Merge tag 'mm-hotfixes-stable-2025-05-17-09-41' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/akpm/mm

Pull hotfixes from Andrew Morton:
 "Nine singleton hotfixes, all MM.  Four are cc:stable"

* tag 'mm-hotfixes-stable-2025-05-17-09-41' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm: userfaultfd: correct dirty flags set for both present and swap pte
  zsmalloc: don't underflow size calculation in zs_obj_write()
  mm/page_alloc: fix race condition in unaccepted memory handling
  mm/page_alloc: ensure try_alloc_pages() plays well with unaccepted memory
  MAINTAINERS: add mm GUP section
  mm/codetag: move tag retrieval back upfront in __free_pages()
  mm/memory: fix mapcount / refcount sanity check for mTHP reuse
  kernel/fork: only call untrack_pfn_clear() on VMAs duplicated for fork()
  mm: hugetlb: fix incorrect fallback for subpool

MAINTAINERS

@@ -15549,6 +15549,18 @@ S:	Maintained
 F:	include/linux/execmem.h
 F:	mm/execmem.c
 
+MEMORY MANAGEMENT - GUP (GET USER PAGES)
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	David Hildenbrand <david@redhat.com>
+R:	Jason Gunthorpe <jgg@nvidia.com>
+R:	John Hubbard <jhubbard@nvidia.com>
+R:	Peter Xu <peterx@redhat.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	mm/gup.c
+
 MEMORY MANAGEMENT - NUMA MEMBLOCKS AND NUMA EMULATION
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Mike Rapoport <rppt@kernel.org>

include/linux/pgalloc_tag.h

@@ -188,6 +188,13 @@ static inline struct alloc_tag *__pgalloc_tag_get(struct page *page)
 	return tag;
 }
 
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page)
+{
+	if (mem_alloc_profiling_enabled())
+		return __pgalloc_tag_get(page);
+	return NULL;
+}
+
 void pgalloc_tag_split(struct folio *folio, int old_order, int new_order);
 void pgalloc_tag_swap(struct folio *new, struct folio *old);
 
@@ -199,6 +206,7 @@ static inline void clear_page_tag_ref(struct page *page) {}
 static inline void alloc_tag_sec_init(void) {}
 static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {}
 static inline void pgalloc_tag_swap(struct folio *new, struct folio *old) {}
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; }
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 

kernel/fork.c

@@ -498,10 +498,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	vma_numab_state_init(new);
 	dup_anon_vma_name(orig, new);
 
-	/* track_pfn_copy() will later take care of copying internal state. */
-	if (unlikely(new->vm_flags & VM_PFNMAP))
-		untrack_pfn_clear(new);
-
 	return new;
 }
 
@@ -672,6 +668,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		tmp = vm_area_dup(mpnt);
 		if (!tmp)
 			goto fail_nomem;
+
+		/* track_pfn_copy() will later take care of copying internal state. */
+		if (unlikely(tmp->vm_flags & VM_PFNMAP))
+			untrack_pfn_clear(tmp);
+
 		retval = vma_dup_policy(mpnt, tmp);
 		if (retval)
 			goto fail_nomem_policy;

mm/hugetlb.c

@@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct folio *folio;
-	long retval, gbl_chg;
+	long retval, gbl_chg, gbl_reserve;
 	map_chg_state map_chg;
 	int ret, idx;
 	struct hugetlb_cgroup *h_cg = NULL;
@@ -3163,8 +3163,16 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
 						    h_cg);
 out_subpool_put:
-	if (map_chg)
-		hugepage_subpool_put_pages(spool, 1);
+	/*
+	 * put page to subpool iff the quota of subpool's rsv_hpages is used
+	 * during hugepage_subpool_get_pages.
+	 */
+	if (map_chg && !gbl_chg) {
+		gbl_reserve = hugepage_subpool_put_pages(spool, 1);
+		hugetlb_acct_memory(h, -gbl_reserve);
+	}
+
+
 out_end_reservation:
 	if (map_chg != MAP_CHG_ENFORCED)
 		vma_end_reservation(h, vma, addr);
@@ -7239,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
 					struct vm_area_struct *vma,
 					vm_flags_t vm_flags)
 {
-	long chg = -1, add = -1;
+	long chg = -1, add = -1, spool_resv, gbl_resv;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	struct resv_map *resv_map;
@@ -7374,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode,
 	return true;
 
 out_put_pages:
-	/* put back original number of pages, chg */
-	(void)hugepage_subpool_put_pages(spool, chg);
+	spool_resv = chg - gbl_reserve;
+	if (spool_resv) {
+		/* put sub pool's reservation back, chg - gbl_reserve */
+		gbl_resv = hugepage_subpool_put_pages(spool, spool_resv);
+		/*
+		 * subpool's reserved pages can not be put back due to race,
+		 * return to hstate.
+		 */
+		hugetlb_acct_memory(h, -gbl_resv);
+	}
 out_uncharge_cgroup:
 	hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
 					    chg * pages_per_huge_page(h), h_cg);

mm/internal.h

@@ -1590,7 +1590,6 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc);
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 void accept_page(struct page *page);
-void unaccepted_cleanup_work(struct work_struct *work);
 #else /* CONFIG_UNACCEPTED_MEMORY */
 static inline void accept_page(struct page *page)
 {

mm/memory.c

@@ -3751,7 +3751,7 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
 
 	/* Stabilize the mapcount vs. refcount and recheck. */
 	folio_lock_large_mapcount(folio);
-	VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio));
+	VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_ref_count(folio), folio);
 
 	if (folio_test_large_maybe_mapped_shared(folio))
 		goto unlock;

mm/mm_init.c

@@ -1441,7 +1441,6 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 	INIT_LIST_HEAD(&zone->unaccepted_pages);
-	INIT_WORK(&zone->unaccepted_cleanup, unaccepted_cleanup_work);
 #endif
 }
 

mm/page_alloc.c

@@ -290,7 +290,8 @@ EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
 static bool page_contains_unaccepted(struct page *page, unsigned int order);
-static bool cond_accept_memory(struct zone *zone, unsigned int order);
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags);
 static bool __free_unaccepted(struct page *page);
 
 int page_group_by_mobility_disabled __read_mostly;
@@ -1151,14 +1152,9 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr)
 		__pgalloc_tag_sub(page, nr);
 }
 
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
+/* When tag is not NULL, assuming mem_alloc_profiling_enabled */
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
 {
-	struct alloc_tag *tag;
-
-	if (!mem_alloc_profiling_enabled())
-		return;
-
-	tag = __pgalloc_tag_get(page);
 	if (tag)
 		this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr);
 }
@@ -1168,7 +1164,7 @@ static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
 static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
 				   unsigned int nr) {}
 static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) {}
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {}
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
@@ -3616,7 +3612,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 			}
 		}
 
-		cond_accept_memory(zone, order);
+		cond_accept_memory(zone, order, alloc_flags);
 
 		/*
 		 * Detect whether the number of free pages is below high
@@ -3643,7 +3639,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 				       gfp_mask)) {
 			int ret;
 
-			if (cond_accept_memory(zone, order))
+			if (cond_accept_memory(zone, order, alloc_flags))
 				goto try_this_zone;
 
 			/*
@@ -3696,7 +3692,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 
 			return page;
 		} else {
-			if (cond_accept_memory(zone, order))
+			if (cond_accept_memory(zone, order, alloc_flags))
 				goto try_this_zone;
 
 			/* Try again if zone has deferred pages */
@@ -4849,7 +4845,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 			goto failed;
 		}
 
-		cond_accept_memory(zone, 0);
+		cond_accept_memory(zone, 0, alloc_flags);
 retry_this_zone:
 		mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages;
 		if (zone_watermark_fast(zone, 0,  mark,
@@ -4858,7 +4854,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 			break;
 		}
 
-		if (cond_accept_memory(zone, 0))
+		if (cond_accept_memory(zone, 0, alloc_flags))
 			goto retry_this_zone;
 
 		/* Try again if zone has deferred pages */
@@ -5065,11 +5061,13 @@ static void ___free_pages(struct page *page, unsigned int order,
 {
 	/* get PageHead before we drop reference */
 	int head = PageHead(page);
+	/* get alloc tag in case the page is released by others */
+	struct alloc_tag *tag = pgalloc_tag_get(page);
 
 	if (put_page_testzero(page))
 		__free_frozen_pages(page, order, fpi_flags);
 	else if (!head) {
-		pgalloc_tag_sub_pages(page, (1 << order) - 1);
+		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
 		while (order-- > 0)
 			__free_frozen_pages(page + (1 << order), order,
 					    fpi_flags);
@@ -7174,16 +7172,8 @@ bool has_managed_dma(void)
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 
-/* Counts number of zones with unaccepted pages. */
-static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages);
-
 static bool lazy_accept = true;
 
-void unaccepted_cleanup_work(struct work_struct *work)
-{
-	static_branch_dec(&zones_with_unaccepted_pages);
-}
-
 static int __init accept_memory_parse(char *p)
 {
 	if (!strcmp(p, "lazy")) {
@@ -7208,11 +7198,7 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order)
 static void __accept_page(struct zone *zone, unsigned long *flags,
 			  struct page *page)
 {
-	bool last;
-
 	list_del(&page->lru);
-	last = list_empty(&zone->unaccepted_pages);
-
 	account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
 	__mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
 	__ClearPageUnaccepted(page);
@@ -7221,28 +7207,6 @@ static void __accept_page(struct zone *zone, unsigned long *flags,
 	accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER);
 
 	__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);
-
-	if (last) {
-		/*
-		 * There are two corner cases:
-		 *
-		 * - If allocation occurs during the CPU bring up,
-		 *   static_branch_dec() cannot be used directly as
-		 *   it causes a deadlock on cpu_hotplug_lock.
-		 *
-		 *   Instead, use schedule_work() to prevent deadlock.
-		 *
-		 * - If allocation occurs before workqueues are initialized,
-		 *   static_branch_dec() should be called directly.
-		 *
-		 *   Workqueues are initialized before CPU bring up, so this
-		 *   will not conflict with the first scenario.
-		 */
-		if (system_wq)
-			schedule_work(&zone->unaccepted_cleanup);
-		else
-			unaccepted_cleanup_work(&zone->unaccepted_cleanup);
-	}
 }
 
 void accept_page(struct page *page)
@@ -7279,20 +7243,17 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	return true;
 }
 
-static inline bool has_unaccepted_memory(void)
-{
-	return static_branch_unlikely(&zones_with_unaccepted_pages);
-}
-
-static bool cond_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags)
 {
 	long to_accept, wmark;
 	bool ret = false;
 
-	if (!has_unaccepted_memory())
+	if (list_empty(&zone->unaccepted_pages))
 		return false;
 
-	if (list_empty(&zone->unaccepted_pages))
+	/* Bailout, since try_to_accept_memory_one() needs to take a lock */
+	if (alloc_flags & ALLOC_TRYLOCK)
 		return false;
 
 	wmark = promo_wmark_pages(zone);
@@ -7325,22 +7286,17 @@ static bool __free_unaccepted(struct page *page)
 {
 	struct zone *zone = page_zone(page);
 	unsigned long flags;
-	bool first = false;
 
 	if (!lazy_accept)
 		return false;
 
 	spin_lock_irqsave(&zone->lock, flags);
-	first = list_empty(&zone->unaccepted_pages);
 	list_add_tail(&page->lru, &zone->unaccepted_pages);
 	account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
 	__mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES);
 	__SetPageUnaccepted(page);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
-	if (first)
-		static_branch_inc(&zones_with_unaccepted_pages);
-
 	return true;
 }
 
@@ -7351,7 +7307,8 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order)
 	return false;
 }
 
-static bool cond_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags)
 {
 	return false;
 }
@@ -7422,11 +7379,6 @@ struct page *try_alloc_pages_noprof(int nid, unsigned int order)
 	if (!pcp_allowed_order(order))
 		return NULL;
 
-#ifdef CONFIG_UNACCEPTED_MEMORY
-	/* Bailout, since try_to_accept_memory_one() needs to take a lock */
-	if (has_unaccepted_memory())
-		return NULL;
-#endif
 	/* Bailout, since _deferred_grow_zone() needs to take a lock */
 	if (deferred_pages_enabled())
 		return NULL;

mm/userfaultfd.c

@@ -1064,8 +1064,13 @@ static int move_present_pte(struct mm_struct *mm,
 	src_folio->index = linear_page_index(dst_vma, dst_addr);
 
 	orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
-	/* Follow mremap() behavior and treat the entry dirty after the move */
-	orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
+	/* Set soft dirty bit so userspace can notice the pte was moved */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	orig_dst_pte = pte_mksoft_dirty(orig_dst_pte);
+#endif
+	if (pte_dirty(orig_src_pte))
+		orig_dst_pte = pte_mkdirty(orig_dst_pte);
+	orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma);
 
 	set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte);
 out:
@@ -1100,6 +1105,9 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 	}
 
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte);
+#endif
 	set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
 	double_pt_unlock(dst_ptl, src_ptl);