On Thu, Oct 29, 2020 at 03:19:50PM +0900, Janghyuck Kim wrote: > To support NUMA systems whose physical address layout is not continuous > on one node, nodes spanning other nodes feature is required. > > Signed-off-by: Janghyuck Kim <janghyuck....@samsung.com> > --- > arch/arm64/Kconfig | 8 ++++++++ > 1 file changed, 8 insertions(+) > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index 49b8d017cba6..18ff7ce9dd60 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -1004,6 +1004,14 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK > config HOLES_IN_ZONE > def_bool y > > +# Some NUMA nodes have memory ranges that span > +# other nodes. Even though a pfn is valid and > +# between a node's start and end pfns, it may not > +# reside on that node. See memmap_init_zone() > +# for details. > +config NODES_SPAN_OTHER_NODES > + depends on NUMA
I guess this patch no longer makes sense after commit acd3f5c441e9 ("mm: remove early_pfn_in_nid() and CONFIG_NODES_SPAN_OTHER_NODES"). -- Catalin