Merge tag 'mm-hotfixes-stable-2023-02-02-19-24-2' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "25 hotfixes, mainly for MM.  13 are cc:stable"

* tag 'mm-hotfixes-stable-2023-02-02-19-24-2' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (26 commits)
  mm: memcg: fix NULL pointer in mem_cgroup_track_foreign_dirty_slowpath()
  Kconfig.debug: fix the help description in SCHED_DEBUG
  mm/swapfile: add cond_resched() in get_swap_pages()
  mm: use stack_depot_early_init for kmemleak
  Squashfs: fix handling and sanity checking of xattr_ids count
  sh: define RUNTIME_DISCARD_EXIT
  highmem: round down the address passed to kunmap_flush_on_unmap()
  migrate: hugetlb: check for hugetlb shared PMD in node migration
  mm: hugetlb: proc: check for hugetlb shared PMD in /proc/PID/smaps
  mm/MADV_COLLAPSE: catch !none !huge !bad pmd lookups
  Revert "mm: kmemleak: alloc gray object for reserved region with direct map"
  freevxfs: Kconfig: fix spelling
  maple_tree: should get pivots boundary by type
  .mailmap: update e-mail address for Eugen Hristev
  mm, mremap: fix mremap() expanding for vma's with vm_ops->close()
  squashfs: harden sanity check in squashfs_read_xattr_id_table
  ia64: fix build error due to switch case label appearing next to declaration
  mm: multi-gen LRU: fix crash during cgroup migration
  Revert "mm: add nodes= arg to memory.reclaim"
  zsmalloc: fix a race with deferred_handles storing
  ...

1 files changed, 21 insertions, 1 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 79be13133322..90acfea40c13 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -847,6 +847,10 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 	return SCAN_SUCCEED;
 }
 
+/*
+ * See pmd_trans_unstable() for how the result may change out from
+ * underneath us, even if we hold mmap_lock in read.
+ */
 static int find_pmd_or_thp_or_none(struct mm_struct *mm,
 				   unsigned long address,
 				   pmd_t **pmd)
@@ -865,8 +869,12 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm,
 #endif
 	if (pmd_none(pmde))
 		return SCAN_PMD_NONE;
+	if (!pmd_present(pmde))
+		return SCAN_PMD_NULL;
 	if (pmd_trans_huge(pmde))
 		return SCAN_PMD_MAPPED;
+	if (pmd_devmap(pmde))
+		return SCAN_PMD_NULL;
 	if (pmd_bad(pmde))
 		return SCAN_PMD_NULL;
 	return SCAN_SUCCEED;
@@ -1642,7 +1650,7 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff,
 		 * has higher cost too. It would also probably require locking
 		 * the anon_vma.
 		 */
-		if (vma->anon_vma) {
+		if (READ_ONCE(vma->anon_vma)) {
 			result = SCAN_PAGE_ANON;
 			goto next;
 		}
@@ -1671,6 +1679,18 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff,
 		if ((cc->is_khugepaged || is_target) &&
 		    mmap_write_trylock(mm)) {
 			/*
+			 * Re-check whether we have an ->anon_vma, because
+			 * collapse_and_free_pmd() requires that either no
+			 * ->anon_vma exists or the anon_vma is locked.
+			 * We already checked ->anon_vma above, but that check
+			 * is racy because ->anon_vma can be populated under the
+			 * mmap lock in read mode.
+			 */
+			if (vma->anon_vma) {
+				result = SCAN_PAGE_ANON;
+				goto unlock_next;
+			}
+			/*
 			 * When a vma is registered with uffd-wp, we can't
 			 * recycle the pmd pgtable because there can be pte
 			 * markers installed.  Skip it only, so the rest mm/vma