smp: Optimize flush_smp_call_function_queue()

The call_single_queue can contain (two) different callbacks,
synchronous and asynchronous. The current interrupt handler runs them
in-order, which means that remote CPUs that are waiting for their
synchronous call can be delayed by running asynchronous callbacks.

Rework the interrupt handler to first run the synchonous callbacks.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200526161907.836818381@infradead.org

kernel/smp.c

@@ -209,9 +209,9 @@ void generic_smp_call_function_single_interrupt(void)
  */
 static void flush_smp_call_function_queue(bool warn_cpu_offline)
 {
-	struct llist_head *head;
-	struct llist_node *entry;
 	call_single_data_t *csd, *csd_next;
+	struct llist_node *entry, *prev;
+	struct llist_head *head;
 	static bool warned;
 
 	lockdep_assert_irqs_disabled();
@@ -235,20 +235,39 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 				csd->func);
 	}
 
+	/*
+	 * First; run all SYNC callbacks, people are waiting for us.
+	 */
+	prev = NULL;
 	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
 		smp_call_func_t func = csd->func;
 		void *info = csd->info;
 
 		/* Do we wait until *after* callback? */
 		if (csd->flags & CSD_FLAG_SYNCHRONOUS) {
+			if (prev) {
+				prev->next = &csd_next->llist;
+			} else {
+				entry = &csd_next->llist;
+			}
 			func(info);
 			csd_unlock(csd);
 		} else {
-			csd_unlock(csd);
-			func(info);
+			prev = &csd->llist;
 		}
 	}
 
+	/*
+	 * Second; run all !SYNC callbacks.
+	 */
+	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
+		smp_call_func_t func = csd->func;
+		void *info = csd->info;
+
+		csd_unlock(csd);
+		func(info);
+	}
+
 	/*
 	 * Handle irq works queued remotely by irq_work_queue_on().
 	 * Smp functions above are typically synchronous so they