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
  ...

5 files changed, 48 insertions, 22 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a4e8dd889e29..2c9d7e55fff5 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -140,6 +140,7 @@ config PPC
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_VM_GET_PAGE_PROT	if PPC_BOOK3S_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_MIGHT_HAVE_PC_PARPORT
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 875730d5af40..eecff2036869 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -13,7 +13,6 @@
 /*
  * Common bits between hash and Radix page table
  */
-#define _PAGE_BIT_SWAP_TYPE	0
 
 #define _PAGE_EXEC		0x00001 /* execute permission */
 #define _PAGE_WRITE		0x00002 /* write access allowed */
@@ -751,17 +750,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 * Don't have overlapping bits with _PAGE_HPTEFLAGS	\
 	 * We filter HPTEFLAGS on set_pte.			\
 	 */							\
-	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
+	BUILD_BUG_ON(_PAGE_HPTEFLAGS & SWP_TYPE_MASK); \
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);	\
+	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_EXCLUSIVE);	\
 	} while (0)
 
 #define SWP_TYPE_BITS 5
-#define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
-				& ((1UL << SWP_TYPE_BITS) - 1))
+#define SWP_TYPE_MASK		((1UL << SWP_TYPE_BITS) - 1)
+#define __swp_type(x)		((x).val & SWP_TYPE_MASK)
 #define __swp_offset(x)		(((x).val & PTE_RPN_MASK) >> PAGE_SHIFT)
 #define __swp_entry(type, offset)	((swp_entry_t) { \
-				((type) << _PAGE_BIT_SWAP_TYPE) \
-				| (((offset) << PAGE_SHIFT) & PTE_RPN_MASK)})
+				(type) | (((offset) << PAGE_SHIFT) & PTE_RPN_MASK)})
 /*
  * swp_entry_t must be independent of pte bits. We build a swp_entry_t from
  * swap type and offset we get from swap and convert that to pte to find a
@@ -774,11 +773,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #define __swp_entry_to_pmd(x)	(pte_pmd(__swp_entry_to_pte(x)))
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SWP_SOFT_DIRTY   (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE))
+#define _PAGE_SWP_SOFT_DIRTY	_PAGE_SOFT_DIRTY
 #else
 #define _PAGE_SWP_SOFT_DIRTY	0UL
 #endif /* CONFIG_MEM_SOFT_DIRTY */
 
+#define _PAGE_SWP_EXCLUSIVE	_PAGE_NON_IDEMPOTENT
+
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
@@ -796,6 +797,22 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 }
 #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
 
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE));
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_EXCLUSIVE));
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_EXCLUSIVE));
+}
+
 static inline bool check_pte_access(unsigned long access, unsigned long ptev)
 {
 	/*
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 6a1a1ac5743b..8a5674fd120d 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -43,11 +43,14 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
 {
-	huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte_t pte;
+
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 	flush_hugetlb_page(vma, addr);
+	return pte;
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 7cb6d18f5cd6..1b024e64c8ec 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -24,18 +24,6 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
-static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
-{
-#ifdef CONFIG_PPC_MEM_KEYS
-	return (vm_flags & VM_SAO) ?
-		__pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) :
-		__pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags));
-#else
-	return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0);
-#endif
-}
-#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
-
 static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
 {
 	if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 052e6590f84f..8b474ab32f67 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -7,6 +7,7 @@
 #include <linux/mm_types.h>
 #include <linux/memblock.h>
 #include <linux/memremap.h>
+#include <linux/pkeys.h>
 #include <linux/debugfs.h>
 #include <misc/cxl-base.h>
 
@@ -549,3 +550,19 @@ unsigned long memremap_compat_align(void)
 }
 EXPORT_SYMBOL_GPL(memremap_compat_align);
 #endif
+
+pgprot_t vm_get_page_prot(unsigned long vm_flags)
+{
+	unsigned long prot = pgprot_val(protection_map[vm_flags &
+					(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
+
+	if (vm_flags & VM_SAO)
+		prot |= _PAGE_SAO;
+
+#ifdef CONFIG_PPC_MEM_KEYS
+	prot |= vmflag_to_pte_pkey_bits(vm_flags);
+#endif
+
+	return __pgprot(prot);
+}
+EXPORT_SYMBOL(vm_get_page_prot);