Merge tag 'mm-stable-2025-05-31-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - "Add folio_mk_pte()" from Matthew Wilcox simplifies the act of
   creating a pte which addresses the first page in a folio and reduces
   the amount of plumbing which architecture must implement to provide
   this.

 - "Misc folio patches for 6.16" from Matthew Wilcox is a shower of
   largely unrelated folio infrastructure changes which clean things up
   and better prepare us for future work.

 - "memory,x86,acpi: hotplug memory alignment advisement" from Gregory
   Price adds early-init code to prevent x86 from leaving physical
   memory unused when physical address regions are not aligned to memory
   block size.

 - "mm/compaction: allow more aggressive proactive compaction" from
   Michal Clapinski provides some tuning of the (sadly, hard-coded (more
   sadly, not auto-tuned)) thresholds for our invokation of proactive
   compaction. In a simple test case, the reduction of a guest VM's
   memory consumption was dramatic.

 - "Minor cleanups and improvements to swap freeing code" from Kemeng
   Shi provides some code cleaups and a small efficiency improvement to
   this part of our swap handling code.

 - "ptrace: introduce PTRACE_SET_SYSCALL_INFO API" from Dmitry Levin
   adds the ability for a ptracer to modify syscalls arguments. At this
   time we can alter only "system call information that are used by
   strace system call tampering, namely, syscall number, syscall
   arguments, and syscall return value.

   This series should have been incorporated into mm.git's "non-MM"
   branch, but I goofed.

 - "fs/proc: extend the PAGEMAP_SCAN ioctl to report guard regions" from
   Andrei Vagin extends the info returned by the PAGEMAP_SCAN ioctl
   against /proc/pid/pagemap. This permits CRIU to more efficiently get
   at the info about guard regions.

 - "Fix parameter passed to page_mapcount_is_type()" from Gavin Shan
   implements that fix. No runtime effect is expected because
   validate_page_before_insert() happens to fix up this error.

 - "kernel/events/uprobes: uprobe_write_opcode() rewrite" from David
   Hildenbrand basically brings uprobe text poking into the current
   decade. Remove a bunch of hand-rolled implementation in favor of
   using more current facilities.

 - "mm/ptdump: Drop assumption that pxd_val() is u64" from Anshuman
   Khandual provides enhancements and generalizations to the pte dumping
   code. This might be needed when 128-bit Page Table Descriptors are
   enabled for ARM.

 - "Always call constructor for kernel page tables" from Kevin Brodsky
   ensures that the ctor/dtor is always called for kernel pgtables, as
   it already is for user pgtables.

   This permits the addition of more functionality such as "insert hooks
   to protect page tables". This change does result in various
   architectures performing unnecesary work, but this is fixed up where
   it is anticipated to occur.

 - "Rust support for mm_struct, vm_area_struct, and mmap" from Alice
   Ryhl adds plumbing to permit Rust access to core MM structures.

 - "fix incorrectly disallowed anonymous VMA merges" from Lorenzo
   Stoakes takes advantage of some VMA merging opportunities which we've
   been missing for 15 years.

 - "mm/madvise: batch tlb flushes for MADV_DONTNEED and MADV_FREE" from
   SeongJae Park optimizes process_madvise()'s TLB flushing.

   Instead of flushing each address range in the provided iovec, we
   batch the flushing across all the iovec entries. The syscall's cost
   was approximately halved with a microbenchmark which was designed to
   load this particular operation.

 - "Track node vacancy to reduce worst case allocation counts" from
   Sidhartha Kumar makes the maple tree smarter about its node
   preallocation.

   stress-ng mmap performance increased by single-digit percentages and
   the amount of unnecessarily preallocated memory was dramaticelly
   reduced.

 - "mm/gup: Minor fix, cleanup and improvements" from Baoquan He removes
   a few unnecessary things which Baoquan noted when reading the code.

 - ""Enhance sysfs handling for memory hotplug in weighted interleave"
   from Rakie Kim "enhances the weighted interleave policy in the memory
   management subsystem by improving sysfs handling, fixing memory
   leaks, and introducing dynamic sysfs updates for memory hotplug
   support". Fixes things on error paths which we are unlikely to hit.

