Re: [PATCH] mm/alloc: fallback to first node if the wanted node offline

[Pingfan Liu]

On Fri, Dec 7, 2018 at 11:56 PM Michal Hocko <mhocko@xxxxxxxxxx> wrote:
>
> On Fri 07-12-18 22:27:13, Pingfan Liu wrote:
> [...]
> > diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
> > index 1308f54..4dc497d 100644
> > --- a/arch/x86/mm/numa.c
> > +++ b/arch/x86/mm/numa.c
> > @@ -754,18 +754,23 @@ void __init init_cpu_to_node(void)
> >  {
> >         int cpu;
> >         u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
> > +       int node, nr;
> >
> >         BUG_ON(cpu_to_apicid == NULL);
> > +       nr = cpumask_weight(cpu_possible_mask);
> > +
> > +       /* bring up all possible node, since dev->numa_node */
> > +       //should check acpi works for node possible,
> > +       for_each_node(node)
> > +               if (!node_online(node))
> > +                       init_memory_less_node(node);
>
> I suspect there is no change if you replace for_each_node by
>         for_each_node_mask(nid, node_possible_map)
>
> here. If that is the case then we are probably calling
> free_area_init_node too early. I do not see it yet though.

Maybe I do not clearly get your meaning, just try to guess. But if you
worry about node_possible_map, then it is dynamically set by
alloc_node_data(). The map is changed after the first time to call
free_area_init_node() for the node with memory.  This logic is the
same as the current x86 code.

Thanks,
Pingfan