Merge tag 'mm-stable-2025-10-03-16-49' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more MM updates from Andrew Morton:
"Only two patch series in this pull request:

   - "mm/memory_hotplug: fixup crash during uevent handling" from Hannes
     Reinecke fixes a race that was causing udev to trigger a crash in
     the memory hotplug code

   - "mm_slot: following fixup for usage of mm_slot_entry()" from Wei
     Yang adds some touchups to the just-merged mm_slot changes"

* tag 'mm-stable-2025-10-03-16-49' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm/khugepaged: use KMEM_CACHE()
  mm/ksm: cleanup mm_slot_entry() invocation
  Documentation/mm: drop pxx_mkdevmap() descriptions from page table helpers
  mm: clean up is_guard_pte_marker()
  drivers/base: move memory_block_add_nid() into the caller
  mm/memory_hotplug: activate node before adding new memory blocks
  drivers/base/memory: add node id parameter to add_memory_block()

Author: torvalds

Documentation/mm/arch_pgtable_helpers.rst

@@ -52,8 +52,6 @@ PTE Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pte_mkspecial             | Creates a special PTE                            |
 +---------------------------+--------------------------------------------------+
-| pte_mkdevmap              | Creates a ZONE_DEVICE mapped PTE                 |
-+---------------------------+--------------------------------------------------+
 | pte_mksoft_dirty          | Creates a soft dirty PTE                         |
 +---------------------------+--------------------------------------------------+
 | pte_clear_soft_dirty      | Clears a soft dirty PTE                          |
@@ -124,8 +122,6 @@ PMD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pmd_mkspecial             | Creates a special PMD                            |
 +---------------------------+--------------------------------------------------+
-| pmd_mkdevmap              | Creates a ZONE_DEVICE mapped PMD                 |
-+---------------------------+--------------------------------------------------+
 | pmd_mksoft_dirty          | Creates a soft dirty PMD                         |
 +---------------------------+--------------------------------------------------+
 | pmd_clear_soft_dirty      | Clears a soft dirty PMD                          |
@@ -185,8 +181,6 @@ PUD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pud_wrprotect             | Creates a write protected PUD                    |
 +---------------------------+--------------------------------------------------+
-| pud_mkdevmap              | Creates a ZONE_DEVICE mapped PUD                 |
-+---------------------------+--------------------------------------------------+
 | pud_mkinvalid             | Invalidates a present PUD; do not call for       |
 |                           | non-present PUD [1]                              |
 +---------------------------+--------------------------------------------------+

drivers/base/memory.c

@@ -769,21 +769,22 @@ static struct zone *early_node_zone_for_memory_block(struct memory_block *mem,
 
 #ifdef CONFIG_NUMA
 /**
- * memory_block_add_nid() - Indicate that system RAM falling into this memory
- *			    block device (partially) belongs to the given node.
+ * memory_block_add_nid_early() - Indicate that early system RAM falling into
+ *				  this memory block device (partially) belongs
+ *				  to the given node.
  * @mem: The memory block device.
  * @nid: The node id.
- * @context: The memory initialization context.
  *
- * Indicate that system RAM falling into this memory block (partially) belongs
- * to the given node. If the context indicates ("early") that we are adding the
- * node during node device subsystem initialization, this will also properly
- * set/adjust mem->zone based on the zone ranges of the given node.
+ * Indicate that early system RAM falling into this memory block (partially)
+ * belongs to the given node. This will also properly set/adjust mem->zone based
+ * on the zone ranges of the given node.
+ *
+ * Memory hotplug handles this on memory block creation, where we can only have
+ * a single nid span a memory block.
  */
-void memory_block_add_nid(struct memory_block *mem, int nid,
-			  enum meminit_context context)
+void memory_block_add_nid_early(struct memory_block *mem, int nid)
 {
-	if (context == MEMINIT_EARLY && mem->nid != nid) {
+	if (mem->nid != nid) {
 		/*
 		 * For early memory we have to determine the zone when setting
 		 * the node id and handle multiple nodes spanning a single
@@ -797,19 +798,18 @@ void memory_block_add_nid(struct memory_block *mem, int nid,
 			mem->zone = early_node_zone_for_memory_block(mem, nid);
 		else
 			mem->zone = NULL;
+		/*
+		 * If this memory block spans multiple nodes, we only indicate
+		 * the last processed node. If we span multiple nodes (not applicable
+		 * to hotplugged memory), zone == NULL will prohibit memory offlining
+		 * and consequently unplug.
+		 */
+		mem->nid = nid;
 	}
-
-	/*
-	 * If this memory block spans multiple nodes, we only indicate
-	 * the last processed node. If we span multiple nodes (not applicable
-	 * to hotplugged memory), zone == NULL will prohibit memory offlining
-	 * and consequently unplug.
-	 */
-	mem->nid = nid;
 }
 #endif
 
-static int add_memory_block(unsigned long block_id, unsigned long state,
+static int add_memory_block(unsigned long block_id, int nid, unsigned long state,
 			    struct vmem_altmap *altmap,
 			    struct memory_group *group)
 {
@@ -827,7 +827,7 @@ static int add_memory_block(unsigned long block_id, unsigned long state,
 
 	mem->start_section_nr = block_id * sections_per_block;
 	mem->state = state;
-	mem->nid = NUMA_NO_NODE;
+	mem->nid = nid;
 	mem->altmap = altmap;
 	INIT_LIST_HEAD(&mem->group_next);
 
