Merge branch 'next' into for-linus

Prepare input updates for 6.11 merge window.

1 files changed, 831 insertions, 466 deletions

diff --git a/mm/memory.c b/mm/memory.c
index cdc4d4c1c858..d2155ced45f8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1,3 +1,4 @@
+
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/mm/memory.c
@@ -77,7 +78,6 @@
 #include <linux/ptrace.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/sysctl.h>
-#include <linux/net_mm.h>
 
 #include <trace/events/kmem.h>
 
@@ -123,9 +123,7 @@ static bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf)
 /*
  * A number of key systems in x86 including ioremap() rely on the assumption
  * that high_memory defines the upper bound on direct map memory, then end
- * of ZONE_NORMAL.  Under CONFIG_DISCONTIG this means that max_low_pfn and
- * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
- * and ZONE_HIGHMEM.
+ * of ZONE_NORMAL.
  */
 void *high_memory;
 EXPORT_SYMBOL(high_memory);
@@ -361,12 +359,10 @@ void free_pgd_range(struct mmu_gather *tlb,
 	} while (pgd++, addr = next, addr != end);
 }
 
-void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
+void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 		   struct vm_area_struct *vma, unsigned long floor,
 		   unsigned long ceiling, bool mm_wr_locked)
 {
-	MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
-
 	do {
 		unsigned long addr = vma->vm_start;
 		struct vm_area_struct *next;
@@ -375,7 +371,9 @@ void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
 		 * Note: USER_PGTABLES_CEILING may be passed as ceiling and may
 		 * be 0.  This will underflow and is okay.
 		 */
-		next = mas_find(&mas, ceiling - 1);
+		next = mas_find(mas, ceiling - 1);
+		if (unlikely(xa_is_zero(next)))
+			next = NULL;
 
 		/*
 		 * Hide vma from rmap and truncate_pagecache before freeing
@@ -396,7 +394,9 @@ void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
 			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
 			       && !is_vm_hugetlb_page(next)) {
 				vma = next;
-				next = mas_find(&mas, ceiling - 1);
+				next = mas_find(mas, ceiling - 1);
+				if (unlikely(xa_is_zero(next)))
+					next = NULL;
 				if (mm_wr_locked)
 					vma_start_write(vma);
 				unlink_anon_vmas(vma);
@@ -474,8 +474,6 @@ static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss)
 {
 	int i;
 
-	if (current->mm == mm)
-		sync_mm_rss(mm);
 	for (i = 0; i < NR_MM_COUNTERS; i++)
 		if (rss[i])
 			add_mm_counter(mm, i, rss[i]);
@@ -694,12 +692,23 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 out:
 	return pfn_to_page(pfn);
 }
+
+struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma,
+				  unsigned long addr, pmd_t pmd)
+{
+	struct page *page = vm_normal_page_pmd(vma, addr, pmd);
+
+	if (page)
+		return page_folio(page);
+	return NULL;
+}
 #endif
 
 static void restore_exclusive_pte(struct vm_area_struct *vma,
 				  struct page *page, unsigned long address,
 				  pte_t *ptep)
 {
+	struct folio *folio = page_folio(page);
 	pte_t orig_pte;
 	pte_t pte;
 	swp_entry_t entry;
@@ -715,14 +724,15 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
 	else if (is_writable_device_exclusive_entry(entry))
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 
-	VM_BUG_ON(pte_write(pte) && !(PageAnon(page) && PageAnonExclusive(page)));
+	VM_BUG_ON_FOLIO(pte_write(pte) && (!folio_test_anon(folio) &&
+					   PageAnonExclusive(page)), folio);
 
 	/*
 	 * No need to take a page reference as one was already
 	 * created when the swap entry was made.
 	 */
-	if (PageAnon(page))
-		page_add_anon_rmap(page, vma, address, RMAP_NONE);
+	if (folio_test_anon(folio))
+		folio_add_anon_rmap_pte(folio, page, vma, address, RMAP_NONE);
 	else
 		/*
 		 * Currently device exclusive access only supports anonymous
@@ -773,6 +783,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	unsigned long vm_flags = dst_vma->vm_flags;
 	pte_t orig_pte = ptep_get(src_pte);
 	pte_t pte = orig_pte;
+	struct folio *folio;
 	struct page *page;
 	swp_entry_t entry = pte_to_swp_entry(orig_pte);
 
@@ -795,9 +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)) {
@@ -817,6 +828,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		}
 	} else if (is_device_private_entry(entry)) {
 		page = pfn_swap_entry_to_page(entry);
+		folio = page_folio(page);
 
 		/*
 		 * Update rss count even for unaddressable pages, as
@@ -827,10 +839,10 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		 * for unaddressable pages, at some point. But for now
 		 * keep things as they are.
 		 */
-		get_page(page);
-		rss[mm_counter(page)]++;
+		folio_get(folio);
+		rss[mm_counter(folio)]++;
 		/* Cannot fail as these pages cannot get pinned. */
-		BUG_ON(page_try_dup_anon_rmap(page, false, src_vma));
+		folio_try_dup_anon_rmap_pte(folio, page, src_vma);
 
 		/*
 		 * We do not preserve soft-dirty information, because so
@@ -860,8 +872,11 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			return -EBUSY;
 		return -ENOENT;
 	} else if (is_pte_marker_entry(entry)) {
-		if (is_swapin_error_entry(entry) || userfaultfd_wp(dst_vma))
-			set_pte_at(dst_mm, addr, dst_pte, pte);
+		pte_marker marker = copy_pte_marker(entry, dst_vma);
+
+		if (marker)
+			set_pte_at(dst_mm, addr, dst_pte,
+				   make_pte_marker(marker));
 		return 0;
 	}
 	if (!userfaultfd_wp(dst_vma))
@@ -915,76 +930,124 @@ 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(page_try_dup_anon_rmap(page, false, src_vma))) {
+		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);
-		page_dup_file_rmap(page, false);
-		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);
+		VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio);
+	} else {
+		folio_dup_file_rmap_pte(folio, page);
+		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 *page_copy_prealloc(struct mm_struct *src_mm,
-		struct vm_area_struct *vma, unsigned long addr)
+static inline struct folio *folio_prealloc(struct mm_struct *src_mm,
+		struct vm_area_struct *vma, unsigned long addr, bool need_zero)
 {
 	struct folio *new_folio;
 
-	new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false);
+	if (need_zero)
+		new_folio = vma_alloc_zeroed_movable_folio(vma, addr);
+	else
+		new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
+					    addr, false);
+
 	if (!new_folio)
 		return NULL;
 
@@ -1008,10 +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;
@@ -1042,6 +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.
@@ -1071,6 +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
@@ -1078,9 +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.
@@ -1097,8 +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);
@@ -1116,10 +1187,10 @@ again:
 	} else if (ret == -EBUSY) {
 		goto out;
 	} else if (ret ==  -EAGAIN) {
-		prealloc = page_copy_prealloc(src_mm, src_vma, addr);
+		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);
 	}
 
@@ -1312,7 +1383,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		 * Use the raw variant of the seqcount_t write API to avoid
 		 * lockdep complaining about preemptibility.
 		 */
-		mmap_assert_write_locked(src_mm);
+		vma_assert_write_locked(src_vma);
 		raw_write_seqcount_begin(&src_mm->write_protect_seq);
 	}
 
@@ -1349,19 +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)
@@ -1378,7 +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 */
@@ -1388,7 +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,
@@ -1396,13 +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);
@@ -1414,8 +1589,11 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = ptep_get(pte);
+		struct folio *folio;
 		struct page *page;
+		int max_nr;
 
+		nr = 1;
 		if (pte_none(ptent))
 			continue;
 
@@ -1423,40 +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);
-			tlb_remove_tlb_entry(tlb, pte, addr);
-			zap_install_uffd_wp_if_needed(vma, addr, pte, details,
-						      ptent);
-			if (unlikely(!page))
-				continue;
-
-			delay_rmap = 0;
-			if (!PageAnon(page)) {
-				if (pte_dirty(ptent)) {
-					set_page_dirty(page);
-					if (tlb_delay_rmap(tlb)) {
-						delay_rmap = 1;
-						force_flush = 1;
-					}
-				}
-				if (pte_young(ptent) && likely(vma_has_recency(vma)))
-					mark_page_accessed(page);
-			}
-			rss[mm_counter(page)]--;
-			if (!delay_rmap) {
-				page_remove_rmap(page, vma, false);
-				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;
@@ -1466,7 +1616,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		if (is_device_private_entry(entry) ||
 		    is_device_exclusive_entry(entry)) {
 			page = pfn_swap_entry_to_page(entry);
-			if (unlikely(!should_zap_page(details, page)))
+			folio = page_folio(page);
+			if (unlikely(!should_zap_folio(details, folio)))
 				continue;
 			/*
 			 * Both device private/exclusive mappings should only
@@ -1475,10 +1626,10 @@ 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))
-				page_remove_rmap(page, vma, false);
-			put_page(page);
+				folio_remove_rmap_pte(folio, page, vma);
+			folio_put(folio);
 		} else if (!non_swap_entry(entry)) {
 			/* Genuine swap entry, hence a private anon page */
 			if (!should_zap_cows(details))
@@ -1487,10 +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
@@ -1500,16 +1651,17 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			    !zap_drop_file_uffd_wp(details))
 				continue;
 		} else if (is_hwpoison_entry(entry) ||
-			   is_swapin_error_entry(entry)) {
+			   is_poisoned_swp_entry(entry)) {
 			if (!should_zap_cows(details))
 				continue;
 		} else {
 			/* We should have covered all the swap entry types */
+			pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
 			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();
@@ -1680,7 +1832,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			if (vma->vm_file) {
 				zap_flags_t zap_flags = details ?
 				    details->zap_flags : 0;
-				__unmap_hugepage_range_final(tlb, vma, start, end,
+				__unmap_hugepage_range(tlb, vma, start, end,
 							     NULL, zap_flags);
 			}
 		} else
@@ -1691,10 +1843,12 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 /**
  * unmap_vmas - unmap a range of memory covered by a list of vma's
  * @tlb: address of the caller's struct mmu_gather
- * @mt: the maple tree
+ * @mas: the maple state
  * @vma: the starting vma
  * @start_addr: virtual address at which to start unmapping
  * @end_addr: virtual address at which to end unmapping
+ * @tree_end: The maximum index to check
+ * @mm_wr_locked: lock flag
  *
  * Unmap all pages in the vma list.
  *
@@ -1707,9 +1861,10 @@ static void unmap_single_vma(struct mmu_gather *tlb,
  * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
  * drops the lock and schedules.
  */
-void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
+void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 		struct vm_area_struct *vma, unsigned long start_addr,
-		unsigned long end_addr, bool mm_wr_locked)
+		unsigned long end_addr, unsigned long tree_end,
+		bool mm_wr_locked)
 {
 	struct mmu_notifier_range range;
 	struct zap_details details = {
@@ -1717,15 +1872,19 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		/* Careful - we need to zap private pages too! */
 		.even_cows = true,
 	};
-	MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm,
 				start_addr, end_addr);
 	mmu_notifier_invalidate_range_start(&range);
 	do {
-		unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
+		unsigned long start = start_addr;
+		unsigned long end = end_addr;
+		hugetlb_zap_begin(vma, &start, &end);
+		unmap_single_vma(tlb, vma, start, end, &details,
 				 mm_wr_locked);
-	} while ((vma = mas_find(&mas, end_addr - 1)) != NULL);
+		hugetlb_zap_end(vma, &details);
+		vma = mas_find(mas, tree_end - 1);
+	} while (vma && likely(!xa_is_zero(vma)));
 	mmu_notifier_invalidate_range_end(&range);
 }
 
@@ -1748,9 +1907,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
 				address, end);
-	if (is_vm_hugetlb_page(vma))
-		adjust_range_if_pmd_sharing_possible(vma, &range.start,
-						     &range.end);
+	hugetlb_zap_begin(vma, &range.start, &range.end);
 	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
@@ -1761,6 +1918,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	unmap_single_vma(&tlb, vma, address, end, details, false);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb);
+	hugetlb_zap_end(vma, details);
 }
 
 /**
@@ -1819,21 +1977,26 @@ pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 
 static int validate_page_before_insert(struct page *page)
 {
-	if (PageAnon(page) || PageSlab(page) || page_has_type(page))
+	struct folio *folio = page_folio(page);
+
+	if (folio_test_anon(folio) || folio_test_slab(folio) ||
+	    page_has_type(page))
 		return -EINVAL;
-	flush_dcache_page(page);
+	flush_dcache_folio(folio);
 	return 0;
 }
 
 static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
 			unsigned long addr, struct page *page, pgprot_t prot)
 {
+	struct folio *folio = page_folio(page);
+
 	if (!pte_none(ptep_get(pte)))
 		return -EBUSY;
 	/* Ok, finally just insert the thing.. */
-	get_page(page);
-	inc_mm_counter(vma->vm_mm, mm_counter_file(page));
-	page_add_file_rmap(page, vma, false);
+	folio_get(folio);
+	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;
 }
@@ -1865,7 +2028,6 @@ out:
 	return retval;
 }
 
-#ifdef pte_index
 static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte,
 			unsigned long addr, struct page *page, pgprot_t prot)
 {
@@ -1880,7 +2042,7 @@ static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte,
 }
 
 /* insert_pages() amortizes the cost of spinlock operations
- * when inserting pages in a loop. Arch *must* define pte_index.
+ * when inserting pages in a loop.
  */
 static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
 			struct page **pages, unsigned long *num, pgprot_t prot)
@@ -1939,7 +2101,6 @@ out:
 	*num = remaining_pages_total;
 	return ret;
 }
-#endif  /* ifdef pte_index */
 
 /**
  * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock.
@@ -1959,7 +2120,6 @@ out:
 int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
 			struct page **pages, unsigned long *num)
 {
-#ifdef pte_index
 	const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1;
 
 	if (addr < vma->vm_start || end_addr >= vma->vm_end)
@@ -1971,18 +2131,6 @@ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
 	}
 	/* Defer page refcount checking till we're about to map that page. */
 	return insert_pages(vma, addr, pages, num, vma->vm_page_prot);
-#else
-	unsigned long idx = 0, pgcount = *num;
-	int err = -EINVAL;
-
-	for (; idx < pgcount; ++idx) {
-		err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]);
-		if (err)
-			break;
-	}
-	*num = pgcount - idx;
-	return err;
-#endif  /* ifdef pte_index */
 }
 EXPORT_SYMBOL(vm_insert_pages);
 
@@ -2833,7 +2981,8 @@ static inline int __wp_page_copy_user(struct page *dst, struct page *src,
 	 * just copying from the original user address. If that
 	 * fails, we just zero-fill it. Live with it.
 	 */
-	kaddr = kmap_atomic(dst);
+	kaddr = kmap_local_page(dst);
+	pagefault_disable();
 	uaddr = (void __user *)(addr & PAGE_MASK);
 
 	/*
@@ -2858,7 +3007,7 @@ static inline int __wp_page_copy_user(struct page *dst, struct page *src,
 
 		entry = pte_mkyoung(vmf->orig_pte);
 		if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
-			update_mmu_cache(vma, addr, vmf->pte);
+			update_mmu_cache_range(vmf, vma, addr, vmf->pte, 1);
 	}
 
 	/*
@@ -2901,7 +3050,8 @@ warn:
 pte_unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
-	kunmap_atomic(kaddr);
+	pagefault_enable();
+	kunmap_local(kaddr);
 	flush_dcache_page(dst);
 
 	return ret;
@@ -2927,10 +3077,9 @@ static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
  *
  * We do this without the lock held, so that it can sleep if it needs to.
  */
-static vm_fault_t do_page_mkwrite(struct vm_fault *vmf)
+static vm_fault_t do_page_mkwrite(struct vm_fault *vmf, struct folio *folio)
 {
 	vm_fault_t ret;
-	struct page *page = vmf->page;
 	unsigned int old_flags = vmf->flags;
 
 	vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
@@ -2945,14 +3094,14 @@ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf)
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
 		return ret;
 	if (unlikely(!(ret & VM_FAULT_LOCKED))) {
-		lock_page(page);
-		if (!page->mapping) {
-			unlock_page(page);
+		folio_lock(folio);
+		if (!folio->mapping) {
+			folio_unlock(folio);
 			return 0; /* retry */
 		}
 		ret |= VM_FAULT_LOCKED;
 	} else
-		VM_BUG_ON_PAGE(!PageLocked(page), page);
+		VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	return ret;
 }
 