 - "mm/damon: auto-tune DAMOS for NUMA setups including tiered memory"
   from SeongJae Park introduces new DAMOS quota goal metrics which
   eliminate the manual tuning which is required when utilizing DAMON
   for memory tiering.

 - "mm/vmalloc.c: code cleanup and improvements" from Baoquan He
   provides cleanups and small efficiency improvements which Baoquan
   found via code inspection.

 - "vmscan: enforce mems_effective during demotion" from Gregory Price
   changes reclaim to respect cpuset.mems_effective during demotion when
   possible. because presently, reclaim explicitly ignores
   cpuset.mems_effective when demoting, which may cause the cpuset
   settings to violated.

   This is useful for isolating workloads on a multi-tenant system from
   certain classes of memory more consistently.

 - "Clean up split_huge_pmd_locked() and remove unnecessary folio
   pointers" from Gavin Guo provides minor cleanups and efficiency gains
   in in the huge page splitting and migrating code.

 - "Use kmem_cache for memcg alloc" from Huan Yang creates a slab cache
   for `struct mem_cgroup', yielding improved memory utilization.

 - "add max arg to swappiness in memory.reclaim and lru_gen" from
   Zhongkun He adds a new "max" argument to the "swappiness=" argument
   for memory.reclaim MGLRU's lru_gen.

   This directs proactive reclaim to reclaim from only anon folios
   rather than file-backed folios.

 - "kexec: introduce Kexec HandOver (KHO)" from Mike Rapoport is the
   first step on the path to permitting the kernel to maintain existing
   VMs while replacing the host kernel via file-based kexec. At this
   time only memblock's reserve_mem is preserved.

 - "mm: Introduce for_each_valid_pfn()" from David Woodhouse provides
   and uses a smarter way of looping over a pfn range. By skipping
   ranges of invalid pfns.

 - "sched/numa: Skip VMA scanning on memory pinned to one NUMA node via
   cpuset.mems" from Libo Chen removes a lot of pointless VMA scanning
   when a task is pinned a single NUMA mode.

   Dramatic performance benefits were seen in some real world cases.

 - "JFS: Implement migrate_folio for jfs_metapage_aops" from Shivank
   Garg addresses a warning which occurs during memory compaction when
   using JFS.

 - "move all VMA allocation, freeing and duplication logic to mm" from
   Lorenzo Stoakes moves some VMA code from kernel/fork.c into the more
   appropriate mm/vma.c.

 - "mm, swap: clean up swap cache mapping helper" from Kairui Song
   provides code consolidation and cleanups related to the folio_index()
   function.

 - "mm/gup: Cleanup memfd_pin_folios()" from Vishal Moola does that.

 - "memcg: Fix test_memcg_min/low test failures" from Waiman Long
   addresses some bogus failures which are being reported by the
   test_memcontrol selftest.

 - "eliminate mmap() retry merge, add .mmap_prepare hook" from Lorenzo
   Stoakes commences the deprecation of file_operations.mmap() in favor
   of the new file_operations.mmap_prepare().

   The latter is more restrictive and prevents drivers from messing with
   things in ways which, amongst other problems, may defeat VMA merging.

 - "memcg: decouple memcg and objcg stocks"" from Shakeel Butt decouples
   the per-cpu memcg charge cache from the objcg's one.

   This is a step along the way to making memcg and objcg charging
   NMI-safe, which is a BPF requirement.

 - "mm/damon: minor fixups and improvements for code, tests, and
   documents" from SeongJae Park is yet another batch of miscellaneous
   DAMON changes. Fix and improve minor problems in code, tests and
   documents.

 - "memcg: make memcg stats irq safe" from Shakeel Butt converts memcg
   stats to be irq safe. Another step along the way to making memcg
   charging and stats updates NMI-safe, a BPF requirement.

 - "Let unmap_hugepage_range() and several related functions take folio
   instead of page" from Fan Ni provides folio conversions in the
   hugetlb code.

