[PATCH] mm/mm_init: handle alloc_percpu failure in free_area_init_core_hotplug

[Gregory Price]

We miss a failed allocation check for pgdat->per_cpu_nodestats, which
results in a NULL deref when we offset into the per-cpu area.

Propagate -ENOMEM up the stack and leave per_cpu_nodestats pointing
at boot_nodestats so a later online can retry the allocation.

hotadd_init_pgdat() returns NULL on failure, which __try_online_node()
already maps to -ENOMEM.

Assisted-by: Sashiko:unknown-model
Fixes: 75ef71840539 ("mm, vmstat: add infrastructure for per-node vmstats")
Signed-off-by: Gregory Price <gourry@xxxxxxxxxx>
---
 include/linux/memory_hotplug.h |  2 +-
 mm/memory_hotplug.c            |  3 ++-
 mm/mm_init.c                   | 14 +++++++++++---
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 7c9d66729c60..f04b915678db 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -289,7 +289,7 @@ static inline void __remove_memory(u64 start, u64 size) {}
 /* Default online_type (MMOP_*) when new memory blocks are added. */
 extern enum mmop mhp_get_default_online_type(void);
 extern void mhp_set_default_online_type(enum mmop online_type);
-extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat);
+extern int __ref free_area_init_core_hotplug(struct pglist_data *pgdat);
 extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
 extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
 extern int add_memory_resource(int nid, struct resource *resource,
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 7ac19fab2263..8b137328dcf0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1263,7 +1263,8 @@ static pg_data_t *hotadd_init_pgdat(int nid)
 	pgdat = NODE_DATA(nid);
 
 	/* init node's zones as empty zones, we don't have any present pages.*/
-	free_area_init_core_hotplug(pgdat);
+	if (free_area_init_core_hotplug(pgdat))
+		return NULL;
 
 	/*
 	 * The node we allocated has no zone fallback lists. For avoiding
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 306ea5c13f54..37fd64ce144d 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1536,7 +1536,7 @@ void __init set_pageblock_order(void)
  * NOTE: this function is only called during memory hotplug
  */
 #ifdef CONFIG_MEMORY_HOTPLUG
-void __ref free_area_init_core_hotplug(struct pglist_data *pgdat)
+int __ref free_area_init_core_hotplug(struct pglist_data *pgdat)
 {
 	int nid = pgdat->node_id;
 	enum zone_type z;
@@ -1544,8 +1544,14 @@ void __ref free_area_init_core_hotplug(struct pglist_data *pgdat)
 
 	pgdat_init_internals(pgdat);
 
-	if (pgdat->per_cpu_nodestats == &boot_nodestats)
-		pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);
+	if (pgdat->per_cpu_nodestats == &boot_nodestats) {
+		struct per_cpu_nodestat __percpu *p;
+
+		p = alloc_percpu(struct per_cpu_nodestat);
+		if (!p)
+			return -ENOMEM;
+		pgdat->per_cpu_nodestats = p;
+	}
 
 	/*
 	 * Reset the nr_zones, order and highest_zoneidx before reuse.
@@ -1583,6 +1589,8 @@ void __ref free_area_init_core_hotplug(struct pglist_data *pgdat)
 		zone->present_pages = 0;
 		zone_init_internals(zone, z, nid, 0);
 	}
+
+	return 0;
 }
 #endif
 
-- 
2.53.0-Meta