xref: /linux/mm/rmap.c (revision a52a93358ac2bef65f15e0069cd410a2b59ae03b)

// SPDX-License-Identifier: GPL-2.0
/*
 * mm/rmap.c - physical to virtual reverse mappings
 *
 * Copyright 2001, Rik van Riel <riel@conectiva.com.br>
 *
 * Simple, low overhead reverse mapping scheme.
 * Please try to keep this thing as modular as possible.
 *
 * Provides methods for unmapping each kind of mapped page:
 * the anon methods track anonymous pages, and
 * the file methods track pages belonging to an inode.
 *
 * Original design by Rik van Riel <riel@conectiva.com.br> 2001
 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
 * Contributions by Hugh Dickins 2003, 2004
 */

/*
 * Lock ordering in mm:
 *
 * inode->i_rwsem	(while writing or truncating, not reading or faulting)
 *   mm->mmap_lock
 *     mapping->invalidate_lock (in filemap_fault)
 *       folio_lock
 *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below)
 *           vma_start_write
 *             mapping->i_mmap_rwsem
 *               anon_vma->rwsem
 *                 mm->page_table_lock or pte_lock
 *                   swap_lock (in swap_duplicate, swap_info_get)
 *                     mmlist_lock (in mmput, drain_mmlist and others)
 *                     mapping->private_lock (in block_dirty_folio)
 *                         i_pages lock (widely used)
 *                           lruvec->lru_lock (in folio_lruvec_lock_irq)
 *                     inode->i_lock (in set_page_dirty's __mark_inode_dirty)
 *                     bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
 *                       sb_lock (within inode_lock in fs/fs-writeback.c)
 *                       i_pages lock (widely used, in set_page_dirty,
 *                                 in arch-dependent flush_dcache_mmap_lock,
 *                                 within bdi.wb->list_lock in __sync_single_inode)
 *
 * anon_vma->rwsem,mapping->i_mmap_rwsem   (memory_failure, collect_procs_anon)
 *   ->tasklist_lock
 *     pte map lock
 *
 * hugetlbfs PageHuge() take locks in this order:
 *   hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
 *     vma_lock (hugetlb specific lock for pmd_sharing)
 *       mapping->i_mmap_rwsem (also used for hugetlb pmd sharing)
 *         folio_lock
 */

#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/leafops.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/huge_mm.h>
#include <linux/backing-dev.h>
#include <linux/page_idle.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>
#include <linux/mm_inline.h>
#include <linux/oom.h>

#include <asm/tlb.h>

#define CREATE_TRACE_POINTS
#include <trace/events/migrate.h>

#include "internal.h"
#include "swap.h"

static struct kmem_cache *anon_vma_cachep;
static struct kmem_cache *anon_vma_chain_cachep;

static inline struct anon_vma *anon_vma_alloc(void)
{
	struct anon_vma *anon_vma;

	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
	if (anon_vma) {
		atomic_set(&anon_vma->refcount, 1);
		anon_vma->num_children = 0;
		anon_vma->num_active_vmas = 0;
		anon_vma->parent = anon_vma;
		/*
		 * Initialise the anon_vma root to point to itself. If called
		 * from fork, the root will be reset to the parents anon_vma.
		 */
		anon_vma->root = anon_vma;
	}

	return anon_vma;
}

static inline void anon_vma_free(struct anon_vma *anon_vma)
{
	VM_BUG_ON(atomic_read(&anon_vma->refcount));

	/*
	 * Synchronize against folio_lock_anon_vma_read() such that
	 * we can safely hold the lock without the anon_vma getting
	 * freed.
	 *
	 * Relies on the full mb implied by the atomic_dec_and_test() from
	 * put_anon_vma() against the acquire barrier implied by
	 * down_read_trylock() from folio_lock_anon_vma_read(). This orders:
	 *
	 * folio_lock_anon_vma_read()	VS	put_anon_vma()
	 *   down_read_trylock()		  atomic_dec_and_test()
	 *   LOCK				  MB
	 *   atomic_read()			  rwsem_is_locked()
	 *
	 * LOCK should suffice since the actual taking of the lock must
	 * happen _before_ what follows.
	 */
	might_sleep();
	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
		anon_vma_lock_write(anon_vma);
		anon_vma_unlock_write(anon_vma);
	}

	kmem_cache_free(anon_vma_cachep, anon_vma);
}

static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp)
{
	return kmem_cache_alloc(anon_vma_chain_cachep, gfp);
}

static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
{
	kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
}

static void anon_vma_chain_assign(struct vm_area_struct *vma,
				  struct anon_vma_chain *avc,
				  struct anon_vma *anon_vma)
{
	avc->vma = vma;
	avc->anon_vma = anon_vma;
	list_add(&avc->same_vma, &vma->anon_vma_chain);
}

/**
 * __anon_vma_prepare - attach an anon_vma to a memory region
 * @vma: the memory region in question
 *
 * This makes sure the memory mapping described by 'vma' has
 * an 'anon_vma' attached to it, so that we can associate the
 * anonymous pages mapped into it with that anon_vma.
 *
 * The common case will be that we already have one, which
 * is handled inline by anon_vma_prepare(). But if
 * not we either need to find an adjacent mapping that we
 * can re-use the anon_vma from (very common when the only
 * reason for splitting a vma has been mprotect()), or we
 * allocate a new one.
 *
 * Anon-vma allocations are very subtle, because we may have
 * optimistically looked up an anon_vma in folio_lock_anon_vma_read()
 * and that may actually touch the rwsem even in the newly
 * allocated vma (it depends on RCU to make sure that the
 * anon_vma isn't actually destroyed).
 *
 * As a result, we need to do proper anon_vma locking even
 * for the new allocation. At the same time, we do not want
 * to do any locking for the common case of already having
 * an anon_vma.
 */
int __anon_vma_prepare(struct vm_area_struct *vma)
{
	struct mm_struct *mm = vma->vm_mm;
	struct anon_vma *anon_vma, *allocated;
	struct anon_vma_chain *avc;

