched_attr *attr);
+extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
+extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
+extern bool __checkparam_dl(const struct sched_attr *attr);
+extern void __dl_clear_params(struct task_struct *p);
+extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
+extern int dl_task_can_attach(struct task_struct *p,
+			      const struct cpumask *cs_cpus_allowed);
+extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
+					const struct cpumask *trial);
+extern bool dl_cpu_busy(unsigned int cpu);
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -344,6 +383,11 @@ extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent);
+extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us);
+extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us);
+extern long sched_group_rt_runtime(struct task_group *tg);
+extern long sched_group_rt_period(struct task_group *tg);
+extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_online_group(struct task_group *tg,
@@ -536,6 +580,30 @@ struct dl_rq {
 #else
 	struct dl_bw dl_bw;
 #endif
+	/*
+	 * "Active utilization" for this runqueue: increased when a
+	 * task wakes up (becomes TASK_RUNNING) and decreased when a
+	 * task blocks
+	 */
+	u64 running_bw;
+
+	/*
+	 * Utilization of the tasks "assigned" to this runqueue (including
+	 * the tasks that are in runqueue and the tasks that executed on this
+	 * CPU and blocked). Increased when a task moves to this runqueue, and
+	 * decreased when the task moves away (migrates, changes scheduling
+	 * policy, or terminates).
+	 * This is needed to compute the "inactive utilization" for the
+	 * runqueue (inactive utilization = this_bw - running_bw).
+	 */
+	u64 this_bw;
+	u64 extra_bw;
+
+	/*
+	 * Inverse of the fraction of CPU utilization that can be reclaimed
+	 * by the GRUB algorithm.
+	 */
+	u64 bw_ratio;
 };
 
 #ifdef CONFIG_SMP
@@ -583,6 +651,11 @@ struct root_domain {
 };
 
 extern struct root_domain def_root_domain;
+extern struct mutex sched_domains_mutex;
+
+extern void init_defrootdomain(void);
+extern int sched_init_domains(const struct cpumask *cpu_map);
+extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 
 #endif /* CONFIG_SMP */
 
@@ -644,7 +717,7 @@ struct rq {
 	unsigned long next_balance;
 	struct mm_struct *prev_mm;
 
-	unsigned int clock_skip_update;
+	unsigned int clock_update_flags;
 	u64 clock;
 	u64 clock_task;
 
@@ -768,28 +841,110 @@ static inline u64 __rq_clock_broken(struct rq *rq)
 	return READ_ONCE(rq->clock);
 }
 
+/*
+ * rq::clock_update_flags bits
+ *
+ * %RQCF_REQ_SKIP - will request skipping of clock update on the next
+ *  call to __schedule(). This is an optimisation to avoid
+ *  neighbouring rq clock updates.
+ *
+ * %RQCF_ACT_SKIP - is set from inside of __schedule() when skipping is
+ *  in effect and calls to update_rq_clock() are being ignored.
+ *
+ * %RQCF_UPDATED - is a debug flag that indicates whether a call has been
+ *  made to update_rq_clock() since the last time rq::lock was pinned.
+ *
+ * If inside of __schedule(), clock_update_flags will have been
+ * shifted left (a left shift is a cheap operation for the fast path
+ * to promote %RQCF_REQ_SKIP to %RQCF_ACT_SKIP), so you must use,
+ *
+ *	if (rq-clock_update_flags >= RQCF_UPDATED)
+ *
+ * to check if %RQCF_UPADTED is set. It'll never be shifted more than
+ * one position though, because the next rq_unpin_lock() will shift it
+ * back.
+ */
+#define RQCF_REQ_SKIP	0x01
+#define RQCF_ACT_SKIP	0x02
+#define RQCF_UPDATED	0x04
+
+static inline void assert_clock_updated(struct rq *rq)
+{
+	/*
+	 * The only reason for not seeing a clock update since the
+	 * last rq_pin_lock() is if we're currently skipping updates.
+	 */
+	SCHED_WARN_ON(rq->clock_update_flags < RQCF_ACT_SKIP);
+}
+
 static inline u64 rq_clock(struct rq *rq)
 {
 	lockdep_assert_held(&rq->lock);
+	assert_clock_updated(rq);
+
 	return rq->clock;
 }
 
 static inline u64 rq_clock_task(struct rq *rq)
 {
 	lockdep_assert_held(&rq->lock);
+	assert_clock_updated(rq);
+
 	return rq->clock_task;
 }
 
