Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
   linux-next for a couple of months without, to my knowledge, any
   negative reports (or any positive ones, come to that).

 - Also the Maple Tree from Liam Howlett. An overlapping range-based
   tree for vmas. It it apparently slightly more efficient in its own
   right, but is mainly targeted at enabling work to reduce mmap_lock
   contention.

   Liam has identified a number of other tree users in the kernel which
   could be beneficially onverted to mapletrees.

   Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
   at [1]. This has yet to be addressed due to Liam's unfortunately
   timed vacation. He is now back and we'll get this fixed up.

 - Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
   clang-generated instrumentation to detect used-unintialized bugs down
   to the single bit level.

   KMSAN keeps finding bugs. New ones, as well as the legacy ones.

 - Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
   memory into THPs.

 - Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
   support file/shmem-backed pages.

 - userfaultfd updates from Axel Rasmussen

 - zsmalloc cleanups from Alexey Romanov

 - cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
   memory-failure

 - Huang Ying adds enhancements to NUMA balancing memory tiering mode's
   page promotion, with a new way of detecting hot pages.

 - memcg updates from Shakeel Butt: charging optimizations and reduced
   memory consumption.

 - memcg cleanups from Kairui Song.

 - memcg fixes and cleanups from Johannes Weiner.

 - Vishal Moola provides more folio conversions

 - Zhang Yi removed ll_rw_block() :(

 - migration enhancements from Peter Xu

 - migration error-path bugfixes from Huang Ying

 - Aneesh Kumar added ability for a device driver to alter the memory
   tiering promotion paths. For optimizations by PMEM drivers, DRM
   drivers, etc.

 - vma merging improvements from Jakub Matěn.

 - NUMA hinting cleanups from David Hildenbrand.

 - xu xin added aditional userspace visibility into KSM merging
   activity.

 - THP & KSM code consolidation from Qi Zheng.

 - more folio work from Matthew Wilcox.

 - KASAN updates from Andrey Konovalov.

 - DAMON cleanups from Kaixu Xia.

 - DAMON work from SeongJae Park: fixes, cleanups.

 - hugetlb sysfs cleanups from Muchun Song.

 - Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.

Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]

* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
  hugetlb: allocate vma lock for all sharable vmas
  hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
  hugetlb: fix vma lock handling during split vma and range unmapping
  mglru: mm/vmscan.c: fix imprecise comments
  mm/mglru: don't sync disk for each aging cycle
  mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
  mm: memcontrol: use do_memsw_account() in a few more places
  mm: memcontrol: deprecate swapaccounting=0 mode
  mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
  mm/secretmem: remove reduntant return value
  mm/hugetlb: add available_huge_pages() func
  mm: remove unused inline functions from include/linux/mm_inline.h
  selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
  selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
  selftests/vm: add thp collapse shmem testing
  selftests/vm: add thp collapse file and tmpfs testing
  selftests/vm: modularize thp collapse memory operations
  selftests/vm: dedup THP helpers
  mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
  mm/madvise: add file and shmem support to MADV_COLLAPSE
  ...

drivers/base/node.c

@@ -20,6 +20,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
+#include <linux/hugetlb.h>
 
 static struct bus_type node_subsys = {
 	.name = "node",
@@ -589,64 +590,9 @@ static const struct attribute_group *node_dev_groups[] = {
 	NULL
 };
 
-#ifdef CONFIG_HUGETLBFS
-/*
- * hugetlbfs per node attributes registration interface:
- * When/if hugetlb[fs] subsystem initializes [sometime after this module],
- * it will register its per node attributes for all online nodes with
- * memory.  It will also call register_hugetlbfs_with_node(), below, to
- * register its attribute registration functions with this node driver.
- * Once these hooks have been initialized, the node driver will call into
- * the hugetlb module to [un]register attributes for hot-plugged nodes.
- */
-static node_registration_func_t __hugetlb_register_node;
-static node_registration_func_t __hugetlb_unregister_node;
-
-static inline bool hugetlb_register_node(struct node *node)
-{
-	if (__hugetlb_register_node &&
-			node_state(node->dev.id, N_MEMORY)) {
-		__hugetlb_register_node(node);
-		return true;
-	}
-	return false;
-}
-
-static inline void hugetlb_unregister_node(struct node *node)
-{
-	if (__hugetlb_unregister_node)
-		__hugetlb_unregister_node(node);
-}
-
-void register_hugetlbfs_with_node(node_registration_func_t doregister,
-				  node_registration_func_t unregister)
-{
-	__hugetlb_register_node   = doregister;
-	__hugetlb_unregister_node = unregister;
-}
-#else
-static inline void hugetlb_register_node(struct node *node) {}
-
-static inline void hugetlb_unregister_node(struct node *node) {}
-#endif
-
 static void node_device_release(struct device *dev)
 {
-	struct node *node = to_node(dev);
-
-#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS)
-	/*
-	 * We schedule the work only when a memory section is
-	 * onlined/offlined on this node. When we come here,
-	 * all the memory on this node has been offlined,
-	 * so we won't enqueue new work to this work.
-	 *
-	 * The work is using node->node_work, so we should
-	 * flush work before freeing the memory.
-	 */
-	flush_work(&node->node_work);
-#endif
-	kfree(node);
+	kfree(to_node(dev));
 }
 
