Merge tag 'mm-hotfixes-stable-2025-05-25-00-58' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull hotfixes from Andrew Morton:
 "22 hotfixes.

  13 are cc:stable and the remainder address post-6.14 issues or aren't
  considered necessary for -stable kernels. 19 are for MM"

* tag 'mm-hotfixes-stable-2025-05-25-00-58' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (22 commits)
  mailmap: add Jarkko's employer email address
  mm: fix copy_vma() error handling for hugetlb mappings
  memcg: always call cond_resched() after fn()
  mm/hugetlb: fix kernel NULL pointer dereference when replacing free hugetlb folios
  mm: vmalloc: only zero-init on vrealloc shrink
  mm: vmalloc: actually use the in-place vrealloc region
  alloc_tag: allocate percpu counters for module tags dynamically
  module: release codetag section when module load fails
  mm/cma: make detection of highmem_start more robust
  MAINTAINERS: add mm memory policy section
  MAINTAINERS: add mm ksm section
  kasan: avoid sleepable page allocation from atomic context
  highmem: add folio_test_partial_kmap()
  MAINTAINERS: add hung-task detector section
  taskstats: fix struct taskstats breaks backward compatibility since version 15
  mm/truncate: fix out-of-bounds when doing a right-aligned split
  MAINTAINERS: add mm reclaim section
  MAINTAINERS: update page allocator section
  mm: fix VM_UFFD_MINOR == VM_SHADOW_STACK on USERFAULTFD=y && ARM64_GCS=y
  mm: mmap: map MAP_STACK to VM_NOHUGEPAGE only if THP is enabled
  ...

9 files changed, 137 insertions, 35 deletions

diff --git a/mm/cma.c b/mm/cma.c
index 15632939f20a..c04be488b099 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -608,7 +608,10 @@ static int __init __cma_declare_contiguous_nid(phys_addr_t *basep,
 	 * complain. Find the boundary by adding one to the last valid
 	 * address.
 	 */
-	highmem_start = __pa(high_memory - 1) + 1;
+	if (IS_ENABLED(CONFIG_HIGHMEM))
+		highmem_start = __pa(high_memory - 1) + 1;
+	else
+		highmem_start = memblock_end_of_DRAM();
 	pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
 		__func__, &size, &base, &limit, &alignment);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7ae38bfb9096..6a3cf7935c14 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1250,7 +1250,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 /*
  * Reset and decrement one ref on hugepage private reservation.
  * Called with mm->mmap_lock writer semaphore held.
- * This function should be only used by move_vma() and operate on
+ * This function should be only used by mremap and operate on
  * same sized vma. It should never come here with last ref on the
  * reservation.
  */
@@ -2949,12 +2949,20 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
 
 	while (start_pfn < end_pfn) {
 		folio = pfn_folio(start_pfn);
+
+		/*
+		 * The folio might have been dissolved from under our feet, so make sure
+		 * to carefully check the state under the lock.
+		 */
+		spin_lock_irq(&hugetlb_lock);
 		if (folio_test_hugetlb(folio)) {
 			h = folio_hstate(folio);
 		} else {
+			spin_unlock_irq(&hugetlb_lock);
 			start_pfn++;
 			continue;
 		}
+		spin_unlock_irq(&hugetlb_lock);
 
 		if (!folio_ref_count(folio)) {
 			ret = alloc_and_dissolve_hugetlb_folio(h, folio,
@@ -7931,3 +7939,17 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 	hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE),
 			ALIGN_DOWN(vma->vm_end, PUD_SIZE));
 }
+
+/*
+ * For hugetlb, mremap() is an odd edge case - while the VMA copying is
+ * performed, we permit both the old and new VMAs to reference the same
+ * reservation.
+ *
+ * We fix this up after the operation succeeds, or if a newly allocated VMA
+ * is closed as a result of a failure to allocate memory.
+ */
+void fixup_hugetlb_reservations(struct vm_area_struct *vma)
+{
+	if (is_vm_hugetlb_page(vma))
+		clear_vma_resv_huge_pages(vma);
+}
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index 88d1c9dcb507..d2c70cd2afb1 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_vm_area_shadow(void *start,
 {
 }
 
