Merge tag 'mm-hotfixes-stable-2023-01-16-15-23' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc hotfixes from Andrew Morton:
 "21 hotfixes. Thirteen of these address pre-6.1 issues and hence have
  the cc:stable tag"

* tag 'mm-hotfixes-stable-2023-01-16-15-23' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (21 commits)
  init/Kconfig: fix typo (usafe -> unsafe)
  nommu: fix split_vma() map_count error
  nommu: fix do_munmap() error path
  nommu: fix memory leak in do_mmap() error path
  MAINTAINERS: update Robert Foss' email address
  proc: fix PIE proc-empty-vm, proc-pid-vm tests
  mm: update mmap_sem comments to refer to mmap_lock
  include/linux/mm: fix release_pages_arg kernel doc comment
  lib/win_minmax: use /* notation for regular comments
  kasan: mark kasan_kunit_executing as static
  nilfs2: fix general protection fault in nilfs_btree_insert()
  Docs/admin-guide/mm/zswap: remove zsmalloc's lack of writeback warning
  mm/hugetlb: pre-allocate pgtable pages for uffd wr-protects
  hugetlb: unshare some PMDs when splitting VMAs
  mm: fix vma->anon_name memory leak for anonymous shmem VMAs
  mm/shmem: restore SHMEM_HUGE_DENY precedence over MADV_COLLAPSE
  mm/MADV_COLLAPSE: don't expand collapse when vm_end is past requested end
  mm/userfaultfd: enable writenotify while userfaultfd-wp is enabled for a VMA
  mm/khugepaged: fix collapse_pte_mapped_thp() to allow anon_vma
  mm/hugetlb: fix uffd-wp handling for migration entries in hugetlb_change_protection()
  ...

7 files changed, 87 insertions, 55 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index db895230ee7e..7fcdb98c9e68 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -94,6 +94,8 @@ static int hugetlb_acct_memory(struct hstate *h, long delta);
 static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
 static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -1181,7 +1183,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 
 /*
  * Reset and decrement one ref on hugepage private reservation.
- * Called with mm->mmap_sem writer semaphore held.
+ * Called with mm->mmap_lock writer semaphore held.
  * This function should be only used by move_vma() and operate on
  * same sized vma. It should never come here with last ref on the
  * reservation.
@@ -4834,6 +4836,25 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
 {
 	if (addr & ~(huge_page_mask(hstate_vma(vma))))
 		return -EINVAL;
+
+	/*
+	 * PMD sharing is only possible for PUD_SIZE-aligned address ranges
+	 * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this
+	 * split, unshare PMDs in the PUD_SIZE interval surrounding addr now.
+	 */
+	if (addr & ~PUD_MASK) {
+		/*
+		 * hugetlb_vm_op_split is called right before we attempt to
+		 * split the VMA. We will need to unshare PMDs in the old and
+		 * new VMAs, so let's unshare before we split.
+		 */
+		unsigned long floor = addr & PUD_MASK;
+		unsigned long ceil = floor + PUD_SIZE;
+
+		if (floor >= vma->vm_start && ceil <= vma->vm_end)
+			hugetlb_unshare_pmds(vma, floor, ceil);
+	}
+
 	return 0;
 }
 
@@ -5131,7 +5152,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
 
 	/*
 	 * We don't have to worry about the ordering of src and dst ptlocks
-	 * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock.
+	 * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock.
 	 */
 	if (src_ptl != dst_ptl)
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -6639,8 +6660,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address, psize);
 		if (!ptep) {
-			address |= last_addr_mask;
-			continue;
+			if (!uffd_wp) {
+				address |= last_addr_mask;
+				continue;
+			}
+			/*
+			 * Userfaultfd wr-protect requires pgtable
+			 * pre-allocations to install pte markers.
+			 */
+			ptep = huge_pte_alloc(mm, vma, address, psize);
+			if (!ptep)
+				break;
 		}
 		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, vma, address, ptep)) {
@@ -6658,16 +6688,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 		pte = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
-			spin_unlock(ptl);
-			continue;
-		}
-		if (unlikely(is_hugetlb_entry_migration(pte))) {
+			/* Nothing to do. */
+		} else if (unlikely(is_hugetlb_entry_migration(pte))) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
 			struct page *page = pfn_swap_entry_to_page(entry);
+			pte_t newpte = pte;
 
