Merge tag 'mm-hotfixes-stable-2024-06-17-11-43' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "Mainly MM singleton fixes. And a couple of ocfs2 regression fixes"

* tag 'mm-hotfixes-stable-2024-06-17-11-43' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  kcov: don't lose track of remote references during softirqs
  mm: shmem: fix getting incorrect lruvec when replacing a shmem folio
  mm/debug_vm_pgtable: drop RANDOM_ORVALUE trick
  mm: fix possible OOB in numa_rebuild_large_mapping()
  mm/migrate: fix kernel BUG at mm/compaction.c:2761!
  selftests: mm: make map_fixed_noreplace test names stable
  mm/memfd: add documentation for MFD_NOEXEC_SEAL MFD_EXEC
  mm: mmap: allow for the maximum number of bits for randomizing mmap_base by default
  gcov: add support for GCC 14
  zap_pid_ns_processes: clear TIF_NOTIFY_SIGNAL along with TIF_SIGPENDING
  mm: huge_memory: fix misused mapping_large_folio_support() for anon folios
  lib/alloc_tag: fix RCU imbalance in pgalloc_tag_get()
  lib/alloc_tag: do not register sysctl interface when CONFIG_SYSCTL=n
  MAINTAINERS: remove Lorenzo as vmalloc reviewer
  Revert "mm: init_mlocked_on_free_v3"
  mm/page_table_check: fix crash on ZONE_DEVICE
  gcc: disable '-Warray-bounds' for gcc-9
  ocfs2: fix NULL pointer dereference in ocfs2_abort_trigger()
  ocfs2: fix NULL pointer dereference in ocfs2_journal_dirty()

10 files changed, 59 insertions, 90 deletions

diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index b104a353b532..e4969fb54da3 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -40,22 +40,7 @@
  * Please refer Documentation/mm/arch_pgtable_helpers.rst for the semantics
  * expectations that are being validated here. All future changes in here
  * or the documentation need to be in sync.
- *
- * On s390 platform, the lower 4 bits are used to identify given page table
- * entry type. But these bits might affect the ability to clear entries with
- * pxx_clear() because of how dynamic page table folding works on s390. So
- * while loading up the entries do not change the lower 4 bits. It does not
- * have affect any other platform. Also avoid the 62nd bit on ppc64 that is
- * used to mark a pte entry.
  */
-#define S390_SKIP_MASK		GENMASK(3, 0)
-#if __BITS_PER_LONG == 64
-#define PPC64_SKIP_MASK		GENMASK(62, 62)
-#else
-#define PPC64_SKIP_MASK		0x0
-#endif
-#define ARCH_SKIP_MASK (S390_SKIP_MASK | PPC64_SKIP_MASK)
-#define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK)
 #define RANDOM_NZVALUE	GENMASK(7, 0)
 
 struct pgtable_debug_args {
@@ -511,8 +496,7 @@ static void __init pud_clear_tests(struct pgtable_debug_args *args)
 		return;
 
 	pr_debug("Validating PUD clear\n");
-	pud = __pud(pud_val(pud) | RANDOM_ORVALUE);
-	WRITE_ONCE(*args->pudp, pud);
+	WARN_ON(pud_none(pud));
 	pud_clear(args->pudp);
 	pud = READ_ONCE(*args->pudp);
 	WARN_ON(!pud_none(pud));
@@ -548,8 +532,7 @@ static void __init p4d_clear_tests(struct pgtable_debug_args *args)
 		return;
 
 	pr_debug("Validating P4D clear\n");
-	p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE);
-	WRITE_ONCE(*args->p4dp, p4d);
+	WARN_ON(p4d_none(p4d));
 	p4d_clear(args->p4dp);
 	p4d = READ_ONCE(*args->p4dp);
 	WARN_ON(!p4d_none(p4d));
@@ -582,8 +565,7 @@ static void __init pgd_clear_tests(struct pgtable_debug_args *args)
 		return;
 
 	pr_debug("Validating PGD clear\n");
-	pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE);
-	WRITE_ONCE(*args->pgdp, pgd);
+	WARN_ON(pgd_none(pgd));
 	pgd_clear(args->pgdp);
 	pgd = READ_ONCE(*args->pgdp);
 	WARN_ON(!pgd_none(pgd));
@@ -634,10 +616,8 @@ static void __init pte_clear_tests(struct pgtable_debug_args *args)
 	if (WARN_ON(!args->ptep))
 		return;
 
-#ifndef CONFIG_RISCV
-	pte = __pte(pte_val(pte) | RANDOM_ORVALUE);
-#endif
 	set_pte_at(args->mm, args->vaddr, args->ptep, pte);
+	WARN_ON(pte_none(pte));
 	flush_dcache_page(page);
 	barrier();
 	ptep_clear(args->mm, args->vaddr, args->ptep);
@@ -650,8 +630,7 @@ static void __init pmd_clear_tests(struct pgtable_debug_args *args)
 	pmd_t pmd = READ_ONCE(*args->pmdp);
 
 	pr_debug("Validating PMD clear\n");
-	pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE);
-	WRITE_ONCE(*args->pmdp, pmd);
+	WARN_ON(pmd_none(pmd));
 	pmd_clear(args->pmdp);
 	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(!pmd_none(pmd));
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 89932fd0f62e..db7946a0a28c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3009,30 +3009,36 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 	if (new_order >= folio_order(folio))
 		return -EINVAL;
 
-	/* Cannot split anonymous THP to order-1 */
-	if (new_order == 1 && folio_test_anon(folio)) {
-		VM_WARN_ONCE(1, "Cannot split to order-1 folio");
-		return -EINVAL;
-	}
-
-	if (new_order) {
-		/* Only swapping a whole PMD-mapped folio is supported */
-		if (folio_test_swapcache(folio))
+	if (folio_test_anon(folio)) {
+		/* order-1 is not supported for anonymous THP. */
+		if (new_order == 1) {
+			VM_WARN_ONCE(1, "Cannot split to order-1 folio");
 			return -EINVAL;
+		}
+	} else if (new_order) {
 		/* Split shmem folio to non-zero order not supported */
 		if (shmem_mapping(folio->mapping)) {
 			VM_WARN_ONCE(1,
 				"Cannot split shmem folio to non-0 order");
 			return -EINVAL;
 		}
-		/* No split if the file system does not support large folio */
-		if (!mapping_large_folio_support(folio->mapping)) {
+		/*
+		 * No split if the file system does not support large folio.
+		 * Note that we might still have THPs in such mappings due to
+		 * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping
+		 * does not actually support large folios properly.
+		 */
+		if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
+		    !mapping_large_folio_support(folio->mapping)) {
 			VM_WARN_ONCE(1,
 				"Cannot split file folio to non-0 order");
 			return -EINVAL;
 		}
 	}
 
+	/* Only swapping a whole PMD-mapped folio is supported */
+	if (folio_test_swapcache(folio) && new_order)
+		return -EINVAL;
 
 	is_hzp = is_huge_zero_folio(folio);
 	if (is_hzp) {
diff --git a/mm/internal.h b/mm/internal.h
index b2c75b12014e..c72c306761a4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -588,7 +588,6 @@ extern void __putback_isolated_page(struct page *page, unsigned int order,
 extern void memblock_free_pages(struct page *page, unsigned long pfn,
 					unsigned int order);
 extern void __free_pages_core(struct page *page, unsigned int order);
-extern void kernel_init_pages(struct page *page, int numpages);
 
 /*
  * This will have no effect, other than possibly generating a warning, if the
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36793e509f47..71fe2a95b8bd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -7745,8 +7745,7 @@ void __mem_cgroup_uncharge_folios(struct folio_batch *folios)
  * @new: Replacement folio.
  *
  * Charge @new as a replacement folio for @old. @old will
- * be uncharged upon free. This is only used by the page cache
- * (in replace_page_cache_folio()).
+ * be uncharged upon free.
  *
  * Both folios must be locked, @new->mapping must be set up.
  */
diff --git a/mm/memory.c b/mm/memory.c
index 0f47a533014e..25a77c4fe4a0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1507,12 +1507,6 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
 		if (unlikely(folio_mapcount(folio) < 0))
 			print_bad_pte(vma, addr, ptent, page);
 	}
-
-	if (want_init_mlocked_on_free() && folio_test_mlocked(folio) &&
-	    !delay_rmap && folio_test_anon(folio)) {
-		kernel_init_pages(page, folio_nr_pages(folio));
-	}
-
 	if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) {
 		*force_flush = true;
 		*force_break = true;
@@ -5106,10 +5100,16 @@ static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_stru
 				       bool ignore_writable, bool pte_write_upgrade)
 {
 	int nr = pte_pfn(fault_pte) - folio_pfn(folio);
-	unsigned long start = max(vmf->address - nr * PAGE_SIZE, vma->vm_start);
-	unsigned long end = min(vmf->address + (folio_nr_pages(folio) - nr) * PAGE_SIZE, vma->vm_end);
-	pte_t *start_ptep = vmf->pte - (vmf->address - start) / PAGE_SIZE;
-	unsigned long addr;
+	unsigned long start, end, addr = vmf->address;
+	unsigned long addr_start = addr - (nr << PAGE_SHIFT);
+	unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE);
+	pte_t *start_ptep;
+
+	/* Stay within the VMA and within the page table. */
+	start = max3(addr_start, pt_start, vma->vm_start);
+	end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE,
+		   vma->vm_end);
+	start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT);
 
 	/* Restore all PTEs' mapping of the large folio */
 	for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) {
diff --git a/mm/migrate.c b/mm/migrate.c
index dd04f578c19c..2cc5a68f6843 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1654,7 +1654,12 @@ static int migrate_pages_batch(struct list_head *from,
 
 			/*
 			 * The rare folio on the deferred split list should
-			 * be split now. It should not count as a failure.
+			 * be split now. It should not count as a failure:
+			 * but increment nr_failed because, without doing so,
+			 * migrate_pages() may report success with (split but
+			 * unmigrated) pages still on its fromlist; whereas it
+			 * always reports success when its fromlist is empty.
+			 *
 			 * Only check it without removing it from the list.
 			 * Since the folio can be on deferred_split_scan()
 			 * local list and removing it can cause the local list
@@ -1669,6 +1674,7 @@ static int migrate_pages_batch(struct list_head *from,
 			if (nr_pages > 2 &&
 			   !list_empty(&folio->_deferred_list)) {
 				if (try_split_folio(folio, split_folios) == 0) {
+					nr_failed++;
 					stats->nr_thp_split += is_thp;
 					stats->nr_split++;
 					continue;
diff --git a/mm/mm_init.c b/mm/mm_init.c
index f72b852bd5b8..3ec04933f7fd 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2523,9 +2523,6 @@ EXPORT_SYMBOL(init_on_alloc);
 DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
 EXPORT_SYMBOL(init_on_free);
 
-DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free);
-EXPORT_SYMBOL(init_mlocked_on_free);
-
 static bool _init_on_alloc_enabled_early __read_mostly
 				= IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON);
 static int __init early_init_on_alloc(char *buf)
@@ -2543,14 +2540,6 @@ static int __init early_init_on_free(char *buf)
 }
 early_param("init_on_free", early_init_on_free);
 
-static bool _init_mlocked_on_free_enabled_early __read_mostly
-				= IS_ENABLED(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON);
-static int __init early_init_mlocked_on_free(char *buf)
-{
-	return kstrtobool(buf, &_init_mlocked_on_free_enabled_early);
-}
-early_param("init_mlocked_on_free", early_init_mlocked_on_free);
-
 DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);
 
 /*
@@ -2578,21 +2567,12 @@ static void __init mem_debugging_and_hardening_init(void)
 	}
 #endif
 
-	if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early ||
-	    _init_mlocked_on_free_enabled_early) &&
+	if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) &&
 	    page_poisoning_requested) {
 		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
-			"will take precedence over init_on_alloc, init_on_free "
-			"and init_mlocked_on_free\n");
+			"will take precedence over init_on_alloc and init_on_free\n");
 		_init_on_alloc_enabled_early = false;
 		_init_on_free_enabled_early = false;
-		_init_mlocked_on_free_enabled_early = false;
-	}
-
-	if (_init_mlocked_on_free_enabled_early && _init_on_free_enabled_early) {
-		pr_info("mem auto-init: init_on_free is on, "
-			"will take precedence over init_mlocked_on_free\n");
-		_init_mlocked_on_free_enabled_early = false;
 	}
 
 	if (_init_on_alloc_enabled_early) {
@@ -2609,17 +2589,9 @@ static void __init mem_debugging_and_hardening_init(void)
 		static_branch_disable(&init_on_free);
 	}
 
-	if (_init_mlocked_on_free_enabled_early) {
-		want_check_pages = true;
-		static_branch_enable(&init_mlocked_on_free);
-	} else {
-		static_branch_disable(&init_mlocked_on_free);
-	}
-
-	if (IS_ENABLED(CONFIG_KMSAN) && (_init_on_alloc_enabled_early ||
-	    _init_on_free_enabled_early || _init_mlocked_on_free_enabled_early))
-		pr_info("mem auto-init: please make sure init_on_alloc, init_on_free and "
-			"init_mlocked_on_free are disabled when running KMSAN\n");
+	if (IS_ENABLED(CONFIG_KMSAN) &&
+	    (_init_on_alloc_enabled_early || _init_on_free_enabled_early))
+		pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n");
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	if (debug_pagealloc_enabled()) {
@@ -2658,10 +2630,9 @@ static void __init report_meminit(void)
 	else
 		stack = "off";
 
-	pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s, mlocked free:%s\n",
+	pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n",
 		stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off",
-		want_init_on_free() ? "on" : "off",
-		want_init_mlocked_on_free() ? "on" : "off");
+		want_init_on_free() ? "on" : "off");
 	if (want_init_on_free())
 		pr_info("mem auto-init: clearing system memory may take some time...\n");
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 222299b5c0e6..7300aa9f14b0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1016,7 +1016,7 @@ static inline bool should_skip_kasan_poison(struct page *page)
 	return page_kasan_tag(page) == KASAN_TAG_KERNEL;
 }
 
-void kernel_init_pages(struct page *page, int numpages)
+static void kernel_init_pages(struct page *page, int numpages)
 {
 	int i;
 
diff --git a/mm/page_table_check.c b/mm/page_table_check.c
index 4169576bed72..509c6ef8de40 100644
--- a/mm/page_table_check.c
+++ b/mm/page_table_check.c
@@ -73,6 +73,9 @@ static void page_table_check_clear(unsigned long pfn, unsigned long pgcnt)
 	page = pfn_to_page(pfn);
 	page_ext = page_ext_get(page);
 
+	if (!page_ext)
+		return;
+
 	BUG_ON(PageSlab(page));
 	anon = PageAnon(page);
 
@@ -110,6 +113,9 @@ static void page_table_check_set(unsigned long pfn, unsigned long pgcnt,
 	page = pfn_to_page(pfn);
 	page_ext = page_ext_get(page);
 
+	if (!page_ext)
+		return;
+
 	BUG_ON(PageSlab(page));
 	anon = PageAnon(page);
 
@@ -140,7 +146,10 @@ void __page_table_check_zero(struct page *page, unsigned int order)
 	BUG_ON(PageSlab(page));
 
 	page_ext = page_ext_get(page);
-	BUG_ON(!page_ext);
+
+	if (!page_ext)
+		return;
+
 	for (i = 0; i < (1ul << order); i++) {
 		struct page_table_check *ptc = get_page_table_check(page_ext);
 
diff --git a/mm/shmem.c b/mm/shmem.c
index f5d60436b604..a8b181a63402 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1786,7 +1786,7 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
 	xa_lock_irq(&swap_mapping->i_pages);
 	error = shmem_replace_entry(swap_mapping, swap_index, old, new);
 	if (!error) {
-		mem_cgroup_migrate(old, new);
+		mem_cgroup_replace_folio(old, new);
 		__lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1);
 		__lruvec_stat_mod_folio(new, NR_SHMEM, 1);
 		__lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1);