Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 269 insertions, 132 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 296e4f05e8..d2155ced45 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -806,9 +806,9 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		}
 		rss[MM_SWAPENTS]++;
 	} else if (is_migration_entry(entry)) {
-		page = pfn_swap_entry_to_page(entry);
+		folio = pfn_swap_entry_folio(entry);
 
-		rss[mm_counter(page)]++;
+		rss[mm_counter(folio)]++;
 
 		if (!is_readable_migration_entry(entry) &&
 				is_cow_mapping(vm_flags)) {
@@ -840,7 +840,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		 * keep things as they are.
 		 */
 		folio_get(folio);
-		rss[mm_counter(page)]++;
+		rss[mm_counter(folio)]++;
 		/* Cannot fail as these pages cannot get pinned. */
 		folio_try_dup_anon_rmap_pte(folio, page, src_vma);
 
@@ -930,68 +930,111 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 	return 0;
 }
 
+static __always_inline void __copy_present_ptes(struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte,
+		pte_t pte, unsigned long addr, int nr)
+{
+	struct mm_struct *src_mm = src_vma->vm_mm;
+
+	/* If it's a COW mapping, write protect it both processes. */
+	if (is_cow_mapping(src_vma->vm_flags) && pte_write(pte)) {
+		wrprotect_ptes(src_mm, addr, src_pte, nr);
+		pte = pte_wrprotect(pte);
+	}
+
+	/* If it's a shared mapping, mark it clean in the child. */
+	if (src_vma->vm_flags & VM_SHARED)
+		pte = pte_mkclean(pte);
+	pte = pte_mkold(pte);
+
+	if (!userfaultfd_wp(dst_vma))
+		pte = pte_clear_uffd_wp(pte);
+
+	set_ptes(dst_vma->vm_mm, addr, dst_pte, pte, nr);
+}
+
 /*
- * Copy one pte.  Returns 0 if succeeded, or -EAGAIN if one preallocated page
- * is required to copy this pte.
+ * Copy one present PTE, trying to batch-process subsequent PTEs that map
+ * consecutive pages of the same folio by copying them as well.
+ *
+ * Returns -EAGAIN if one preallocated page is required to copy the next PTE.
+ * Otherwise, returns the number of copied PTEs (at least 1).
  */
 static inline int
-copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
-		 pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
-		 struct folio **prealloc)
+copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		 pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr,
+		 int max_nr, int *rss, struct folio **prealloc)
 {
-	struct mm_struct *src_mm = src_vma->vm_mm;
-	unsigned long vm_flags = src_vma->vm_flags;
-	pte_t pte = ptep_get(src_pte);
 	struct page *page;
 	struct folio *folio;
+	bool any_writable;
+	fpb_t flags = 0;
+	int err, nr;
 
 	page = vm_normal_page(src_vma, addr, pte);
-	if (page)
-		folio = page_folio(page);
-	if (page && folio_test_anon(folio)) {
+	if (unlikely(!page))
+		goto copy_pte;
+
+	folio = page_folio(page);
+
+	/*
+	 * If we likely have to copy, just don't bother with batching. Make
+	 * sure that the common "small folio" case is as fast as possible
+	 * by keeping the batching logic separate.
+	 */
+	if (unlikely(!*prealloc && folio_test_large(folio) && max_nr != 1)) {
+		if (src_vma->vm_flags & VM_SHARED)
+			flags |= FPB_IGNORE_DIRTY;
+		if (!vma_soft_dirty_enabled(src_vma))
+			flags |= FPB_IGNORE_SOFT_DIRTY;
+
+		nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags,
+				     &any_writable);
+		folio_ref_add(folio, nr);
+		if (folio_test_anon(folio)) {
+			if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page,
+								  nr, src_vma))) {
+				folio_ref_sub(folio, nr);
+				return -EAGAIN;
+			}
+			rss[MM_ANONPAGES] += nr;
+			VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio);
+		} else {
+			folio_dup_file_rmap_ptes(folio, page, nr);
+			rss[mm_counter_file(folio)] += nr;
+		}
+		if (any_writable)
+			pte = pte_mkwrite(pte, src_vma);
+		__copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte,
+				    addr, nr);
+		return nr;
+	}
+
+	folio_get(folio);
+	if (folio_test_anon(folio)) {
 		/*
 		 * If this page may have been pinned by the parent process,
 		 * copy the page immediately for the child so that we'll always
 		 * guarantee the pinned page won't be randomly replaced in the
 		 * future.
 		 */
-		folio_get(folio);
 		if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, src_vma))) {
 			/* Page may be pinned, we have to copy. */
 			folio_put(folio);
-			return copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
-						 addr, rss, prealloc, page);
+			err = copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
+						addr, rss, prealloc, page);
+			return err ? err : 1;
 		}
 		rss[MM_ANONPAGES]++;
-	} else if (page) {
-		folio_get(folio);
+		VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio);
+	} else {
 		folio_dup_file_rmap_pte(folio, page);
-		rss[mm_counter_file(page)]++;
-	}
-
-	/*
-	 * If it's a COW mapping, write protect it both
-	 * in the parent and the child
-	 */
-	if (is_cow_mapping(vm_flags) && pte_write(pte)) {
-		ptep_set_wrprotect(src_mm, addr, src_pte);
-		pte = pte_wrprotect(pte);
+		rss[mm_counter_file(folio)]++;
 	}
-	VM_BUG_ON(page && folio_test_anon(folio) && PageAnonExclusive(page));
 