 /*
@@ -665,13 +611,13 @@ static int register_node(struct node *node, int num)
 	node->dev.groups = node_dev_groups;
 	error = device_register(&node->dev);
 
-	if (error)
+	if (error) {
 		put_device(&node->dev);
-	else {
+	} else {
 		hugetlb_register_node(node);
-
 		compaction_register_node(node);
 	}
+
 	return error;
 }
 
@@ -684,8 +630,8 @@ static int register_node(struct node *node, int num)
  */
 void unregister_node(struct node *node)
 {
+	hugetlb_unregister_node(node);
 	compaction_unregister_node(node);
-	hugetlb_unregister_node(node);		/* no-op, if memoryless node */
 	node_remove_accesses(node);
 	node_remove_caches(node);
 	device_unregister(&node->dev);
@@ -907,74 +853,8 @@ void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
 			   (void *)&nid, func);
 	return;
 }
-
-#ifdef CONFIG_HUGETLBFS
-/*
- * Handle per node hstate attribute [un]registration on transistions
- * to/from memoryless state.
- */
-static void node_hugetlb_work(struct work_struct *work)
-{
-	struct node *node = container_of(work, struct node, node_work);
-
-	/*
-	 * We only get here when a node transitions to/from memoryless state.
-	 * We can detect which transition occurred by examining whether the
-	 * node has memory now.  hugetlb_register_node() already check this
-	 * so we try to register the attributes.  If that fails, then the
-	 * node has transitioned to memoryless, try to unregister the
-	 * attributes.
-	 */
-	if (!hugetlb_register_node(node))
-		hugetlb_unregister_node(node);
-}
-
-static void init_node_hugetlb_work(int nid)
-{
-	INIT_WORK(&node_devices[nid]->node_work, node_hugetlb_work);
-}
-
-static int node_memory_callback(struct notifier_block *self,
-				unsigned long action, void *arg)
-{
-	struct memory_notify *mnb = arg;
-	int nid = mnb->status_change_nid;
-
-	switch (action) {
-	case MEM_ONLINE:
-	case MEM_OFFLINE:
-		/*
-		 * offload per node hstate [un]registration to a work thread
-		 * when transitioning to/from memoryless state.
-		 */
-		if (nid != NUMA_NO_NODE)
-			schedule_work(&node_devices[nid]->node_work);
-		break;
-
-	case MEM_GOING_ONLINE:
-	case MEM_GOING_OFFLINE:
-	case MEM_CANCEL_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-#endif	/* CONFIG_HUGETLBFS */
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-#if !defined(CONFIG_MEMORY_HOTPLUG) || !defined(CONFIG_HUGETLBFS)
-static inline int node_memory_callback(struct notifier_block *self,
-				unsigned long action, void *arg)
-{
-	return NOTIFY_OK;
-}
-
-static void init_node_hugetlb_work(int nid) { }
-
-#endif
-
 int __register_one_node(int nid)
 {
 	int error;
@@ -993,8 +873,6 @@ int __register_one_node(int nid)
 	}
 
 	INIT_LIST_HEAD(&node_devices[nid]->access_list);
-	/* initialize work queue for memory hot plug */
-	init_node_hugetlb_work(nid);
 	node_init_caches(nid);
 
 	return error;
@@ -1065,13 +943,8 @@ static const struct attribute_group *cpu_root_attr_groups[] = {
 	NULL,
 };
 
-#define NODE_CALLBACK_PRI	2	/* lower than SLAB */
 void __init node_dev_init(void)
 {
-	static struct notifier_block node_memory_callback_nb = {
-		.notifier_call = node_memory_callback,
-		.priority = NODE_CALLBACK_PRI,
-	};
 	int ret, i;
 
  	BUILD_BUG_ON(ARRAY_SIZE(node_state_attr) != NR_NODE_STATES);
@@ -1081,8 +954,6 @@ void __init node_dev_init(void)
 	if (ret)
 		panic("%s() failed to register subsystem: %d\n", __func__, ret);
 
-	register_hotmemory_notifier(&node_memory_callback_nb);
-
 	/*
 	 * Create all node devices, which will properly link the node
 	 * to applicable memory block devices and already created cpu devices.