clockevents: Prevent clockevent_devices list corruption on cpu hotplug

commit bb6eddf7676e1c1f3e637aa93c5224488d99036f upstream.

Xiaotian Feng triggered a list corruption in the clock events list on
CPU hotplug and debugged the root cause.

If a CPU registers more than one per cpu clock event device, then only
the active clock event device is removed on CPU_DEAD. The unused
devices are kept in the clock events device list.

On CPU up the clock event devices are registered again, which means
that we list_add an already enqueued list_head. That results in list
corruption.

Resolve this by removing all devices which are associated to the dead
CPU on CPU_DEAD.

Reported-by: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 620b58abdc3295307990978671b81173feb8ff47..9484be456d69b8f5858dd42a2e158f217a1e820f 100644 (file)
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -237,8 +237,9 @@ void clockevents_exchange_device(struct clock_event_device *old,
  */
 void clockevents_notify(unsigned long reason, void *arg)
 {
-       struct list_head *node, *tmp;
+       struct clock_event_device *dev, *tmp;
        unsigned long flags;
+       int cpu;
 
        spin_lock_irqsave(&clockevents_lock, flags);
        clockevents_do_notify(reason, arg);
@@ -249,8 +250,19 @@ void clockevents_notify(unsigned long reason, void *arg)
                 * Unregister the clock event devices which were
                 * released from the users in the notify chain.
                 */
-               list_for_each_safe(node, tmp, &clockevents_released)
-                       list_del(node);
+               list_for_each_entry_safe(dev, tmp, &clockevents_released, list)
+                       list_del(&dev->list);
+               /*
+                * Now check whether the CPU has left unused per cpu devices
+                */
+               cpu = *((int *)arg);
+               list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) {
+                       if (cpumask_test_cpu(cpu, dev->cpumask) &&
+                           cpumask_weight(dev->cpumask) == 1) {
+                               BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+                               list_del(&dev->list);
+                       }
+               }
                break;
        default:
                break;