-	/*
-	 * If it's a shared mapping, mark it clean in
-	 * the child
-	 */
-	if (vm_flags & VM_SHARED)
-		pte = pte_mkclean(pte);
-	pte = pte_mkold(pte);
-
-	if (!userfaultfd_wp(dst_vma))
-		pte = pte_clear_uffd_wp(pte);
-
-	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
-	return 0;
+copy_pte:
+	__copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, 1);
+	return 1;
 }
 
 static inline struct folio *folio_prealloc(struct mm_struct *src_mm,
@@ -1028,10 +1071,11 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	pte_t *src_pte, *dst_pte;
 	pte_t ptent;
 	spinlock_t *src_ptl, *dst_ptl;
-	int progress, ret = 0;
+	int progress, max_nr, ret = 0;
 	int rss[NR_MM_COUNTERS];
 	swp_entry_t entry = (swp_entry_t){0};
 	struct folio *prealloc = NULL;
+	int nr;
 
 again:
 	progress = 0;
@@ -1062,6 +1106,8 @@ again:
 	arch_enter_lazy_mmu_mode();
 
 	do {
+		nr = 1;
+
 		/*
 		 * We are holding two locks at this point - either of them
 		 * could generate latencies in another task on another CPU.
@@ -1091,6 +1137,8 @@ again:
 				progress += 8;
 				continue;
 			}
+			ptent = ptep_get(src_pte);
+			VM_WARN_ON_ONCE(!pte_present(ptent));
 
 			/*
 			 * Device exclusive entry restored, continue by copying
@@ -1098,9 +1146,10 @@ again:
 			 */
 			WARN_ON_ONCE(ret != -ENOENT);
 		}
-		/* copy_present_pte() will clear `*prealloc' if consumed */
-		ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte,
-				       addr, rss, &prealloc);
+		/* copy_present_ptes() will clear `*prealloc' if consumed */
+		max_nr = (end - addr) / PAGE_SIZE;
+		ret = copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte,
+					ptent, addr, max_nr, rss, &prealloc);
 		/*
 		 * If we need a pre-allocated page for this pte, drop the
 		 * locks, allocate, and try again.
@@ -1117,8 +1166,10 @@ again:
 			folio_put(prealloc);
 			prealloc = NULL;
 		}
-		progress += 8;
-	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
+		nr = ret;
+		progress += 8 * nr;
+	} while (dst_pte += nr, src_pte += nr, addr += PAGE_SIZE * nr,
+		 addr != end);
 
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(orig_src_pte, src_ptl);
@@ -1139,7 +1190,7 @@ again:
 		prealloc = folio_prealloc(src_mm, src_vma, addr, false);
 		if (!prealloc)
 			return -ENOMEM;
-	} else if (ret) {
+	} else if (ret < 0) {
 		VM_WARN_ON_ONCE(1);
 	}
 
