entry: Explicitly flush pending rcuog wakeup before last rescheduling point

Following the idle loop model, cleanly check for pending rcuog wakeup
before the last rescheduling point on resuming to user mode. This
way we can avoid to do it from rcu_user_enter() with the last resort
self-IPI hack that enforces rescheduling.
Signed-off-by: NFrederic Weisbecker <frederic@kernel.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20210131230548.32970-5-frederic@kernel.org

kernel/entry/common.c

@@ -184,6 +184,10 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		 * enabled above.
 		 */
 		local_irq_disable_exit_to_user();
+
+		/* Check if any of the above work has queued a deferred wakeup */
+		rcu_nocb_flush_deferred_wakeup();
+
 		ti_work = READ_ONCE(current_thread_info()->flags);
 	}
 
@@ -197,6 +201,9 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 
 	lockdep_assert_irqs_disabled();
 
+	/* Flush pending rcuog wakeup before the last need_resched() check */
+	rcu_nocb_flush_deferred_wakeup();
+
 	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
 		ti_work = exit_to_user_mode_loop(regs, ti_work);
 

kernel/rcu/tree.c

@@ -707,13 +707,15 @@ noinstr void rcu_user_enter(void)
 	lockdep_assert_irqs_disabled();
 
 	/*
-	 * We may be past the last rescheduling opportunity in the entry code.
-	 * Trigger a self IPI that will fire and reschedule once we resume to
-	 * user/guest mode.
+	 * Other than generic entry implementation, we may be past the last
+	 * rescheduling opportunity in the entry code. Trigger a self IPI
+	 * that will fire and reschedule once we resume in user/guest mode.
 	 */
 	instrumentation_begin();
+	if (!IS_ENABLED(CONFIG_GENERIC_ENTRY) || (current->flags & PF_VCPU)) {
 		if (do_nocb_deferred_wakeup(rdp) && need_resched())
 			irq_work_queue(this_cpu_ptr(&late_wakeup_work));
+	}
 	instrumentation_end();
 
 	rcu_eqs_enter(true);