* tag 'mm-stable-2025-05-31-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (285 commits)
  mm: pcp: increase pcp->free_count threshold to trigger free_high
  mm/hugetlb: convert use of struct page to folio in __unmap_hugepage_range()
  mm/hugetlb: refactor __unmap_hugepage_range() to take folio instead of page
  mm/hugetlb: refactor unmap_hugepage_range() to take folio instead of page
  mm/hugetlb: pass folio instead of page to unmap_ref_private()
  memcg: objcg stock trylock without irq disabling
  memcg: no stock lock for cpu hot-unplug
  memcg: make __mod_memcg_lruvec_state re-entrant safe against irqs
  memcg: make count_memcg_events re-entrant safe against irqs
  memcg: make mod_memcg_state re-entrant safe against irqs
  memcg: move preempt disable to callers of memcg_rstat_updated
  memcg: memcg_rstat_updated re-entrant safe against irqs
  mm: khugepaged: decouple SHMEM and file folios' collapse
  selftests/eventfd: correct test name and improve messages
  alloc_tag: check mem_profiling_support in alloc_tag_init
  Docs/damon: update titles and brief introductions to explain DAMOS
  selftests/damon/_damon_sysfs: read tried regions directories in order
  mm/damon/tests/core-kunit: add a test for damos_set_filters_default_reject()
  mm/damon/paddr: remove unused variable, folio_list, in damon_pa_stat()
  mm/damon/sysfs-schemes: fix wrong comment on damons_sysfs_quota_goal_metric_strs
  ...

1 files changed, 107 insertions, 101 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 340edee108c0..ab986dd09b6a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -932,6 +932,11 @@ static struct vmap_node *vmap_nodes = &single;
 static __read_mostly unsigned int nr_vmap_nodes = 1;
 static __read_mostly unsigned int vmap_zone_size = 1;
 
+/* A simple iterator over all vmap-nodes. */
+#define for_each_vmap_node(vn)	\
+	for ((vn) = &vmap_nodes[0];	\
+		(vn) < &vmap_nodes[nr_vmap_nodes]; (vn)++)
+
 static inline unsigned int
 addr_to_node_id(unsigned long addr)
 {
@@ -950,6 +955,19 @@ id_to_node(unsigned int id)
 	return &vmap_nodes[id % nr_vmap_nodes];
 }
 
+static inline unsigned int
+node_to_id(struct vmap_node *node)
+{
+	/* Pointer arithmetic. */
+	unsigned int id = node - vmap_nodes;
+
+	if (likely(id < nr_vmap_nodes))
+		return id;
+
+	WARN_ONCE(1, "An address 0x%p is out-of-bounds.\n", node);
+	return 0;
+}
+
 /*
  * We use the value 0 to represent "no node", that is why
  * an encoded value will be the node-id incremented by 1.
@@ -1022,7 +1040,8 @@ static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
 static void drain_vmap_area_work(struct work_struct *work);
 static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work);
 
-static atomic_long_t nr_vmalloc_pages;
+static __cacheline_aligned_in_smp atomic_long_t nr_vmalloc_pages;
+static __cacheline_aligned_in_smp atomic_long_t vmap_lazy_nr;
 
 unsigned long vmalloc_nr_pages(void)
 {
@@ -1088,12 +1107,11 @@ find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va)
 {
 	unsigned long va_start_lowest;
 	struct vmap_node *vn;
-	int i;
 
 repeat:
-	for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) {
-		vn = &vmap_nodes[i];
+	va_start_lowest = 0;
 
+	for_each_vmap_node(vn) {
 		spin_lock(&vn->busy.lock);
 		*va = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
 
@@ -1730,7 +1748,7 @@ va_clip(struct rb_root *root, struct list_head *head,
 			 */
 			lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
 			if (!lva)
-				return -1;
+				return -ENOMEM;
 		}
 
