1 files changed, 118 insertions, 19 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7b34c7826ca5..71b10a9b73cf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4,6 +4,7 @@
 #include <linux/sched/rt.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
+#include <linux/kernel_stat.h>
 #include <linux/binfmts.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
@@ -222,7 +223,7 @@ 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;
+extern void init_dl_bw(struct dl_bw *dl_b);
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -583,6 +584,13 @@ struct root_domain {
 };
 
 extern struct root_domain def_root_domain;
+extern struct mutex sched_domains_mutex;
+extern cpumask_var_t fallback_doms;
+extern cpumask_var_t sched_domains_tmpmask;
+
+extern void init_defrootdomain(void);
+extern int init_sched_domains(const struct cpumask *cpu_map);
+extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 
 #endif /* CONFIG_SMP */
 
@@ -644,7 +652,7 @@ 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 +776,110 @@ 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 +893,16 @@ 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 {
@@ -969,7 +1069,7 @@ static inline void sched_ttwu_pending(void) { }
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
-#include "auto_group.h"
+#include "autogroup.h"
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -1245,7 +1345,7 @@ 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
@@ -1501,11 +1601,6 @@ 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)
@@ -1515,7 +1610,7 @@ 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);
 }
 
@@ -1524,7 +1619,7 @@ 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);
 }
@@ -1674,6 +1769,10 @@ 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 */
 
 /*
@@ -1750,8 +1849,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 struct irqtime {
-	u64			hardirq_time;
-	u64			softirq_time;
+	u64			tick_delta;
 	u64			irq_start_time;
 	struct u64_stats_sync	sync;
 };
@@ -1761,12 +1859,13 @@ DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
 static inline u64 irq_time_read(int cpu)
 {
 	struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
+	u64 *cpustat = kcpustat_cpu(cpu).cpustat;
 	unsigned int seq;
 	u64 total;
 
 	do {
 		seq = __u64_stats_fetch_begin(&irqtime->sync);
-		total = irqtime->softirq_time + irqtime->hardirq_time;
+		total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ];
 	} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
 
 	return total;