On Thu, Dec 6, 2018 at 6:03 PM Pingfan Liu <kernelf...@gmail.com> wrote:
>
> [...]
> > THanks for pointing this out. It made my life easier. So It think the
> > bug is that we call init_memory_less_node from this path. I suspect
> > numa_register_memblks is the right place to do this. So I admit I
> > am not 100% sure but could you give this a try please?
> >
> Sure.
>
> > diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
> > index 1308f5408bf7..4575ae4d5449 100644
> > --- a/arch/x86/mm/numa.c
> > +++ b/arch/x86/mm/numa.c
> > @@ -527,6 +527,19 @@ static void __init numa_clear_kernel_node_hotplug(void)
> >         }
> >  }
> >
> > +static void __init init_memory_less_node(int nid)
> > +{
> > +       unsigned long zones_size[MAX_NR_ZONES] = {0};
> > +       unsigned long zholes_size[MAX_NR_ZONES] = {0};
> > +
> > +       free_area_init_node(nid, zones_size, 0, zholes_size);
> > +
> > +       /*
> > +        * All zonelists will be built later in start_kernel() after per cpu
> > +        * areas are initialized.
> > +        */
> > +}
> > +
> >  static int __init numa_register_memblks(struct numa_meminfo *mi)
> >  {
> >         unsigned long uninitialized_var(pfn_align);
> > @@ -592,6 +605,8 @@ static int __init numa_register_memblks(struct 
> > numa_meminfo *mi)
> >                         continue;
> >
> >                 alloc_node_data(nid);
> > +               if (!end)
> > +                       init_memory_less_node(nid);
> >         }
> >
> >         /* Dump memblock with node info and return. */
> > @@ -721,21 +736,6 @@ void __init x86_numa_init(void)
> >         numa_init(dummy_numa_init);
> >  }
> >
> > -static void __init init_memory_less_node(int nid)
> > -{
> > -       unsigned long zones_size[MAX_NR_ZONES] = {0};
> > -       unsigned long zholes_size[MAX_NR_ZONES] = {0};
> > -
> > -       /* Allocate and initialize node data. Memory-less node is now 
> > online.*/
> > -       alloc_node_data(nid);
> > -       free_area_init_node(nid, zones_size, 0, zholes_size);
> > -
> > -       /*
> > -        * All zonelists will be built later in start_kernel() after per cpu
> > -        * areas are initialized.
> > -        */
> > -}
> > -
> >  /*
> >   * Setup early cpu_to_node.
> >   *
> > @@ -763,9 +763,6 @@ void __init init_cpu_to_node(void)
> >                 if (node == NUMA_NO_NODE)
> >                         continue;
> >
> > -               if (!node_online(node))
> > -                       init_memory_less_node(node);
> > -
> >                 numa_set_node(cpu, node);
> >         }
> >  }
> > --
> Which commit is this patch applied on? I can not apply it on latest linux 
> tree.
>
I applied it by manual, will see the test result. I think it should
work since you instance all the node.
But there are two things worth to consider:
-1st. why x86 do not bring up all nodes by default, apparently it will
be more simple by that way
-2nd. there are other archs, do they obey the rules?

Thanks,
Pingfan

Reply via email to