@@ -2965,20 +3114,20 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping;
-	struct page *page = vmf->page;
+	struct folio *folio = page_folio(vmf->page);
 	bool dirtied;
 	bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite;
 
-	dirtied = set_page_dirty(page);
-	VM_BUG_ON_PAGE(PageAnon(page), page);
+	dirtied = folio_mark_dirty(folio);
+	VM_BUG_ON_FOLIO(folio_test_anon(folio), folio);
 	/*
-	 * Take a local copy of the address_space - page.mapping may be zeroed
-	 * by truncate after unlock_page().   The address_space itself remains
-	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
+	 * Take a local copy of the address_space - folio.mapping may be zeroed
+	 * by truncate after folio_unlock().   The address_space itself remains
+	 * pinned by vma->vm_file's reference.  We rely on folio_unlock()'s
 	 * release semantics to prevent the compiler from undoing this copying.
 	 */
-	mapping = page_rmapping(page);
-	unlock_page(page);
+	mapping = folio_raw_mapping(folio);
+	folio_unlock(folio);
 
 	if (!page_mkwrite)
 		file_update_time(vma->vm_file);
@@ -3014,34 +3163,65 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
  * case, all we need to do here is to mark the page as writable and update
  * any related book-keeping.
  */
-static inline void wp_page_reuse(struct vm_fault *vmf)
+static inline void wp_page_reuse(struct vm_fault *vmf, struct folio *folio)
 	__releases(vmf->ptl)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct page *page = vmf->page;
 	pte_t entry;
 
 	VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE));
-	VM_BUG_ON(page && PageAnon(page) && !PageAnonExclusive(page));
 
-	/*
-	 * Clear the pages cpupid information as the existing
-	 * information potentially belongs to a now completely
-	 * unrelated process.
-	 */
-	if (page)
-		page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1);
+	if (folio) {
+		VM_BUG_ON(folio_test_anon(folio) &&
+			  !PageAnonExclusive(vmf->page));
+		/*
+		 * Clear the folio's cpupid information as the existing
+		 * information potentially belongs to a now completely
+		 * unrelated process.
+		 */
+		folio_xchg_last_cpupid(folio, (1 << LAST_CPUPID_SHIFT) - 1);
+	}
 
 	flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 	entry = pte_mkyoung(vmf->orig_pte);
 	entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
-		update_mmu_cache(vma, vmf->address, vmf->pte);
+		update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	count_vm_event(PGREUSE);
 }
 
 /*
+ * We could add a bitflag somewhere, but for now, we know that all
+ * vm_ops that have a ->map_pages have been audited and don't need
+ * the mmap_lock to be held.
+ */
+static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+
+	if (vma->vm_ops->map_pages || !(vmf->flags & FAULT_FLAG_VMA_LOCK))
+		return 0;
+	vma_end_read(vma);
+	return VM_FAULT_RETRY;
+}
+
+vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+
+	if (likely(vma->anon_vma))
+		return 0;
+	if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
+		vma_end_read(vma);
+		return VM_FAULT_RETRY;
+	}
+	if (__anon_vma_prepare(vma))
+		return VM_FAULT_OOM;
+	return 0;
+}
+
+/*
  * Handle the case of a page which we actually need to copy to a new page,
  * either due to COW or unsharing.
  *
@@ -3068,27 +3248,27 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	pte_t entry;
 	int page_copied = 0;
 	struct mmu_notifier_range range;
-	int ret;
+	vm_fault_t ret;
+	bool pfn_is_zero;
 
 	delayacct_wpcopy_start();
 
 	if (vmf->page)
 		old_folio = page_folio(vmf->page);
-	if (unlikely(anon_vma_prepare(vma)))
+	ret = vmf_anon_prepare(vmf);
+	if (unlikely(ret))
+		goto out;
+
+	pfn_is_zero = is_zero_pfn(pte_pfn(vmf->orig_pte));
+	new_folio = folio_prealloc(mm, vma, vmf->address, pfn_is_zero);
+	if (!new_folio)
 		goto oom;
 
-	if (is_zero_pfn(pte_pfn(vmf->orig_pte))) {
-		new_folio = vma_alloc_zeroed_movable_folio(vma, vmf->address);
-		if (!new_folio)
-			goto oom;
-	} else {
-		new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
-				vmf->address, false);
-		if (!new_folio)
-			goto oom;
+	if (!pfn_is_zero) {
+		int err;
 
-		ret = __wp_page_copy_user(&new_folio->page, vmf->page, vmf);
-		if (ret) {
+		err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf);
+		if (err) {
 			/*
 			 * COW failed, if the fault was solved by other,
 			 * it's fine. If not, userspace would re-fault on
@@ -3101,15 +3281,11 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 				folio_put(old_folio);
 
 			delayacct_wpcopy_end();
-			return ret == -EHWPOISON ? VM_FAULT_HWPOISON : 0;
+			return err == -EHWPOISON ? VM_FAULT_HWPOISON : 0;
 		}
 		kmsan_copy_page_meta(&new_folio->page, vmf->page);
 	}
 
-	if (mem_cgroup_charge(new_folio, mm, GFP_KERNEL))
-		goto oom_free_new;
-	folio_throttle_swaprate(new_folio, GFP_KERNEL);
-
 	__folio_mark_uptodate(new_folio);
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
@@ -3124,10 +3300,11 @@ 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 {
+			ksm_might_unmap_zero_page(mm, vmf->orig_pte);
 			inc_mm_counter(mm, MM_ANONPAGES);
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
@@ -3149,7 +3326,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		 * that left a window where the new PTE could be loaded into
 		 * some TLBs while the old PTE remains in others.
 		 */
-		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
+		ptep_clear_flush(vma, vmf->address, vmf->pte);
 		folio_add_new_anon_rmap(new_folio, vma, vmf->address);
 		folio_add_lru_vma(new_folio, vma);
 		/*
@@ -3159,7 +3336,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		 */
 		BUG_ON(unshare && pte_write(entry));
 		set_pte_at_notify(mm, vmf->address, vmf->pte, entry);
-		update_mmu_cache(vma, vmf->address, vmf->pte);
+		update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
 		if (old_folio) {
 			/*
 			 * Only after switching the pte to the new page may
@@ -3171,10 +3348,10 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			 * threads.
 			 *
 			 * The critical issue is to order this
-			 * page_remove_rmap with the ptp_clear_flush above.
-			 * Those stores are ordered by (if nothing else,)
+			 * folio_remove_rmap_pte() with the ptp_clear_flush
+			 * above. Those stores are ordered by (if nothing else,)
 			 * the barrier present in the atomic_add_negative
-			 * in page_remove_rmap.
+			 * in folio_remove_rmap_pte();
 			 *
 			 * Then the TLB flush in ptep_clear_flush ensures that
 			 * no process can access the old page before the
@@ -3183,7 +3360,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			 * mapcount is visible. So transitively, TLBs to
 			 * old page will be flushed before it can be reused.
 			 */
-			page_remove_rmap(vmf->page, vma, false);
+			folio_remove_rmap_pte(old_folio, vmf->page, vma);
 		}
 
 		/* Free the old page.. */
@@ -3195,30 +3372,26 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 	}
 
-	/*
-	 * No need to double call mmu_notifier->invalidate_range() callback as
-	 * the above ptep_clear_flush_notify() did already call it.
-	 */
-	mmu_notifier_invalidate_range_only_end(&range);
+	mmu_notifier_invalidate_range_end(&range);
 
 	if (new_folio)
 		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);
 	}
 
 	delayacct_wpcopy_end();
 	return 0;
-oom_free_new:
-	folio_put(new_folio);
 oom:
+	ret = VM_FAULT_OOM;
+out:
 	if (old_folio)
 		folio_put(old_folio);
 
 	delayacct_wpcopy_end();
-	return VM_FAULT_OOM;
+	return ret;
 }
 
 /**
@@ -3226,6 +3399,7 @@ oom:
  *			  writeable once the page is prepared
  *
  * @vmf: structure describing the fault
+ * @folio: the folio of vmf->page
  *
  * This function handles all that is needed to finish a write page fault in a
  * shared mapping due to PTE being read-only once the mapped page is prepared.
@@ -3237,7 +3411,7 @@ oom:
  * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before
  * we acquired PTE lock.
  */
-vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
+static vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf, struct folio *folio)
 {
 	WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
 	vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address,
@@ -3253,7 +3427,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		return VM_FAULT_NOPAGE;
 	}
-	wp_page_reuse(vmf);
+	wp_page_reuse(vmf, folio);
 	return 0;
 }
 