+struct vmalloc_populate_data {
+	unsigned long start;
+	struct page **pages;
+};
+
 static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
-				      void *unused)
+				      void *_data)
 {
-	unsigned long page;
+	struct vmalloc_populate_data *data = _data;
+	struct page *page;
 	pte_t pte;
+	int index;
 
 	if (likely(!pte_none(ptep_get(ptep))))
 		return 0;
 
-	page = __get_free_page(GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
-
-	__memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE);
-	pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL);
+	index = PFN_DOWN(addr - data->start);
+	page = data->pages[index];
+	__memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE);
+	pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL);
 
 	spin_lock(&init_mm.page_table_lock);
 	if (likely(pte_none(ptep_get(ptep)))) {
 		set_pte_at(&init_mm, addr, ptep, pte);
-		page = 0;
+		data->pages[index] = NULL;
 	}
 	spin_unlock(&init_mm.page_table_lock);
-	if (page)
-		free_page(page);
+
+	return 0;
+}
+
+static void ___free_pages_bulk(struct page **pages, int nr_pages)
+{
+	int i;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (pages[i]) {
+			__free_pages(pages[i], 0);
+			pages[i] = NULL;
+		}
+	}
+}
+
+static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
+{
+	unsigned long nr_populated, nr_total = nr_pages;
+	struct page **page_array = pages;
+
+	while (nr_pages) {
+		nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages);
+		if (!nr_populated) {
+			___free_pages_bulk(page_array, nr_total - nr_pages);
+			return -ENOMEM;
+		}
+		pages += nr_populated;
+		nr_pages -= nr_populated;
+	}
+
 	return 0;
 }
 
+static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
+{
+	unsigned long nr_pages, nr_total = PFN_UP(end - start);
+	struct vmalloc_populate_data data;
+	int ret = 0;
+
+	data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	if (!data.pages)
+		return -ENOMEM;
+
+	while (nr_total) {
+		nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0]));
+		ret = ___alloc_pages_bulk(data.pages, nr_pages);
+		if (ret)
+			break;
+
+		data.start = start;
+		ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE,
+					  kasan_populate_vmalloc_pte, &data);
+		___free_pages_bulk(data.pages, nr_pages);
+		if (ret)
+			break;
+
+		start += nr_pages * PAGE_SIZE;
+		nr_total -= nr_pages;
+	}
+
+	free_page((unsigned long)data.pages);
+
+	return ret;
+}
+
 int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 {
 	unsigned long shadow_start, shadow_end;
@@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 	shadow_start = PAGE_ALIGN_DOWN(shadow_start);
 	shadow_end = PAGE_ALIGN(shadow_end);
 
-	ret = apply_to_page_range(&init_mm, shadow_start,
-				  shadow_end - shadow_start,
-				  kasan_populate_vmalloc_pte, NULL);
+	ret = __kasan_populate_vmalloc(shadow_start, shadow_end);
 	if (ret)
 		return ret;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c96c1f2b9cf5..2d4d65f25fec 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1168,7 +1168,6 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 {
 	struct mem_cgroup *iter;
 	int ret = 0;
-	int i = 0;
 
 	BUG_ON(mem_cgroup_is_root(memcg));
 
@@ -1178,10 +1177,9 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 
 		css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it);
 		while (!ret && (task = css_task_iter_next(&it))) {
-			/* Avoid potential softlockup warning */
-			if ((++i & 1023) == 0)
-				cond_resched();
 			ret = fn(task, arg);
+			/* Avoid potential softlockup warning */
+			cond_resched();
 		}
 		css_task_iter_end(&it);
 		if (ret) {
diff --git a/mm/mremap.c b/mm/mremap.c
index 7db9da609c84..0d4948b720e2 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -1188,8 +1188,7 @@ static int copy_vma_and_data(struct vma_remap_struct *vrm,
 		mremap_userfaultfd_prep(new_vma, vrm->uf);
 	}
 
-	if (is_vm_hugetlb_page(vma))
-		clear_vma_resv_huge_pages(vma);
+	fixup_hugetlb_reservations(vma);
 
 	/* Tell pfnmap has moved from this vma */
 	if (unlikely(vma->vm_flags & VM_PFNMAP))
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8258349e49ac..47fa713ccb4d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4562,6 +4562,14 @@ restart:
 	}
 
 retry:
+	/*
+	 * Deal with possible cpuset update races or zonelist updates to avoid
+	 * infinite retries.
+	 */
+	if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
+	    check_retry_zonelist(zonelist_iter_cookie))
+		goto restart;
+
 	/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
 	if (alloc_flags & ALLOC_KSWAPD)
 		wake_all_kswapds(order, gfp_mask, ac);
diff --git a/mm/truncate.c b/mm/truncate.c
index 5d98054094d1..f2aaf99f2990 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -191,6 +191,7 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio)
 bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 {
 	loff_t pos = folio_pos(folio);
+	size_t size = folio_size(folio);
 	unsigned int offset, length;
 	struct page *split_at, *split_at2;
 
@@ -198,14 +199,13 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 		offset = start - pos;
 	else
 		offset = 0;
-	length = folio_size(folio);
-	if (pos + length <= (u64)end)
-		length = length - offset;
+	if (pos + size <= (u64)end)
+		length = size - offset;
 	else
 		length = end + 1 - pos - offset;
 
 	folio_wait_writeback(folio);
-	if (length == folio_size(folio)) {
+	if (length == size) {
 		truncate_inode_folio(folio->mapping, folio);
 		return true;
 	}
@@ -224,16 +224,20 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 		return true;
 
 	split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE);
-	split_at2 = folio_page(folio,
-			PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE);
-
 	if (!try_folio_split(folio, split_at, NULL)) {
 		/*
 		 * try to split at offset + length to make sure folios within
 		 * the range can be dropped, especially to avoid memory waste
 		 * for shmem truncate
 		 */
-		struct folio *folio2 = page_folio(split_at2);
+		struct folio *folio2;
+
+		if (offset + length == size)
+			goto no_split;
+
+		split_at2 = folio_page(folio,
+				PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE);
+		folio2 = page_folio(split_at2);
 
 		if (!folio_try_get(folio2))
 			goto no_split;
diff --git a/mm/vma.c b/mm/vma.c
index 839d12f02c88..a468d4c29c0c 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -1834,6 +1834,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	return new_vma;
 
 out_vma_link:
+	fixup_hugetlb_reservations(new_vma);
 	vma_close(new_vma);
 
 	if (new_vma->vm_file)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 2d7511654831..00cf1b575c89 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -4093,8 +4093,8 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 	 * would be a good heuristic for when to shrink the vm_area?
 	 */
 	if (size <= old_size) {
-		/* Zero out "freed" memory. */
-		if (want_init_on_free())
+		/* Zero out "freed" memory, potentially for future realloc. */
+		if (want_init_on_free() || want_init_on_alloc(flags))
 			memset((void *)p + size, 0, old_size - size);
 		vm->requested_size = size;
 		kasan_poison_vmalloc(p + size, old_size - size);
@@ -4107,10 +4107,13 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 	if (size <= alloced_size) {
 		kasan_unpoison_vmalloc(p + old_size, size - old_size,
 				       KASAN_VMALLOC_PROT_NORMAL);
-		/* Zero out "alloced" memory. */
-		if (want_init_on_alloc(flags))
-			memset((void *)p + old_size, 0, size - old_size);
+		/*
+		 * No need to zero memory here, as unused memory will have
+		 * already been zeroed at initial allocation time or during
+		 * realloc shrink time.
+		 */
 		vm->requested_size = size;
+		return (void *)p;
 	}
 
 	/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */