Alexey,
this is still not finalized but it would really help if you could give
it a spin on your setup. I still have to think about how to transition
from a memoryless node to standard node (in hotplug code). Also there
might be other surprises on the way.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c5952749ad40..8ed8db2ccb13 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6382,7 +6382,11 @@ static void __build_all_zonelists(void *data)
if (self && !node_online(self->node_id)) {
build_zonelists(self);
} else {
- for_each_online_node(nid) {
+ /*
+ * All possible nodes have pgdat preallocated
+ * free_area_init
+ */
+ for_each_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
build_zonelists(pgdat);
@@ -8032,8 +8036,32 @@ void __init free_area_init(unsigned long *max_zone_pfn)
/* Initialise every node */
mminit_verify_pageflags_layout();
setup_nr_node_ids();
- for_each_online_node(nid) {
- pg_data_t *pgdat = NODE_DATA(nid);
+ for_each_node(nid) {
+ pg_data_t *pgdat;
+
+ if (!node_online(nid)) {
+ pr_warn("Node %d uninitialized by the platform. Please report with boot dmesg.\n", nid);
+
+ /* Allocator not initialized yet */
+ pgdat = memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES);
+ if (!pgdat) {
+ pr_err("Cannot allocate %zuB for node %d.\n",
+ sizeof(*pgdat), nid);
+ continue;
+ }
+ /* TODO do we need this for memoryless nodes */
+ pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);
+ arch_refresh_nodedata(nid, pgdat);
+ free_area_init_memoryless_node(nid);
+ /*
+ * not marking this node online because we do not want to
+ * confuse userspace by sysfs files/directories for node
+ * without any memory attached to it (see topology_init)
+ */
+ continue;
+ }
+
+ pgdat = NODE_DATA(nid);
free_area_init_node(nid);
/* Any memory on that node */
--
Michal Hocko
SUSE Labs
