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, 34 insertions, 60 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 4ddaf6ad73ef..768e5261fdae 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -116,9 +116,30 @@ extern struct kobj_attribute shmem_enabled_attr;
 
 extern unsigned long transparent_hugepage_flags;
 
+#define hugepage_flags_enabled()					       \
+	(transparent_hugepage_flags &				       \
+	 ((1<<TRANSPARENT_HUGEPAGE_FLAG) |		       \
+	  (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)))
+#define hugepage_flags_always()				\
+	(transparent_hugepage_flags &			\
+	 (1<<TRANSPARENT_HUGEPAGE_FLAG))
+
+/*
+ * Do the below checks:
+ *   - For file vma, check if the linear page offset of vma is
+ *     HPAGE_PMD_NR aligned within the file.  The hugepage is
+ *     guaranteed to be hugepage-aligned within the file, but we must
+ *     check that the PMD-aligned addresses in the VMA map to
+ *     PMD-aligned offsets within the file, else the hugepage will
+ *     not be PMD-mappable.
+ *   - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE
+ *     area.
+ */
 static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
-		unsigned long haddr)
+		unsigned long addr)
 {
+	unsigned long haddr;
+
 	/* Don't have to check pgoff for anonymous vma */
 	if (!vma_is_anonymous(vma)) {
 		if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
@@ -126,53 +147,13 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
 			return false;
 	}
 
-	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
-		return false;
-	return true;
-}
+	haddr = addr & HPAGE_PMD_MASK;
 
-static inline bool transhuge_vma_enabled(struct vm_area_struct *vma,
-					  unsigned long vm_flags)
-{
-	/* Explicitly disabled through madvise. */
-	if ((vm_flags & VM_NOHUGEPAGE) ||
-	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
+	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
 		return false;
 	return true;
 }
 
-/*
- * to be used on vmas which are known to support THP.
- * Use transparent_hugepage_active otherwise
- */
-static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
-{
-
-	/*
-	 * If the hardware/firmware marked hugepage support disabled.
-	 */
-	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX))
-		return false;
-
-	if (!transhuge_vma_enabled(vma, vma->vm_flags))
-		return false;
-
-	if (vma_is_temporary_stack(vma))
-		return false;
-
-	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG))
-		return true;
-
-	if (vma_is_dax(vma))
-		return true;
-
-	if (transparent_hugepage_flags &
-				(1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))
-		return !!(vma->vm_flags & VM_HUGEPAGE);
-
-	return false;
-}
-
 static inline bool file_thp_enabled(struct vm_area_struct *vma)
 {
 	struct inode *inode;
@@ -187,7 +168,9 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
 	       !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
 }
 
-bool transparent_hugepage_active(struct vm_area_struct *vma);
+bool hugepage_vma_check(struct vm_area_struct *vma,
+			unsigned long vm_flags,
+			bool smaps, bool in_pf);
 
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
@@ -290,7 +273,7 @@ static inline bool is_huge_zero_page(struct page *page)
 
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
-	return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd);
+	return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd);
 }
 
 static inline bool is_huge_zero_pud(pud_t pud)
@@ -311,8 +294,8 @@ static inline bool thp_migration_supported(void)
 static inline struct list_head *page_deferred_list(struct page *page)
 {
 	/*
-	 * Global or memcg deferred list in the second tail pages is
-	 * occupied by compound_head.
+	 * See organization of tail pages of compound page in
+	 * "struct page" definition.
 	 */
 	return &page[2].deferred_list;
 }
@@ -331,24 +314,15 @@ static inline bool folio_test_pmd_mappable(struct folio *folio)
 	return false;
 }
 
-static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
-{
-	return false;
-}
-
-static inline bool transparent_hugepage_active(struct vm_area_struct *vma)
-{
-	return false;
-}
-
 static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
-		unsigned long haddr)
+		unsigned long addr)
 {
 	return false;
 }
 
-static inline bool transhuge_vma_enabled(struct vm_area_struct *vma,
-					  unsigned long vm_flags)
+static inline bool hugepage_vma_check(struct vm_area_struct *vma,
+				       unsigned long vm_flags,
+				       bool smaps, bool in_pf)
 {
 	return false;
 }