powerpc/numa: Associate numa node to its cpu earlier

powerpc is the only platform that do not rely on
cpu_up()->try_online_node() to bring up a numa node,
and special cases it, instead, deep in its own machinery:

dlpar_online_cpu
 find_and_online_cpu_nid
  try_online_node

This should not be needed, but the thing is that the try_online_node()
from cpu_up() will not apply on the right node, because cpu_to_node()
will return the old mapping numa<->cpu that gets set on boot stage
for all possible cpus.

That can be seen easily if we try to print out the numa node passed
to try_online_node() in cpu_up().

The thing is that the numa<->cpu mapping does not get updated till a much
later stage in start_secondary:

start_secondary:
 set_numa_node(numa_cpu_lookup_table[cpu])

But we do not really care, as we already now the
CPU <-> NUMA associativity back in find_and_online_cpu_nid(),
so let us make use of that and set the proper numa<->cpu mapping,
so cpu_to_node() in cpu_up() returns the right node and
try_online_node() can do its work.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Tested-by: Geetika Moolchandani <Geetika.Moolchandani1@ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220411074934.4632-1-osalvador@suse.de

3 files changed, 11 insertions, 31 deletions

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 36fcafb1fd6d..8a4d4f4d9749 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -111,14 +111,10 @@ static inline void unmap_cpu_from_node(unsigned long cpu) {}
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
-extern int find_and_online_cpu_nid(int cpu);
+void find_and_update_cpu_nid(int cpu);
 extern int cpu_to_coregroup_id(int cpu);
 #else
-static inline int find_and_online_cpu_nid(int cpu)
-{
-	return 0;
-}
-
+static inline void find_and_update_cpu_nid(int cpu) {}
 static inline int cpu_to_coregroup_id(int cpu)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 4680e310e68a..0801b2ce9b7d 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1422,42 +1422,26 @@ out:
 	return rc;
 }
 
-int find_and_online_cpu_nid(int cpu)
+void find_and_update_cpu_nid(int cpu)
 {
 	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	int new_nid;
 
 	/* Use associativity from first thread for all siblings */
 	if (vphn_get_associativity(cpu, associativity))
-		return cpu_to_node(cpu);
+		return;
 
+	/* Do not have previous associativity, so find it now. */
 	new_nid = associativity_to_nid(associativity);
-	if (new_nid < 0 || !node_possible(new_nid))
-		new_nid = first_online_node;
 
-	if (!node_online(new_nid)) {
-#ifdef CONFIG_MEMORY_HOTPLUG
-		/*
-		 * Need to ensure that NODE_DATA is initialized for a node from
-		 * available memory (see memblock_alloc_try_nid). If unable to
-		 * init the node, then default to nearest node that has memory
-		 * installed. Skip onlining a node if the subsystems are not
-		 * yet initialized.
-		 */
-		if (!topology_inited || try_online_node(new_nid))
-			new_nid = first_online_node;
-#else
-		/*
-		 * Default to using the nearest node that has memory installed.
-		 * Otherwise, it would be necessary to patch the kernel MM code
-		 * to deal with more memoryless-node error conditions.
-		 */
+	if (new_nid < 0 || !node_possible(new_nid))
 		new_nid = first_online_node;
-#endif
-	}
+	else
+		// Associate node <-> cpu, so cpu_up() calls
+		// try_online_node() on the right node.
+		set_cpu_numa_node(cpu, new_nid);
 
 	pr_debug("%s:%d cpu %d nid %d\n", __func__, __LINE__, cpu, new_nid);
-	return new_nid;
 }
 
 int cpu_to_coregroup_id(int cpu)
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index b81fc846d99c..0f8cd8b06432 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -398,7 +398,7 @@ static int dlpar_online_cpu(struct device_node *dn)
 			if (get_hard_smp_processor_id(cpu) != thread)
 				continue;
 			cpu_maps_update_done();
-			find_and_online_cpu_nid(cpu);
+			find_and_update_cpu_nid(cpu);
 			rc = device_online(get_cpu_device(cpu));
 			if (rc) {
 				dlpar_offline_cpu(dn);