Merge tag 'v4.4.163' into linux-linaro-lsk-v4.4

This is the 4.4.163 stable release

8 files changed, 70 insertions, 39 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 0eb11b4ac4c7..daa4e0782cf7 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -270,9 +270,7 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
 
 static void prog_fd_array_put_ptr(void *ptr)
 {
-	struct bpf_prog *prog = ptr;
-
-	bpf_prog_put_rcu(prog);
+	bpf_prog_put(ptr);
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4b9bbfe764e8..04fc1022ad9f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -487,7 +487,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
 	free_uid(user);
 }
 
-static void __prog_put_common(struct rcu_head *rcu)
+static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 {
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
@@ -496,17 +496,10 @@ static void __prog_put_common(struct rcu_head *rcu)
 	bpf_prog_free(aux->prog);
 }
 
-/* version of bpf_prog_put() that is called after a grace period */
-void bpf_prog_put_rcu(struct bpf_prog *prog)
-{
-	if (atomic_dec_and_test(&prog->aux->refcnt))
-		call_rcu(&prog->aux->rcu, __prog_put_common);
-}
-
 void bpf_prog_put(struct bpf_prog *prog)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt))
-		__prog_put_common(&prog->aux->rcu);
+		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_put);
 
@@ -514,7 +507,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 {
 	struct bpf_prog *prog = filp->private_data;
 
-	bpf_prog_put_rcu(prog);
+	bpf_prog_put(prog);
 	return 0;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0d800be8959a..3e82fa0c6b4e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7143,6 +7143,8 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
 			goto unlock;
 
 		list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+			if (event->cpu != smp_processor_id())
+				continue;
 			if (event->attr.type != PERF_TYPE_TRACEPOINT)
 				continue;
 			if (event->attr.config != entry->type)
@@ -7264,7 +7266,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 	prog = event->tp_event->prog;
 	if (prog && event->tp_event->bpf_prog_owner == event) {
 		event->tp_event->prog = NULL;
-		bpf_prog_put_rcu(prog);
+		bpf_prog_put(prog);
 	}
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 65ed3501c2ca..4743e1f2a3d1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7817,11 +7817,9 @@ void sched_destroy_group(struct task_group *tg)
 void sched_offline_group(struct task_group *tg)
 {
 	unsigned long flags;
-	int i;
 
 	/* end participation in shares distribution */
-	for_each_possible_cpu(i)
-		unregister_fair_sched_group(tg, i);
+	unregister_fair_sched_group(tg);
 
 	spin_lock_irqsave(&task_group_lock, flags);
 	list_del_rcu(&tg->list);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3b136fb4422c..c2af250547bb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3624,9 +3624,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	/*
 	 * Add to the _head_ of the list, so that an already-started
-	 * distribute_cfs_runtime will not see us
+	 * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
+	 * not running add to the tail so that later runqueues don't get starved.
 	 */
-	list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	if (cfs_b->distribute_running)
+		list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	else
+		list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
 
 	/*
 	 * If we're the first throttled task, make sure the bandwidth
@@ -3769,14 +3773,16 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	 * in us over-using our runtime if it is all used during this loop, but
 	 * only by limited amounts in that extreme case.
 	 */
-	while (throttled && cfs_b->runtime > 0) {
+	while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
 		runtime = cfs_b->runtime;
+		cfs_b->distribute_running = 1;
 		raw_spin_unlock(&cfs_b->lock);
 		/* we can't nest cfs_b->lock while distributing bandwidth */
 		runtime = distribute_cfs_runtime(cfs_b, runtime,
 						 runtime_expires);
 		raw_spin_lock(&cfs_b->lock);
 
