All of lore.kernel.org
 help / color / mirror / Atom feed
From: Oleg Nesterov <oleg@redhat.com>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org, dave@stgolabs.net,
	waiman.long@hp.com, raghavendra.kt@linux.vnet.ibm.com
Subject: [PATCH] sched/completion: completion_done() should serialize with complete()
Date: Thu, 12 Feb 2015 20:59:13 +0100	[thread overview]
Message-ID: <20150212195913.GA30430@redhat.com> (raw)
In-Reply-To: <20150212003430.GA28656@linux.vnet.ibm.com>

Commit de30ec47302c "Remove unnecessary ->wait.lock serialization when
reading completion state" was not correct, without lock/unlock the code
like stop_machine_from_inactive_cpu()

	while (!completion_done())
		cpu_relax();

can return before complete() finishes its spin_unlock() which writes to
this memory. And spin_unlock_wait().

While at it, change try_wait_for_completion() to use READ_ONCE().

Reported-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Reported-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>

--- x/kernel/sched/completion.c
+++ x/kernel/sched/completion.c
@@ -274,7 +274,7 @@ bool try_wait_for_completion(struct comp
 	 * first without taking the lock so we can
 	 * return early in the blocking case.
 	 */
-	if (!ACCESS_ONCE(x->done))
+	if (!READ_ONCE(x->done))
 		return 0;
 
 	spin_lock_irqsave(&x->wait.lock, flags);
@@ -297,6 +297,11 @@ EXPORT_SYMBOL(try_wait_for_completion);
  */
 bool completion_done(struct completion *x)
 {
-	return !!ACCESS_ONCE(x->done);
+	if (!READ_ONCE(x->done))
+		return false;
+
+	smp_rmb();
+	spin_unlock_wait(&x->wait.lock);
+	return true;
 }
 EXPORT_SYMBOL(completion_done);


  parent reply	other threads:[~2015-02-12 20:01 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-02-12  0:34 BUG: spinlock bad magic on CPU#0, migration/0/9 Paul E. McKenney
2015-02-12  3:15 ` Davidlohr Bueso
2015-02-12  3:43   ` Paul E. McKenney
2015-02-12 17:28   ` Oleg Nesterov
2015-02-12 17:41     ` Oleg Nesterov
2015-02-12 17:58       ` Davidlohr Bueso
2015-02-12 19:10       ` Nicholas Mc Guire
2015-02-12 19:37         ` Oleg Nesterov
2015-02-12 21:27           ` Oleg Nesterov
2015-02-13 18:17             ` Nicholas Mc Guire
2015-02-13 18:53               ` Oleg Nesterov
2015-02-14  8:35                 ` Nicholas Mc Guire
2015-02-14 14:00                   ` Oleg Nesterov
2015-02-12 19:59         ` Davidlohr Bueso
2015-02-12 19:32       ` Nicholas Mc Guire
2015-02-12 19:39         ` Oleg Nesterov
2015-02-12 19:59 ` Oleg Nesterov [this message]
2015-02-13 21:09   ` [PATCH] sched/completion: completion_done() should serialize with complete() Paul E. McKenney
2015-02-13 21:56   ` Davidlohr Bueso
2015-02-13 22:02     ` Davidlohr Bueso
2015-02-16  8:21   ` Peter Zijlstra
2015-02-16 16:51     ` Oleg Nesterov
2015-02-18 17:06   ` [tip:sched/core] sched/completion: Serialize completion_done() " tip-bot for Oleg Nesterov

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=20150212195913.GA30430@redhat.com \
    --to=oleg@redhat.com \
    --cc=dave@stgolabs.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=raghavendra.kt@linux.vnet.ibm.com \
    --cc=waiman.long@hp.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.