[PATCH V3 2/2] pseries/initnodes: Ensure nodes initialized for hotplug

[Michael Bringmann]

To: linuxppc-dev@xxxxxxxxxxxxxxxx
To: linux-kernel@xxxxxxxxxxxxxxx
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Michael Bringmann <mwb@xxxxxxxxxxxxxxxxxx>
Cc: John Allen <jallen@xxxxxxxxxxxxxxxxxx>
Cc: Nathan Fontenot <nfont@xxxxxxxxxxxxxxxxxx>
Subject: [PATCH V3 2/2] pseries/initnodes: Ensure nodes initialized for hotplug

pseries/nodes: On pseries systems which allow 'hot-add' of CPU,
it may occur that the new resources are to be inserted into nodes
that were not used for memory resources at bootup.  Many different
configurations of PowerPC resources may need to be supported depending
upon the environment.  This patch fixes some problems encountered at
runtime with configurations that support memory-less nodes, or that
hot-add resources during system execution after boot.

Signed-off-by: Michael Bringmann <mwb@xxxxxxxxxxxxxxxxxx>
---
 arch/powerpc/mm/numa.c |   35 +++++++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index f885ab7..37f697dc1 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -551,7 +551,7 @@ static int numa_setup_cpu(unsigned long lcpu)
 	nid = of_node_to_nid_single(cpu);
 
 out_present:
-	if (nid < 0 || !node_online(nid))
+	if (nid < 0 || !node_possible(nid))
 		nid = first_online_node;
 
 	map_cpu_to_node(lcpu, nid);
@@ -1311,6 +1311,35 @@ static long vphn_get_associativity(unsigned long cpu,
 	return rc;
 }
 
+static int verify_node_preparation(int nid)
+{
+	/*
+	 * Need to allocate/initialize NODE_DATA from a node with
+	 * memory (see memblock_alloc_try_nid).  Code executed after
+	 * boot (like local_memory_node) often does not know enough
+	 * to recover fully for memoryless nodes. 
+	 */
+	if (NODE_DATA(nid) == NULL) {
+		int ret;
+		printk(KERN_INFO "%s:%d node %d (%d)\n", __FUNCTION__, __LINE__, nid, first_online_node);
+		setup_node_data(nid, 0, 0);
+		printk(KERN_INFO "%s:%d node %d (%d)\n", __FUNCTION__, __LINE__, nid, first_online_node);
+		ret = try_online_node(nid);
+		printk(KERN_INFO "%s:%d node %d (%d) %d %p\n", __FUNCTION__, __LINE__, nid, first_online_node, ret, NODE_DATA(nid));
+
+		/*
+		 * Node structures successfully initialized, but
+		 * we still need the node to be offline.
+		 */
+		node_set_offline(nid);
+	}
+
+	if (NODE_DATA(nid)->node_spanned_pages == 0)
+		return first_online_node;
+
+	return nid;
+}
+
 /*
  * Update the CPU maps and sysfs entries for a single CPU when its NUMA
  * characteristics change. This function doesn't perform any locking and is
@@ -1419,9 +1448,11 @@ int numa_update_cpu_topology(bool cpus_locked)
 		/* Use associativity from first thread for all siblings */
 		vphn_get_associativity(cpu, associativity);
 		new_nid = associativity_to_nid(associativity);
-		if (new_nid < 0 || !node_online(new_nid))
+		if (new_nid < 0 || !node_possible(new_nid))
 			new_nid = first_online_node;
 
+		new_nid = verify_node_preparation(new_nid);
+
 		if (new_nid == numa_cpu_lookup_table[cpu]) {
 			cpumask_andnot(&cpu_associativity_changes_mask,
 					&cpu_associativity_changes_mask,