[Xen-devel] Re: [PATCH] enable pvhvm vcpu placement in kernel

[Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>]

On Thu, Oct 27, 2011 at 10:28:59PM -0700, zhenzhong.duan@xxxxxxxxxx wrote:
> pvhvm running with more than 32 vcpus and pv_irq/pv_time enabled 
> need vcpu placement to work, or else it will softlockup.

Stefano?

> 
> Signed-off-by: Zhenzhong Duan <zhenzhong.duan@xxxxxxxxxx>
> ---
> diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
> index da8afd5..1f92865 100644
> --- a/arch/x86/xen/enlighten.c
> +++ b/arch/x86/xen/enlighten.c
> @@ -1356,7 +1356,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct 
> notifier_block *self,
>       int cpu = (long)hcpu;
>       switch (action) {
>       case CPU_UP_PREPARE:
> -             per_cpu(xen_vcpu, cpu) = 
> &HYPERVISOR_shared_info->vcpu_info[cpu];
> +             xen_vcpu_setup(cpu);
>               if (xen_have_vector_callback)
>                       xen_init_lock_cpu(cpu);
>               break;
> @@ -1386,7 +1386,6 @@ static void __init xen_hvm_guest_init(void)
>       xen_hvm_smp_init();
>       register_cpu_notifier(&xen_hvm_cpu_notifier);
>       xen_unplug_emulated_devices();
> -     have_vcpu_info_placement = 0;
>       x86_init.irqs.intr_init = xen_init_IRQ;
>       xen_hvm_init_time_ops();
>       xen_hvm_init_mmu_ops();

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel