summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2013-06-26 12:17:32 +0200
committerThomas Gleixner <tglx@linutronix.de>2013-07-02 14:26:44 +0200
commitc9b5a266b103af873abb9ac03bc3d067702c8f4b (patch)
tree91e5ec118a7e96b998e18a8601d8f14c76d94823
parentx86: xen: Sync the CMOS RTC as well as the Xen wallclock (diff)
downloadlinux-c9b5a266b103af873abb9ac03bc3d067702c8f4b.tar.xz
linux-c9b5a266b103af873abb9ac03bc3d067702c8f4b.zip
tick: Make oneshot broadcast robust vs. CPU offlining
In periodic mode we remove offline cpus from the broadcast propagation mask. In oneshot mode we fail to do so. This was not a problem so far, but the recent changes to the broadcast propagation introduced a constellation which can result in a NULL pointer dereference. What happens is: CPU0 CPU1 idle() arch_idle() tick_broadcast_oneshot_control(OFF); set cpu1 in tick_broadcast_force_mask if (cpu_offline()) arch_cpu_dead() cpu_dead_cleanup(cpu1) cpu1 tickdevice pointer = NULL broadcast interrupt dereference cpu1 tickdevice pointer -> OOPS We dereference the pointer because cpu1 is still set in tick_broadcast_force_mask and tick_do_broadcast() expects a valid cpumask and therefor lacks any further checks. Remove the cpu from the tick_broadcast_force_mask before we set the tick device pointer to NULL. Also add a sanity check to the oneshot broadcast function, so we can detect such issues w/o crashing the machine. Reported-by: Prarit Bhargava <prarit@redhat.com> Cc: athorlton@sgi.com Cc: CAI Qian <caiqian@redhat.com> Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1306261303260.4013@ionos.tec.linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
-rw-r--r--kernel/time/tick-broadcast.c13
1 files changed, 11 insertions, 2 deletions
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index d067c01586f5..4790037163f6 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -533,6 +533,13 @@ again:
cpumask_clear(tick_broadcast_force_mask);
/*
+ * Sanity check. Catch the case where we try to broadcast to
+ * offline cpus.
+ */
+ if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask)))
+ cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+ /*
* Wakeup the cpus which have an expired event.
*/
tick_do_broadcast(tmpmask);
@@ -773,10 +780,12 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
- * Clear the broadcast mask flag for the dead cpu, but do not
- * stop the broadcast device!
+ * Clear the broadcast masks for the dead cpu, but do not stop
+ * the broadcast device!
*/
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}