Post RCU callbacks at early boot

index 254ac97d64ef..9b5ed5333c9a 100644
@@ -1328,20 +1328,30 @@ void rcu_cpu_stall_reset(void)
 }
 
 /*
- * Initialize the specified rcu_data structure's callback list to empty.
+ * Initialize the specified rcu_data structure's default callback list
+ * to empty.  The default callback list is the one that is not used by
+ * no-callbacks CPUs.
  */
-static void init_callback_list(struct rcu_data *rdp)
+static void init_default_callback_list(struct rcu_data *rdp)
 {
 	int i;
 
-	if (init_nocb_callback_list(rdp))
-		return;
 	rdp->nxtlist = NULL;
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
 		rdp->nxttail[i] = &rdp->nxtlist;
 }
 
 /*
+ * Initialize the specified rcu_data structure's callback list to empty.
+ */
+static void init_callback_list(struct rcu_data *rdp)
+{
+	if (init_nocb_callback_list(rdp))
+		return;
+	init_default_callback_list(rdp);
+}
+
+/*
  * Determine the value that ->completed will have at the end of the
  * next subsequent grace period.  This is used to tag callbacks so that
  * a CPU can invoke callbacks in a timely fashion even if that CPU has

index 9b5ed5333c9a..37193daf2b62 100644
@@ -91,8 +91,10 @@ static const char *tp_##sname##_varname __used __tracepoint_string = sname##_var
 
 #define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
 DEFINE_RCU_TPS(sname) \
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
 struct rcu_state sname##_state = { \
 	.level = { &sname##_state.node[0] }, \
+	.rda = &sname##_data, \
 	.call = cr, \
 	.fqs_state = RCU_GP_IDLE, \
 	.gpnum = 0UL - 300UL, \

@@ -104,8 +106,7 @@ struct rcu_state sname##_state = { \
 	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
 	.name = RCU_STATE_NAME(sname), \
 	.abbr = sabbr, \
-}; \
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data)
+}
 
 RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);

@@ -3815,7 +3816,6 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 		}
 	}
 
-	rsp->rda = rda;
 	init_waitqueue_head(&rsp->gp_wq);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {

index 37193daf2b62..ff2e42ebb64b 100644
@@ -2839,11 +2839,21 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 
 		if (cpu != -1)
 			rdp = per_cpu_ptr(rsp->rda, cpu);
-		offline = !__call_rcu_nocb(rdp, head, lazy, flags);
-		WARN_ON_ONCE(offline);
-		/* _call_rcu() is illegal on offline CPU; leak the callback. */
-		local_irq_restore(flags);
-		return;
+		if (likely(rdp->mynode)) {
+			/* Post-boot, so this should be for a no-CBs CPU. */
+			offline = !__call_rcu_nocb(rdp, head, lazy, flags);
+			WARN_ON_ONCE(offline);
+			/* Offline CPU, _call_rcu() illegal, leak callback.  */
+			local_irq_restore(flags);
+			return;
+		}
+		/*
+		 * Very early boot, before rcu_init().  Initialize if needed
+		 * and then drop through to queue the callback.
+		 */
+		BUG_ON(cpu != -1);
+		if (!likely(rdp->nxtlist))
+			init_default_callback_list(rdp);
 	}
 	ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1;
 	if (lazy)

index 371c5538c789..9b7f8c8ca355 100644
@@ -1938,7 +1938,8 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
 		rhp = ACCESS_ONCE(rdp->nocb_follower_head);
 
 	/* Having no rcuo kthread but CBs after scheduler starts is bad! */
-	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) {
+	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp &&
+	    rcu_scheduler_fully_active) {
 		/* RCU callback enqueued before CPU first came online??? */
 		pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
 		       cpu, rhp->func);

index ff2e42ebb64b..02fa29a4d104 100644
@@ -3584,7 +3584,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
-	init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
+	if (!rdp->nxtlist)
+		init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
 	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	rcu_sysidle_init_percpu_data(rdp->dynticks);
 	atomic_set(&rdp->dynticks->dynticks,

index 02fa29a4d104..c5241cdd4daf 100644
@@ -2852,6 +2852,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		 * and then drop through to queue the callback.
 		 */
 		BUG_ON(cpu != -1);
+		WARN_ON_ONCE(!rcu_is_watching());
 		if (!likely(rdp->nxtlist))
 			init_default_callback_list(rdp);
 	}

index 9b7f8c8ca355..bb947ef1a2a4 100644
@@ -2386,18 +2386,8 @@ void __init rcu_init_nohz(void)
 		pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
 
 	for_each_rcu_flavor(rsp) {
-		for_each_cpu(cpu, rcu_nocb_mask) {
-			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-
-			/*
-			 * If there are early callbacks, they will need
-			 * to be moved to the nocb lists.
-			 */
-			WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] !=
-				     &rdp->nxtlist &&
-				     rdp->nxttail[RCU_NEXT_TAIL] != NULL);
-			init_nocb_callback_list(rdp);
-		}
+		for_each_cpu(cpu, rcu_nocb_mask)
+			init_nocb_callback_list(per_cpu_ptr(rsp->rda, cpu));
 		rcu_organize_nocb_kthreads(rsp);
 	}
 }

@@ -2534,6 +2524,16 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return false;
 
+	/* If there are early-boot callbacks, move them to nocb lists. */
+	if (rdp->nxtlist) {
+		rdp->nocb_head = rdp->nxtlist;
+		rdp->nocb_tail = rdp->nxttail[RCU_NEXT_TAIL];
+		atomic_long_set(&rdp->nocb_q_count, rdp->qlen);
+		atomic_long_set(&rdp->nocb_q_count_lazy, rdp->qlen_lazy);
+		rdp->nxtlist = NULL;
+		rdp->qlen = 0;
+		rdp->qlen_lazy = 0;
+	}
 	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
 	return true;
 }

index c5241cdd4daf..21f3d5007d77 100644
@@ -3920,6 +3920,8 @@ void __init rcu_init(void)
 {
 	int cpu;
 
+	rcu_early_boot_tests();
+
 	rcu_bootup_announce();
 	rcu_init_geometry();
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);

@@ -3936,8 +3938,6 @@ void __init rcu_init(void)
 	pm_notifier(rcu_pm_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-
-	rcu_early_boot_tests();
 }
 
 #include "tree_plugin.h"