[tip:sched/core] sched/completion: Serialize completion_done() with complete()

From: tip-bot for Oleg Nesterov
Date: Wed Feb 18 2015 - 12:08:42 EST

Commit-ID: bc9560155f4063bbc9be71bd69d6726d41b47653
Gitweb: http://git.kernel.org/tip/bc9560155f4063bbc9be71bd69d6726d41b47653
Author: Oleg Nesterov <oleg@xxxxxxxxxx>
AuthorDate: Thu, 12 Feb 2015 20:59:13 +0100
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 18 Feb 2015 14:27:40 +0100

sched/completion: Serialize completion_done() with complete()

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())

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@xxxxxxxxxxxxxxxxxx>
Reported-by: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Tested-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
[ Added a comment with the barrier. ]
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Nicholas Mc Guire <der.herr@xxxxxxx>
Cc: raghavendra.kt@xxxxxxxxxxxxxxxxxx
Cc: waiman.long@xxxxxx
Fixes: de30ec47302c ("sched/completion: Remove unnecessary ->wait.lock serialization when reading completion state")
Link: http://lkml.kernel.org/r/20150212195913.GA30430@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
kernel/sched/completion.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 7052d3f..8d0f35d 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -274,7 +274,7 @@ bool try_wait_for_completion(struct completion *x)
* 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 +297,21 @@ EXPORT_SYMBOL(try_wait_for_completion);
bool completion_done(struct completion *x)
- return !!ACCESS_ONCE(x->done);
+ if (!READ_ONCE(x->done))
+ return false;
+ /*
+ * If ->done, we need to wait for complete() to release ->wait.lock
+ * otherwise we can end up freeing the completion before complete()
+ * is done referencing it.
+ *
+ * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders
+ * the loads of ->done and ->wait.lock such that we cannot observe
+ * the lock before complete() acquires it while observing the ->done
+ * after it's acquired the lock.
+ */
+ smp_rmb();
+ spin_unlock_wait(&x->wait.lock);
+ return true;
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/