-			if (!is_readable_migration_entry(entry)) {
-				pte_t newpte;
-
+			if (is_writable_migration_entry(entry)) {
 				if (PageAnon(page))
 					entry = make_readable_exclusive_migration_entry(
 								swp_offset(entry));
@@ -6675,25 +6702,22 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 					entry = make_readable_migration_entry(
 								swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
-				if (uffd_wp)
-					newpte = pte_swp_mkuffd_wp(newpte);
-				else if (uffd_wp_resolve)
-					newpte = pte_swp_clear_uffd_wp(newpte);
-				set_huge_pte_at(mm, address, ptep, newpte);
 				pages++;
 			}
-			spin_unlock(ptl);
-			continue;
-		}
-		if (unlikely(pte_marker_uffd_wp(pte))) {
-			/*
-			 * This is changing a non-present pte into a none pte,
-			 * no need for huge_ptep_modify_prot_start/commit().
-			 */
+
+			if (uffd_wp)
+				newpte = pte_swp_mkuffd_wp(newpte);
+			else if (uffd_wp_resolve)
+				newpte = pte_swp_clear_uffd_wp(newpte);
+			if (!pte_same(pte, newpte))
+				set_huge_pte_at(mm, address, ptep, newpte);
+		} else if (unlikely(is_pte_marker(pte))) {
+			/* No other markers apply for now. */
+			WARN_ON_ONCE(!pte_marker_uffd_wp(pte));
 			if (uffd_wp_resolve)
+				/* Safe to modify directly (non-present->none). */
 				huge_pte_clear(mm, address, ptep, psize);
-		}
-		if (!huge_pte_none(pte)) {
+		} else if (!huge_pte_none(pte)) {
 			pte_t old_pte;
 			unsigned int shift = huge_page_shift(hstate_vma(vma));
 
@@ -7328,26 +7352,21 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re
 	}
 }
 
-/*
- * This function will unconditionally remove all the shared pmd pgtable entries
- * within the specific vma for a hugetlbfs memory range.
- */
-void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+				   unsigned long start,
+				   unsigned long end)
 {
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct mm_struct *mm = vma->vm_mm;
 	struct mmu_notifier_range range;
-	unsigned long address, start, end;
+	unsigned long address;
 	spinlock_t *ptl;
 	pte_t *ptep;
 
 	if (!(vma->vm_flags & VM_MAYSHARE))
 		return;
 
-	start = ALIGN(vma->vm_start, PUD_SIZE);
-	end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
-
 	if (start >= end)
 		return;
 
@@ -7379,6 +7398,16 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 	mmu_notifier_invalidate_range_end(&range);
 }
 
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+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));
+}
+
 #ifdef CONFIG_CMA
 static bool cma_reserve_called __initdata;
 
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 1d02757e90a3..22598b20c7b7 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(kasan_restore_multi_shot);
  * Whether the KASAN KUnit test suite is currently being executed.
  * Updated in kasan_test.c.
  */
-bool kasan_kunit_executing;
+static bool kasan_kunit_executing;
 
 void kasan_kunit_test_suite_start(void)
 {
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 5cb401aa2b9d..79be13133322 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1460,14 +1460,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
 		return SCAN_VMA_CHECK;
 
-	/*
-	 * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings
-	 * that got written to. Without this, we'd have to also lock the
-	 * anon_vma if one exists.
-	 */
-	if (vma->anon_vma)
-		return SCAN_VMA_CHECK;
-
 	/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
 	if (userfaultfd_wp(vma))
 		return SCAN_PTE_UFFD_WP;
@@ -1567,8 +1559,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	}
 
 	/* step 4: remove pte entries */
+	/* we make no change to anon, but protect concurrent anon page lookup */
+	if (vma->anon_vma)
+		anon_vma_lock_write(vma->anon_vma);
+
 	collapse_and_free_pmd(mm, vma, haddr, pmd);
 
+	if (vma->anon_vma)
+		anon_vma_unlock_write(vma->anon_vma);
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 
 maybe_install_pmd:
@@ -2649,7 +2647,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 				goto out_nolock;
 			}
 
