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, 66 insertions, 18 deletions

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index f4f4077b97aa..3cdc16cfd867 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -12,6 +12,7 @@
 #include <linux/bug.h>
 #include <linux/errno.h>
 #include <asm-generic/pgtable_uffd.h>
+#include <linux/page_table_check.h>
 
 #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
 	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
@@ -259,14 +260,6 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
-#ifndef __HAVE_ARCH_PTEP_CLEAR
-static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
-{
-	pte_clear(mm, addr, ptep);
-}
-#endif
-
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address,
@@ -274,10 +267,17 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 {
 	pte_t pte = *ptep;
 	pte_clear(mm, address, ptep);
+	page_table_check_pte_clear(mm, address, pte);
 	return pte;
 }
 #endif
 
+static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep)
+{
+	ptep_get_and_clear(mm, addr, ptep);
+}
+
 #ifndef __HAVE_ARCH_PTEP_GET
 static inline pte_t ptep_get(pte_t *ptep)
 {
@@ -347,7 +347,10 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
+
 	pmd_clear(pmdp);
+	page_table_check_pmd_clear(mm, address, pmd);
+
 	return pmd;
 }
 #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
@@ -359,6 +362,8 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
 	pud_t pud = *pudp;
 
 	pud_clear(pudp);
+	page_table_check_pud_clear(mm, address, pud);
+
 	return pud;
 }
 #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
@@ -570,6 +575,26 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
+
+/*
+ * pmdp_invalidate_ad() invalidates the PMD while changing a transparent
+ * hugepage mapping in the page tables. This function is similar to
+ * pmdp_invalidate(), but should only be used if the access and dirty bits would
+ * not be cleared by the software in the new PMD value. The function ensures
+ * that hardware changes of the access and dirty bits updates would not be lost.
+ *
+ * Doing so can allow in certain architectures to avoid a TLB flush in most
+ * cases. Yet, another TLB flush might be necessary later if the PMD update
+ * itself requires such flush (e.g., if protection was set to be stricter). Yet,
+ * even when a TLB flush is needed because of the update, the caller may be able
+ * to batch these TLB flushing operations, so fewer TLB flush operations are
+ * needed.
+ */
+extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
+				unsigned long address, pmd_t *pmdp);
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
@@ -738,7 +763,7 @@ static inline void arch_swap_invalidate_area(int type)
 #endif
 
 #ifndef __HAVE_ARCH_SWAP_RESTORE
-static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
+static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 {
 }
 #endif
@@ -1003,6 +1028,35 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define arch_start_context_switch(prev)	do {} while (0)
 #endif
 
+/*
+ * When replacing an anonymous page by a real (!non) swap entry, we clear
+ * PG_anon_exclusive from the page and instead remember whether the flag was
+ * set in the swp pte. During fork(), we have to mark the entry as !exclusive
+ * (possibly shared). On swapin, we use that information to restore
+ * PG_anon_exclusive, which is very helpful in cases where we might have
+ * additional (e.g., FOLL_GET) references on a page and wouldn't be able to
+ * detect exclusivity.
+ *
+ * These functions don't apply to non-swap entries (e.g., migration, hwpoison,
+ * ...).
+ */
+#ifndef __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return pte;
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return false;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return pte;
+}
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION
 static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
@@ -1394,16 +1448,13 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #ifndef __PAGETABLE_P4D_FOLDED
 int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
-int p4d_clear_huge(p4d_t *p4d);
+void p4d_clear_huge(p4d_t *p4d);
 #else
 static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
 }
-static inline int p4d_clear_huge(p4d_t *p4d)
-{
-	return 0;
-}
+static inline void p4d_clear_huge(p4d_t *p4d) { }
 #endif /* !__PAGETABLE_P4D_FOLDED */
 
 int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
@@ -1426,10 +1477,7 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
 }
-static inline int p4d_clear_huge(p4d_t *p4d)
-{
-	return 0;
-}
+static inline void p4d_clear_huge(p4d_t *p4d) { }
 static inline int pud_clear_huge(pud_t *pud)
 {
 	return 0;