 		/*
@@ -1744,7 +1762,7 @@ va_clip(struct rb_root *root, struct list_head *head,
 		 */
 		va->va_start = nva_start_addr + size;
 	} else {
-		return -1;
+		return -EINVAL;
 	}
 
 	if (type != FL_FIT_TYPE) {
@@ -1773,19 +1791,19 @@ va_alloc(struct vmap_area *va,
 
 	/* Check the "vend" restriction. */
 	if (nva_start_addr + size > vend)
-		return vend;
+		return -ERANGE;
 
 	/* Update the free vmap_area. */
 	ret = va_clip(root, head, va, nva_start_addr, size);
 	if (WARN_ON_ONCE(ret))
-		return vend;
+		return ret;
 
 	return nva_start_addr;
 }
 
 /*
  * Returns a start address of the newly allocated area, if success.
- * Otherwise a vend is returned that indicates failure.
+ * Otherwise an error value is returned that indicates failure.
  */
 static __always_inline unsigned long
 __alloc_vmap_area(struct rb_root *root, struct list_head *head,
@@ -1810,14 +1828,13 @@ __alloc_vmap_area(struct rb_root *root, struct list_head *head,
 
 	va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size);
 	if (unlikely(!va))
-		return vend;
+		return -ENOENT;
 
 	nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend);
-	if (nva_start_addr == vend)
-		return vend;
 
 #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
-	find_vmap_lowest_match_check(root, head, size, align);
+	if (!IS_ERR_VALUE(nva_start_addr))
+		find_vmap_lowest_match_check(root, head, size, align);
 #endif
 
 	return nva_start_addr;
@@ -1947,7 +1964,7 @@ node_alloc(unsigned long size, unsigned long align,
 	struct vmap_area *va;
 
 	*vn_id = 0;
-	*addr = vend;
+	*addr = -EINVAL;
 
 	/*
 	 * Fallback to a global heap if not vmalloc or there
@@ -2027,20 +2044,20 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	}
 
 retry:
-	if (addr == vend) {
+	if (IS_ERR_VALUE(addr)) {
 		preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node);
 		addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list,
 			size, align, vstart, vend);
 		spin_unlock(&free_vmap_area_lock);
 	}
 
-	trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend);
+	trace_alloc_vmap_area(addr, size, align, vstart, vend, IS_ERR_VALUE(addr));
 
 	/*
-	 * If an allocation fails, the "vend" address is
+	 * If an allocation fails, the error value is
 	 * returned. Therefore trigger the overflow path.
 	 */
-	if (unlikely(addr == vend))
+	if (IS_ERR_VALUE(addr))
 		goto overflow;
 
 	va->va_start = addr;
@@ -2132,8 +2149,6 @@ static unsigned long lazy_max_pages(void)
 	return log * (32UL * 1024 * 1024 / PAGE_SIZE);
 }
 
-static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0);
-
 /*
  * Serialize vmap purging.  There is no actual critical section protected
  * by this lock, but we want to avoid concurrent calls for performance
@@ -2143,7 +2158,6 @@ static DEFINE_MUTEX(vmap_purge_lock);
 
 /* for per-CPU blocks */
 static void purge_fragmented_blocks_allcpus(void);
-static cpumask_t purge_nodes;
 
 static void
 reclaim_list_global(struct list_head *head)
@@ -2166,7 +2180,7 @@ decay_va_pool_node(struct vmap_node *vn, bool full_decay)
 	LIST_HEAD(decay_list);
 	struct rb_root decay_root = RB_ROOT;
 	struct vmap_area *va, *nva;
-	unsigned long n_decay;
+	unsigned long n_decay, pool_len;
 	int i;
 
 	for (i = 0; i < MAX_VA_SIZE_PAGES; i++) {
@@ -2180,22 +2194,20 @@ decay_va_pool_node(struct vmap_node *vn, bool full_decay)
 		list_replace_init(&vn->pool[i].head, &tmp_list);
 		spin_unlock(&vn->pool_lock);
 
-		if (full_decay)
-			WRITE_ONCE(vn->pool[i].len, 0);
+		pool_len = n_decay = vn->pool[i].len;
+		WRITE_ONCE(vn->pool[i].len, 0);
 
 		/* Decay a pool by ~25% out of left objects. */
-		n_decay = vn->pool[i].len >> 2;
+		if (!full_decay)
+			n_decay >>= 2;
+		pool_len -= n_decay;
 
 		list_for_each_entry_safe(va, nva, &tmp_list, list) {
+			if (!n_decay--)
+				break;
+
 			list_del_init(&va->list);
 			merge_or_add_vmap_area(va, &decay_root, &decay_list);
-
-			if (!full_decay) {
-				WRITE_ONCE(vn->pool[i].len, vn->pool[i].len - 1);
-
-				if (!--n_decay)
-					break;
-			}
 		}
 
 		/*
@@ -2204,9 +2216,10 @@ decay_va_pool_node(struct vmap_node *vn, bool full_decay)
 		 * can populate the pool therefore a simple list replace
 		 * operation takes place here.
 		 */
-		if (!full_decay && !list_empty(&tmp_list)) {
+		if (!list_empty(&tmp_list)) {
 			spin_lock(&vn->pool_lock);
 			list_replace_init(&tmp_list, &vn->pool[i].head);
+			WRITE_ONCE(vn->pool[i].len, pool_len);
 			spin_unlock(&vn->pool_lock);
 		}
 	}
@@ -2276,6 +2289,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end,
 {
 	unsigned long nr_purged_areas = 0;
 	unsigned int nr_purge_helpers;
+	static cpumask_t purge_nodes;
 	unsigned int nr_purge_nodes;
 	struct vmap_node *vn;
 	int i;
@@ -2287,9 +2301,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end,
 	 */
 	purge_nodes = CPU_MASK_NONE;
 
-	for (i = 0; i < nr_vmap_nodes; i++) {
-		vn = &vmap_nodes[i];
-
+	for_each_vmap_node(vn) {
 		INIT_LIST_HEAD(&vn->purge_list);
 		vn->skip_populate = full_pool_decay;
 		decay_va_pool_node(vn, full_pool_decay);
@@ -2308,7 +2320,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end,
 		end = max(end, list_last_entry(&vn->purge_list,
 			struct vmap_area, list)->va_end);
 
-		cpumask_set_cpu(i, &purge_nodes);
+		cpumask_set_cpu(node_to_id(vn), &purge_nodes);
 	}
 
 	nr_purge_nodes = cpumask_weight(&purge_nodes);
@@ -2387,7 +2399,7 @@ static void free_vmap_area_noflush(struct vmap_area *va)
 	if (WARN_ON_ONCE(!list_empty(&va->list)))
 		return;
 
-	nr_lazy = atomic_long_add_return(va_size(va) >> PAGE_SHIFT,
+	nr_lazy = atomic_long_add_return_relaxed(va_size(va) >> PAGE_SHIFT,
 					 &vmap_lazy_nr);
 
 	/*
@@ -2453,7 +2465,7 @@ struct vmap_area *find_vmap_area(unsigned long addr)
 
 		if (va)
 			return va;
-	} while ((i = (i + 1) % nr_vmap_nodes) != j);
+	} while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j);
 
 	return NULL;
 }
@@ -2479,7 +2491,7 @@ static struct vmap_area *find_unlink_vmap_area(unsigned long addr)
 
 		if (va)
 			return va;
-	} while ((i = (i + 1) % nr_vmap_nodes) != j);
+	} while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j);
 
 	return NULL;
 }
@@ -2948,10 +2960,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
  */
 void vm_unmap_aliases(void)
 {
-	unsigned long start = ULONG_MAX, end = 0;
-	int flush = 0;
-
-	_vm_unmap_aliases(start, end, flush);
+	_vm_unmap_aliases(ULONG_MAX, 0, 0);
 }
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
@@ -3132,7 +3141,7 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm)
 	/*
 	 * Before removing VM_UNINITIALIZED,
 	 * we should make sure that vm has proper values.
-	 * Pair with smp_rmb() in show_numa_info().
+	 * Pair with smp_rmb() in vread_iter() and vmalloc_info_show().
 	 */
 	smp_wmb();
 	vm->flags &= ~VM_UNINITIALIZED;
@@ -3403,12 +3412,13 @@ void vfree(const void *addr)
 