-			hend = vma->vm_end & HPAGE_PMD_MASK;
+			hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
 		}
 		mmap_assert_locked(mm);
 		memset(cc->node_load, 0, sizeof(cc->node_load));
diff --git a/mm/madvise.c b/mm/madvise.c
index a56a6d17e201..b6ea204d4e23 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -130,7 +130,7 @@ static int replace_anon_vma_name(struct vm_area_struct *vma,
 #endif /* CONFIG_ANON_VMA_NAME */
 /*
  * Update the vm_flags on region of a vma, splitting it or merging it as
- * necessary.  Must be called with mmap_sem held for writing;
+ * necessary.  Must be called with mmap_lock held for writing;
  * Caller should ensure anon_name stability by raising its refcount even when
  * anon_name belongs to a valid vma because this function might free that vma.
  */
diff --git a/mm/mmap.c b/mm/mmap.c
index 87d929316d57..425a9349e610 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1524,6 +1524,10 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 	if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma))
 		return 1;
 
+	/* Do we need write faults for uffd-wp tracking? */
+	if (userfaultfd_wp(vma))
+		return 1;
+
 	/* Specialty mapping? */
 	if (vm_flags & VM_PFNMAP)
 		return 0;
@@ -2290,7 +2294,7 @@ static inline int munmap_sidetree(struct vm_area_struct *vma,
  * @start: The aligned start address to munmap.
  * @end: The aligned end address to munmap.
  * @uf: The userfaultfd list_head
- * @downgrade: Set to true to attempt a write downgrade of the mmap_sem
+ * @downgrade: Set to true to attempt a write downgrade of the mmap_lock
  *
  * If @downgrade is true, check return code for potential release of the lock.
  */
@@ -2465,7 +2469,7 @@ map_count_exceeded:
  * @len: The length of the range to munmap
  * @uf: The userfaultfd list_head
  * @downgrade: set to true if the user wants to attempt to write_downgrade the
- * mmap_sem
+ * mmap_lock
  *
  * This function takes a @mas that is either pointing to the previous VMA or set
  * to MA_START and sets it up to remove the mapping(s).  The @len will be
diff --git a/mm/nommu.c b/mm/nommu.c
index 214c70e1d059..5b83938ecb67 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -559,7 +559,6 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas)
 
 static void setup_vma_to_mm(struct vm_area_struct *vma, struct mm_struct *mm)
 {
-	mm->map_count++;
 	vma->vm_mm = mm;
 
 	/* add the VMA to the mapping */
@@ -587,6 +586,7 @@ static void mas_add_vma_to_mm(struct ma_state *mas, struct mm_struct *mm,
 	BUG_ON(!vma->vm_region);
 
 	setup_vma_to_mm(vma, mm);
+	mm->map_count++;
 
 	/* add the VMA to the tree */
 	vma_mas_store(vma, mas);
@@ -1240,6 +1240,7 @@ share:
 error_just_free:
 	up_write(&nommu_region_sem);
 error:
+	mas_destroy(&mas);
 	if (region->vm_file)
 		fput(region->vm_file);
 	kmem_cache_free(vm_region_jar, region);
@@ -1250,7 +1251,6 @@ error:
 
 sharing_violation:
 	up_write(&nommu_region_sem);
-	mas_destroy(&mas);
 	pr_warn("Attempt to share mismatched mappings\n");
 	ret = -EINVAL;
 	goto error;
@@ -1347,6 +1347,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vma->vm_file)
 		return -ENOMEM;
 
+	mm = vma->vm_mm;
 	if (mm->map_count >= sysctl_max_map_count)
 		return -ENOMEM;
 
@@ -1398,6 +1399,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	mas_set_range(&mas, vma->vm_start, vma->vm_end - 1);
 	mas_store(&mas, vma);
 	vma_mas_store(new, &mas);
+	mm->map_count++;
 	return 0;
 
 err_mas_preallocate:
@@ -1509,7 +1511,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list
 erase_whole_vma:
 	if (delete_vma_from_mm(vma))
 		ret = -ENOMEM;
-	delete_vma(mm, vma);
+	else
+		delete_vma(mm, vma);
 	return ret;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index c301487be5fb..0005ab2c29af 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -478,12 +478,10 @@ bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode,
 	if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
 	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
 		return false;
-	if (shmem_huge_force)
-		return true;
-	if (shmem_huge == SHMEM_HUGE_FORCE)
-		return true;
 	if (shmem_huge == SHMEM_HUGE_DENY)
 		return false;
+	if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE)
+		return true;
 
 	switch (SHMEM_SB(inode->i_sb)->huge) {
 	case SHMEM_HUGE_ALWAYS: