RE: [BISECTION RESULT] sched: revert cpu_clock topre-27ec4407790d075c325e1f4da0a19c56953cce23 state

[Luck, Tony]

+u64 sched_clock_cpu(int cpu)
+{
+       if (unlikely(!sched_clock_running))
+               return 0;
+
+       return sched_clock();
+}

This looks like it will solve the issue on the boot cpu.  It
leaves a potential hole as we bring up other cpus if[1] there
are any printk() calls before they get to cpu_init() to
initialize ar.kr3.  This code path is all under arch/ia64
though ... so if we shoot ourselves in the foot, it will be
our own fault.

-Tony

[1] Currently there is just one Dprintk() call in this path
at the start of start_secondary() ... I could put it inside
#ifndef CONFIG_PRINTK_TIME so as not to surprise anyone that
enabled it.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/