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, 79 insertions, 12 deletions

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 45c358538f13..0b6632f18364 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -33,6 +33,7 @@
 #include <linux/mmdebug.h>
 #include <linux/mm_types.h>
 #include <linux/sched.h>
+#include <linux/page_table_check.h>
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
@@ -96,6 +97,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
 #define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
+#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
 #define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
 #define pte_devmap(pte)		(!!(pte_val(pte) & PTE_DEVMAP))
@@ -312,8 +314,8 @@ static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep,
 		     __func__, pte_val(old_pte), pte_val(pte));
 }
 
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pte)
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte)
 {
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte);
@@ -343,6 +345,13 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	set_pte(ptep, pte);
 }
 
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pte)
+{
+	page_table_check_pte_set(mm, addr, ptep, pte);
+	return __set_pte_at(mm, addr, ptep, pte);
+}
+
 /*
  * Huge pte definitions.
  */
@@ -402,6 +411,22 @@ static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot)
 	return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT);
 }
 
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_val(pte) & PTE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
+}
+
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * See the comment in include/linux/pgtable.h
@@ -438,6 +463,8 @@ static inline int pmd_trans_huge(pmd_t pmd)
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_valid(pmd)		pte_valid(pmd_pte(pmd))
+#define pmd_user(pmd)		pte_user(pmd_pte(pmd))
+#define pmd_user_exec(pmd)	pte_user_exec(pmd_pte(pmd))
 #define pmd_cont(pmd)		pte_cont(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
@@ -485,8 +512,19 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 #define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
 #define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
-#define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
-#define set_pud_at(mm, addr, pudp, pud)	set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud))
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	page_table_check_pmd_set(mm, addr, pmdp, pmd);
+	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+}
+
+static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
+			      pud_t *pudp, pud_t pud)
+{
+	page_table_check_pud_set(mm, addr, pudp, pud);
+	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+}
 
 #define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))
 #define __phys_to_p4d_val(phys)	__phys_to_pte_val(phys)
@@ -627,6 +665,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 #define pud_present(pud)	pte_present(pud_pte(pud))
 #define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
 #define pud_valid(pud)		pte_valid(pud_pte(pud))
+#define pud_user(pud)		pte_user(pud_pte(pud))
+
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
@@ -799,6 +839,23 @@ static inline int pgd_devmap(pgd_t pgd)
 }
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_CHECK
+static inline bool pte_user_accessible_page(pte_t pte)
+{
+	return pte_present(pte) && (pte_user(pte) || pte_user_exec(pte));
+}
+
+static inline bool pmd_user_accessible_page(pmd_t pmd)
+{
+	return pmd_present(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+}
+
+static inline bool pud_user_accessible_page(pud_t pud)
+{
+	return pud_present(pud) && pud_user(pud);
+}
+#endif
+
 /*
  * Atomic pte/pmd modifications.
  */
@@ -860,7 +917,11 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address, pte_t *ptep)
 {
-	return __pte(xchg_relaxed(&pte_val(*ptep), 0));
+	pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0));
+
+	page_table_check_pte_clear(mm, address, pte);
+
+	return pte;
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -868,7 +929,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long address, pmd_t *pmdp)
 {
-	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
+	pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0));
+
+	page_table_check_pmd_clear(mm, address, pmd);
+
+	return pmd;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -902,6 +967,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmdp, pmd_t pmd)
 {
+	page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd);
 	return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd)));
 }
 #endif
@@ -909,12 +975,13 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 /*
  * Encode and decode a swap entry:
  *	bits 0-1:	present (must be zero)
- *	bits 2-7:	swap type
+ *	bits 2:		remember PG_anon_exclusive
+ *	bits 3-7:	swap type
  *	bits 8-57:	swap offset
  *	bit  58:	PTE_PROT_NONE (must be zero)
  */
-#define __SWP_TYPE_SHIFT	2
-#define __SWP_TYPE_BITS		6
+#define __SWP_TYPE_SHIFT	3
+#define __SWP_TYPE_BITS		5
 #define __SWP_OFFSET_BITS	50
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
@@ -964,10 +1031,10 @@ static inline void arch_swap_invalidate_area(int type)
 }
 
 #define __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)
 {
-	if (system_supports_mte() && mte_restore_tags(entry, page))
-		set_bit(PG_mte_tagged, &page->flags);
+	if (system_supports_mte() && mte_restore_tags(entry, &folio->page))
+		set_bit(PG_mte_tagged, &folio->flags);
 }
 
 #endif /* CONFIG_ARM64_MTE */