From b5dc8db4a135a1f4505558e492621380f4adb8e8 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 20 Jan 2011 14:44:33 -0800 Subject: kernel/smp.c: fix smp_call_function_many() SMP race commit 6dc19899958e420a931274b94019e267e2396d3e upstream. I noticed a failure where we hit the following WARN_ON in generic_smp_call_function_interrupt: if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) continue; data->csd.func(data->csd.info); refs = atomic_dec_return(&data->refs); WARN_ON(refs < 0); <------------------------- We atomically tested and cleared our bit in the cpumask, and yet the number of cpus left (ie refs) was 0. How can this be? It turns out commit 54fdade1c3332391948ec43530c02c4794a38172 ("generic-ipi: make struct call_function_data lockless") is at fault. It removes locking from smp_call_function_many and in doing so creates a rather complicated race. The problem comes about because: - The smp_call_function_many interrupt handler walks call_function.queue without any locking. - We reuse a percpu data structure in smp_call_function_many. - We do not wait for any RCU grace period before starting the next smp_call_function_many. Imagine a scenario where CPU A does two smp_call_functions back to back, and CPU B does an smp_call_function in between. We concentrate on how CPU C handles the calls: CPU A CPU B CPU C CPU D smp_call_function smp_call_function_interrupt walks call_function.queue sees data from CPU A on list smp_call_function smp_call_function_interrupt walks call_function.queue sees (stale) CPU A on list smp_call_function int clears last ref on A list_del_rcu, unlock smp_call_function reuses percpu *data A data->cpumask sees and clears bit in cpumask might be using old or new fn! decrements refs below 0 set data->refs (too late!) The important thing to note is since the interrupt handler walks a potentially stale call_function.queue without any locking, then another cpu can view the percpu *data structure at any time, even when the owner is in the process of initialising it. The following test case hits the WARN_ON 100% of the time on my PowerPC box (having 128 threads does help :) #include #include #define ITERATIONS 100 static void do_nothing_ipi(void *dummy) { } static void do_ipis(struct work_struct *dummy) { int i; for (i = 0; i < ITERATIONS; i++) smp_call_function(do_nothing_ipi, NULL, 1); printk(KERN_DEBUG "cpu %d finished\n", smp_processor_id()); } static struct work_struct work[NR_CPUS]; static int __init testcase_init(void) { int cpu; for_each_online_cpu(cpu) { INIT_WORK(&work[cpu], do_ipis); schedule_work_on(cpu, &work[cpu]); } return 0; } static void __exit testcase_exit(void) { } module_init(testcase_init) module_exit(testcase_exit) MODULE_LICENSE("GPL"); MODULE_AUTHOR("Anton Blanchard"); I tried to fix it by ordering the read and the write of ->cpumask and ->refs. In doing so I missed a critical case but Paul McKenney was able to spot my bug thankfully :) To ensure we arent viewing previous iterations the interrupt handler needs to read ->refs then ->cpumask then ->refs _again_. Thanks to Milton Miller and Paul McKenney for helping to debug this issue. [miltonm@bga.com: add WARN_ON and BUG_ON, remove extra read of refs before initial read of mask that doesn't help (also noted by Peter Zijlstra), adjust comments, hopefully clarify scenario ] [miltonm@bga.com: remove excess tests] Signed-off-by: Anton Blanchard Signed-off-by: Milton Miller Cc: Ingo Molnar Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- kernel/smp.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/kernel/smp.c b/kernel/smp.c index c9d1c7835c2f..ea5dc8f13937 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -193,6 +193,24 @@ void generic_smp_call_function_interrupt(void) list_for_each_entry_rcu(data, &call_function.queue, csd.list) { int refs; + /* + * Since we walk the list without any locks, we might + * see an entry that was completed, removed from the + * list and is in the process of being reused. + * + * We must check that the cpu is in the cpumask before + * checking the refs, and both must be set before + * executing the callback on this cpu. + */ + + if (!cpumask_test_cpu(cpu, data->cpumask)) + continue; + + smp_rmb(); + + if (atomic_read(&data->refs) == 0) + continue; + if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) continue; @@ -201,6 +219,8 @@ void generic_smp_call_function_interrupt(void) refs = atomic_dec_return(&data->refs); WARN_ON(refs < 0); if (!refs) { + WARN_ON(!cpumask_empty(data->cpumask)); + spin_lock(&call_function.lock); list_del_rcu(&data->csd.list); spin_unlock(&call_function.lock); @@ -401,11 +421,21 @@ void smp_call_function_many(const struct cpumask *mask, data = &__get_cpu_var(cfd_data); csd_lock(&data->csd); + BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask)); data->csd.func = func; data->csd.info = info; cpumask_and(data->cpumask, mask, cpu_online_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. + */ + smp_wmb(); + atomic_set(&data->refs, cpumask_weight(data->cpumask)); spin_lock_irqsave(&call_function.lock, flags); -- cgit v1.2.3