5 files changed, 58 insertions, 11 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5c883fe8e440..2a906f20fba7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -74,6 +74,7 @@
 #include <linux/context_tracking.h>
 #include <linux/compiler.h>
 #include <linux/frame.h>
+#include <linux/prefetch.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -2972,6 +2973,23 @@ EXPORT_PER_CPU_SYMBOL(kstat);
 EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
 
 /*
+ * The function fair_sched_class.update_curr accesses the struct curr
+ * and its field curr->exec_start; when called from task_sched_runtime(),
+ * we observe a high rate of cache misses in practice.
+ * Prefetching this data results in improved performance.
+ */
+static inline void prefetch_curr_exec_start(struct task_struct *p)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	struct sched_entity *curr = (&p->se)->cfs_rq->curr;
+#else
+	struct sched_entity *curr = (&task_rq(p)->cfs)->curr;
+#endif
+	prefetch(curr);
+	prefetch(&curr->exec_start);
+}
+
+/*
  * Return accounted runtime for the task.
  * In case the task is currently running, return the runtime plus current's
  * pending runtime that have not been accounted yet.
@@ -3005,6 +3023,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	 * thread, breaking clock_gettime().
 	 */
 	if (task_current(rq, p) && task_on_rq_queued(p)) {
+		prefetch_curr_exec_start(p);
 		update_rq_clock(rq);
 		p->sched_class->update_curr(rq);
 	}
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5be58820465c..d4184498c9f5 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -168,7 +168,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 
 	if (old_idx == IDX_INVALID) {
 		cp->size++;
-		cp->elements[cp->size - 1].dl = 0;
+		cp->elements[cp->size - 1].dl = dl;
 		cp->elements[cp->size - 1].cpu = cpu;
 		cp->elements[cpu].idx = cp->size - 1;
 		cpudl_change_key(cp, cp->size - 1, dl);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 1934f658c036..a846cf89eb96 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -263,6 +263,11 @@ void account_idle_time(cputime_t cputime)
 		cpustat[CPUTIME_IDLE] += (__force u64) cputime;
 }
 
+/*
+ * When a guest is interrupted for a longer amount of time, missed clock
+ * ticks are not redelivered later. Due to that, this function may on
+ * occasion account more time than the calling functions think elapsed.
+ */
 static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
 {
 #ifdef CONFIG_PARAVIRT
@@ -371,7 +376,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 	 * idle, or potentially user or system time. Due to rounding,
 	 * other time can exceed ticks occasionally.
 	 */
-	other = account_other_time(cputime);
+	other = account_other_time(ULONG_MAX);
 	if (other >= cputime)
 		return;
 	cputime -= other;
@@ -486,7 +491,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	}
 
 	cputime = cputime_one_jiffy;
-	steal = steal_account_process_time(cputime);
+	steal = steal_account_process_time(ULONG_MAX);
 
 	if (steal >= cputime)
 		return;
@@ -508,13 +513,21 @@ void account_process_tick(struct task_struct *p, int user_tick)
  */
 void account_idle_ticks(unsigned long ticks)
 {
+	cputime_t cputime, steal;
 
 	if (sched_clock_irqtime) {
 		irqtime_account_idle_ticks(ticks);
 		return;
 	}
 
-	account_idle_time(jiffies_to_cputime(ticks));
+	cputime = jiffies_to_cputime(ticks);
+	steal = steal_account_process_time(ULONG_MAX);
+
+	if (steal >= cputime)
+		return;
+
+	cputime -= steal;
+	account_idle_time(cputime);
 }
 
 /*
@@ -606,19 +619,25 @@ static void cputime_adjust(struct task_cputime *curr,
 	stime = curr->stime;
 	utime = curr->utime;
 
-	if (utime == 0) {
-		stime = rtime;
+	/*
+	 * If either stime or both stime and utime are 0, assume all runtime is
+	 * userspace. Once a task gets some ticks, the monotonicy code at
+	 * 'update' will ensure things converge to the observed ratio.
+	 */
+	if (stime == 0) {
+		utime = rtime;
 		goto update;
 	}
 
-	if (stime == 0) {
-		utime = rtime;
+	if (utime == 0) {
+		stime = rtime;
 		goto update;
 	}
 
 	stime = scale_stime((__force u64)stime, (__force u64)rtime,
 			    (__force u64)(stime + utime));
 
+update:
 	/*
 	 * Make sure stime doesn't go backwards; this preserves monotonicity
 	 * for utime because rtime is monotonic.
@@ -641,7 +660,6 @@ static void cputime_adjust(struct task_cputime *curr,
 		stime = rtime - utime;
 	}
 
-update:
 	prev->stime = stime;
 	prev->utime = utime;
 out:
@@ -686,6 +704,13 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
 	unsigned long now = READ_ONCE(jiffies);
 	cputime_t delta, other;
 
+	/*
+	 * Unlike tick based timing, vtime based timing never has lost
+	 * ticks, and no need for steal time accounting to make up for
+	 * lost ticks. Vtime accounts a rounded version of actual
+	 * elapsed time. Limit account_other_time to prevent rounding
+	 * errors from causing elapsed vtime to go negative.
+	 */
 	delta = jiffies_to_cputime(now - tsk->vtime_snap);
 	other = account_other_time(delta);
 	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fcb7f0217ff4..1ce8867283dc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -658,8 +658,11 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 *
 	 * XXX figure out if select_task_rq_dl() deals with offline cpus.
 	 */
-	if (unlikely(!rq->online))
+	if (unlikely(!rq->online)) {
+		lockdep_unpin_lock(&rq->lock, rf.cookie);
 		rq = dl_task_offline_migration(rq, p);
+		rf.cookie = lockdep_pin_lock(&rq->lock);
+	}
 
 	/*
 	 * Queueing this task back might have overloaded rq, check if we need
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4088eedea763..039de34f1521 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4269,7 +4269,7 @@ static void sync_throttle(struct task_group *tg, int cpu)
 	pcfs_rq = tg->parent->cfs_rq[cpu];
 
 	cfs_rq->throttle_count = pcfs_rq->throttle_count;
-	pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+	cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
 }
 
 /* conditionally throttle active cfs_rq's from put_prev_entity() */