@@ -854,13 +854,6 @@ static int add_memory_block(unsigned long block_id, unsigned long state,
 	return 0;
 }
 
-static int add_hotplug_memory_block(unsigned long block_id,
-				    struct vmem_altmap *altmap,
-				    struct memory_group *group)
-{
-	return add_memory_block(block_id, MEM_OFFLINE, altmap, group);
-}
-
 static void remove_memory_block(struct memory_block *memory)
 {
 	if (WARN_ON_ONCE(memory->dev.bus != &memory_subsys))
@@ -886,7 +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));
@@ -900,7 +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_hotplug_memory_block(block_id, altmap, group);
+		ret = add_memory_block(block_id, nid, MEM_OFFLINE, altmap, group);
 		if (ret)
 			break;
 	}
@@ -1005,7 +998,7 @@ void __init memory_dev_init(void)
 			continue;
 
 		block_id = memory_block_id(nr);
-		ret = add_memory_block(block_id, MEM_ONLINE, NULL, NULL);
+		ret = add_memory_block(block_id, NUMA_NO_NODE, MEM_ONLINE, NULL, NULL);
 		if (ret) {
 			panic("%s() failed to add memory block: %d\n",
 			      __func__, ret);

drivers/base/node.c

@@ -819,13 +819,10 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 static void do_register_memory_block_under_node(int nid,
-						struct memory_block *mem_blk,
-						enum meminit_context context)
+						struct memory_block *mem_blk)
 {
 	int ret;
 
-	memory_block_add_nid(mem_blk, nid, context);
-
 	ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 				       &mem_blk->dev.kobj,
 				       kobject_name(&mem_blk->dev.kobj));
@@ -853,7 +850,7 @@ static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
 {
 	int nid = *(int *)arg;
 
-	do_register_memory_block_under_node(nid, mem_blk, MEMINIT_HOTPLUG);
+	do_register_memory_block_under_node(nid, mem_blk);
 	return 0;
 }
 
@@ -893,7 +890,8 @@ static void register_memory_blocks_under_nodes(void)
 			if (!mem)
 				continue;
 
-			do_register_memory_block_under_node(nid, mem, MEMINIT_EARLY);
+			memory_block_add_nid_early(mem, nid);
+			do_register_memory_block_under_node(nid, mem);
 			put_device(&mem->dev);
 		}
 

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);
@@ -202,8 +202,7 @@ static inline unsigned long phys_to_block_id(unsigned long phys)
 }
 
 #ifdef CONFIG_NUMA
-void memory_block_add_nid(struct memory_block *mem, int nid,
-			  enum meminit_context context);
+void memory_block_add_nid_early(struct memory_block *mem, int nid);
 #endif /* CONFIG_NUMA */
 int memory_block_advise_max_size(unsigned long size);
 unsigned long memory_block_advised_max_size(void);

mm/khugepaged.c

@@ -376,10 +376,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
 
 int __init khugepaged_init(void)
 {
-	mm_slot_cache = kmem_cache_create("khugepaged_mm_slot",
-					  sizeof(struct mm_slot),
-					  __alignof__(struct mm_slot),
-					  0, NULL);
+	mm_slot_cache = KMEM_CACHE(mm_slot, 0);
 	if (!mm_slot_cache)
 		return -ENOMEM;
 

mm/ksm.c

@@ -2921,7 +2921,7 @@ int __ksm_enter(struct mm_struct *mm)
 
 void __ksm_exit(struct mm_struct *mm)
 {
-	struct ksm_mm_slot *mm_slot;
+	struct ksm_mm_slot *mm_slot = NULL;
 	struct mm_slot *slot;
 	int easy_to_free = 0;
 
@@ -2936,19 +2936,20 @@ void __ksm_exit(struct mm_struct *mm)
 
 	spin_lock(&ksm_mmlist_lock);
 	slot = mm_slot_lookup(mm_slots_hash, mm);
-	if (slot) {
-		mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot);
-		if (ksm_scan.mm_slot != mm_slot) {
-			if (!mm_slot->rmap_list) {
-				hash_del(&slot->hash);
-				list_del(&slot->mm_node);
-				easy_to_free = 1;
-			} else {
-				list_move(&slot->mm_node,
-					  &ksm_scan.mm_slot->slot.mm_node);
-			}
-		}
+	if (!slot)
+		goto unlock;
+	mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot);
+	if (ksm_scan.mm_slot == mm_slot)
+		goto unlock;
+	if (!mm_slot->rmap_list) {
+		hash_del(&slot->hash);
+		list_del(&slot->mm_node);
+		easy_to_free = 1;
+	} else {
+		list_move(&slot->mm_node,
+			  &ksm_scan.mm_slot->slot.mm_node);
 	}
+unlock:
 	spin_unlock(&ksm_mmlist_lock);
 
 	if (easy_to_free) {

mm/madvise.c

@@ -1071,8 +1071,8 @@ static bool is_valid_guard_vma(struct vm_area_struct *vma, bool allow_locked)
 
 static bool is_guard_pte_marker(pte_t ptent)
 {
-	return is_pte_marker(ptent) &&
-		is_guard_swp_entry(pte_to_swp_entry(ptent));
+	return is_swap_pte(ptent) &&
+	       is_guard_swp_entry(pte_to_swp_entry(ptent));
 }
 
 static int guard_install_pud_entry(pud_t *pud, unsigned long addr,

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: