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
  ...

11 files changed, 196 insertions, 35 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6f59517c4356..cf531fbcd229 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -76,7 +76,6 @@ config X86
 	select ARCH_HAS_EARLY_DEBUG		if KGDB
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
-	select ARCH_HAS_FILTER_PGPROT
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
@@ -95,6 +94,7 @@ config X86
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_VM_GET_PAGE_PROT
 	select ARCH_HAS_DEBUG_WX
 	select ARCH_HAS_ZONE_DMA_SET if EXPERT
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
@@ -121,6 +121,7 @@ config X86
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_HUGE_PMD_SHARE
+	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP	if X86_64
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_THP_SWAP		if X86_64
 	select ARCH_HAS_PARANOID_L1D_FLUSH
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 62ab07e24aef..44e2d6f1dbaa 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -649,11 +649,6 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
-static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
-{
-	return canon_pgprot(prot);
-}
-
 static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 					 enum page_cache_mode pcm,
 					 enum page_cache_mode new_pcm)
@@ -1077,16 +1072,6 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	return pte;
 }
 
-#define __HAVE_ARCH_PTEP_CLEAR
-static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
-{
-	if (IS_ENABLED(CONFIG_PAGE_TABLE_CHECK))
-		ptep_get_and_clear(mm, addr, ptep);
-	else
-		pte_clear(mm, addr, ptep);
-}
-
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm,
 				      unsigned long addr, pte_t *ptep)
@@ -1173,6 +1158,11 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 	}
 }
 #endif
+
+#define __HAVE_ARCH_PMDP_INVALIDATE_AD
+extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
+				unsigned long address, pmd_t *pmdp);
+
 /*
  * Page table pages are page-aligned.  The lower half of the top
  * level is used for userspace and the top half for the kernel.
@@ -1291,6 +1281,23 @@ static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
 		unsigned long addr, pud_t *pud)
 {
 }
+#ifdef _PAGE_SWP_EXCLUSIVE
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE);
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE);
+}
+#endif /* _PAGE_SWP_EXCLUSIVE */
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
@@ -1430,6 +1437,23 @@ static inline bool arch_faults_on_old_pte(void)
 	return false;
 }
 
+#ifdef CONFIG_PAGE_TABLE_CHECK
+static inline bool pte_user_accessible_page(pte_t pte)
+{
+	return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER);
+}
+
+static inline bool pmd_user_accessible_page(pmd_t pmd)
+{
+	return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && (pmd_val(pmd) & _PAGE_USER);
+}
+
+static inline bool pud_user_accessible_page(pud_t pud)
+{
+	return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && (pud_val(pud) & _PAGE_USER);
+}
+#endif
+
 #endif	/* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_H */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 56d0399a0cd1..e479491da8d5 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -186,7 +186,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|F|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| E|F|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -203,6 +203,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
  * F (2) in swp entry is used to record when a pagetable is
  * writeprotected by userfaultfd WP support.
  *
+ * E (3) in swp entry is used to rememeber PG_anon_exclusive.
+ *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
  *
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 91ac10654570..70e360a2e5fb 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -163,4 +163,9 @@ extern unsigned int ptrs_per_p4d;
 
 #define PGD_KERNEL_START	((PAGE_SIZE / 2) / sizeof(pgd_t))
 
+/*
+ * We borrow bit 3 to remember PG_anon_exclusive.
+ */
+#define _PAGE_SWP_EXCLUSIVE	_PAGE_PWT
+
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 407084d9fd99..bdaf8391e2e0 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -110,9 +110,11 @@
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #define _PAGE_DEVMAP	(_AT(u64, 1) << _PAGE_BIT_DEVMAP)
+#define _PAGE_SOFTW4	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW4)
 #else
 #define _PAGE_NX	(_AT(pteval_t, 0))
 #define _PAGE_DEVMAP	(_AT(pteval_t, 0))
+#define _PAGE_SOFTW4	(_AT(pteval_t, 0))
 #endif
 
 #define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 98fa0a114074..4af5579c7ef7 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -259,6 +259,103 @@ static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
 
 extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 
+static inline bool pte_flags_need_flush(unsigned long oldflags,
+					unsigned long newflags,
+					bool ignore_access)
+{
+	/*
+	 * Flags that require a flush when cleared but not when they are set.
+	 * Only include flags that would not trigger spurious page-faults.
+	 * Non-present entries are not cached. Hardware would set the
+	 * dirty/access bit if needed without a fault.
+	 */
+	const pteval_t flush_on_clear = _PAGE_DIRTY | _PAGE_PRESENT |
+					_PAGE_ACCESSED;
+	const pteval_t software_flags = _PAGE_SOFTW1 | _PAGE_SOFTW2 |
+					_PAGE_SOFTW3 | _PAGE_SOFTW4;
+	const pteval_t flush_on_change = _PAGE_RW | _PAGE_USER | _PAGE_PWT |
+			  _PAGE_PCD | _PAGE_PSE | _PAGE_GLOBAL | _PAGE_PAT |
+			  _PAGE_PAT_LARGE | _PAGE_PKEY_BIT0 | _PAGE_PKEY_BIT1 |
+			  _PAGE_PKEY_BIT2 | _PAGE_PKEY_BIT3 | _PAGE_NX;
+	unsigned long diff = oldflags ^ newflags;
+
+	BUILD_BUG_ON(flush_on_clear & software_flags);
+	BUILD_BUG_ON(flush_on_clear & flush_on_change);
+	BUILD_BUG_ON(flush_on_change & software_flags);
+
+	/* Ignore software flags */
+	diff &= ~software_flags;
+
+	if (ignore_access)
+		diff &= ~_PAGE_ACCESSED;
+
+	/*
+	 * Did any of the 'flush_on_clear' flags was clleared set from between
+	 * 'oldflags' and 'newflags'?
+	 */
+	if (diff & oldflags & flush_on_clear)
+		return true;
+
+	/* Flush on modified flags. */
+	if (diff & flush_on_change)
+		return true;
+
+	/* Ensure there are no flags that were left behind */
+	if (IS_ENABLED(CONFIG_DEBUG_VM) &&
+	    (diff & ~(flush_on_clear | software_flags | flush_on_change))) {
+		VM_WARN_ON_ONCE(1);
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * pte_needs_flush() checks whether permissions were demoted and require a
+ * flush. It should only be used for userspace PTEs.
+ */
+static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
+{
+	/* !PRESENT -> * ; no need for flush */
+	if (!(pte_flags(oldpte) & _PAGE_PRESENT))
+		return false;
+
+	/* PFN changed ; needs flush */
+	if (pte_pfn(oldpte) != pte_pfn(newpte))
+		return true;
+
+	/*
+	 * check PTE flags; ignore access-bit; see comment in
+	 * ptep_clear_flush_young().
+	 */
+	return pte_flags_need_flush(pte_flags(oldpte), pte_flags(newpte),
+				    true);
+}
+#define pte_needs_flush pte_needs_flush
+
+/*
+ * huge_pmd_needs_flush() checks whether permissions were demoted and require a
+ * flush. It should only be used for userspace huge PMDs.
+ */
+static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
+{
+	/* !PRESENT -> * ; no need for flush */
+	if (!(pmd_flags(oldpmd) & _PAGE_PRESENT))
+		return false;
+
+	/* PFN changed ; needs flush */
+	if (pmd_pfn(oldpmd) != pmd_pfn(newpmd))
+		return true;
+
+	/*
+	 * check PMD flags; do not ignore access-bit; see
+	 * pmdp_clear_flush_young().
+	 */
+	return pte_flags_need_flush(pmd_flags(oldpmd), pmd_flags(newpmd),
+				    false);
+}
+#define huge_pmd_needs_flush huge_pmd_needs_flush
+
 #endif /* !MODULE */
 
 static inline void __native_tlb_flush_global(unsigned long cr4)
diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h
index d4a8d0424bfb..775dbd3aff73 100644
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -5,20 +5,6 @@
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-/*
- * Take the 4 protection key bits out of the vma->vm_flags
- * value and turn them in to the bits that we can put in
- * to a pte.
- *
- * Only override these if Protection Keys are available
- * (which is only on 64-bit).
- */
-#define arch_vm_get_page_prot(vm_flags)	__pgprot(	\
-		((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) |	\
-		((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) |	\
-		((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) |	\
-		((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0))
-
 #define arch_calc_vm_prot_bits(prot, key) (		\
 		((key) & 0x1 ? VM_PKEY_BIT0 : 0) |      \
 		((key) & 0x2 ? VM_PKEY_BIT1 : 0) |      \
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index d957dc15b371..f8220fd2c169 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -20,7 +20,7 @@ CFLAGS_REMOVE_mem_encrypt_identity.o	= -pg
 endif
 
 obj-y				:=  init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \
-				    pgtable.o physaddr.o tlb.o cpu_entry_area.o maccess.o
+				    pgtable.o physaddr.o tlb.o cpu_entry_area.o maccess.o pgprot.o
 
 obj-y				+= pat/
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 61d0ab154f96..cb290a2f0747 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1269,7 +1269,7 @@ static struct kcore_list kcore_vsyscall;
 
 static void __init register_page_bootmem_info(void)
 {
-#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)
+#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP)
 	int i;
 
 	for_each_online_node(i)
diff --git a/arch/x86/mm/pgprot.c b/arch/x86/mm/pgprot.c
new file mode 100644
index 000000000000..763742782286
--- /dev/null
+++ b/arch/x86/mm/pgprot.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <asm/pgtable.h>
+
+pgprot_t vm_get_page_prot(unsigned long vm_flags)
+{
+	unsigned long val = pgprot_val(protection_map[vm_flags &
+				      (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	/*
+	 * Take the 4 protection key bits out of the vma->vm_flags value and
+	 * turn them in to the bits that we can put in to a pte.
+	 *
+	 * Only override these if Protection Keys are available (which is only
+	 * on 64-bit).
+	 */
+	if (vm_flags & VM_PKEY_BIT0)
+		val |= _PAGE_PKEY_BIT0;
+	if (vm_flags & VM_PKEY_BIT1)
+		val |= _PAGE_PKEY_BIT1;
+	if (vm_flags & VM_PKEY_BIT2)
+		val |= _PAGE_PKEY_BIT2;
+	if (vm_flags & VM_PKEY_BIT3)
+		val |= _PAGE_PKEY_BIT3;
+#endif
+
+	val = __sme_set(val);
+	if (val & _PAGE_PRESENT)
+		val &= __supported_pte_mask;
+	return __pgprot(val);
+}
+EXPORT_SYMBOL(vm_get_page_prot);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3481b35cb4ec..a932d7712d85 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -608,6 +608,16 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 
 	return young;
 }
+
+pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
+			 pmd_t *pmdp)
+{
+	/*
+	 * No flush is necessary. Once an invalid PTE is established, the PTE's
+	 * access and dirty bits cannot be updated.
+	 */
+	return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
+}
 #endif
 
 /**
@@ -676,9 +686,8 @@ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
  *
  * No 512GB pages yet -- always return 0
  */
-int p4d_clear_huge(p4d_t *p4d)
+void p4d_clear_huge(p4d_t *p4d)
 {
-	return 0;
 }
 #endif