5 files changed, 32 insertions, 9 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 301079d06f24..7b6646a8c067 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -908,6 +908,15 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 }
 
 /*
+ * Initialize event state based on the perf_event_attr::disabled.
+ */
+static inline void perf_event__state_init(struct perf_event *event)
+{
+        event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF :
+                                              PERF_EVENT_STATE_INACTIVE;
+}
+
+/*
  * Called at perf_event creation and when events are attached/detached from a
  * group.
  */
@@ -6179,8 +6188,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
         event->overflow_handler = overflow_handler;
         event->overflow_handler_context = context;
 
-        if (attr->disabled)
-                event->state = PERF_EVENT_STATE_OFF;
+        perf_event__state_init(event);
 
         pmu = NULL;
 
@@ -6609,9 +6617,17 @@ SYSCALL_DEFINE5(perf_event_open,
 
                 mutex_lock(&gctx->mutex);
                 perf_remove_from_context(group_leader);
+
+                /*
+                 * Removing from the context ends up with disabled
+                 * event. What we want here is event in the initial
+                 * startup state, ready to be add into new context.
+                 */
+                perf_event__state_init(group_leader);
                 list_for_each_entry(sibling, &group_leader->sibling_list,
                                     group_entry) {
                         perf_remove_from_context(sibling);
+                        perf_event__state_init(sibling);
                         put_ctx(gctx);
                 }
                 mutex_unlock(&gctx->mutex);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index f6e5ec2932b4..c1cc7e17ff9d 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -40,8 +40,7 @@
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
 static bool have_rcu_nocb_mask;     /* Was rcu_nocb_mask allocated? */
-static bool rcu_nocb_poll;          /* Offload kthread are to poll. */
-module_param(rcu_nocb_poll, bool, 0444);
+static bool __read_mostly rcu_nocb_poll;    /* Offload kthread are to poll. */
 static char __initdata nocb_buf[NR_CPUS * 5];
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
@@ -2159,6 +2158,13 @@ static int __init rcu_nocb_setup(char *str)
 }
 __setup("rcu_nocbs=", rcu_nocb_setup);
 
+static int __init parse_rcu_nocb_poll(char *arg)
+{
+        rcu_nocb_poll = 1;
+        return 0;
+}
+early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
+
 /* Is the specified CPU a no-CPUs CPU? */
 static bool is_nocb_cpu(int cpu)
 {
@@ -2366,10 +2372,11 @@ static int rcu_nocb_kthread(void *arg)
         for (;;) {
                 /* If not polling, wait for next batch of callbacks. */
                 if (!rcu_nocb_poll)
-                        wait_event(rdp->nocb_wq, rdp->nocb_head);
+                        wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
                 list = ACCESS_ONCE(rdp->nocb_head);
                 if (!list) {
                         schedule_timeout_interruptible(1);
+                        flush_signals(current);
                         continue;
                 }
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2cd3c1b4e582..7ae4c4c5420e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -222,8 +222,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
                         cfs_rq->runnable_load_avg);
         SEQ_printf(m, "  .%-30s: %lld\n", "blocked_load_avg",
                         cfs_rq->blocked_load_avg);
-        SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
-                        atomic64_read(&cfs_rq->tg->load_avg));
+        SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_avg",
+                        (unsigned long long)atomic64_read(&cfs_rq->tg->load_avg));
         SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_contrib",
                         cfs_rq->tg_load_contrib);
         SEQ_printf(m, "  .%-30s: %d\n", "tg_runnable_contrib",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5eea8707234a..81fa53643409 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2663,7 +2663,7 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
         hrtimer_cancel(&cfs_b->slack_timer);
 }
 
-static void unthrottle_offline_cfs_rqs(struct rq *rq)
+static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
         struct cfs_rq *cfs_rq;
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 418feb01344e..4f02b2847357 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -566,7 +566,7 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 static int do_balance_runtime(struct rt_rq *rt_rq)
 {
         struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
-        struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+        struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd;
         int i, weight, more = 0;
         u64 rt_period;