Merge branch 'linux-4.14.y_for_4.14-2.0.x-imx' into 4.14-2.0.x-imx

5 files changed, 40 insertions, 8 deletions

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 6d689c039189..d0d39f714f47 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -605,10 +605,9 @@ fail:
 
 stop_kthread:
 	sugov_kthread_stop(sg_policy);
-
-free_sg_policy:
 	mutex_unlock(&global_tunables_lock);
 
+free_sg_policy:
 	sugov_policy_free(sg_policy);
 
 disable_fast_switch:
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b2589c7e9439..22770168bff8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -217,7 +217,6 @@ static void task_non_contending(struct task_struct *p)
 	if (dl_se->dl_runtime == 0)
 		return;
 
-	WARN_ON(hrtimer_active(&dl_se->inactive_timer));
 	WARN_ON(dl_se->dl_non_contending);
 
 	zerolag_time = dl_se->deadline -
@@ -234,7 +233,7 @@ static void task_non_contending(struct task_struct *p)
 	 * If the "0-lag time" already passed, decrease the active
 	 * utilization now, instead of starting a timer
 	 */
-	if (zerolag_time < 0) {
+	if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
 		if (dl_task(p))
 			sub_running_bw(dl_se->dl_bw, dl_rq);
 		if (!dl_task(p) || p->state == TASK_DEAD) {
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2f93e4a2d9f6..187c04a34ba1 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -339,6 +339,7 @@ void register_sched_domain_sysctl(void)
 {
 	static struct ctl_table *cpu_entries;
 	static struct ctl_table **cpu_idx;
+	static bool init_done = false;
 	char buf[32];
 	int i;
 
@@ -368,7 +369,10 @@ void register_sched_domain_sysctl(void)
 	if (!cpumask_available(sd_sysctl_cpus)) {
 		if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
 			return;
+	}
 
+	if (!init_done) {
+		init_done = true;
 		/* init to possible to not have holes in @cpu_entries */
 		cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f33b24080b1c..af7de1f9906c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2026,6 +2026,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 	if (p->last_task_numa_placement) {
 		delta = runtime - p->last_sum_exec_runtime;
 		*period = now - p->last_task_numa_placement;
+
+		/* Avoid time going backwards, prevent potential divide error: */
+		if (unlikely((s64)*period < 0))
+			*period = 0;
 	} else {
 		delta = p->se.avg.load_sum / p->se.load.weight;
 		*period = LOAD_AVG_MAX;
@@ -4672,12 +4676,15 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
+extern const u64 max_cfs_quota_period;
+
 static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, period_timer);
 	int overrun;
 	int idle = 0;
+	int count = 0;
 
 	raw_spin_lock(&cfs_b->lock);
 	for (;;) {
@@ -4685,6 +4692,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (!overrun)
 			break;
 
+		if (++count > 3) {
+			u64 new, old = ktime_to_ns(cfs_b->period);
+
+			new = (old * 147) / 128; /* ~115% */
+			new = min(new, max_cfs_quota_period);
+
+			cfs_b->period = ns_to_ktime(new);
+
+			/* since max is 1s, this is limited to 1e9^2, which fits in u64 */
+			cfs_b->quota *= new;
+			cfs_b->quota = div64_u64(cfs_b->quota, old);
+
+			pr_warn_ratelimited(
+        "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
+	                        smp_processor_id(),
+	                        div_u64(new, NSEC_PER_USEC),
+                                div_u64(cfs_b->quota, NSEC_PER_USEC));
+
+			/* reset count so we don't come right back in here */
+			count = 0;
+		}
+
 		idle = do_sched_cfs_period_timer(cfs_b, overrun);
 	}
 	if (idle)
@@ -5651,6 +5680,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 
 #ifdef CONFIG_SCHED_SMT
 DEFINE_STATIC_KEY_FALSE(sched_smt_present);
+EXPORT_SYMBOL_GPL(sched_smt_present);
 
 static inline void set_idle_cores(int cpu, int val)
 {
@@ -7017,10 +7047,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	if (cfs_rq->last_h_load_update == now)
 		return;
 
-	cfs_rq->h_load_next = NULL;
+	WRITE_ONCE(cfs_rq->h_load_next, NULL);
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->h_load_next = se;
+		WRITE_ONCE(cfs_rq->h_load_next, se);
 		if (cfs_rq->last_h_load_update == now)
 			break;
 	}
@@ -7030,7 +7060,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 		cfs_rq->last_h_load_update = now;
 	}
 
-	while ((se = cfs_rq->h_load_next) != NULL) {
+	while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
 		load = cfs_rq->h_load;
 		load = div64_ul(load * se->avg.load_avg,
 			cfs_rq_load_avg(cfs_rq) + 1);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 659e075ef70b..9dcd80ed9d4c 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -499,7 +499,7 @@ static int __init isolated_cpu_setup(char *str)
 __setup("isolcpus=", isolated_cpu_setup);
 
 struct s_data {
-	struct sched_domain ** __percpu sd;
+	struct sched_domain * __percpu *sd;
 	struct root_domain	*rd;
 };