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, 58 insertions, 12 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index b0183450e484..f85e5a4c070b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1575,13 +1575,14 @@ static inline bool page_maybe_dma_pinned(struct page *page)
 
 /*
  * This should most likely only be called during fork() to see whether we
- * should break the cow immediately for a page on the src mm.
+ * should break the cow immediately for an anon page on the src mm.
+ *
+ * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq.
  */
 static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 					  struct page *page)
 {
-	if (!is_cow_mapping(vma->vm_flags))
-		return false;
+	VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1));
 
 	if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
 		return false;
@@ -1845,9 +1846,6 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
-int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
-			  struct mmu_notifier_range *range, pte_t **ptepp,
-			  pmd_t **pmdpp, spinlock_t **ptlp);
 int follow_pte(struct mm_struct *mm, unsigned long address,
 	       pte_t **ptepp, spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
@@ -1969,10 +1967,11 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 #define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
 					    MM_CP_UFFD_WP_RESOLVE)
 
-extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+extern unsigned long change_protection(struct mmu_gather *tlb,
+			      struct vm_area_struct *vma, unsigned long start,
 			      unsigned long end, pgprot_t newprot,
 			      unsigned long cp_flags);
-extern int mprotect_fixup(struct vm_area_struct *vma,
+extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			  struct vm_area_struct **pprev, unsigned long start,
 			  unsigned long end, unsigned long newflags);
 
@@ -3005,6 +3004,45 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
 	return 0;
 }
 
+/*
+ * Indicates for which pages that are write-protected in the page table,
+ * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the
+ * GUP pin will remain consistent with the pages mapped into the page tables
+ * of the MM.
+ *
+ * Temporary unmapping of PageAnonExclusive() pages or clearing of
+ * PageAnonExclusive() has to protect against concurrent GUP:
+ * * Ordinary GUP: Using the PT lock
+ * * GUP-fast and fork(): mm->write_protect_seq
+ * * GUP-fast and KSM or temporary unmapping (swap, migration):
+ *   clear/invalidate+flush of the page table entry
+ *
+ * Must be called with the (sub)page that's actually referenced via the
+ * page table entry, which might not necessarily be the head page for a
+ * PTE-mapped THP.
+ */
+static inline bool gup_must_unshare(unsigned int flags, struct page *page)
+{
+	/*
+	 * FOLL_WRITE is implicitly handled correctly as the page table entry
+	 * has to be writable -- and if it references (part of) an anonymous
+	 * folio, that part is required to be marked exclusive.
+	 */
+	if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN)
+		return false;
+	/*
+	 * Note: PageAnon(page) is stable until the page is actually getting
+	 * freed.
+	 */
+	if (!PageAnon(page))
+		return false;
+	/*
+	 * Note that PageKsm() pages cannot be exclusive, and consequently,
+	 * cannot get pinned.
+	 */
+	return !PageAnonExclusive(page);
+}
+
 typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
 extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
 			       unsigned long size, pte_fn_t fn, void *data);
@@ -3149,7 +3187,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
 }
 #endif
 
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 int vmemmap_remap_free(unsigned long start, unsigned long end,
 		       unsigned long reuse);
 int vmemmap_remap_alloc(unsigned long start, unsigned long end,
@@ -3158,13 +3196,14 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end,
 
 void *sparse_buffer_alloc(unsigned long size);
 struct page * __populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap);
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
-			    struct vmem_altmap *altmap);
+			    struct vmem_altmap *altmap, struct page *reuse);
 void *vmemmap_alloc_block(unsigned long size, int node);
 struct vmem_altmap;
 void *vmemmap_alloc_block_buf(unsigned long size, int node,
@@ -3252,7 +3291,6 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_DAX,
 	MF_MSG_UNSPLIT_THP,
-	MF_MSG_DIFFERENT_PAGE_SIZE,
 	MF_MSG_UNKNOWN,
 };
 
@@ -3391,4 +3429,12 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 }
 #endif
 
+/*
+ * Whether to drop the pte markers, for example, the uffd-wp information for
+ * file-backed memory.  This should only be specified when we will completely
+ * drop the page in the mm, either by truncation or unmapping of the vma.  By
+ * default, the flag is not set.
+ */
+#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
+
 #endif /* _LINUX_MM_H */