On Fri, Jul 10, 2015 at 06:03:54PM +0200, Dario Faggioli wrote:
> On Fri, 2015-07-10 at 16:25 +0100, Jan Beulich wrote:
> > >>> On 10.07.15 at 17:13, wrote:
>
> > > cpu_down()
> > > stop_machine_run(take_cpu_down, ...)
> > > notifier_call_chain(&cpu_chain, CPU_DYING, ...)
> > > __cpu_di
On Fri, 2015-07-10 at 16:25 +0100, Jan Beulich wrote:
> >>> On 10.07.15 at 17:13, wrote:
> > cpu_down()
> > stop_machine_run(take_cpu_down, ...)
> > notifier_call_chain(&cpu_chain, CPU_DYING, ...)
> > __cpu_disable()
> > remove_siblinginfo()
> > __cpu_die()
> > notifier_call_cha
On Fri, 2015-07-10 at 16:13 +0100, Jan Beulich wrote:
> >>> On 10.07.15 at 16:57, wrote:
> > ...
> > (XEN) Preparing system for ACPI S5 state.
> > (XEN) Disabling non-boot CPUs ...
> > (XEN) Broke affinity for irq 9
> > (XEN) cpu=1 cpu_to_socket=4294967295
> > (XEN) [ Xen-4.6-unstable x86_
>>> On 10.07.15 at 17:13, wrote:
On 10.07.15 at 16:57, wrote:
>> I added this printk:
>>
>> printk(" cpu=%u cpu_to_socket=%u\n", cpu, socket);
>>
>> Right before this chunk of code, in cpu_smpboot_free():
>>
>> if ( cpumask_empty(socket_cpumask[socket]) )
>> {
>> xfree(so
>>> On 10.07.15 at 16:57, wrote:
> I added this printk:
>
> printk(" cpu=%u cpu_to_socket=%u\n", cpu, socket);
>
> Right before this chunk of code, in cpu_smpboot_free():
>
> if ( cpumask_empty(socket_cpumask[socket]) )
> {
> xfree(socket_cpumask[socket]);
> socket_cpum
On Fri, 2015-07-10 at 15:47 +0100, Andrew Cooper wrote:
> On 10/07/15 15:29, Dario Faggioli wrote:
> > (XEN) Xen call trace:
> > (XEN)[] cpu_smpboot_free+0x2b/0x255
> > (XEN)[] cpu_smpboot_callback+0x317/0x327
> > (XEN)[] notifier_call_chain+0x67/0x87
> > (XEN)[] cpu_down+0xd9/0x12
On 10/07/15 15:29, Dario Faggioli wrote:
> On Thu, 2015-07-09 at 22:23 +0800, Chao Peng wrote:
>> For booting cpu, the socket number is not needed to be 0 so
>> it needs to be computed by cpu number.
>>
> This made my system boot, yes... but now it does not shutdown! :-/
>
> I'm attaching the splat
On Thu, 2015-07-09 at 22:23 +0800, Chao Peng wrote:
> For booting cpu, the socket number is not needed to be 0 so
> it needs to be computed by cpu number.
>
This made my system boot, yes... but now it does not shutdown! :-/
I'm attaching the splat I see, reliably, on my testbox.
I'll try have a
On 07/09/2015 11:16 AM, Andrew Cooper wrote:
On 09/07/15 15:23, Chao Peng wrote:
For booting cpu, the socket number is not needed to be 0 so
it needs to be computed by cpu number.
For secondary cpu, phys_proc_id is not valid in CPU_PREPARE
notifier(cpu_smpboot_alloc), so cpu_to_socket(cpu) can'
On 09/07/15 15:23, Chao Peng wrote:
> For booting cpu, the socket number is not needed to be 0 so
> it needs to be computed by cpu number.
>
> For secondary cpu, phys_proc_id is not valid in CPU_PREPARE
> notifier(cpu_smpboot_alloc), so cpu_to_socket(cpu) can't be used.
> Instead, pre-allocate seco
For booting cpu, the socket number is not needed to be 0 so
it needs to be computed by cpu number.
For secondary cpu, phys_proc_id is not valid in CPU_PREPARE
notifier(cpu_smpboot_alloc), so cpu_to_socket(cpu) can't be used.
Instead, pre-allocate secondary_cpu_mask in cpu_smpboot_alloc()
and later
11 matches
Mail list logo
