mm/memory_hotplug: activate node before adding new memory blocks

The sysfs attributes for memory blocks require the node ID to be set and
initialized, so move the node activation before adding new memory blocks.
This also has the nice side effect that the BUG_ON() can be converted into
a WARN_ON() as we now can handle registration errors.

Link: https://lkml.kernel.org/r/20250729064637.51662-3-hare@kernel.org
Fixes: b9ff036082cd ("mm/memory_hotplug.c: make add_memory_resource use __try_online_node")
Signed-off-by: Hannes Reinecke <hare@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Donet Tom <donettom@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 894d3891292bf648cd6eba437f21dc28a264a9cf..fb212a889e6534305e15f5d08f1919e1bb32b150 100644 (file)
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -879,7 +879,7 @@ static void remove_memory_block(struct memory_block *memory)
  * Called under device_hotplug_lock.
  */
 int create_memory_block_devices(unsigned long start, unsigned long size,
-                               struct vmem_altmap *altmap,
+                               int nid, struct vmem_altmap *altmap,
                                struct memory_group *group)
 {
        const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
@@ -893,7 +893,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size,
                return -EINVAL;
 
        for (block_id = start_block_id; block_id != end_block_id; block_id++) {
-               ret = add_memory_block(block_id, NUMA_NO_NODE, MEM_OFFLINE, altmap, group);
+               ret = add_memory_block(block_id, nid, MEM_OFFLINE, altmap, group);
                if (ret)
                        break;
        }

diff --git a/include/linux/memory.h b/include/linux/memory.h
index 40eb70ccb09d5ebd0033b68e923cce75cd708dd8..4a29153e372effa23df7771ad5a3ece136414779 100644 (file)
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -159,7 +159,7 @@ static inline unsigned long memory_block_advised_max_size(void)
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size,
-                               struct vmem_altmap *altmap,
+                               int nid, struct vmem_altmap *altmap,
                                struct memory_group *group);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e9f14de4a9c9e8aea36a35755e92180e159625df..0be83039c3b5e0ad36aea86075339b332803ae4f 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1477,7 +1477,7 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
                }
 
                /* create memory block devices after memory was added */
-               ret = create_memory_block_devices(cur_start, memblock_size,
+               ret = create_memory_block_devices(cur_start, memblock_size, nid,
                                                  params.altmap, group);
                if (ret) {
                        arch_remove_memory(cur_start, memblock_size, NULL);
@@ -1539,8 +1539,16 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 
        ret = __try_online_node(nid, false);
        if (ret < 0)
-               goto error;
-       new_node = ret;
+               goto error_memblock_remove;
+       if (ret) {
+               node_set_online(nid);
+               ret = register_one_node(nid);
+               if (WARN_ON(ret)) {
+                       node_set_offline(nid);
+                       goto error_memblock_remove;
+               }
+               new_node = true;
+       }
 
        /*
         * Self hosted memmap array
@@ -1556,24 +1564,13 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
                        goto error;
 
                /* create memory block devices after memory was added */
-               ret = create_memory_block_devices(start, size, NULL, group);
+               ret = create_memory_block_devices(start, size, nid, NULL, group);
                if (ret) {
                        arch_remove_memory(start, size, params.altmap);
                        goto error;
                }
        }
 
-       if (new_node) {
-               /* If sysfs file of new node can't be created, cpu on the node
-                * can't be hot-added. There is no rollback way now.
-                * So, check by BUG_ON() to catch it reluctantly..
-                * We online node here. We can't roll back from here.
-                */
-               node_set_online(nid);
-               ret = register_one_node(nid);
-               BUG_ON(ret);
-       }
-
        register_memory_blocks_under_node_hotplug(nid, PFN_DOWN(start),
                                          PFN_UP(start + size - 1));
 
@@ -1597,6 +1594,11 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 
        return ret;
 error:
+       if (new_node) {
+               node_set_offline(nid);
+               unregister_one_node(nid);
+       }
+error_memblock_remove:
        if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
                memblock_remove(start, size);
 error_mem_hotplug_end: