diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1050d6d3922c182f09bfe602ee07e3a185f4be80..403306b86e78bb40b8c9a9dd319db4f951fe7860 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1829,6 +1829,8 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	rdp->qlen++;
 	if (lazy)
 		rdp->qlen_lazy++;
+	else
+		rcu_idle_count_callbacks_posted();
 
 	if (__is_kfree_rcu_offset((unsigned long)func))
 		trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func,
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index cdd1be0a40720f0a436951035be9f3adc68d1815..36ca28ecedc67028242dd6b9d51acb691120eb11 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -471,6 +471,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu);
 static void rcu_prepare_for_idle_init(int cpu);
 static void rcu_cleanup_after_idle(int cpu);
 static void rcu_prepare_for_idle(int cpu);
+static void rcu_idle_count_callbacks_posted(void);
 static void print_cpu_stall_info_begin(void);
 static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 0f007b363dbae07284285b28970e3e7f0cda5da9..50c17975d4f42904384225b37b1478d41d1e8fa5 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1938,6 +1938,14 @@ static void rcu_prepare_for_idle(int cpu)
 {
 }
 
+/*
+ * Don't bother keeping a running count of the number of RCU callbacks
+ * posted because CONFIG_RCU_FAST_NO_HZ=n.
+ */
+static void rcu_idle_count_callbacks_posted(void)
+{
+}
+
 #else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 /*
@@ -1981,6 +1989,10 @@ static void rcu_prepare_for_idle(int cpu)
 static DEFINE_PER_CPU(int, rcu_dyntick_drain);
 static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
 static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
+static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires);
+static DEFINE_PER_CPU(bool, rcu_idle_first_pass);
+static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted);
+static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap);
 
 /*
  * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
@@ -1993,6 +2005,8 @@ static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
  */
 int rcu_needs_cpu(int cpu)
 {
+	/* Flag a new idle sojourn to the idle-entry state machine. */
+	per_cpu(rcu_idle_first_pass, cpu) = 1;
 	/* If no callbacks, RCU doesn't need the CPU. */
 	if (!rcu_cpu_has_callbacks(cpu))
 		return 0;
@@ -2095,6 +2109,26 @@ static void rcu_cleanup_after_idle(int cpu)
  */
 static void rcu_prepare_for_idle(int cpu)
 {
+	/*
+	 * If this is an idle re-entry, for example, due to use of
+	 * RCU_NONIDLE() or the new idle-loop tracing API within the idle
+	 * loop, then don't take any state-machine actions, unless the
+	 * momentary exit from idle queued additional non-lazy callbacks.
+	 * Instead, repost the rcu_idle_gp_timer if this CPU has callbacks
+	 * pending.
+	 */
+	if (!per_cpu(rcu_idle_first_pass, cpu) &&
+	    (per_cpu(rcu_nonlazy_posted, cpu) ==
+	     per_cpu(rcu_nonlazy_posted_snap, cpu))) {
+		if (rcu_cpu_has_callbacks(cpu))
+			mod_timer(&per_cpu(rcu_idle_gp_timer, cpu),
+				  per_cpu(rcu_idle_gp_timer_expires, cpu));
+		return;
+	}
+	per_cpu(rcu_idle_first_pass, cpu) = 0;
+	per_cpu(rcu_nonlazy_posted_snap, cpu) =
+		per_cpu(rcu_nonlazy_posted, cpu) - 1;
+
 	/*
 	 * If there are no callbacks on this CPU, enter dyntick-idle mode.
 	 * Also reset state to avoid prejudicing later attempts.
@@ -2127,11 +2161,15 @@ static void rcu_prepare_for_idle(int cpu)
 		per_cpu(rcu_dyntick_drain, cpu) = 0;
 		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
 		if (rcu_cpu_has_nonlazy_callbacks(cpu))
-			mod_timer(&per_cpu(rcu_idle_gp_timer, cpu),
-					   jiffies + RCU_IDLE_GP_DELAY);
+			per_cpu(rcu_idle_gp_timer_expires, cpu) =
+					   jiffies + RCU_IDLE_GP_DELAY;
 		else
-			mod_timer(&per_cpu(rcu_idle_gp_timer, cpu),
-					   jiffies + RCU_IDLE_LAZY_GP_DELAY);
+			per_cpu(rcu_idle_gp_timer_expires, cpu) =
+					   jiffies + RCU_IDLE_LAZY_GP_DELAY;
+		mod_timer(&per_cpu(rcu_idle_gp_timer, cpu),
+			  per_cpu(rcu_idle_gp_timer_expires, cpu));
+		per_cpu(rcu_nonlazy_posted_snap, cpu) =
+			per_cpu(rcu_nonlazy_posted, cpu);
 		return; /* Nothing more to do immediately. */
 	} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
 		/* We have hit the limit, so time to give up. */
@@ -2171,6 +2209,17 @@ static void rcu_prepare_for_idle(int cpu)
 		trace_rcu_prep_idle("Callbacks drained");
 }
 
+/*
+ * Keep a running count of callbacks posted so that rcu_prepare_for_idle()
+ * can detect when something out of the idle loop posts a callback.
+ * Of course, it had better do so either from a trace event designed to
+ * be called from idle or from within RCU_NONIDLE().
+ */
+static void rcu_idle_count_callbacks_posted(void)
+{
+	__this_cpu_add(rcu_nonlazy_posted, 1);
+}
+
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 #ifdef CONFIG_RCU_CPU_STALL_INFO