-#define RQCF_REQ_SKIP	0x01
-#define RQCF_ACT_SKIP	0x02
-
 static inline void rq_clock_skip_update(struct rq *rq, bool skip)
 {
 	lockdep_assert_held(&rq->lock);
 	if (skip)
-		rq->clock_skip_update |= RQCF_REQ_SKIP;
+		rq->clock_update_flags |= RQCF_REQ_SKIP;
 	else
-		rq->clock_skip_update &= ~RQCF_REQ_SKIP;
+		rq->clock_update_flags &= ~RQCF_REQ_SKIP;
+}
+
+struct rq_flags {
+	unsigned long flags;
+	struct pin_cookie cookie;
+#ifdef CONFIG_SCHED_DEBUG
+	/*
+	 * A copy of (rq::clock_update_flags & RQCF_UPDATED) for the
+	 * current pin context is stashed here in case it needs to be
+	 * restored in rq_repin_lock().
+	 */
+	unsigned int clock_update_flags;
+#endif
+};
+
+static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
+{
+	rf->cookie = lockdep_pin_lock(&rq->lock);
+
+#ifdef CONFIG_SCHED_DEBUG
+	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+	rf->clock_update_flags = 0;
+#endif
+}
+
+static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
+{
+#ifdef CONFIG_SCHED_DEBUG
+	if (rq->clock_update_flags > RQCF_ACT_SKIP)
+		rf->clock_update_flags = RQCF_UPDATED;
+#endif
+
+	lockdep_unpin_lock(&rq->lock, rf->cookie);
+}
+
+static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
+{
+	lockdep_repin_lock(&rq->lock, rf->cookie);
+
+#ifdef CONFIG_SCHED_DEBUG
+	/*
+	 * Restore the value we stashed in @rf for this pin context.
+	 */
+	rq->clock_update_flags |= rf->clock_update_flags;
+#endif
 }
 
 #ifdef CONFIG_NUMA
@@ -803,6 +958,16 @@ extern int sched_max_numa_distance;
 extern bool find_numa_distance(int distance);
 #endif
 
+#ifdef CONFIG_NUMA
+extern void sched_init_numa(void);
+extern void sched_domains_numa_masks_set(unsigned int cpu);
+extern void sched_domains_numa_masks_clear(unsigned int cpu);
+#else
+static inline void sched_init_numa(void) { }
+static inline void sched_domains_numa_masks_set(unsigned int cpu) { }
+static inline void sched_domains_numa_masks_clear(unsigned int cpu) { }
+#endif
+
 #ifdef CONFIG_NUMA_BALANCING
 /* The regions in numa_faults array from task_struct */
 enum numa_faults_stats {
@@ -904,7 +1069,11 @@ struct sched_group_capacity {
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
 
-	unsigned long cpumask[0]; /* iteration mask */
+#ifdef CONFIG_SCHED_DEBUG
+	int id;
+#endif
+
+	unsigned long cpumask[0]; /* balance mask */
 };
 
 struct sched_group {
@@ -925,16 +1094,15 @@ struct sched_group {
 	unsigned long cpumask[0];
 };
 
-static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
+static inline struct cpumask *sched_group_span(struct sched_group *sg)
 {
 	return to_cpumask(sg->cpumask);
 }
 
 /*
- * cpumask masking which cpus in the group are allowed to iterate up the domain
- * tree.
+ * See build_balance_mask().
  */
-static inline struct cpumask *sched_group_mask(struct sched_group *sg)
+static inline struct cpumask *group_balance_mask(struct sched_group *sg)
 {
 	return to_cpumask(sg->sgc->cpumask);
 }
@@ -945,7 +1113,7 @@ static inline struct cpumask *sched_group_mask(struct sched_group *sg)
  */
 static inline unsigned int group_first_cpu(struct sched_group *group)
 {
-	return cpumask_first(sched_group_cpus(group));
+	return cpumask_first(sched_group_span(group));
 }
 
 extern int group_balance_cpu(struct sched_group *sg);
@@ -969,7 +1137,7 @@ static inline void sched_ttwu_pending(void) { }
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
-#include "auto_group.h"
+#include "autogroup.h"
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -1210,15 +1378,17 @@ extern const u32 sched_prio_to_wmult[40];
 #define DEQUEUE_SLEEP		0x01
 #define DEQUEUE_SAVE		0x02 /* matches ENQUEUE_RESTORE */
 #define DEQUEUE_MOVE		0x04 /* matches ENQUEUE_MOVE */
+#define DEQUEUE_NOCLOCK		0x08 /* matches ENQUEUE_NOCLOCK */
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_RESTORE		0x02
 #define ENQUEUE_MOVE		0x04
+#define ENQUEUE_NOCLOCK		0x08
 
