diff options
authorMilton Miller <miltonm@bga.com>2011-03-15 13:27:17 -0600
committerEric Miao <eric.miao@canonical.com>2011-11-10 07:39:01 +0800
commit7470f4bc13e9d6edd98ef57b753f0bb464cc2657 (patch)
parent113be749eab5e7c340e050d3e04462affa915e20 (diff)
smp_call_function_many: handle concurrent clearing of mask
commit 723aae25d5cdb09962901d36d526b44d4be1051c upstream. Mike Galbraith reported finding a lockup ("perma-spin bug") where the cpumask passed to smp_call_function_many was cleared by other cpu(s) while a cpu was preparing its call_data block, resulting in no cpu to clear the last ref and unlock the block. Having cpus clear their bit asynchronously could be useful on a mask of cpus that might have a translation context, or cpus that need a push to complete an rcu window. Instead of adding a BUG_ON and requiring yet another cpumask copy, just detect the race and handle it. Note: arch_send_call_function_ipi_mask must still handle an empty cpumask because the data block is globally visible before the that arch callback is made. And (obviously) there are no guarantees to which cpus are notified if the mask is changed during the call; only cpus that were online and had their mask bit set during the whole call are guaranteed to be called. Reported-by: Mike Galbraith <efault@gmx.de> Reported-by: Jan Beulich <JBeulich@novell.com> Acked-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Milton Miller <miltonm@bga.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> (cherry picked from commit d1342fed517f89ad4c3d956d9e214d72c06bb7c1)
1 files changed, 10 insertions, 3 deletions
diff --git a/kernel/smp.c b/kernel/smp.c
index 7c6ded5effd..954548906af 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -450,7 +450,7 @@ void smp_call_function_many(const struct cpumask *mask,
struct call_function_data *data;
unsigned long flags;
- int cpu, next_cpu, this_cpu = smp_processor_id();
+ int refs, cpu, next_cpu, this_cpu = smp_processor_id();
* Can deadlock when called with interrupts disabled.
@@ -461,7 +461,7 @@ void smp_call_function_many(const struct cpumask *mask,
WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
&& !oops_in_progress && !early_boot_irqs_disabled);
- /* So, what's a CPU they want? Ignoring this one. */
+ /* Try to fastpath. So, what's a CPU they want? Ignoring this one. */
cpu = cpumask_first_and(mask, cpu_online_mask);
if (cpu == this_cpu)
cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
@@ -519,6 +519,13 @@ void smp_call_function_many(const struct cpumask *mask,
/* We rely on the "and" being processed before the store */
cpumask_and(data->cpumask, mask, cpu_online_mask);
cpumask_clear_cpu(this_cpu, data->cpumask);
+ refs = cpumask_weight(data->cpumask);
+ /* Some callers race with other cpus changing the passed mask */
+ if (unlikely(!refs)) {
+ csd_unlock(&data->csd);
+ return;
+ }
raw_spin_lock_irqsave(&call_function.lock, flags);
@@ -532,7 +539,7 @@ void smp_call_function_many(const struct cpumask *mask,
* to the cpumask before this write to refs, which indicates
* data is on the list and is ready to be processed.
- atomic_set(&data->refs, cpumask_weight(data->cpumask));
+ atomic_set(&data->refs, refs);
raw_spin_unlock_irqrestore(&call_function.lock, flags);