From e6cd1e07a185d5f9b0aa75e020df02d3c1c44940 Mon Sep 17 00:00:00 2001 From: Milton Miller Date: Tue, 15 Mar 2011 13:27:16 -0600 Subject: call_function_many: fix list delete vs add race Peter pointed out there was nothing preventing the list_del_rcu in smp_call_function_interrupt from running before the list_add_rcu in smp_call_function_many. Fix this by not setting refs until we have gotten the lock for the list. Take advantage of the wmb in list_add_rcu to save an explicit additional one. I tried to force this race with a udelay before the lock & list_add and by mixing all 64 online cpus with just 3 random cpus in the mask, but was unsuccessful. Still, inspection shows a valid race, and the fix is a extension of the existing protection window in the current code. Cc: stable@kernel.org (v2.6.32 and later) Reported-by: Peter Zijlstra Signed-off-by: Milton Miller Signed-off-by: Linus Torvalds --- kernel/smp.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'kernel/smp.c') diff --git a/kernel/smp.c b/kernel/smp.c index 9910744f0856..aaeee20c5634 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -491,14 +491,15 @@ void smp_call_function_many(const struct cpumask *mask, cpumask_clear_cpu(this_cpu, data->cpumask); /* - * To ensure the interrupt handler gets an complete view - * we order the cpumask and refs writes and order the read - * of them in the interrupt handler. In addition we may - * only clear our own cpu bit from the mask. + * We reuse the call function data without waiting for any grace + * period after some other cpu removes it from the global queue. + * This means a cpu might find our data block as it is writen. + * The interrupt handler waits until it sees refs filled out + * while its cpu mask bit is set; here we may only clear our + * own cpu mask bit, and must wait to set refs until we are sure + * previous writes are complete and we have obtained the lock to + * add the element to the queue. */ - smp_wmb(); - - atomic_set(&data->refs, cpumask_weight(data->cpumask)); raw_spin_lock_irqsave(&call_function.lock, flags); /* @@ -507,6 +508,11 @@ void smp_call_function_many(const struct cpumask *mask, * will not miss any other list entries: */ list_add_rcu(&data->csd.list, &call_function.queue); + /* + * We rely on the wmb() in list_add_rcu to order the writes + * to func, data, and cpumask before this write to refs. + */ + atomic_set(&data->refs, cpumask_weight(data->cpumask)); raw_spin_unlock_irqrestore(&call_function.lock, flags); /* -- cgit v1.2.3