diff --git a/kernel/smp.c b/kernel/smp.c
index 306f8180b0d5..80c33f8de14f 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -29,6 +29,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
 
+static void flush_smp_call_function_queue(bool warn_cpu_offline);
+
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
@@ -51,12 +53,27 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
+		/* Fall-through to the CPU_DEAD[_FROZEN] case. */
 
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		free_cpumask_var(cfd->cpumask);
 		free_percpu(cfd->csd);
 		break;
+
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		/*
+		 * The IPIs for the smp-call-function callbacks queued by other
+		 * CPUs might arrive late, either due to hardware latencies or
+		 * because this CPU disabled interrupts (inside stop-machine)
+		 * before the IPIs were sent. So flush out any pending callbacks
+		 * explicitly (without waiting for the IPIs to arrive), to
+		 * ensure that the outgoing CPU doesn't go offline with work
+		 * still pending.
+		 */
+		flush_smp_call_function_queue(false);
+		break;
 #endif
 	};
 
@@ -177,23 +194,47 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
 	return 0;
 }
 
-/*
- * Invoked by arch to handle an IPI for call function single. Must be
- * called from the arch with interrupts disabled.
+/**
+ * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks
+ *
+ * Invoked by arch to handle an IPI for call function single.
+ * Must be called with interrupts disabled.
  */
 void generic_smp_call_function_single_interrupt(void)
 {
+	flush_smp_call_function_queue(true);
+}
+
+/**
+ * flush_smp_call_function_queue - Flush pending smp-call-function callbacks
+ *
+ * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an
+ *		      offline CPU. Skip this check if set to 'false'.
+ *
+ * Flush any pending smp-call-function callbacks queued on this CPU. This is
+ * invoked by the generic IPI handler, as well as by a CPU about to go offline,
+ * to ensure that all pending IPI callbacks are run before it goes completely
+ * offline.
+ *
+ * Loop through the call_single_queue and run all the queued callbacks.
+ * Must be called with interrupts disabled.
+ */
+static void flush_smp_call_function_queue(bool warn_cpu_offline)
+{
+	struct llist_head *head;
 	struct llist_node *entry;
 	struct call_single_data *csd, *csd_next;
 	static bool warned;
 
-	entry = llist_del_all(&__get_cpu_var(call_single_queue));
+	WARN_ON(!irqs_disabled());
+
+	head = &__get_cpu_var(call_single_queue);
+	entry = llist_del_all(head);
 	entry = llist_reverse_order(entry);
 
-	/*
-	 * Shouldn't receive this interrupt on a cpu that is not yet online.
-	 */
-	if (unlikely(!cpu_online(smp_processor_id()) && !warned)) {
+	/* There shouldn't be any pending callbacks on an offline CPU. */
+	if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) &&
+		     !warned && !llist_empty(head))) {
 		warned = true;
 		WARN(1, "IPI on offline CPU %d\n", smp_processor_id());