@@ -1369,19 +1420,16 @@ static inline bool should_zap_cows(struct zap_details *details)
 	return details->even_cows;
 }
 
-/* Decides whether we should zap this page with the page pointer specified */
-static inline bool should_zap_page(struct zap_details *details, struct page *page)
+/* Decides whether we should zap this folio with the folio pointer specified */
+static inline bool should_zap_folio(struct zap_details *details,
+				    struct folio *folio)
 {
-	/* If we can make a decision without *page.. */
+	/* If we can make a decision without *folio.. */
 	if (should_zap_cows(details))
 		return true;
 
-	/* E.g. the caller passes NULL for the case of a zero page */
-	if (!page)
-		return true;
-
-	/* Otherwise we should only zap non-anon pages */
-	return !PageAnon(page);
+	/* Otherwise we should only zap non-anon folios */
+	return !folio_test_anon(folio);
 }
 
 static inline bool zap_drop_file_uffd_wp(struct zap_details *details)
@@ -1398,7 +1446,7 @@ static inline bool zap_drop_file_uffd_wp(struct zap_details *details)
  */
 static inline void
 zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
-			      unsigned long addr, pte_t *pte,
+			      unsigned long addr, pte_t *pte, int nr,
 			      struct zap_details *details, pte_t pteval)
 {
 	/* Zap on anonymous always means dropping everything */
@@ -1408,7 +1456,113 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
 	if (zap_drop_file_uffd_wp(details))
 		return;
 
-	pte_install_uffd_wp_if_needed(vma, addr, pte, pteval);
+	for (;;) {
+		/* the PFN in the PTE is irrelevant. */
+		pte_install_uffd_wp_if_needed(vma, addr, pte, pteval);
+		if (--nr == 0)
+			break;
+		pte++;
+		addr += PAGE_SIZE;
+	}
+}
+
+static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, struct folio *folio,
+		struct page *page, pte_t *pte, pte_t ptent, unsigned int nr,
+		unsigned long addr, struct zap_details *details, int *rss,
+		bool *force_flush, bool *force_break)
+{
+	struct mm_struct *mm = tlb->mm;
+	bool delay_rmap = false;
+
+	if (!folio_test_anon(folio)) {
+		ptent = get_and_clear_full_ptes(mm, addr, pte, nr, tlb->fullmm);
+		if (pte_dirty(ptent)) {
+			folio_mark_dirty(folio);
+			if (tlb_delay_rmap(tlb)) {
+				delay_rmap = true;
+				*force_flush = true;
+			}
+		}
+		if (pte_young(ptent) && likely(vma_has_recency(vma)))
+			folio_mark_accessed(folio);
+		rss[mm_counter(folio)] -= nr;
+	} else {
+		/* We don't need up-to-date accessed/dirty bits. */
+		clear_full_ptes(mm, addr, pte, nr, tlb->fullmm);
+		rss[MM_ANONPAGES] -= nr;
+	}
+	/* Checking a single PTE in a batch is sufficient. */
+	arch_check_zapped_pte(vma, ptent);
+	tlb_remove_tlb_entries(tlb, pte, nr, addr);
+	if (unlikely(userfaultfd_pte_wp(vma, ptent)))
+		zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details,
+					      ptent);
+
+	if (!delay_rmap) {
+		folio_remove_rmap_ptes(folio, page, nr, vma);
+
+		/* Only sanity-check the first page in a batch. */
+		if (unlikely(page_mapcount(page) < 0))
+			print_bad_pte(vma, addr, ptent, page);
+	}
+	if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) {
+		*force_flush = true;
+		*force_break = true;
+	}
+}
+
+/*
+ * Zap or skip at least one present PTE, trying to batch-process subsequent
+ * PTEs that map consecutive pages of the same folio.
+ *
+ * Returns the number of processed (skipped or zapped) PTEs (at least 1).
+ */
+static inline int zap_present_ptes(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pte_t *pte, pte_t ptent,
+		unsigned int max_nr, unsigned long addr,
+		struct zap_details *details, int *rss, bool *force_flush,
+		bool *force_break)
+{
+	const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
+	struct mm_struct *mm = tlb->mm;
+	struct folio *folio;
+	struct page *page;
+	int nr;
+
+	page = vm_normal_page(vma, addr, ptent);
+	if (!page) {
+		/* We don't need up-to-date accessed/dirty bits. */
+		ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm);
+		arch_check_zapped_pte(vma, ptent);
+		tlb_remove_tlb_entry(tlb, pte, addr);
+		if (userfaultfd_pte_wp(vma, ptent))
+			zap_install_uffd_wp_if_needed(vma, addr, pte, 1,
+						      details, ptent);
+		ksm_might_unmap_zero_page(mm, ptent);
+		return 1;
+	}
+
+	folio = page_folio(page);
+	if (unlikely(!should_zap_folio(details, folio)))
+		return 1;
+
+	/*
+	 * Make sure that the common "small folio" case is as fast as possible
+	 * by keeping the batching logic separate.
+	 */
+	if (unlikely(folio_test_large(folio) && max_nr != 1)) {
+		nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags,
+				     NULL);
+
+		zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr,
+				       addr, details, rss, force_flush,
+				       force_break);
+		return nr;
+	}
+	zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr,
+			       details, rss, force_flush, force_break);
+	return 1;
 }
 
