From bc9560155f4063bbc9be71bd69d6726d41b47653 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 12 Feb 2015 20:59:13 +0100 Subject: 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()) 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 Reported-by: Davidlohr Bueso Tested-by: Paul E. McKenney Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) [ Added a comment with the barrier. ] Cc: Linus Torvalds Cc: Nicholas Mc Guire Cc: raghavendra.kt@linux.vnet.ibm.com Cc: waiman.long@hp.com Fixes: de30ec47302c ("sched/completion: Remove unnecessary ->wait.lock serialization when reading completion state") Link: http://lkml.kernel.org/r/20150212195913.GA30430@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/completion.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'kernel') 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; } EXPORT_SYMBOL(completion_done); -- cgit v1.1