linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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()
Date: Thu, 09 Sep 2021 12:59:16 +0200	[thread overview]
Message-ID: <20210909110203.767330253@infradead.org> (raw)
In-Reply-To: 20210909105915.757320973@infradead.org

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)



  reply	other threads:[~2021-09-09 11:04 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-09 10:59 [PATCH 0/4] locking/rwbase: Assorted fixes Peter Zijlstra
2021-09-09 10:59 ` Peter Zijlstra [this message]
2021-09-09 13:45   ` [PATCH 1/4] sched/wakeup: Strengthen current_save_and_set_rtlock_wait_state() Will Deacon
2021-09-09 14:27     ` Peter Zijlstra
2021-09-10 12:57       ` Will Deacon
2021-09-10 13:17         ` Peter Zijlstra
2021-09-10 14:01           ` Peter Zijlstra
2021-09-10 15:06             ` Will Deacon
2021-09-10 16:07             ` Waiman Long
2021-09-10 17:09               ` Peter Zijlstra
2021-09-12  3:57       ` Boqun Feng
2021-09-10 12:45   ` Sebastian Andrzej Siewior
2021-09-13 22:08   ` Thomas Gleixner
2021-09-13 22:52     ` Thomas Gleixner
2021-09-14  6:45       ` Peter Zijlstra
2021-09-09 10:59 ` [PATCH 2/4] locking/rwbase: Properly match set_and_save_state() to restore_state() Peter Zijlstra
2021-09-09 13:53   ` Will Deacon
2021-09-14  7:31   ` Thomas Gleixner
2021-09-16 11:59   ` [tip: locking/urgent] " tip-bot2 for Peter Zijlstra
2021-09-09 10:59 ` [PATCH 3/4] locking/rwbase: Fix rwbase_write_lock() vs __rwbase_read_lock() Peter Zijlstra
2021-09-14  7:45   ` Thomas Gleixner
2021-09-14 13:59     ` Peter Zijlstra
2021-09-14 15:00       ` Thomas Gleixner
2021-09-16 11:59       ` [tip: locking/urgent] locking/rwbase: Extract __rwbase_write_trylock() tip-bot2 for Peter Zijlstra
2021-09-09 10:59 ` [PATCH 4/4] locking/rwbase: Take care of ordering guarantee for fastpath reader Peter Zijlstra
2021-09-14  7:46   ` Thomas Gleixner
2021-09-16 11:59   ` [tip: locking/urgent] " tip-bot2 for Boqun Feng

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210909110203.767330253@infradead.org \
    --to=peterz@infradead.org \
    --cc=bigeasy@linutronix.de \
    --cc=boqun.feng@gmail.com \
    --cc=bristot@redhat.com \
    --cc=dave@stgolabs.net \
    --cc=efault@gmx.de \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longman@redhat.com \
    --cc=mingo@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).