Vitaly Kuznetsov <vkuzn...@redhat.com> writes: > A hang on CPU0 onlining after a preceding offlining is observed. Trace > shows that CPU0 is stuck in check_tsc_sync_target() waiting for source > CPU to run check_tsc_sync_source() but this never happens. Source CPU, > in its turn, is stuck on synchronize_sched() which is called from > native_cpu_up() -> do_boot_cpu() -> unregister_nmi_handler(). > > Fix the issue by moving unregister_nmi_handler() from do_boot_cpu() to > native_cpu_up() after cpu onlining is done. > > Signed-off-by: Vitaly Kuznetsov <vkuzn...@redhat.com> > --- > RFC part: I tested the fix on KVM and Xen guests and it works just fine > but CPU0 hotplug is not something I'm really familiar with, I may be > missing some important details. I also skipped code archeology to figure > out when things got broken.
Any comments? This can be considered as non-RFC if not :-) -- Vitaly