-#define ENQUEUE_HEAD		0x08
-#define ENQUEUE_REPLENISH	0x10
+#define ENQUEUE_HEAD		0x10
+#define ENQUEUE_REPLENISH	0x20
 #ifdef CONFIG_SMP
-#define ENQUEUE_MIGRATED	0x20
+#define ENQUEUE_MIGRATED	0x40
 #else
 #define ENQUEUE_MIGRATED	0x00
 #endif
@@ -1245,7 +1415,7 @@ struct sched_class {
 	 */
 	struct task_struct * (*pick_next_task) (struct rq *rq,
 						struct task_struct *prev,
-						struct pin_cookie cookie);
+						struct rq_flags *rf);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
@@ -1299,7 +1469,11 @@ static inline void set_curr_task(struct rq *rq, struct task_struct *curr)
 	curr->sched_class->set_curr_task(rq);
 }
 
+#ifdef CONFIG_SMP
 #define sched_class_highest (&stop_sched_class)
+#else
+#define sched_class_highest (&dl_sched_class)
+#endif
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
@@ -1344,6 +1518,8 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq)
 }
 #endif
 
+extern void schedule_idle(void);
+
 extern void sysrq_sched_debug_show(void);
 extern void sched_init_granularity(void);
 extern void update_max_interval(void);
@@ -1361,7 +1537,12 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime
 extern struct dl_bandwidth def_dl_bandwidth;
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
 
+#define BW_SHIFT	20
+#define BW_UNIT		(1 << BW_SHIFT)
+#define RATIO_SHIFT	8
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
@@ -1501,13 +1682,9 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
 static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
-struct rq_flags {
-	unsigned long flags;
-	struct pin_cookie cookie;
-};
-
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	__acquires(rq->lock);
+
 struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	__acquires(p->pi_lock)
 	__acquires(rq->lock);
@@ -1515,7 +1692,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
 	__releases(rq->lock)
 {
-	lockdep_unpin_lock(&rq->lock, rf->cookie);
+	rq_unpin_lock(rq, rf);
 	raw_spin_unlock(&rq->lock);
 }
 
@@ -1524,11 +1701,67 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	__releases(rq->lock)
 	__releases(p->pi_lock)
 {
-	lockdep_unpin_lock(&rq->lock, rf->cookie);
+	rq_unpin_lock(rq, rf);
 	raw_spin_unlock(&rq->lock);
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
+static inline void
+rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock_irqsave(&rq->lock, rf->flags);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock_irq(&rq->lock);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock(&rq->lock);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_relock(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock(&rq->lock);
+	rq_repin_lock(rq, rf);
+}
+
+static inline void
+rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+}
+
+static inline void
+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock_irq(&rq->lock);
+}
+
+static inline void
+rq_unlock(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock(&rq->lock);
+}
+
 #ifdef CONFIG_SMP
 #ifdef CONFIG_PREEMPT
 
@@ -1674,6 +1907,10 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 		__release(rq2->lock);
 }
 
+extern void set_rq_online (struct rq *rq);
+extern void set_rq_offline(struct rq *rq);
+extern bool sched_smp_initialized;
+
 #else /* CONFIG_SMP */
 
 /*
@@ -1718,7 +1955,6 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
 extern void
 print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
-
 #ifdef CONFIG_NUMA_BALANCING
 extern void
 show_numa_stats(struct task_struct *p, struct seq_file *m);
@@ -1748,16 +1984,48 @@ extern void nohz_balance_exit_idle(unsigned int cpu);
 static inline void nohz_balance_exit_idle(unsigned int cpu) { }
 #endif
 
+
+#ifdef CONFIG_SMP
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
+	int i;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	for_each_cpu_and(i, rd->span, cpu_active_mask) {
+		struct rq *rq = cpu_rq(i);
+
+		rq->dl.extra_bw += bw;
+	}
+}
+#else
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
+
+	dl->extra_bw += bw;
+}
+#endif
+
+
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 struct irqtime {
-	u64			hardirq_time;
-	u64			softirq_time;
+	u64			total;
+	u64			tick_delta;
 	u64			irq_start_time;
 	struct u64_stats_sync	sync;
 };
 
 DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
 
+/*
+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * and never move forward.
+ */
 static inline u64 irq_time_read(int cpu)
 {
 	struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
@@ -1766,7 +2034,7 @@ static inline u64 irq_time_read(int cpu)
 
 	do {
 		seq = __u64_stats_fetch_begin(&irqtime->sync);
-		total = irqtime->softirq_time + irqtime->hardirq_time;
+		total = irqtime->total;
 	} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
 
 	return total;