Merge tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Most of the MM queue. A few things are still pending.

  Liam's maple tree rework didn't make it. This has resulted in a few
  other minor patch series being held over for next time.

  Multi-gen LRU still isn't merged as we were waiting for mapletree to
  stabilize. The current plan is to merge MGLRU into -mm soon and to
  later reintroduce mapletree, with a view to hopefully getting both
  into 6.1-rc1.

  Summary:

   - The usual batches of cleanups from Baoquan He, Muchun Song, Miaohe
     Lin, Yang Shi, Anshuman Khandual and Mike Rapoport

   - Some kmemleak fixes from Patrick Wang and Waiman Long

   - DAMON updates from SeongJae Park

   - memcg debug/visibility work from Roman Gushchin

   - vmalloc speedup from Uladzislau Rezki

   - more folio conversion work from Matthew Wilcox

   - enhancements for coherent device memory mapping from Alex Sierra

   - addition of shared pages tracking and CoW support for fsdax, from
     Shiyang Ruan

   - hugetlb optimizations from Mike Kravetz

   - Mel Gorman has contributed some pagealloc changes to improve
     latency and realtime behaviour.

   - mprotect soft-dirty checking has been improved by Peter Xu

   - Many other singleton patches all over the place"

 [ XFS merge from hell as per Darrick Wong in

   https://lore.kernel.org/all/YshKnxb4VwXycPO8@magnolia/ ]

* tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (282 commits)
  tools/testing/selftests/vm/hmm-tests.c: fix build
  mm: Kconfig: fix typo
  mm: memory-failure: convert to pr_fmt()
  mm: use is_zone_movable_page() helper
  hugetlbfs: fix inaccurate comment in hugetlbfs_statfs()
  hugetlbfs: cleanup some comments in inode.c
  hugetlbfs: remove unneeded header file
  hugetlbfs: remove unneeded hugetlbfs_ops forward declaration
  hugetlbfs: use helper macro SZ_1{K,M}
  mm: cleanup is_highmem()
  mm/hmm: add a test for cross device private faults
  selftests: add soft-dirty into run_vmtests.sh
  selftests: soft-dirty: add test for mprotect
  mm/mprotect: fix soft-dirty check in can_change_pte_writable()
  mm: memcontrol: fix potential oom_lock recursion deadlock
  mm/gup.c: fix formatting in check_and_migrate_movable_page()
  xfs: fail dax mount if reflink is enabled on a partition
  mm/memcontrol.c: remove the redundant updating of stats_flush_threshold
  userfaultfd: don't fail on unrecognized features
  hugetlb_cgroup: fix wrong hugetlb cgroup numa stat
  ...

1 files changed, 17 insertions, 10 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 1c6027adc542..4ba73f5aa8bb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -624,6 +624,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 		if (is_zero_pfn(pfn))
 			return NULL;
 		if (pte_devmap(pte))
+		/*
+		 * NOTE: New users of ZONE_DEVICE will not set pte_devmap()
+		 * and will have refcounts incremented on their struct pages
+		 * when they are inserted into PTEs, thus they are safe to
+		 * return here. Legacy ZONE_DEVICE pages that set pte_devmap()
+		 * do not have refcounts. Example of legacy ZONE_DEVICE is
+		 * MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers.
+		 */
 			return NULL;
 
 		print_bad_pte(vma, addr, pte, NULL);
@@ -736,7 +744,7 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
 		 * Currently device exclusive access only supports anonymous
 		 * memory so the entry shouldn't point to a filebacked page.
 		 */
-		WARN_ON_ONCE(!PageAnon(page));
+		WARN_ON_ONCE(1);
 
 	set_pte_at(vma->vm_mm, address, ptep, pte);
 
@@ -1245,7 +1253,7 @@ vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 	if (userfaultfd_wp(dst_vma))
 		return true;
 
-	if (src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP))
+	if (src_vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
 		return true;
 
 	if (src_vma->anon_vma)
@@ -3020,7 +3028,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
 		balance_dirty_pages_ratelimited(mapping);
 		if (fpin) {
 			fput(fpin);
-			return VM_FAULT_RETRY;
+			return VM_FAULT_COMPLETED;
 		}
 	}
 
@@ -4434,10 +4442,6 @@ late_initcall(fault_around_debugfs);
  * It uses vm_ops->map_pages() to map the pages, which skips the page if it's
  * not ready to be mapped: not up-to-date, locked, etc.
  *
- * This function is called with the page table lock taken. In the split ptlock
- * case the page table lock only protects only those entries which belong to
- * the page table corresponding to the fault address.
- *
  * This function doesn't cross the VMA boundaries, in order to call map_pages()
  * only once.
  *
@@ -4696,7 +4700,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	pte = pte_modify(old_pte, vma->vm_page_prot);
 
 	page = vm_normal_page(vma, vmf->address, pte);
-	if (!page)
+	if (!page || is_zone_device_page(page))
 		goto out_map;
 
 	/* TODO: handle PTE-mapped THP */
@@ -4966,6 +4970,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		.gfp_mask = __get_fault_gfp_mask(vma),
 	};
 	struct mm_struct *mm = vma->vm_mm;
+	unsigned long vm_flags = vma->vm_flags;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	vm_fault_t ret;
@@ -4979,7 +4984,8 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	if (!vmf.pud)
 		return VM_FAULT_OOM;
 retry_pud:
-	if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) {
+	if (pud_none(*vmf.pud) &&
+	    hugepage_vma_check(vma, vm_flags, false, true)) {
 		ret = create_huge_pud(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
@@ -5012,7 +5018,8 @@ retry_pud:
 	if (pud_trans_unstable(vmf.pud))
 		goto retry_pud;
 
-	if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) {
+	if (pmd_none(*vmf.pmd) &&
+	    hugepage_vma_check(vma, vm_flags, false, true)) {
 		ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;