+		cfs_b->distribute_running = 0;
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
 
 		cfs_b->runtime -= min(runtime, cfs_b->runtime);
@@ -3887,6 +3893,11 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 
 	/* confirm we're still not at a refresh boundary */
 	raw_spin_lock(&cfs_b->lock);
+	if (cfs_b->distribute_running) {
+		raw_spin_unlock(&cfs_b->lock);
+		return;
+	}
+
 	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
 		raw_spin_unlock(&cfs_b->lock);
 		return;
@@ -3896,6 +3907,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 		runtime = cfs_b->runtime;
 
 	expires = cfs_b->runtime_expires;
+	if (runtime)
+		cfs_b->distribute_running = 1;
+
 	raw_spin_unlock(&cfs_b->lock);
 
 	if (!runtime)
@@ -3906,6 +3920,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	raw_spin_lock(&cfs_b->lock);
 	if (expires == cfs_b->runtime_expires)
 		cfs_b->runtime -= min(runtime, cfs_b->runtime);
+	cfs_b->distribute_running = 0;
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -4017,6 +4032,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	cfs_b->period_timer.function = sched_cfs_period_timer;
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
+	cfs_b->distribute_running = 0;
 }
 
 static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
@@ -8154,11 +8170,8 @@ void free_fair_sched_group(struct task_group *tg)
 	for_each_possible_cpu(i) {
 		if (tg->cfs_rq)
 			kfree(tg->cfs_rq[i]);
-		if (tg->se) {
-			if (tg->se[i])
-				remove_entity_load_avg(tg->se[i]);
+		if (tg->se)
 			kfree(tg->se[i]);
-		}
 	}
 
 	kfree(tg->cfs_rq);
@@ -8206,21 +8219,29 @@ err:
 	return 0;
 }
 
-void unregister_fair_sched_group(struct task_group *tg, int cpu)
+void unregister_fair_sched_group(struct task_group *tg)
 {
-	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
+	struct rq *rq;
+	int cpu;
 
-	/*
-	* Only empty task groups can be destroyed; so we can speculatively
-	* check on_list without danger of it being re-added.
-	*/
-	if (!tg->cfs_rq[cpu]->on_list)
-		return;
+	for_each_possible_cpu(cpu) {
+		if (tg->se[cpu])
+			remove_entity_load_avg(tg->se[cpu]);
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+		/*
+		 * Only empty task groups can be destroyed; so we can speculatively
+		 * check on_list without danger of it being re-added.
+		 */
+		if (!tg->cfs_rq[cpu]->on_list)
+			continue;
+
+		rq = cpu_rq(cpu);
+
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
 }
 
 void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
@@ -8302,7 +8323,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	return 1;
 }
 
-void unregister_fair_sched_group(struct task_group *tg, int cpu) { }
+void unregister_fair_sched_group(struct task_group *tg) { }
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 4a2ef5a02fd3..bfd573122e0d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -132,7 +132,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  */
 static void cpuidle_idle_call(void)
 {
-	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_device *dev = cpuidle_get_device();
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int next_state, entered_state;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0c9ebd82a684..6893ee31df4d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -233,6 +233,8 @@ struct cfs_bandwidth {
 	/* statistics */
 	int nr_periods, nr_throttled;
 	u64 throttled_time;
+
+	bool distribute_running;
 #endif
 };
 
@@ -308,7 +310,7 @@ extern int tg_nop(struct task_group *tg, void *data);
 
 extern void free_fair_sched_group(struct task_group *tg);
 extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
-extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
+extern void unregister_fair_sched_group(struct task_group *tg);
 extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 			struct sched_entity *se, int cpu,
 			struct sched_entity *parent);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e409ddce8754..1a47a64d623f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1757,7 +1757,17 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 {
 	__buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack(tr, buffer, flags, 0, pc, regs);
+	/*
+	 * If regs is not set, then skip the following callers:
+	 *   trace_buffer_unlock_commit_regs
+	 *   event_trigger_unlock_commit
+	 *   trace_event_buffer_commit
+	 *   trace_event_raw_event_sched_switch
+	 * Note, we can still get here via blktrace, wakeup tracer
+	 * and mmiotrace, but that's ok if they lose a function or
+	 * two. They are that meaningful.
+	 */
+	ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
@@ -1816,6 +1826,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	trace.skip		= skip;
 
 	/*
+	 * Add two, for this function and the call to save_stack_trace()
+	 * If regs is set, then these functions will not be in the way.
+	 */
+	if (!regs)
+		trace.skip += 2;
+
+	/*
 	 * Since events can happen in NMIs there's no safe way to
 	 * use the per cpu ftrace_stacks. We reserve it and if an interrupt
 	 * or NMI comes in, it will just have to use the default