Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Message-ID: <20210909110203.767330253@infradead.org>
User-Agent: quilt/0.66
Date:   Thu, 09 Sep 2021 12:59:16 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     tglx@linutronix.de, boqun.feng@gmail.com
Cc:     linux-kernel@vger.kernel.org, peterz@infradead.org,
        Ingo Molnar <mingo@kernel.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Davidlohr Bueso <dave@stgolabs.net>,
        Will Deacon <will@kernel.org>,
        Waiman Long <longman@redhat.com>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
        Mike Galbraith <efault@gmx.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>
Subject: [PATCH 1/4] sched/wakeup: Strengthen current_save_and_set_rtlock_wait_state()
References: <20210909105915.757320973@infradead.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Precedence: bulk

While looking at current_save_and_set_rtlock_wait_state() I'm thinking
it really ought to use smp_store_mb(), because something like:

	current_save_and_set_rtlock_wait_state();
	for (;;) {
		if (try_lock())
			break;

		raw_spin_unlock_irq(&lock->wait_lock);
		schedule();
		raw_spin_lock_irq(&lock->wait_lock);

		set_current_state(TASK_RTLOCK_WAIT);
	}
	current_restore_rtlock_saved_state();

which is the advertised usage in the comment, is actually broken,
since trylock() will only need a load-acquire in general and that
could be re-ordered against the state store, which could lead to a
missed wakeup -> BAD (tm).

While there, make them consistent with the IRQ usage in
set_special_state().

Fixes: 5f220be21418 ("sched/wakeup: Prepare for RT sleeping spin/rwlocks")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/sched.h |   19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -245,7 +245,8 @@ struct task_group;
  *		if (try_lock())
  *			break;
  *		raw_spin_unlock_irq(&lock->wait_lock);
- *		schedule_rtlock();
+ *		if (!cond)
+ *			schedule_rtlock();
  *		raw_spin_lock_irq(&lock->wait_lock);
  *		set_current_state(TASK_RTLOCK_WAIT);
  *	}
@@ -253,22 +254,24 @@ struct task_group;
  */
 #define current_save_and_set_rtlock_wait_state()			\
 	do {								\
-		lockdep_assert_irqs_disabled();				\
-		raw_spin_lock(&current->pi_lock);			\
+		unsigned long flags; /* may shadow */			\
+									\
+		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
 		current->saved_state = current->__state;		\
 		debug_rtlock_wait_set_state();				\
-		WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT);		\
-		raw_spin_unlock(&current->pi_lock);			\
+		smp_store_mb(current->__state, TASK_RTLOCK_WAIT);	\
+		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0);
 
 #define current_restore_rtlock_saved_state()				\
 	do {								\
-		lockdep_assert_irqs_disabled();				\
-		raw_spin_lock(&current->pi_lock);			\
+		unsigned long flags; /* may shadow */			\
+									\
+		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
 		debug_rtlock_wait_restore_state();			\
 		WRITE_ONCE(current->__state, current->saved_state);	\
 		current->saved_state = TASK_RUNNING;			\
-		raw_spin_unlock(&current->pi_lock);			\
+		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0);
 
 #define get_current_state()	READ_ONCE(current->__state)