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
@@ -1416,13 +1570,14 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				unsigned long addr, unsigned long end,
 				struct zap_details *details)
 {
+	bool force_flush = false, force_break = false;
 	struct mm_struct *mm = tlb->mm;
-	int force_flush = 0;
 	int rss[NR_MM_COUNTERS];
 	spinlock_t *ptl;
 	pte_t *start_pte;
 	pte_t *pte;
 	swp_entry_t entry;
+	int nr;
 
 	tlb_change_page_size(tlb, PAGE_SIZE);
 	init_rss_vec(rss);
@@ -1436,7 +1591,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		pte_t ptent = ptep_get(pte);
 		struct folio *folio;
 		struct page *page;
+		int max_nr;
 
+		nr = 1;
 		if (pte_none(ptent))
 			continue;
 
@@ -1444,44 +1601,12 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			break;
 
 		if (pte_present(ptent)) {
-			unsigned int delay_rmap;
-
-			page = vm_normal_page(vma, addr, ptent);
-			if (unlikely(!should_zap_page(details, page)))
-				continue;
-			ptent = ptep_get_and_clear_full(mm, addr, pte,
-							tlb->fullmm);
-			arch_check_zapped_pte(vma, ptent);
-			tlb_remove_tlb_entry(tlb, pte, addr);
-			zap_install_uffd_wp_if_needed(vma, addr, pte, details,
-						      ptent);
-			if (unlikely(!page)) {
-				ksm_might_unmap_zero_page(mm, ptent);
-				continue;
-			}
-
-			folio = page_folio(page);
-			delay_rmap = 0;
-			if (!folio_test_anon(folio)) {
-				if (pte_dirty(ptent)) {
-					folio_mark_dirty(folio);
-					if (tlb_delay_rmap(tlb)) {
-						delay_rmap = 1;
-						force_flush = 1;
-					}
-				}
-				if (pte_young(ptent) && likely(vma_has_recency(vma)))
-					folio_mark_accessed(folio);
-			}
-			rss[mm_counter(page)]--;
-			if (!delay_rmap) {
-				folio_remove_rmap_pte(folio, page, vma);
-				if (unlikely(page_mapcount(page) < 0))
-					print_bad_pte(vma, addr, ptent, page);
-			}
-			if (unlikely(__tlb_remove_page(tlb, page, delay_rmap))) {
-				force_flush = 1;
-				addr += PAGE_SIZE;
+			max_nr = (end - addr) / PAGE_SIZE;
+			nr = zap_present_ptes(tlb, vma, pte, ptent, max_nr,
+					      addr, details, rss, &force_flush,
+					      &force_break);
+			if (unlikely(force_break)) {
+				addr += nr * PAGE_SIZE;
 				break;
 			}
 			continue;
@@ -1492,7 +1617,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		    is_device_exclusive_entry(entry)) {
 			page = pfn_swap_entry_to_page(entry);
 			folio = page_folio(page);
-			if (unlikely(!should_zap_page(details, page)))
+			if (unlikely(!should_zap_folio(details, folio)))
 				continue;
 			/*
 			 * Both device private/exclusive mappings should only
@@ -1501,7 +1626,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			 * see zap_install_uffd_wp_if_needed().
 			 */
 			WARN_ON_ONCE(!vma_is_anonymous(vma));
-			rss[mm_counter(page)]--;
+			rss[mm_counter(folio)]--;
 			if (is_device_private_entry(entry))
 				folio_remove_rmap_pte(folio, page, vma);
 			folio_put(folio);
@@ -1513,10 +1638,10 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			if (unlikely(!free_swap_and_cache(entry)))
 				print_bad_pte(vma, addr, ptent, NULL);
 		} else if (is_migration_entry(entry)) {
-			page = pfn_swap_entry_to_page(entry);
-			if (!should_zap_page(details, page))
+			folio = pfn_swap_entry_folio(entry);
+			if (!should_zap_folio(details, folio))
 				continue;
-			rss[mm_counter(page)]--;
+			rss[mm_counter(folio)]--;
 		} else if (pte_marker_entry_uffd_wp(entry)) {
 			/*
 			 * For anon: always drop the marker; for file: only
@@ -1535,8 +1660,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			WARN_ON_ONCE(1);
 		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
-		zap_install_uffd_wp_if_needed(vma, addr, pte, details, ptent);
-	} while (pte++, addr += PAGE_SIZE, addr != end);
+		zap_install_uffd_wp_if_needed(vma, addr, pte, 1, details, ptent);
+	} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);
 
 	add_mm_rss_vec(mm, rss);
 	arch_leave_lazy_mmu_mode();
@@ -1870,7 +1995,7 @@ static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
 		return -EBUSY;
 	/* Ok, finally just insert the thing.. */
 	folio_get(folio);
-	inc_mm_counter(vma->vm_mm, mm_counter_file(page));
+	inc_mm_counter(vma->vm_mm, mm_counter_file(folio));
 	folio_add_file_rmap_pte(folio, page, vma);
 	set_pte_at(vma->vm_mm, addr, pte, mk_pte(page, prot));
 	return 0;
@@ -3081,7 +3206,7 @@ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf)
 	return VM_FAULT_RETRY;
 }
 
-static vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
+vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 
@@ -3175,7 +3300,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
 		if (old_folio) {
 			if (!folio_test_anon(old_folio)) {
-				dec_mm_counter(mm, mm_counter_file(&old_folio->page));
+				dec_mm_counter(mm, mm_counter_file(old_folio));
 				inc_mm_counter(mm, MM_ANONPAGES);
 			}
 		} else {
@@ -3253,7 +3378,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		folio_put(new_folio);
 	if (old_folio) {
 		if (page_copied)
-			free_swap_cache(&old_folio->page);
+			free_swap_cache(old_folio);
 		folio_put(old_folio);
 	}
 
@@ -3376,6 +3501,16 @@ static bool wp_can_reuse_anon_folio(struct folio *folio,
 				    struct vm_area_struct *vma)
 {
 	/*
+	 * We could currently only reuse a subpage of a large folio if no
+	 * other subpages of the large folios are still mapped. However,
+	 * let's just consistently not reuse subpages even if we could
+	 * reuse in that scenario, and give back a large folio a bit
+	 * sooner.
+	 */
+	if (folio_test_large(folio))
+		return false;
+
+	/*
 	 * We have to verify under folio lock: these early checks are
 	 * just an optimization to avoid locking the folio and freeing
 	 * the swapcache if there is little hope that we can reuse.
@@ -4170,8 +4305,8 @@ static bool pte_range_none(pte_t *pte, int nr_pages)
 
 static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	struct vm_area_struct *vma = vmf->vma;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	unsigned long orders;
 	struct folio *folio;
 	unsigned long addr;
@@ -4223,15 +4358,21 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
 		folio = vma_alloc_folio(gfp, order, vma, addr, true);
 		if (folio) {
+			if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
+				folio_put(folio);
+				goto next;
+			}
+			folio_throttle_swaprate(folio, gfp);
 			clear_huge_page(&folio->page, vmf->address, 1 << order);
 			return folio;
 		}
+next:
 		order = next_order(&orders, order);
 	}
 
 fallback:
 #endif
-	return vma_alloc_zeroed_movable_folio(vmf->vma, vmf->address);
+	return folio_prealloc(vma->vm_mm, vma, vmf->address, true);
 }
 
