"Aneesh Kumar K.V" <aneesh.ku...@linux.ibm.com> writes: > I guess we should have here. > > modified arch/powerpc/mm/numa.c > @@ -416,12 +416,11 @@ static int of_get_assoc_arrays(struct assoc_arrays > *aa) > static int of_drconf_to_nid_single(struct drmem_lmb *lmb) > { > struct assoc_arrays aa = { .arrays = NULL }; > - /* is that correct? */ > int default_nid = 0; > int nid = default_nid; > int rc, index; > > - if (!numa_enabled) > + if ((min_common_depth < 0) || !numa_enabled) > return NUMA_NO_NODE; > > rc = of_get_assoc_arrays(&aa); > > > Nathan, > > Can you check this?
Looks like it would do the right thing. Just checking: do people still need numa=off? Seems like it's a maintenance burden :-)