Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Almost all of MM here. A few things are still getting finished off,
  reviewed, etc.

   - Yang Shi has improved the behaviour of khugepaged collapsing of
     readonly file-backed transparent hugepages.

   - Johannes Weiner has arranged for zswap memory use to be tracked and
     managed on a per-cgroup basis.

   - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for
     runtime enablement of the recent huge page vmemmap optimization
     feature.

   - Baolin Wang contributes a series to fix some issues around hugetlb
     pagetable invalidation.

   - Zhenwei Pi has fixed some interactions between hwpoisoned pages and
     virtualization.

   - Tong Tiangen has enabled the use of the presently x86-only
     page_table_check debugging feature on arm64 and riscv.

   - David Vernet has done some fixup work on the memcg selftests.

   - Peter Xu has taught userfaultfd to handle write protection faults
     against shmem- and hugetlbfs-backed files.

   - More DAMON development from SeongJae Park - adding online tuning of
     the feature and support for monitoring of fixed virtual address
     ranges. Also easier discovery of which monitoring operations are
     available.

   - Nadav Amit has done some optimization of TLB flushing during
     mprotect().

   - Neil Brown continues to labor away at improving our swap-over-NFS
     support.

   - David Hildenbrand has some fixes to anon page COWing versus
     get_user_pages().

   - Peng Liu fixed some errors in the core hugetlb code.

   - Joao Martins has reduced the amount of memory consumed by
     device-dax's compound devmaps.

   - Some cleanups of the arch-specific pagemap code from Anshuman
     Khandual.

   - Muchun Song has found and fixed some errors in the TLB flushing of
     transparent hugepages.

   - Roman Gushchin has done more work on the memcg selftests.

  ... and, of course, many smaller fixes and cleanups. Notably, the
  customary million cleanup serieses from Miaohe Lin"

* tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits)
  mm: kfence: use PAGE_ALIGNED helper
  selftests: vm: add the "settings" file with timeout variable
  selftests: vm: add "test_hmm.sh" to TEST_FILES
  selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests
  selftests: vm: add migration to the .gitignore
  selftests/vm/pkeys: fix typo in comment
  ksm: fix typo in comment
  selftests: vm: add process_mrelease tests
  Revert "mm/vmscan: never demote for memcg reclaim"
  mm/kfence: print disabling or re-enabling message
  include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace"
  include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion"
  mm: fix a potential infinite loop in start_isolate_page_range()
  MAINTAINERS: add Muchun as co-maintainer for HugeTLB
  zram: fix Kconfig dependency warning
  mm/shmem: fix shmem folio swapoff hang
  cgroup: fix an error handling path in alloc_pagecache_max_30M()
  mm: damon: use HPAGE_PMD_SIZE
  tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
  nodemask.h: fix compilation error with GCC12
  ...

1 files changed, 111 insertions, 13 deletions

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index d356ab4047f7..fe220df499f1 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -13,10 +13,10 @@
  * get good packing density in that tree, so the index should be dense in
  * the low-order bits.
  *
- * We arrange the `type' and `offset' fields so that `type' is at the seven
+ * We arrange the `type' and `offset' fields so that `type' is at the six
  * high-order bits of the swp_entry_t and `offset' is right-aligned in the
  * remaining bits.  Although `type' itself needs only five bits, we allow for
- * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry().
+ * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry().
  *
  * swp_entry_t's are *never* stored anywhere in their arch-dependent format.
  */
@@ -26,6 +26,8 @@
 /* Clear all flags but only keep swp_entry_t related information */
 static inline pte_t pte_swp_clear_flags(pte_t pte)
 {
+	if (pte_swp_exclusive(pte))
+		pte = pte_swp_clear_exclusive(pte);
 	if (pte_swp_soft_dirty(pte))
 		pte = pte_swp_clear_soft_dirty(pte);
 	if (pte_swp_uffd_wp(pte))
@@ -194,6 +196,7 @@ static inline bool is_writable_device_exclusive_entry(swp_entry_t entry)
 static inline int is_migration_entry(swp_entry_t entry)
 {
 	return unlikely(swp_type(entry) == SWP_MIGRATION_READ ||
+			swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE ||
 			swp_type(entry) == SWP_MIGRATION_WRITE);
 }
 
@@ -202,11 +205,26 @@ static inline int is_writable_migration_entry(swp_entry_t entry)
 	return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE);
 }
 
+static inline int is_readable_migration_entry(swp_entry_t entry)
+{
+	return unlikely(swp_type(entry) == SWP_MIGRATION_READ);
+}
+
+static inline int is_readable_exclusive_migration_entry(swp_entry_t entry)
+{
+	return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE);
+}
+
 static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
 {
 	return swp_entry(SWP_MIGRATION_READ, offset);
 }
 
+static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset)
+{
+	return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset);
+}
+
 static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
 {
 	return swp_entry(SWP_MIGRATION_WRITE, offset);
@@ -224,6 +242,11 @@ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
 	return swp_entry(0, 0);
 }
 
+static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset)
+{
+	return swp_entry(0, 0);
+}
+
 static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
 {
 	return swp_entry(0, 0);
@@ -244,9 +267,92 @@ static inline int is_writable_migration_entry(swp_entry_t entry)
 {
 	return 0;
 }
+static inline int is_readable_migration_entry(swp_entry_t entry)
+{
+	return 0;
+}
 
 #endif
 
+typedef unsigned long pte_marker;
+
+#define  PTE_MARKER_UFFD_WP  BIT(0)
+#define  PTE_MARKER_MASK     (PTE_MARKER_UFFD_WP)
+
+#ifdef CONFIG_PTE_MARKER
+
+static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
+{
+	return swp_entry(SWP_PTE_MARKER, marker);
+}
+
+static inline bool is_pte_marker_entry(swp_entry_t entry)
+{
+	return swp_type(entry) == SWP_PTE_MARKER;
+}
+
+static inline pte_marker pte_marker_get(swp_entry_t entry)
+{
+	return swp_offset(entry) & PTE_MARKER_MASK;
+}
+
+static inline bool is_pte_marker(pte_t pte)
+{
+	return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte));
+}
+
+#else /* CONFIG_PTE_MARKER */
+
+static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
+{
+	/* This should never be called if !CONFIG_PTE_MARKER */
+	WARN_ON_ONCE(1);
+	return swp_entry(0, 0);
+}
+
+static inline bool is_pte_marker_entry(swp_entry_t entry)
+{
+	return false;
+}
+
+static inline pte_marker pte_marker_get(swp_entry_t entry)
+{
+	return 0;
+}
+
+static inline bool is_pte_marker(pte_t pte)
+{
+	return false;
+}
+
+#endif /* CONFIG_PTE_MARKER */
+
+static inline pte_t make_pte_marker(pte_marker marker)
+{
+	return swp_entry_to_pte(make_pte_marker_entry(marker));
+}
+
+/*
+ * This is a special version to check pte_none() just to cover the case when
+ * the pte is a pte marker.  It existed because in many cases the pte marker
+ * should be seen as a none pte; it's just that we have stored some information
+ * onto the none pte so it becomes not-none any more.
+ *
+ * It should be used when the pte is file-backed, ram-based and backing
+ * userspace pages, like shmem.  It is not needed upon pgtables that do not
+ * support pte markers at all.  For example, it's not needed on anonymous
+ * memory, kernel-only memory (including when the system is during-boot),
+ * non-ram based generic file-system.  It's fine to be used even there, but the
+ * extra pte marker check will be pure overhead.
+ *
+ * For systems configured with !CONFIG_PTE_MARKER this will be automatically
+ * optimized to pte_none().
+ */
+static inline int pte_none_mostly(pte_t pte)
+{
+	return pte_none(pte) || is_pte_marker(pte);
+}
+
 static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
 {
 	struct page *p = pfn_to_page(swp_offset(entry));
@@ -274,7 +380,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry)
 struct page_vma_mapped_walk;
 
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
-extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
+extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		struct page *page);
 
 extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw,
@@ -304,10 +410,10 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
 
 static inline int is_pmd_migration_entry(pmd_t pmd)
 {
-	return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
+	return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
 }
 #else
-static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
+static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		struct page *page)
 {
 	BUILD_BUG();
@@ -387,18 +493,10 @@ static inline void num_poisoned_pages_inc(void)
 }
 #endif
 
-#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \
-    defined(CONFIG_DEVICE_PRIVATE)
 static inline int non_swap_entry(swp_entry_t entry)
 {
 	return swp_type(entry) >= MAX_SWAPFILES;
 }
-#else
-static inline int non_swap_entry(swp_entry_t entry)
-{
-	return 0;
-}
-#endif
 
 #endif /* CONFIG_MMU */
 #endif /* _LINUX_SWAPOPS_H */