@@ -3269,50 +3443,108 @@ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf)
 		vm_fault_t ret;
 
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		ret = vmf_can_call_fault(vmf);
+		if (ret)
+			return ret;
+
 		vmf->flags |= FAULT_FLAG_MKWRITE;
 		ret = vma->vm_ops->pfn_mkwrite(vmf);
 		if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))
 			return ret;
-		return finish_mkwrite_fault(vmf);
+		return finish_mkwrite_fault(vmf, NULL);
 	}
-	wp_page_reuse(vmf);
+	wp_page_reuse(vmf, NULL);
 	return 0;
 }
 
-static vm_fault_t wp_page_shared(struct vm_fault *vmf)
+static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio)
 	__releases(vmf->ptl)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret = 0;
 
-	get_page(vmf->page);
+	folio_get(folio);
 
 	if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
 		vm_fault_t tmp;
 
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
-		tmp = do_page_mkwrite(vmf);
+		tmp = vmf_can_call_fault(vmf);
+		if (tmp) {
+			folio_put(folio);
+			return tmp;
+		}
+
+		tmp = do_page_mkwrite(vmf, folio);
 		if (unlikely(!tmp || (tmp &
 				      (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
-			put_page(vmf->page);
+			folio_put(folio);
 			return tmp;
 		}
-		tmp = finish_mkwrite_fault(vmf);
+		tmp = finish_mkwrite_fault(vmf, folio);
 		if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
-			unlock_page(vmf->page);
-			put_page(vmf->page);
+			folio_unlock(folio);
+			folio_put(folio);
 			return tmp;
 		}
 	} else {
-		wp_page_reuse(vmf);
-		lock_page(vmf->page);
+		wp_page_reuse(vmf, folio);
+		folio_lock(folio);
 	}
 	ret |= fault_dirty_shared_page(vmf);
-	put_page(vmf->page);
+	folio_put(folio);
 
 	return ret;
 }
 
+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.
+	 *
+	 * KSM doesn't necessarily raise the folio refcount.
+	 */
+	if (folio_test_ksm(folio) || folio_ref_count(folio) > 3)
+		return false;
+	if (!folio_test_lru(folio))
+		/*
+		 * We cannot easily detect+handle references from
+		 * remote LRU caches or references to LRU folios.
+		 */
+		lru_add_drain();
+	if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio))
+		return false;
+	if (!folio_trylock(folio))
+		return false;
+	if (folio_test_swapcache(folio))
+		folio_free_swap(folio);
+	if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) {
+		folio_unlock(folio);
+		return false;
+	}
+	/*
+	 * Ok, we've got the only folio reference from our mapping
+	 * and the folio is locked, it's dark out, and we're wearing
+	 * sunglasses. Hit it.
+	 */
+	folio_move_anon_rmap(folio, vma);
+	folio_unlock(folio);
+	return true;
+}
+
 /*
  * This routine handles present pages, when
  * * users try to write to a shared page (FAULT_FLAG_WRITE)
@@ -3341,11 +3573,28 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
 	struct vm_area_struct *vma = vmf->vma;
 	struct folio *folio = NULL;
+	pte_t pte;
 
 	if (likely(!unshare)) {
 		if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) {
-			pte_unmap_unlock(vmf->pte, vmf->ptl);
-			return handle_userfault(vmf, VM_UFFD_WP);
+			if (!userfaultfd_wp_async(vma)) {
+				pte_unmap_unlock(vmf->pte, vmf->ptl);
+				return handle_userfault(vmf, VM_UFFD_WP);
+			}
+
+			/*
+			 * Nothing needed (cache flush, TLB invalidations,
+			 * etc.) because we're only removing the uffd-wp bit,
+			 * which is completely invisible to the user.
+			 */
+			pte = pte_clear_uffd_wp(ptep_get(vmf->pte));
+
+			set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
+			/*
+			 * Update this to be prepared for following up CoW
+			 * handling
+			 */
+			vmf->orig_pte = pte;
 		}
 
 		/*
@@ -3359,6 +3608,9 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
 
+	if (vmf->page)
+		folio = page_folio(vmf->page);
+
 	/*
 	 * Shared mapping: we are guaranteed to have VM_WRITE and
 	 * FAULT_FLAG_WRITE set at this point.
@@ -3373,65 +3625,27 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		 */
 		if (!vmf->page)
 			return wp_pfn_shared(vmf);
-		return wp_page_shared(vmf);
+		return wp_page_shared(vmf, folio);
 	}
 
-	if (vmf->page)
-		folio = page_folio(vmf->page);
-
 	/*
 	 * Private mapping: create an exclusive anonymous page copy if reuse
 	 * is impossible. We might miss VM_WRITE for FOLL_FORCE handling.
+	 *
+	 * If we encounter a page that is marked exclusive, we must reuse
+	 * the page without further checks.
 	 */
-	if (folio && folio_test_anon(folio)) {
-		/*
-		 * If the page is exclusive to this process we must reuse the
-		 * page without further checks.
-		 */
-		if (PageAnonExclusive(vmf->page))
-			goto reuse;
-
-		/*
-		 * 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.
-		 *
-		 * KSM doesn't necessarily raise the folio refcount.
-		 */
-		if (folio_test_ksm(folio) || folio_ref_count(folio) > 3)
-			goto copy;
-		if (!folio_test_lru(folio))
-			/*
-			 * We cannot easily detect+handle references from
-			 * remote LRU caches or references to LRU folios.
-			 */
-			lru_add_drain();
-		if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio))
-			goto copy;
-		if (!folio_trylock(folio))
-			goto copy;
-		if (folio_test_swapcache(folio))
-			folio_free_swap(folio);
-		if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) {
-			folio_unlock(folio);
-			goto copy;
-		}
-		/*
-		 * Ok, we've got the only folio reference from our mapping
-		 * and the folio is locked, it's dark out, and we're wearing
-		 * sunglasses. Hit it.
-		 */
-		page_move_anon_rmap(vmf->page, vma);
-		folio_unlock(folio);
-reuse:
+	if (folio && folio_test_anon(folio) &&
+	    (PageAnonExclusive(vmf->page) || wp_can_reuse_anon_folio(folio, vma))) {
+		if (!PageAnonExclusive(vmf->page))
+			SetPageAnonExclusive(vmf->page);
 		if (unlikely(unshare)) {
 			pte_unmap_unlock(vmf->pte, vmf->ptl);
 			return 0;
 		}
-		wp_page_reuse(vmf);
+		wp_page_reuse(vmf, folio);
 		return 0;
 	}
-copy:
 	/*
 	 * Ok, we need to copy. Oh, well..
 	 */
@@ -3495,7 +3709,7 @@ void unmap_mapping_folio(struct folio *folio)
 	VM_BUG_ON(!folio_test_locked(folio));
 
 	first_index = folio->index;
-	last_index = folio->index + folio_nr_pages(folio) - 1;
+	last_index = folio_next_index(folio) - 1;
 
 	details.even_cows = false;
 	details.single_folio = folio;
@@ -3559,8 +3773,8 @@ EXPORT_SYMBOL_GPL(unmap_mapping_pages);
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows)
 {
-	pgoff_t hba = holebegin >> PAGE_SHIFT;
-	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT;
+	pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	/* Check for overflow. */
 	if (sizeof(holelen) > sizeof(hlen)) {
@@ -3582,6 +3796,7 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
 	struct folio *folio = page_folio(vmf->page);
 	struct vm_area_struct *vma = vmf->vma;
 	struct mmu_notifier_range range;
+	vm_fault_t ret;
 
 	/*
 	 * We need a reference to lock the folio because we don't hold
@@ -3594,9 +3809,10 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
 	if (!folio_try_get(folio))
 		return 0;
 
