diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h
index 812961b1d064..659d13a7ddaa 100644
--- a/include/linux/rcu_segcblist.h
+++ b/include/linux/rcu_segcblist.h
@@ -136,6 +136,20 @@ struct rcu_cblist {
  *  |--------------------------------------------------------------------------|
  *  |                           SEGCBLIST_RCU_CORE   |                         |
  *  |                           SEGCBLIST_LOCKING    |                         |
+ *  |                           SEGCBLIST_OFFLOADED  |                         |
+ *  |                           SEGCBLIST_KTHREAD_CB |                         |
+ *  |                           SEGCBLIST_KTHREAD_GP                           |
+ *  |                                                                          |
+ *  |   CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core()    |
+ *  |   handles callbacks concurrently. Bypass enqueue is enabled.             |
+ *  |   Invoke RCU core so we make sure not to preempt it in the middle with   |
+ *  |   leaving some urgent work unattended within a jiffy.                    |
+ *  ----------------------------------------------------------------------------
+ *                                      |
+ *                                      v
+ *  |--------------------------------------------------------------------------|
+ *  |                           SEGCBLIST_RCU_CORE   |                         |
+ *  |                           SEGCBLIST_LOCKING    |                         |
  *  |                           SEGCBLIST_KTHREAD_CB |                         |
  *  |                           SEGCBLIST_KTHREAD_GP                           |
  *  |                                                                          |
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index c07aab6e39ef..81145c3ece25 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -265,12 +265,10 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
  */
 void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload)
 {
-	if (offload) {
+	if (offload)
 		rcu_segcblist_set_flags(rsclp, SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED);
-	} else {
-		rcu_segcblist_set_flags(rsclp, SEGCBLIST_RCU_CORE);
+	else
 		rcu_segcblist_clear_flags(rsclp, SEGCBLIST_OFFLOADED);
-	}
 }
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e905d7e4ddb9..a329adfece86 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2707,6 +2707,23 @@ static __latent_entropy void rcu_core(void)
 	unsigned long flags;
 	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
+	/*
+	 * On RT rcu_core() can be preempted when IRQs aren't disabled.
+	 * Therefore this function can race with concurrent NOCB (de-)offloading
+	 * on this CPU and the below condition must be considered volatile.
+	 * However if we race with:
+	 *
+	 * _ Offloading:   In the worst case we accelerate or process callbacks
+	 *                 concurrently with NOCB kthreads. We are guaranteed to
+	 *                 call rcu_nocb_lock() if that happens.
+	 *
+	 * _ Deoffloading: In the worst case we miss callbacks acceleration or
+	 *                 processing. This is fine because the early stage
+	 *                 of deoffloading invokes rcu_core() after setting
+	 *                 SEGCBLIST_RCU_CORE. So we guarantee that we'll process
+	 *                 what could have been dismissed without the need to wait
+	 *                 for the next rcu_pending() check in the next jiffy.
+	 */
 	const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist);
 
 	if (cpu_is_offline(smp_processor_id()))
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index b3e07d0bfbbf..2461fe8d0c23 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -990,6 +990,15 @@ static long rcu_nocb_rdp_deoffload(void *arg)
 	 * will refuse to put anything into the bypass.
 	 */
 	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
+	/*
+	 * Start with invoking rcu_core() early. This way if the current thread
+	 * happens to preempt an ongoing call to rcu_core() in the middle,
+	 * leaving some work dismissed because rcu_core() still thinks the rdp is
+	 * completely offloaded, we are guaranteed a nearby future instance of
+	 * rcu_core() to catch up.
+	 */
+	rcu_segcblist_set_flags(cblist, SEGCBLIST_RCU_CORE);
+	invoke_rcu_core();
 	ret = rdp_offload_toggle(rdp, false, flags);
 	swait_event_exclusive(rdp->nocb_state_wq,
 			      !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB |