Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Almost all of MM here. A few things are still getting finished off,
  reviewed, etc.

   - Yang Shi has improved the behaviour of khugepaged collapsing of
     readonly file-backed transparent hugepages.

   - Johannes Weiner has arranged for zswap memory use to be tracked and
     managed on a per-cgroup basis.

   - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for
     runtime enablement of the recent huge page vmemmap optimization
     feature.

   - Baolin Wang contributes a series to fix some issues around hugetlb
     pagetable invalidation.

   - Zhenwei Pi has fixed some interactions between hwpoisoned pages and
     virtualization.

   - Tong Tiangen has enabled the use of the presently x86-only
     page_table_check debugging feature on arm64 and riscv.

   - David Vernet has done some fixup work on the memcg selftests.

   - Peter Xu has taught userfaultfd to handle write protection faults
     against shmem- and hugetlbfs-backed files.

   - More DAMON development from SeongJae Park - adding online tuning of
     the feature and support for monitoring of fixed virtual address
     ranges. Also easier discovery of which monitoring operations are
     available.

   - Nadav Amit has done some optimization of TLB flushing during
     mprotect().

   - Neil Brown continues to labor away at improving our swap-over-NFS
     support.

   - David Hildenbrand has some fixes to anon page COWing versus
     get_user_pages().

   - Peng Liu fixed some errors in the core hugetlb code.

   - Joao Martins has reduced the amount of memory consumed by
     device-dax's compound devmaps.

   - Some cleanups of the arch-specific pagemap code from Anshuman
     Khandual.

   - Muchun Song has found and fixed some errors in the TLB flushing of
     transparent hugepages.

   - Roman Gushchin has done more work on the memcg selftests.

  ... and, of course, many smaller fixes and cleanups. Notably, the
  customary million cleanup serieses from Miaohe Lin"

* tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits)
  mm: kfence: use PAGE_ALIGNED helper
  selftests: vm: add the "settings" file with timeout variable
  selftests: vm: add "test_hmm.sh" to TEST_FILES
  selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests
  selftests: vm: add migration to the .gitignore
  selftests/vm/pkeys: fix typo in comment
  ksm: fix typo in comment
  selftests: vm: add process_mrelease tests
  Revert "mm/vmscan: never demote for memcg reclaim"
  mm/kfence: print disabling or re-enabling message
  include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace"
  include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion"
  mm: fix a potential infinite loop in start_isolate_page_range()
  MAINTAINERS: add Muchun as co-maintainer for HugeTLB
  zram: fix Kconfig dependency warning
  mm/shmem: fix shmem folio swapoff hang
  cgroup: fix an error handling path in alloc_pagecache_max_30M()
  mm: damon: use HPAGE_PMD_SIZE
  tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
  nodemask.h: fix compilation error with GCC12
  ...

1 files changed, 97 insertions, 97 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 21d82636c291..e51588e95f57 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -177,6 +177,7 @@ static bool remove_migration_pte(struct folio *folio,
 	DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION);
 
 	while (page_vma_mapped_walk(&pvmw)) {
+		rmap_t rmap_flags = RMAP_NONE;
 		pte_t pte;
 		swp_entry_t entry;
 		struct page *new;
@@ -211,6 +212,9 @@ static bool remove_migration_pte(struct folio *folio,
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
+		if (folio_test_anon(folio) && !is_readable_migration_entry(entry))
+			rmap_flags |= RMAP_EXCLUSIVE;
+
 		if (unlikely(is_device_private_page(new))) {
 			if (pte_write(pte))
 				entry = make_writable_device_private_entry(
@@ -232,15 +236,17 @@ static bool remove_migration_pte(struct folio *folio,
 			pte = pte_mkhuge(pte);
 			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
 			if (folio_test_anon(folio))
-				hugepage_add_anon_rmap(new, vma, pvmw.address);
+				hugepage_add_anon_rmap(new, vma, pvmw.address,
+						       rmap_flags);
 			else
-				page_dup_rmap(new, true);
+				page_dup_file_rmap(new, true);
 			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
 		} else
 #endif
 		{
 			if (folio_test_anon(folio))
-				page_add_anon_rmap(new, vma, pvmw.address, false);
+				page_add_anon_rmap(new, vma, pvmw.address,
+						   rmap_flags);
 			else
 				page_add_file_rmap(new, vma, false);
 			set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
@@ -471,11 +477,6 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 
 	xas_lock_irq(&xas);
 	expected_count = 2 + page_has_private(page);
-	if (page_count(page) != expected_count || xas_load(&xas) != page) {
-		xas_unlock_irq(&xas);
-		return -EAGAIN;
-	}
-
 	if (!page_ref_freeze(page, expected_count)) {
 		xas_unlock_irq(&xas);
 		return -EAGAIN;
@@ -517,6 +518,12 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
 		folio_set_workingset(newfolio);
 	if (folio_test_checked(folio))
 		folio_set_checked(newfolio);
+	/*
+	 * PG_anon_exclusive (-> PG_mappedtodisk) is always migrated via
+	 * migration entries. We can still have PG_anon_exclusive set on an
+	 * effectively unmapped and unreferenced first sub-pages of an
+	 * anonymous THP: we can simply copy it here via PG_mappedtodisk.
+	 */
 	if (folio_test_mappedtodisk(folio))
 		folio_set_mappedtodisk(newfolio);
 
@@ -836,21 +843,21 @@ static int fallback_migrate_page(struct address_space *mapping,
  *   < 0 - error code
  *  MIGRATEPAGE_SUCCESS - success
  */
-static int move_to_new_page(struct page *newpage, struct page *page,
+static int move_to_new_folio(struct folio *dst, struct folio *src,
 				enum migrate_mode mode)
 {
 	struct address_space *mapping;
 	int rc = -EAGAIN;
-	bool is_lru = !__PageMovable(page);
+	bool is_lru = !__PageMovable(&src->page);
 
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
+	VM_BUG_ON_FOLIO(!folio_test_locked(src), src);
+	VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst);
 
-	mapping = page_mapping(page);
+	mapping = folio_mapping(src);
 
 	if (likely(is_lru)) {
 		if (!mapping)
-			rc = migrate_page(mapping, newpage, page, mode);
+			rc = migrate_page(mapping, &dst->page, &src->page, mode);
 		else if (mapping->a_ops->migratepage)
 			/*
 			 * Most pages have a mapping and most filesystems
@@ -859,54 +866,54 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 			 * migratepage callback. This is the most common path
 			 * for page migration.
 			 */
-			rc = mapping->a_ops->migratepage(mapping, newpage,
-							page, mode);
+			rc = mapping->a_ops->migratepage(mapping, &dst->page,
+							&src->page, mode);
 		else
-			rc = fallback_migrate_page(mapping, newpage,
-							page, mode);
+			rc = fallback_migrate_page(mapping, &dst->page,
+							&src->page, mode);
 	} else {
 		/*
 		 * In case of non-lru page, it could be released after
 		 * isolation step. In that case, we shouldn't try migration.
 		 */
-		VM_BUG_ON_PAGE(!PageIsolated(page), page);
-		if (!PageMovable(page)) {
+		VM_BUG_ON_FOLIO(!folio_test_isolated(src), src);
+		if (!folio_test_movable(src)) {
 			rc = MIGRATEPAGE_SUCCESS;
-			ClearPageIsolated(page);
+			folio_clear_isolated(src);
 			goto out;
 		}
 
-		rc = mapping->a_ops->migratepage(mapping, newpage,
-						page, mode);
+		rc = mapping->a_ops->migratepage(mapping, &dst->page,
+						&src->page, mode);
 		WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS &&
-			!PageIsolated(page));
+				!folio_test_isolated(src));
 	}
 
 	/*
-	 * When successful, old pagecache page->mapping must be cleared before
-	 * page is freed; but stats require that PageAnon be left as PageAnon.
+	 * When successful, old pagecache src->mapping must be cleared before
+	 * src is freed; but stats require that PageAnon be left as PageAnon.
 	 */
 	if (rc == MIGRATEPAGE_SUCCESS) {
-		if (__PageMovable(page)) {
-			VM_BUG_ON_PAGE(!PageIsolated(page), page);
+		if (__PageMovable(&src->page)) {
+			VM_BUG_ON_FOLIO(!folio_test_isolated(src), src);
 
 			/*
 			 * We clear PG_movable under page_lock so any compactor
 			 * cannot try to migrate this page.
 			 */
-			ClearPageIsolated(page);
+			folio_clear_isolated(src);
 		}
 
 		/*
-		 * Anonymous and movable page->mapping will be cleared by
+		 * Anonymous and movable src->mapping will be cleared by
 		 * free_pages_prepare so don't reset it here for keeping
 		 * the type to work PageAnon, for example.
 		 */
-		if (!PageMappingFlags(page))
-			page->mapping = NULL;
+		if (!folio_mapping_flags(src))
+			src->mapping = NULL;
 
-		if (likely(!is_zone_device_page(newpage)))
-			flush_dcache_folio(page_folio(newpage));
+		if (likely(!folio_is_zone_device(dst)))
+			flush_dcache_folio(dst);
 	}
 out:
 	return rc;
@@ -994,7 +1001,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		goto out_unlock;
 
 	if (unlikely(!is_lru)) {
-		rc = move_to_new_page(newpage, page, mode);
+		rc = move_to_new_folio(dst, folio, mode);
 		goto out_unlock_both;
 	}
 
@@ -1025,7 +1032,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	}
 
 	if (!page_mapped(page))
-		rc = move_to_new_page(newpage, page, mode);
+		rc = move_to_new_folio(dst, folio, mode);
 
 	/*
 	 * When successful, push newpage to LRU immediately: so that if it
@@ -1230,7 +1237,6 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 		goto put_anon;
 
 	if (page_mapped(hpage)) {
-		bool mapping_locked = false;
 		enum ttu_flags ttu = 0;
 
 		if (!PageAnon(hpage)) {
@@ -1244,19 +1250,18 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 			if (unlikely(!mapping))
 				goto unlock_put_anon;
 
-			mapping_locked = true;
-			ttu |= TTU_RMAP_LOCKED;
+			ttu = TTU_RMAP_LOCKED;
 		}
 
 		try_to_migrate(src, ttu);
 		page_was_mapped = 1;
 
-		if (mapping_locked)
+		if (ttu & TTU_RMAP_LOCKED)
 			i_mmap_unlock_write(mapping);
 	}
 
 	if (!page_mapped(hpage))
-		rc = move_to_new_page(new_hpage, hpage, mode);
+		rc = move_to_new_folio(dst, src, mode);
 
 	if (page_was_mapped)
 		remove_migration_ptes(src,
@@ -1412,14 +1417,11 @@ retry:
 						nr_thp_split++;
 						goto retry;
 					}
-
-					nr_failed_pages += nr_subpages;
-					break;
-				}
-
 				/* Hugetlb migration is unsupported */
-				if (!no_subpage_counting)
+				} else if (!no_subpage_counting) {
 					nr_failed++;
+				}
+
 				nr_failed_pages += nr_subpages;
 				break;
 			case -ENOMEM:
@@ -1434,28 +1436,30 @@ retry:
 						nr_thp_split++;
 						goto retry;
 					}
-
-					nr_failed_pages += nr_subpages;
-					goto out;
+				} else if (!no_subpage_counting) {
+					nr_failed++;
 				}
 
-				if (!no_subpage_counting)
-					nr_failed++;
 				nr_failed_pages += nr_subpages;
+				/*
+				 * There might be some subpages of fail-to-migrate THPs
+				 * left in thp_split_pages list. Move them back to migration
+				 * list so that they could be put back to the right list by
+				 * the caller otherwise the page refcnt will be leaked.
+				 */
+				list_splice_init(&thp_split_pages, from);
+				nr_thp_failed += thp_retry;
 				goto out;
 			case -EAGAIN:
-				if (is_thp) {
+				if (is_thp)
 					thp_retry++;
-					break;
-				}
-				retry++;
+				else
+					retry++;
 				break;
 			case MIGRATEPAGE_SUCCESS:
 				nr_succeeded += nr_subpages;
-				if (is_thp) {
+				if (is_thp)
 					nr_thp_succeeded++;
-					break;
-				}
 				break;
 			default:
 				/*
@@ -1464,14 +1468,11 @@ retry:
 				 * removed from migration page list and not
 				 * retried in the next outer loop.
 				 */
-				if (is_thp) {
+				if (is_thp)
 					nr_thp_failed++;
-					nr_failed_pages += nr_subpages;
-					break;
-				}
-
-				if (!no_subpage_counting)
+				else if (!no_subpage_counting)
 					nr_failed++;
+
 				nr_failed_pages += nr_subpages;
 				break;
 			}
@@ -1606,8 +1607,8 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 
 	mmap_read_lock(mm);
 	err = -EFAULT;
-	vma = find_vma(mm, addr);
-	if (!vma || addr < vma->vm_start || !vma_migratable(vma))
+	vma = vma_lookup(mm, addr);
+	if (!vma || !vma_migratable(vma))
 		goto out;
 
 	/* FOLL_DUMP to ignore special (like zero) pages */
@@ -1802,13 +1803,18 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 			goto set_status;
 
 		/* FOLL_DUMP to ignore special (like zero) pages */
-		page = follow_page(vma, addr, FOLL_DUMP);
+		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
 
 		err = PTR_ERR(page);
 		if (IS_ERR(page))
 			goto set_status;
 
-		err = page ? page_to_nid(page) : -ENOENT;
+		if (page) {
+			err = page_to_nid(page);
+			put_page(page);
+		} else {
+			err = -ENOENT;
+		}
 set_status:
 		*status = err;
 
@@ -1844,16 +1850,12 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
 			 const void __user * __user *pages,
 			 int __user *status)
 {
-#define DO_PAGES_STAT_CHUNK_NR 16
+#define DO_PAGES_STAT_CHUNK_NR 16UL
 	const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
 	int chunk_status[DO_PAGES_STAT_CHUNK_NR];
 
 	while (nr_pages) {
-		unsigned long chunk_nr;
-
-		chunk_nr = nr_pages;
-		if (chunk_nr > DO_PAGES_STAT_CHUNK_NR)
-			chunk_nr = DO_PAGES_STAT_CHUNK_NR;
+		unsigned long chunk_nr = min(nr_pages, DO_PAGES_STAT_CHUNK_NR);
 
 		if (in_compat_syscall()) {
 			if (get_compat_pages_array(chunk_pages, pages,
@@ -1969,7 +1971,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Returns true if this is a safe migration target node for misplaced NUMA
- * pages. Currently it only checks the watermarks which crude
+ * pages. Currently it only checks the watermarks which is crude.
  */
 static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 				   unsigned long nr_migrate_pages)
@@ -1979,7 +1981,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
 		struct zone *zone = pgdat->node_zones + z;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		/* Avoid waking kswapd by allocating pages_to_migrate pages. */
@@ -2015,7 +2017,6 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 
 static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 {
-	int page_lru;
 	int nr_pages = thp_nr_pages(page);
 	int order = compound_order(page);
 
@@ -2032,7 +2033,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
 			return 0;
 		for (z = pgdat->nr_zones - 1; z >= 0; z--) {
-			if (populated_zone(pgdat->node_zones + z))
+			if (managed_zone(pgdat->node_zones + z))
 				break;
 		}
 		wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE);
@@ -2042,8 +2043,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 	if (isolate_lru_page(page))
 		return 0;
 
-	page_lru = page_is_file_lru(page);
-	mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
+	mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page),
 			    nr_pages);
 
 	/*
@@ -2116,7 +2116,6 @@ out:
 	return 0;
 }
 #endif /* CONFIG_NUMA_BALANCING */
-#endif /* CONFIG_NUMA */
 
 /*
  * node_demotion[] example:
@@ -2250,7 +2249,6 @@ out:
 	return target;
 }
 
-#if defined(CONFIG_HOTPLUG_CPU)
 /* Disable reclaim-based migration. */
 static void __disable_all_migrate_targets(void)
 {
@@ -2353,8 +2351,8 @@ out_clear:
  */
 static void __set_migration_target_nodes(void)
 {
-	nodemask_t next_pass	= NODE_MASK_NONE;
-	nodemask_t this_pass	= NODE_MASK_NONE;
+	nodemask_t next_pass;
+	nodemask_t this_pass;
 	nodemask_t used_targets = NODE_MASK_NONE;
 	int node, best_distance;
 
@@ -2443,6 +2441,7 @@ void set_migration_target_nodes(void)
  * __set_migration_target_nodes() can be used as opposed to
  * set_migration_target_nodes().
  */
+#ifdef CONFIG_MEMORY_HOTPLUG
 static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
 						 unsigned long action, void *_arg)
 {
@@ -2488,15 +2487,17 @@ static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
 
 	return notifier_from_errno(0);
 }
+#endif
 
 void __init migrate_on_reclaim_init(void)
 {
-	node_demotion = kmalloc_array(nr_node_ids,
-				      sizeof(struct demotion_nodes),
-				      GFP_KERNEL);
+	node_demotion = kcalloc(nr_node_ids,
+				sizeof(struct demotion_nodes),
+				GFP_KERNEL);
 	WARN_ON(!node_demotion);
-
+#ifdef CONFIG_MEMORY_HOTPLUG
 	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
+#endif
 	/*
 	 * At this point, all numa nodes with memory/CPus have their state
 	 * properly set, so we can build the demotion order now.
@@ -2507,7 +2508,6 @@ void __init migrate_on_reclaim_init(void)
 	set_migration_target_nodes();
 	cpus_read_unlock();
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 bool numa_demotion_enabled = false;
 
@@ -2523,12 +2523,11 @@ static ssize_t numa_demotion_enabled_store(struct kobject *kobj,
 					   struct kobj_attribute *attr,
 					   const char *buf, size_t count)
 {
-	if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1))
-		numa_demotion_enabled = true;
-	else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1))
-		numa_demotion_enabled = false;
-	else
-		return -EINVAL;
+	ssize_t ret;
+
+	ret = kstrtobool(buf, &numa_demotion_enabled);
+	if (ret)
+		return ret;
 
 	return count;
 }
@@ -2568,4 +2567,5 @@ delete_obj:
 	return err;
 }
 subsys_initcall(numa_init_sysfs);
-#endif
+#endif /* CONFIG_SYSFS */
+#endif /* CONFIG_NUMA */