 	if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS))
 		vm_reset_perms(vm);
+	/* All pages of vm should be charged to same memcg, so use first one. */
+	if (vm->nr_pages && !(vm->flags & VM_MAP_PUT_PAGES))
+		mod_memcg_page_state(vm->pages[0], MEMCG_VMALLOC, -vm->nr_pages);
 	for (i = 0; i < vm->nr_pages; i++) {
 		struct page *page = vm->pages[i];
 
 		BUG_ON(!page);
-		if (!(vm->flags & VM_MAP_PUT_PAGES))
-			mod_memcg_page_state(page, MEMCG_VMALLOC, -1);
 		/*
 		 * High-order allocs for huge vmallocs are split, so
 		 * can be freed as an array of order-0 allocations
@@ -3704,12 +3714,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		node, page_order, nr_small_pages, area->pages);
 
 	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
-	if (gfp_mask & __GFP_ACCOUNT) {
-		int i;
-
-		for (i = 0; i < area->nr_pages; i++)
-			mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1);
-	}
+	/* All pages of vm should be charged to same memcg, so use first one. */
+	if (gfp_mask & __GFP_ACCOUNT && area->nr_pages)
+		mod_memcg_page_state(area->pages[0], MEMCG_VMALLOC,
+				     area->nr_pages);
 
 	/*
 	 * If not enough pages were obtained to accomplish an
@@ -4967,39 +4975,37 @@ bool vmalloc_dump_obj(void *object)
 #endif
 
 #ifdef CONFIG_PROC_FS
-static void show_numa_info(struct seq_file *m, struct vm_struct *v)
-{
-	if (IS_ENABLED(CONFIG_NUMA)) {
-		unsigned int nr, *counters = m->private;
-		unsigned int step = 1U << vm_area_page_order(v);
 
-		if (!counters)
-			return;
+/*
+ * Print number of pages allocated on each memory node.
+ *
+ * This function can only be called if CONFIG_NUMA is enabled
+ * and VM_UNINITIALIZED bit in v->flags is disabled.
+ */
+static void show_numa_info(struct seq_file *m, struct vm_struct *v,
+				 unsigned int *counters)
+{
+	unsigned int nr;
+	unsigned int step = 1U << vm_area_page_order(v);
 
-		if (v->flags & VM_UNINITIALIZED)
-			return;
-		/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
-		smp_rmb();
+	if (!counters)
+		return;
 
-		memset(counters, 0, nr_node_ids * sizeof(unsigned int));
+	memset(counters, 0, nr_node_ids * sizeof(unsigned int));
 
-		for (nr = 0; nr < v->nr_pages; nr += step)
-			counters[page_to_nid(v->pages[nr])] += step;
-		for_each_node_state(nr, N_HIGH_MEMORY)
-			if (counters[nr])
-				seq_printf(m, " N%u=%u", nr, counters[nr]);
-	}
+	for (nr = 0; nr < v->nr_pages; nr += step)
+		counters[page_to_nid(v->pages[nr])] += step;
+	for_each_node_state(nr, N_HIGH_MEMORY)
+		if (counters[nr])
+			seq_printf(m, " N%u=%u", nr, counters[nr]);
 }
 
 static void show_purge_info(struct seq_file *m)
 {
 	struct vmap_node *vn;
 	struct vmap_area *va;
-	int i;
-
-	for (i = 0; i < nr_vmap_nodes; i++) {
-		vn = &vmap_nodes[i];
 
+	for_each_vmap_node(vn) {
 		spin_lock(&vn->lazy.lock);
 		list_for_each_entry(va, &vn->lazy.head, list) {
 			seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
@@ -5015,11 +5021,12 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
 	struct vmap_node *vn;
 	struct vmap_area *va;
 	struct vm_struct *v;
-	int i;
+	unsigned int *counters;
 
-	for (i = 0; i < nr_vmap_nodes; i++) {
-		vn = &vmap_nodes[i];
+	if (IS_ENABLED(CONFIG_NUMA))
+		counters = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
 
+	for_each_vmap_node(vn) {
 		spin_lock(&vn->busy.lock);
 		list_for_each_entry(va, &vn->busy.head, list) {
 			if (!va->vm) {
@@ -5032,6 +5039,11 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
 			}
 
 			v = va->vm;
+			if (v->flags & VM_UNINITIALIZED)
+				continue;
+
+			/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
+			smp_rmb();
 
 			seq_printf(m, "0x%pK-0x%pK %7ld",
 				v->addr, v->addr + v->size, v->size);
@@ -5066,7 +5078,9 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
 			if (is_vmalloc_addr(v->pages))
 				seq_puts(m, " vpages");
 
-			show_numa_info(m, v);
+			if (IS_ENABLED(CONFIG_NUMA))
+				show_numa_info(m, v, counters);
+
 			seq_putc(m, '\n');
 		}
 		spin_unlock(&vn->busy.lock);
@@ -5076,19 +5090,14 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
 	 * As a final step, dump "unpurged" areas.
 	 */
 	show_purge_info(m);
+	if (IS_ENABLED(CONFIG_NUMA))
+		kfree(counters);
 	return 0;
 }
 
 static int __init proc_vmalloc_init(void)
 {
-	void *priv_data = NULL;
-
-	if (IS_ENABLED(CONFIG_NUMA))
-		priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
-
-	proc_create_single_data("vmallocinfo",
-		0400, NULL, vmalloc_info_show, priv_data);
-
+	proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show);
 	return 0;
 }
 module_init(proc_vmalloc_init);
@@ -5140,7 +5149,7 @@ static void __init vmap_init_free_space(void)
 static void vmap_init_nodes(void)
 {
 	struct vmap_node *vn;
-	int i, n;
+	int i;
 
 #if BITS_PER_LONG == 64
 	/*
@@ -5157,7 +5166,7 @@ static void vmap_init_nodes(void)
 	 * set of cores. Therefore a per-domain purging is supposed to
 	 * be added as well as a per-domain balancing.
 	 */
-	n = clamp_t(unsigned int, num_possible_cpus(), 1, 128);
+	int n = clamp_t(unsigned int, num_possible_cpus(), 1, 128);
 
 	if (n > 1) {
 		vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT | __GFP_NOWARN);
@@ -5172,8 +5181,7 @@ static void vmap_init_nodes(void)
 	}
 #endif
 
-	for (n = 0; n < nr_vmap_nodes; n++) {
-		vn = &vmap_nodes[n];
+	for_each_vmap_node(vn) {
 		vn->busy.root = RB_ROOT;
 		INIT_LIST_HEAD(&vn->busy.head);
 		spin_lock_init(&vn->busy.lock);
@@ -5194,15 +5202,13 @@ static void vmap_init_nodes(void)
 static unsigned long
 vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
-	unsigned long count;
+	unsigned long count = 0;
 	struct vmap_node *vn;
-	int i, j;
-
-	for (count = 0, i = 0; i < nr_vmap_nodes; i++) {
-		vn = &vmap_nodes[i];
+	int i;
 
-		for (j = 0; j < MAX_VA_SIZE_PAGES; j++)
-			count += READ_ONCE(vn->pool[j].len);
+	for_each_vmap_node(vn) {
+		for (i = 0; i < MAX_VA_SIZE_PAGES; i++)
+			count += READ_ONCE(vn->pool[i].len);
 	}
 
 	return count ? count : SHRINK_EMPTY;
@@ -5211,10 +5217,10 @@ vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 static unsigned long
 vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
-	int i;
+	struct vmap_node *vn;
 
-	for (i = 0; i < nr_vmap_nodes; i++)
-		decay_va_pool_node(&vmap_nodes[i], true);
+	for_each_vmap_node(vn)
+		decay_va_pool_node(vn, true);
 
 	return SHRINK_STOP;
 }