 /*
@@ -4298,10 +4439,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	nr_pages = folio_nr_pages(folio);
 	addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
 
-	if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL))
-		goto oom_free_page;
-	folio_throttle_swaprate(folio, GFP_KERNEL);
-
 	/*
 	 * The memory barrier inside __folio_mark_uptodate makes sure that
 	 * preceding stores to the page contents become visible before
@@ -4355,8 +4492,6 @@ unlock:
 release:
 	folio_put(folio);
 	goto unlock;
-oom_free_page:
-	folio_put(folio);
 oom:
 	return VM_FAULT_OOM;
 }
@@ -4480,7 +4615,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	if (write)
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
-	add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR);
+	add_mm_counter(vma->vm_mm, mm_counter_file(folio), HPAGE_PMD_NR);
 	folio_add_file_rmap_pmd(folio, page, vma);
 
 	/*
@@ -4543,7 +4678,7 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio,
 		folio_add_new_anon_rmap(folio, vma, addr);
 		folio_add_lru_vma(folio, vma);
 	} else {
-		add_mm_counter(vma->vm_mm, mm_counter_file(page), nr);
+		add_mm_counter(vma->vm_mm, mm_counter_file(folio), nr);
 		folio_add_file_rmap_ptes(folio, page, nr, vma);
 	}
 	set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr);
@@ -4653,7 +4788,8 @@ static int fault_around_bytes_set(void *data, u64 val)
 	 * The minimum value is 1 page, however this results in no fault-around
 	 * at all. See should_fault_around().
 	 */
-	fault_around_pages = max(rounddown_pow_of_two(val) >> PAGE_SHIFT, 1UL);
+	val = max(val, PAGE_SIZE);
+	fault_around_pages = rounddown_pow_of_two(val) >> PAGE_SHIFT;
 
 	return 0;
 }
@@ -4928,18 +5064,18 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	int flags = 0;
 
 	/*
-	 * The "pte" at this point cannot be used safely without
-	 * validation through pte_unmap_same(). It's of NUMA type but
-	 * the pfn may be screwed if the read is non atomic.
+	 * The pte cannot be used safely until we verify, while holding the page
+	 * table lock, that its contents have not changed during fault handling.
 	 */
 	spin_lock(vmf->ptl);
-	if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
+	/* Read the live PTE from the page tables: */
+	old_pte = ptep_get(vmf->pte);
+
+	if (unlikely(!pte_same(old_pte, vmf->orig_pte))) {
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		goto out;
 	}
 
-	/* Get the normal PTE  */
-	old_pte = ptep_get(vmf->pte);
 	pte = pte_modify(old_pte, vma->vm_page_prot);
 
 	/*
@@ -6167,7 +6303,7 @@ static int clear_subpage(unsigned long addr, int idx, void *arg)
 {
 	struct page *page = arg;
 
-	clear_user_highpage(page + idx, addr);
+	clear_user_highpage(nth_page(page, idx), addr);
 	return 0;
 }
 
@@ -6217,10 +6353,11 @@ struct copy_subpage_arg {
 static int copy_subpage(unsigned long addr, int idx, void *arg)
 {
 	struct copy_subpage_arg *copy_arg = arg;
+	struct page *dst = nth_page(copy_arg->dst, idx);
+	struct page *src = nth_page(copy_arg->src, idx);
 
-	if (copy_mc_user_highpage(copy_arg->dst + idx, copy_arg->src + idx,
-				  addr, copy_arg->vma)) {
-		memory_failure_queue(page_to_pfn(copy_arg->src + idx), 0);
+	if (copy_mc_user_highpage(dst, src, addr, copy_arg->vma)) {
+		memory_failure_queue(page_to_pfn(src), 0);
 		return -EHWPOISON;
 	}
 	return 0;