-	if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) {
+	ret = folio_lock_or_retry(folio, vmf);
+	if (ret) {
 		folio_put(folio);
-		return VM_FAULT_RETRY;
+		return ret;
 	}
 	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0,
 				vma->vm_mm, vmf->address & PAGE_MASK,
@@ -3647,7 +3863,7 @@ static vm_fault_t pte_marker_clear(struct vm_fault *vmf)
 	 * none pte.  Otherwise it means the pte could have changed, so retry.
 	 *
 	 * This should also cover the case where e.g. the pte changed
-	 * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_SWAPIN_ERROR.
+	 * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_POISONED.
 	 * So is_pte_marker() check is not enough to safely drop the pte.
 	 */
 	if (pte_same(vmf->orig_pte, ptep_get(vmf->pte)))
@@ -3693,8 +3909,8 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	/* Higher priority than uffd-wp when data corrupted */
-	if (marker & PTE_MARKER_SWAPIN_ERROR)
-		return VM_FAULT_SIGBUS;
+	if (marker & PTE_MARKER_POISONED)
+		return VM_FAULT_HWPOISON;
 
 	if (pte_marker_entry_uffd_wp(entry))
 		return pte_marker_handle_uffd_wp(vmf);
@@ -3718,21 +3934,16 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	struct page *page;
 	struct swap_info_struct *si = NULL;
 	rmap_t rmap_flags = RMAP_NONE;
+	bool need_clear_cache = false;
 	bool exclusive = false;
 	swp_entry_t entry;
 	pte_t pte;
-	int locked;
 	vm_fault_t ret = 0;
 	void *shadow = NULL;
 
 	if (!pte_unmap_same(vmf))
 		goto out;
 
-	if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
-		ret = VM_FAULT_RETRY;
-		goto out;
-	}
-
 	entry = pte_to_swp_entry(vmf->orig_pte);
 	if (unlikely(non_swap_entry(entry))) {
 		if (is_migration_entry(entry)) {
@@ -3742,6 +3953,16 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			vmf->page = pfn_swap_entry_to_page(entry);
 			ret = remove_device_exclusive_entry(vmf);
 		} else if (is_device_private_entry(entry)) {
+			if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
+				/*
+				 * migrate_to_ram is not yet ready to operate
+				 * under VMA lock.
+				 */
+				vma_end_read(vma);
+				ret = VM_FAULT_RETRY;
+				goto out;
+			}
+
 			vmf->page = pfn_swap_entry_to_page(entry);
 			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
 					vmf->address, &vmf->ptl);
@@ -3782,6 +4003,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (!folio) {
 		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
 		    __swap_count(entry) == 1) {
+			/*
+			 * Prevent parallel swapin from proceeding with
+			 * the cache flag. Otherwise, another thread may
+			 * finish swapin first, free the entry, and swapout
+			 * reusing the same entry. It's undetectable as
+			 * pte_same() returns true due to entry reuse.
+			 */
+			if (swapcache_prepare(entry)) {
+				/* Relax a bit to prevent rapid repeated page faults */
+				schedule_timeout_uninterruptible(1);
+				goto out;
+			}
+			need_clear_cache = true;
+
 			/* skip swapcache */
 			folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
 						vma, vmf->address, false);
@@ -3804,9 +4039,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 				folio_add_lru(folio);
 
-				/* To provide entry to swap_readpage() */
-				folio_set_swap_entry(folio, entry);
-				swap_readpage(page, true, NULL);
+				/* To provide entry to swap_read_folio() */
+				folio->swap = entry;
+				swap_read_folio(folio, true, NULL);
 				folio->private = NULL;
 			}
 		} else {
@@ -3843,12 +4078,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		goto out_release;
 	}
 
-	locked = folio_lock_or_retry(folio, vma->vm_mm, vmf->flags);
-
-	if (!locked) {
-		ret |= VM_FAULT_RETRY;
+	ret |= folio_lock_or_retry(folio, vmf);
+	if (ret & VM_FAULT_RETRY)
 		goto out_release;
-	}
 
 	if (swapcache) {
 		/*
@@ -3859,7 +4091,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		 * changed.
 		 */
 		if (unlikely(!folio_test_swapcache(folio) ||
-			     page_private(page) != entry.val))
+			     page_swap_entry(page).val != entry.val))
 			goto out_page;
 
 		/*
@@ -3867,15 +4099,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		 * page->index of !PageKSM() pages would be nonlinear inside the
 		 * anon VMA -- PageKSM() is lost on actual swapout.
 		 */
-		page = ksm_might_need_to_copy(page, vma, vmf->address);
-		if (unlikely(!page)) {
+		folio = ksm_might_need_to_copy(folio, vma, vmf->address);
+		if (unlikely(!folio)) {
 			ret = VM_FAULT_OOM;
+			folio = swapcache;
 			goto out_page;
-		} else if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
+		} else if (unlikely(folio == ERR_PTR(-EHWPOISON))) {
 			ret = VM_FAULT_HWPOISON;
+			folio = swapcache;
 			goto out_page;
 		}
-		folio = page_folio(page);
+		if (folio != swapcache)
+			page = folio_page(folio, 0);
 
 		/*
 		 * If we want to map a page that's in the swapcache writable, we
@@ -3993,10 +4228,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 	/* ksm created a completely new copy */
 	if (unlikely(folio != swapcache && swapcache)) {
-		page_add_new_anon_rmap(page, vma, vmf->address);
+		folio_add_new_anon_rmap(folio, vma, vmf->address);
 		folio_add_lru_vma(folio, vma);
 	} else {
-		page_add_anon_rmap(page, vma, vmf->address, rmap_flags);
+		folio_add_anon_rmap_pte(folio, page, vma, vmf->address,
+					rmap_flags);
 	}
 
 	VM_BUG_ON(!folio_test_anon(folio) ||
@@ -4026,11 +4262,14 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	}
 
 	/* No need to invalidate - it was non-present before */
-	update_mmu_cache(vma, vmf->address, vmf->pte);
+	update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
 unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
+	/* Clear the swap cache pin for direct swapin after PTL unlock */
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	if (si)
 		put_swap_device(si);
 	return ret;
@@ -4045,11 +4284,97 @@ out_release:
 		folio_unlock(swapcache);
 		folio_put(swapcache);
 	}
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	if (si)
 		put_swap_device(si);
 	return ret;
 }
 
+static bool pte_range_none(pte_t *pte, int nr_pages)
+{
+	int i;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (!pte_none(ptep_get_lockless(pte + i)))
+			return false;
+	}
+
+	return true;
+}
+
+static struct folio *alloc_anon_folio(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	unsigned long orders;
+	struct folio *folio;
+	unsigned long addr;
+	pte_t *pte;
+	gfp_t gfp;
+	int order;
+
+	/*
+	 * If uffd is active for the vma we need per-page fault fidelity to
+	 * maintain the uffd semantics.
+	 */
+	if (unlikely(userfaultfd_armed(vma)))
+		goto fallback;
+
+	/*
+	 * Get a list of all the (large) orders below PMD_ORDER that are enabled
+	 * for this vma. Then filter out the orders that can't be allocated over
+	 * the faulting address and still be fully contained in the vma.
+	 */
+	orders = thp_vma_allowable_orders(vma, vma->vm_flags, false, true, true,
+					  BIT(PMD_ORDER) - 1);
+	orders = thp_vma_suitable_orders(vma, vmf->address, orders);
+
+	if (!orders)
+		goto fallback;
+
+	pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK);
+	if (!pte)
+		return ERR_PTR(-EAGAIN);
+
+	/*
+	 * Find the highest order where the aligned range is completely
+	 * pte_none(). Note that all remaining orders will be completely
+	 * pte_none().
+	 */
+	order = highest_order(orders);
+	while (orders) {
+		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
+		if (pte_range_none(pte + pte_index(addr), 1 << order))
+			break;
+		order = next_order(&orders, order);
+	}
+
+	pte_unmap(pte);
+
+	/* Try allocating the highest of the remaining orders. */
+	gfp = vma_thp_gfp_mask(vma);
+	while (orders) {
+		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 folio_prealloc(vma->vm_mm, vma, vmf->address, true);
+}
+
 /*
  * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
@@ -4059,9 +4384,12 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 {
 	bool uffd_wp = vmf_orig_pte_uffd_wp(vmf);
 	struct vm_area_struct *vma = vmf->vma;
+	unsigned long addr = vmf->address;
 	struct folio *folio;
 	vm_fault_t ret = 0;
+	int nr_pages = 1;
 	pte_t entry;
+	int i;
 
 	/* File mapping without ->vm_ops ? */
 	if (vma->vm_flags & VM_SHARED)
@@ -4101,13 +4429,15 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	/* Allocate our own private page. */
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
-	folio = vma_alloc_zeroed_movable_folio(vma, vmf->address);
+	/* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */
+	folio = alloc_anon_folio(vmf);
+	if (IS_ERR(folio))
+		return 0;
 	if (!folio)
 		goto oom;
 
-	if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL))
-		goto oom_free_page;
-	folio_throttle_swaprate(folio, GFP_KERNEL);
+	nr_pages = folio_nr_pages(folio);
+	addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
 
 	/*
 	 * The memory barrier inside __folio_mark_uptodate makes sure that
@@ -4119,14 +4449,17 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	entry = mk_pte(&folio->page, vma->vm_page_prot);
 	entry = pte_sw_mkyoung(entry);
 	if (vma->vm_flags & VM_WRITE)
-		entry = pte_mkwrite(pte_mkdirty(entry));
+		entry = pte_mkwrite(pte_mkdirty(entry), vma);
 
-	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
-			&vmf->ptl);
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl);
 	if (!vmf->pte)
 		goto release;
-	if (vmf_pte_changed(vmf)) {
-		update_mmu_tlb(vma, vmf->address, vmf->pte);
+	if (nr_pages == 1 && vmf_pte_changed(vmf)) {
+		update_mmu_tlb(vma, addr, vmf->pte);
+		goto release;
+	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
+		for (i = 0; i < nr_pages; i++)
+			update_mmu_tlb(vma, addr + PAGE_SIZE * i, vmf->pte + i);
 		goto release;
 	}
 
@@ -4141,16 +4474,17 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 		return handle_userfault(vmf, VM_UFFD_MISSING);
 	}
 
-	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
-	folio_add_new_anon_rmap(folio, vma, vmf->address);
+	folio_ref_add(folio, nr_pages - 1);
+	add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
+	folio_add_new_anon_rmap(folio, vma, addr);
 	folio_add_lru_vma(folio, vma);
 setpte:
 	if (uffd_wp)
 		entry = pte_mkuffd_wp(entry);
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
+	set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages);
 
 	/* No need to invalidate - it was non-present before */
-	update_mmu_cache(vma, vmf->address, vmf->pte);
+	update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr_pages);
 unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -4158,8 +4492,6 @@ unlock:
 release:
 	folio_put(folio);
 	goto unlock;
-oom_free_page:
-	folio_put(folio);
 oom:
 	return VM_FAULT_OOM;
 }
@@ -4172,6 +4504,7 @@ oom:
 static vm_fault_t __do_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio;
 	vm_fault_t ret;
 
 	/*
@@ -4200,27 +4533,26 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 			    VM_FAULT_DONE_COW)))
 		return ret;
 
+	folio = page_folio(vmf->page);
 	if (unlikely(PageHWPoison(vmf->page))) {
-		struct page *page = vmf->page;
 		vm_fault_t poisonret = VM_FAULT_HWPOISON;
 		if (ret & VM_FAULT_LOCKED) {
-			if (page_mapped(page))
-				unmap_mapping_pages(page_mapping(page),
-						    page->index, 1, false);
-			/* Retry if a clean page was removed from the cache. */
-			if (invalidate_inode_page(page))
+			if (page_mapped(vmf->page))
+				unmap_mapping_folio(folio);
+			/* Retry if a clean folio was removed from the cache. */
+			if (mapping_evict_folio(folio->mapping, folio))
 				poisonret = VM_FAULT_NOPAGE;
-			unlock_page(page);
+			folio_unlock(folio);
 		}
-		put_page(page);
+		folio_put(folio);
 		vmf->page = NULL;
 		return poisonret;
 	}
 
 	if (unlikely(!(ret & VM_FAULT_LOCKED)))
-		lock_page(vmf->page);
+		folio_lock(folio);
 	else
-		VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page);
+		VM_BUG_ON_PAGE(!folio_test_locked(folio), vmf->page);
 
 	return ret;
 }
@@ -4241,18 +4573,17 @@ static void deposit_prealloc_pte(struct vm_fault *vmf)
 
 vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	pmd_t entry;
-	int i;
 	vm_fault_t ret = VM_FAULT_FALLBACK;
 
-	if (!transhuge_vma_suitable(vma, haddr))
+	if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
 		return ret;
 
-	page = compound_head(page);
-	if (compound_order(page) != HPAGE_PMD_ORDER)
+	if (page != &folio->page || folio_order(folio) != HPAGE_PMD_ORDER)
 		return ret;
 
 	/*
@@ -4261,7 +4592,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	 * check.  This kind of THP just can be PTE mapped.  Access to
 	 * the corrupted subpage should trigger SIGBUS as expected.
 	 */
-	if (unlikely(PageHasHWPoisoned(page)))
+	if (unlikely(folio_test_has_hwpoisoned(folio)))
 		return ret;
 
 	/*
@@ -4278,15 +4609,14 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	if (unlikely(!pmd_none(*vmf->pmd)))
 		goto out;
 
-	for (i = 0; i < HPAGE_PMD_NR; i++)
-		flush_icache_page(vma, page + i);
+	flush_icache_pages(vma, page, HPAGE_PMD_NR);
 
 	entry = mk_huge_pmd(page, vma->vm_page_prot);
 	if (write)
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
-	add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR);
-	page_add_file_rmap(page, vma, true);
+	add_mm_counter(vma->vm_mm, mm_counter_file(folio), HPAGE_PMD_NR);
+	folio_add_file_rmap_pmd(folio, page, vma);
 
 	/*
 	 * deposit and withdraw with pmd lock held
@@ -4312,15 +4642,24 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 }
 #endif
 
-void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
+/**
+ * set_pte_range - Set a range of PTEs to point to pages in a folio.
+ * @vmf: Fault decription.
+ * @folio: The folio that contains @page.
+ * @page: The first page to create a PTE for.
+ * @nr: The number of PTEs to create.
+ * @addr: The first address to create a PTE for.
+ */
+void set_pte_range(struct vm_fault *vmf, struct folio *folio,
+		struct page *page, unsigned int nr, unsigned long addr)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool uffd_wp = vmf_orig_pte_uffd_wp(vmf);
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
-	bool prefault = vmf->address != addr;
+	bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE);
 	pte_t entry;
 
-	flush_icache_page(vma, page);
+	flush_icache_pages(vma, page, nr);
 	entry = mk_pte(page, vma->vm_page_prot);
 
 	if (prefault && arch_wants_old_prefaulted_pte())
@@ -4334,14 +4673,18 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 		entry = pte_mkuffd_wp(entry);
 	/* copy-on-write page */
 	if (write && !(vma->vm_flags & VM_SHARED)) {
-		inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
-		page_add_new_anon_rmap(page, vma, addr);
-		lru_cache_add_inactive_or_unevictable(page, vma);
+		add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr);
+		VM_BUG_ON_FOLIO(nr != 1, folio);
+		folio_add_new_anon_rmap(folio, vma, addr);
+		folio_add_lru_vma(folio, vma);
 	} else {
-		inc_mm_counter(vma->vm_mm, mm_counter_file(page));
-		page_add_file_rmap(page, vma, false);
+		add_mm_counter(vma->vm_mm, mm_counter_file(folio), nr);
+		folio_add_file_rmap_ptes(folio, page, nr, vma);
 	}
-	set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
+	set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr);
+
+	/* no need to invalidate: a not-present page won't be cached */
+	update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr);
 }
 
 static bool vmf_pte_changed(struct vm_fault *vmf)
@@ -4409,11 +4752,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 
 	/* Re-check under ptl */
 	if (likely(!vmf_pte_changed(vmf))) {
-		do_set_pte(vmf, page, vmf->address);
-
-		/* no need to invalidate: a not-present page won't be cached */
-		update_mmu_cache(vma, vmf->address, vmf->pte);
+		struct folio *folio = page_folio(page);
 
+		set_pte_range(vmf, folio, page, 1, vmf->address);
 		ret = 0;
 	} else {
 		update_mmu_tlb(vma, vmf->address, vmf->pte);
@@ -4447,7 +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;
 }
@@ -4532,6 +4874,7 @@ static inline bool should_fault_around(struct vm_fault *vmf)
 static vm_fault_t do_read_fault(struct vm_fault *vmf)
 {
 	vm_fault_t ret = 0;
+	struct folio *folio;
 
 	/*
 	 * Let's call ->map_pages() first and use ->fault() as fallback
@@ -4544,35 +4887,39 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf)
 			return ret;
 	}
 
+	ret = vmf_can_call_fault(vmf);
+	if (ret)
+		return ret;
+
 	ret = __do_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 
 	ret |= finish_fault(vmf);
-	unlock_page(vmf->page);
+	folio = page_folio(vmf->page);
+	folio_unlock(folio);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
-		put_page(vmf->page);
+		folio_put(folio);
 	return ret;
 }
 
 static vm_fault_t do_cow_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio;
 	vm_fault_t ret;
 
-	if (unlikely(anon_vma_prepare(vma)))
-		return VM_FAULT_OOM;
+	ret = vmf_can_call_fault(vmf);
+	if (!ret)
+		ret = vmf_anon_prepare(vmf);
+	if (ret)
+		return ret;
 
-	vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address);
-	if (!vmf->cow_page)
+	folio = folio_prealloc(vma->vm_mm, vma, vmf->address, false);
+	if (!folio)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm,
-				GFP_KERNEL)) {
-		put_page(vmf->cow_page);
-		return VM_FAULT_OOM;
-	}
-	folio_throttle_swaprate(page_folio(vmf->cow_page), GFP_KERNEL);
+	vmf->cow_page = &folio->page;
 
 	ret = __do_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
@@ -4581,7 +4928,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
 		return ret;
 
 	copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma);
-	__SetPageUptodate(vmf->cow_page);
+	__folio_mark_uptodate(folio);
 
 	ret |= finish_fault(vmf);
 	unlock_page(vmf->page);
@@ -4590,7 +4937,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
 		goto uncharge_out;
 	return ret;
 uncharge_out:
-	put_page(vmf->cow_page);
+	folio_put(folio);
 	return ret;
 }
 
@@ -4598,21 +4945,28 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret, tmp;
+	struct folio *folio;
+
+	ret = vmf_can_call_fault(vmf);
+	if (ret)
+		return ret;
 
 	ret = __do_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 
+	folio = page_folio(vmf->page);
+
 	/*
 	 * Check if the backing address space wants to know that the page is
 	 * about to become writable
 	 */
 	if (vma->vm_ops->page_mkwrite) {
-		unlock_page(vmf->page);
-		tmp = do_page_mkwrite(vmf);
+		folio_unlock(folio);
+		tmp = do_page_mkwrite(vmf, folio);
 		if (unlikely(!tmp ||
 				(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
-			put_page(vmf->page);
+			folio_put(folio);
 			return tmp;
 		}
 	}
@@ -4620,8 +4974,8 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
 	ret |= finish_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
 					VM_FAULT_RETRY))) {
-		unlock_page(vmf->page);
-		put_page(vmf->page);
+		folio_unlock(folio);
+		folio_put(folio);
 		return ret;
 	}
 
@@ -4681,10 +5035,10 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 	return ret;
 }
 
-int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
+int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma,
 		      unsigned long addr, int page_nid, int *flags)
 {
-	get_page(page);
+	folio_get(folio);
 
 	/* Record the current PID acceesing VMA */
 	vma_set_access_pid_bit(vma);
@@ -4695,14 +5049,14 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
 		*flags |= TNF_FAULT_LOCAL;
 	}
 
-	return mpol_misplaced(page, vma, addr);
+	return mpol_misplaced(folio, vma, addr);
 }
 
 static vm_fault_t do_numa_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct page *page = NULL;
-	int page_nid = NUMA_NO_NODE;
+	struct folio *folio = NULL;
+	int nid = NUMA_NO_NODE;
 	bool writable = false;
 	int last_cpupid;
 	int target_nid;
@@ -4710,18 +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);
 
 	/*
@@ -4733,12 +5087,12 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	    can_change_pte_writable(vma, vmf->address, pte))
 		writable = true;
 
-	page = vm_normal_page(vma, vmf->address, pte);
-	if (!page || is_zone_device_page(page))
+	folio = vm_normal_folio(vma, vmf->address, pte);
+	if (!folio || folio_is_zone_device(folio))
 		goto out_map;
 
 	/* TODO: handle PTE-mapped THP */
-	if (PageCompound(page))
+	if (folio_test_large(folio))
 		goto out_map;
 
 	/*
@@ -4753,34 +5107,33 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 		flags |= TNF_NO_GROUP;
 
 	/*
-	 * Flag if the page is shared between multiple address spaces. This
+	 * Flag if the folio is shared between multiple address spaces. This
 	 * is later used when determining whether to group tasks together
 	 */
-	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
+	if (folio_estimated_sharers(folio) > 1 && (vma->vm_flags & VM_SHARED))
 		flags |= TNF_SHARED;
 
-	page_nid = page_to_nid(page);
+	nid = folio_nid(folio);
 	/*
 	 * For memory tiering mode, cpupid of slow memory page is used
 	 * to record page access time.  So use default value.
 	 */
 	if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
-	    !node_is_toptier(page_nid))
+	    !node_is_toptier(nid))
 		last_cpupid = (-1 & LAST_CPUPID_MASK);
 	else
-		last_cpupid = page_cpupid_last(page);
-	target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid,
-			&flags);
+		last_cpupid = folio_last_cpupid(folio);
+	target_nid = numa_migrate_prep(folio, vma, vmf->address, nid, &flags);
 	if (target_nid == NUMA_NO_NODE) {
-		put_page(page);
+		folio_put(folio);
 		goto out_map;
 	}
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	writable = false;
 
 	/* Migrate to the requested node */
-	if (migrate_misplaced_page(page, vma, target_nid)) {
-		page_nid = target_nid;
+	if (migrate_misplaced_folio(folio, vma, target_nid)) {
+		nid = target_nid;
 		flags |= TNF_MIGRATED;
 	} else {
 		flags |= TNF_MIGRATE_FAIL;
@@ -4796,8 +5149,8 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	}
 
 out:
-	if (page_nid != NUMA_NO_NODE)
-		task_numa_fault(last_cpupid, page_nid, 1, flags);
+	if (nid != NUMA_NO_NODE)
+		task_numa_fault(last_cpupid, nid, 1, flags);
 	return 0;
 out_map:
 	/*
@@ -4808,45 +5161,51 @@ out_map:
 	pte = pte_modify(old_pte, vma->vm_page_prot);
 	pte = pte_mkyoung(pte);
 	if (writable)
-		pte = pte_mkwrite(pte);
+		pte = pte_mkwrite(pte, vma);
 	ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
-	update_mmu_cache(vma, vmf->address, vmf->pte);
+	update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	goto out;
 }
 
 static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 {
-	if (vma_is_anonymous(vmf->vma))
+	struct vm_area_struct *vma = vmf->vma;
+	if (vma_is_anonymous(vma))
 		return do_huge_pmd_anonymous_page(vmf);
-	if (vmf->vma->vm_ops->huge_fault)
-		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
+	if (vma->vm_ops->huge_fault)
+		return vma->vm_ops->huge_fault(vmf, PMD_ORDER);
 	return VM_FAULT_FALLBACK;
 }
 
 /* `inline' is required to avoid gcc 4.1.2 build error */
 static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
 	vm_fault_t ret;
 
-	if (vma_is_anonymous(vmf->vma)) {
+	if (vma_is_anonymous(vma)) {
 		if (likely(!unshare) &&
-		    userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
+		    userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) {
+			if (userfaultfd_wp_async(vmf->vma))
+				goto split;
 			return handle_userfault(vmf, VM_UFFD_WP);
+		}
 		return do_huge_pmd_wp_page(vmf);
 	}
 
-	if (vmf->vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
-		if (vmf->vma->vm_ops->huge_fault) {
-			ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
+	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
+		if (vma->vm_ops->huge_fault) {
+			ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER);
 			if (!(ret & VM_FAULT_FALLBACK))
 				return ret;
 		}
 	}
 
+split:
 	/* COW or write-notify handled on pte level: split pmd. */
-	__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
+	__split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL);
 
 	return VM_FAULT_FALLBACK;
 }
@@ -4855,11 +5214,12 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 {
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
 	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+	struct vm_area_struct *vma = vmf->vma;
 	/* No support for anonymous transparent PUD pages yet */
-	if (vma_is_anonymous(vmf->vma))
+	if (vma_is_anonymous(vma))
 		return VM_FAULT_FALLBACK;
-	if (vmf->vma->vm_ops->huge_fault)
-		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+	if (vma->vm_ops->huge_fault)
+		return vma->vm_ops->huge_fault(vmf, PUD_ORDER);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 	return VM_FAULT_FALLBACK;
 }
@@ -4868,21 +5228,22 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
 {
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
 	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret;
 
 	/* No support for anonymous transparent PUD pages yet */
-	if (vma_is_anonymous(vmf->vma))
+	if (vma_is_anonymous(vma))
 		goto split;
-	if (vmf->vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
-		if (vmf->vma->vm_ops->huge_fault) {
-			ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
+		if (vma->vm_ops->huge_fault) {
+			ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER);
 			if (!(ret & VM_FAULT_FALLBACK))
 				return ret;
 		}
 	}
 split:
 	/* COW or write-notify not handled on PUD level: split pud.*/
-	__split_huge_pud(vmf->vma, vmf->pud, vmf->address);
+	__split_huge_pud(vma, vmf->pud, vmf->address);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 	return VM_FAULT_FALLBACK;
 }
@@ -4959,7 +5320,8 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 	entry = pte_mkyoung(entry);
 	if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry,
 				vmf->flags & FAULT_FLAG_WRITE)) {
-		update_mmu_cache(vmf->vma, vmf->address, vmf->pte);
+		update_mmu_cache_range(vmf, vmf->vma, vmf->address,
+				vmf->pte, 1);
 	} else {
 		/* Skip spurious TLB flush for retried page fault */
 		if (vmf->flags & FAULT_FLAG_TRIED)
@@ -4980,10 +5342,10 @@ unlock:
 }
 
 /*
- * By the time we get here, we already hold the mm semaphore
- *
- * The mmap_lock may have been released depending on flags and our
- * return value.  See filemap_fault() and __folio_lock_or_retry().
+ * On entry, we hold either the VMA lock or the mmap_lock
+ * (FAULT_FLAG_VMA_LOCK tells you which).  If VM_FAULT_RETRY is set in
+ * the result, the mmap_lock is not held on exit.  See filemap_fault()
+ * and __folio_lock_or_retry().
  */
 static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		unsigned long address, unsigned int flags)
@@ -5012,7 +5374,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		return VM_FAULT_OOM;
 retry_pud:
 	if (pud_none(*vmf.pud) &&
-	    hugepage_vma_check(vma, vm_flags, false, true, true)) {
+	    thp_vma_allowable_order(vma, vm_flags, false, true, true, PUD_ORDER)) {
 		ret = create_huge_pud(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
@@ -5046,7 +5408,7 @@ retry_pud:
 		goto retry_pud;
 
 	if (pmd_none(*vmf.pmd) &&
-	    hugepage_vma_check(vma, vm_flags, false, true, true)) {
+	    thp_vma_allowable_order(vma, vm_flags, false, true, true, PMD_ORDER)) {
 		ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
@@ -5081,7 +5443,7 @@ retry_pud:
 
 /**
  * mm_account_fault - Do page fault accounting
- *
+ * @mm: mm from which memcg should be extracted. It can be NULL.
  * @regs: the pt_regs struct pointer.  When set to NULL, will skip accounting
  *        of perf event counters, but we'll still do the per-task accounting to
  *        the task who triggered this page fault.
@@ -5189,6 +5551,17 @@ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma,
 				 !is_cow_mapping(vma->vm_flags)))
 			return VM_FAULT_SIGSEGV;
 	}
+#ifdef CONFIG_PER_VMA_LOCK
+	/*
+	 * Per-VMA locks can't be used with FAULT_FLAG_RETRY_NOWAIT because of
+	 * the assumption that lock is dropped on VM_FAULT_RETRY.
+	 */
+	if (WARN_ON_ONCE((*flags &
+			(FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)) ==
+			(FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)))
+		return VM_FAULT_SIGSEGV;
+#endif
+
 	return 0;
 }
 
@@ -5261,7 +5634,7 @@ static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs
 		return true;
 
 	if (regs && !user_mode(regs)) {
-		unsigned long ip = instruction_pointer(regs);
+		unsigned long ip = exception_ip(regs);
 		if (!search_exception_tables(ip))
 			return false;
 	}
@@ -5286,7 +5659,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r
 {
 	mmap_read_unlock(mm);
 	if (regs && !user_mode(regs)) {
-		unsigned long ip = instruction_pointer(regs);
+		unsigned long ip = exception_ip(regs);
 		if (!search_exception_tables(ip))
 			return false;
 	}
@@ -5386,10 +5759,6 @@ retry:
 	if (!vma)
 		goto inval;
 
-	/* Only anonymous and tcp vmas are supported for now */
-	if (!vma_is_anonymous(vma) && !vma_is_tcp(vma))
-		goto inval;
-
 	if (!vma_start_read(vma))
 		goto inval;
 
@@ -5399,14 +5768,7 @@ retry:
 	 * concurrent mremap() with MREMAP_DONTUNMAP could dissociate the VMA
 	 * from its anon_vma.
 	 */
-	if (unlikely(!vma->anon_vma && !vma_is_tcp(vma)))
-		goto inval_end_read;
-
-	/*
-	 * Due to the possibility of userfault handler dropping mmap_lock, avoid
-	 * it for now and fall back to page fault handling under mmap_lock.
-	 */
-	if (userfaultfd_armed(vma))
+	if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma))
 		goto inval_end_read;
 
 	/* Check since vm_start/vm_end might change before we lock the VMA */
@@ -5611,6 +5973,10 @@ int follow_phys(struct vm_area_struct *vma,
 		goto out;
 	pte = ptep_get(ptep);
 
+	/* Never return PFNs of anon folios in COW mappings. */
+	if (vm_normal_folio(vma, address, pte))
+		goto unlock;
+
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
 		goto unlock;
 
@@ -5693,8 +6059,8 @@ EXPORT_SYMBOL_GPL(generic_access_phys);
 /*
  * Access another process' address space as given in mm.
  */
-int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf,
-		       int len, unsigned int gup_flags)
+static int __access_remote_vm(struct mm_struct *mm, unsigned long addr,
+			      void *buf, int len, unsigned int gup_flags)
 {
 	void *old_buf = buf;
 	int write = gup_flags & FOLL_WRITE;
@@ -5717,7 +6083,7 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf,
 		struct page *page = get_user_page_vma_remote(mm, addr,
 							     gup_flags, &vma);
 
-		if (IS_ERR_OR_NULL(page)) {
+		if (IS_ERR(page)) {
 			/* We might need to expand the stack to access it */
 			vma = vma_lookup(mm, addr);
 			if (!vma) {
@@ -5731,7 +6097,6 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf,
 				continue;
 			}
 
-
 			/*
 			 * Check if this is a VM_IO | VM_PFNMAP VMA, which
 			 * we can access using slightly different code.
@@ -5750,7 +6115,7 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf,
 			if (bytes > PAGE_SIZE-offset)
 				bytes = PAGE_SIZE-offset;
 
-			maddr = kmap(page);
+			maddr = kmap_local_page(page);
 			if (write) {
 				copy_to_user_page(vma, page, addr,
 						  maddr + offset, buf, bytes);
@@ -5759,8 +6124,7 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf,
 				copy_from_user_page(vma, page, addr,
 						    buf, maddr + offset, bytes);
 			}
-			kunmap(page);
-			put_page(page);
+			unmap_and_put_page(page, maddr);
 		}
 		len -= bytes;
 		buf += bytes;
@@ -5939,7 +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;
 }
 
@@ -5989,10 +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;
@@ -6059,19 +6424,19 @@ void __init ptlock_cache_init(void)
 			SLAB_PANIC, NULL);
 }
 
-bool ptlock_alloc(struct page *page)
+bool ptlock_alloc(struct ptdesc *ptdesc)
 {
 	spinlock_t *ptl;
 
 	ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
 	if (!ptl)
 		return false;
-	page->ptl = ptl;
+	ptdesc->ptl = ptl;
 	return true;
 }
 
-void ptlock_free(struct page *page)
+void ptlock_free(struct ptdesc *ptdesc)
 {
-	kmem_cache_free(page_ptl_cachep, page->ptl);
+	kmem_cache_free(page_ptl_cachep, ptdesc->ptl);
 }
 #endif