	mmap_assert_locked(mm);
	might_sleep();

	avc = anon_vma_chain_alloc(GFP_KERNEL);
	if (!avc)
		goto out_enomem;

	anon_vma = find_mergeable_anon_vma(vma);
	allocated = NULL;
	if (!anon_vma) {
		anon_vma = anon_vma_alloc();
		if (unlikely(!anon_vma))
			goto out_enomem_free_avc;
		anon_vma->num_children++; /* self-parent link for new root */
		allocated = anon_vma;
	}

	anon_vma_lock_write(anon_vma);
	/* page_table_lock to protect against threads */
	spin_lock(&mm->page_table_lock);
	if (likely(!vma->anon_vma)) {
		/*
		 * Make anon_vma fields visible before anon_vma is published.
		 * Paired with an address dependency in reusable_anon_vma().
		 */
		smp_store_release(&vma->anon_vma, anon_vma);
		anon_vma_chain_assign(vma, avc, anon_vma);
		anon_rmap_tree_insert(avc, anon_vma);
		anon_vma->num_active_vmas++;
		allocated = NULL;
		avc = NULL;
	}
	spin_unlock(&mm->page_table_lock);
	anon_vma_unlock_write(anon_vma);

	if (unlikely(allocated))
		put_anon_vma(allocated);
	if (unlikely(avc))
		anon_vma_chain_free(avc);

	return 0;

 out_enomem_free_avc:
	anon_vma_chain_free(avc);
 out_enomem:
	return -ENOMEM;
}

static void check_anon_vma_clone(struct vm_area_struct *dst,
				 struct vm_area_struct *src,
				 enum vma_operation operation)
{
	/* The write lock must be held. */
	mmap_assert_write_locked(src->vm_mm);
	/* If not a fork then must be on same mm. */
	VM_WARN_ON_ONCE(operation != VMA_OP_FORK && dst->vm_mm != src->vm_mm);

	/* If we have anything to do src->anon_vma must be provided. */
	VM_WARN_ON_ONCE(!src->anon_vma && !list_empty(&src->anon_vma_chain));
	VM_WARN_ON_ONCE(!src->anon_vma && dst->anon_vma);
	/* We are establishing a new anon_vma_chain. */
	VM_WARN_ON_ONCE(!list_empty(&dst->anon_vma_chain));
	/*
	 * On fork, dst->anon_vma is set NULL (temporarily). Otherwise, anon_vma
	 * must be the same across dst and src.
	 */
	VM_WARN_ON_ONCE(dst->anon_vma && dst->anon_vma != src->anon_vma);
	/*
	 * Essentially equivalent to above - if not a no-op, we should expect
	 * dst->anon_vma to be set for everything except a fork.
	 */
	VM_WARN_ON_ONCE(operation != VMA_OP_FORK && src->anon_vma &&
			!dst->anon_vma);
	/* For the anon_vma to be compatible, it can only be singular. */
	VM_WARN_ON_ONCE(operation == VMA_OP_MERGE_UNFAULTED &&
			!list_is_singular(&src->anon_vma_chain));
#ifdef CONFIG_PER_VMA_LOCK
	/* Only merging an unfaulted VMA leaves the destination attached. */
	VM_WARN_ON_ONCE(operation != VMA_OP_MERGE_UNFAULTED &&
			vma_is_attached(dst));
#endif
}

static void maybe_reuse_anon_vma(struct vm_area_struct *dst,
		struct anon_vma *anon_vma)
{
	/* If already populated, nothing to do.*/
	if (dst->anon_vma)
		return;

	/*
	 * We reuse an anon_vma if any linking VMAs were unmapped and it has
	 * only a single child at most.
	 */
	if (anon_vma->num_active_vmas > 0)
		return;
	if (anon_vma->num_children > 1)
		return;

	dst->anon_vma = anon_vma;
	anon_vma->num_active_vmas++;
}

static void cleanup_partial_anon_vmas(struct vm_area_struct *vma);

/**
 * anon_vma_clone - Establishes new anon_vma_chain objects in @dst linking to
 * all of the anon_vma objects contained within @src anon_vma_chain's.
 * @dst: The destination VMA with an empty anon_vma_chain.
 * @src: The source VMA we wish to duplicate.
 * @operation: The type of operation which resulted in the clone.
 *
 * This is the heart of the VMA side of the anon_vma implementation - we invoke
 * this function whenever we need to set up a new VMA's anon_vma state.
 *
 * This is invoked for:
 *
 * - VMA Merge, but only when @dst is unfaulted and @src is faulted - meaning we
 *   clone @src into @dst.
 * - VMA split.
 * - VMA (m)remap.
 * - Fork of faulted VMA.
 *
 * In all cases other than fork this is simply a duplication. Fork additionally
 * adds a new active anon_vma.
 *
 * ONLY in the case of fork do we try to 'reuse' existing anon_vma's in an
 * anon_vma hierarchy, reusing anon_vma's which have no VMA associated with them
 * but do have a single child. This is to avoid waste of memory when repeatedly
 * forking.
 *
 * Returns: 0 on success, -ENOMEM on failure.
 */
int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src,
		   enum vma_operation operation)
{
	struct anon_vma_chain *avc, *pavc;
	struct anon_vma *active_anon_vma = src->anon_vma;

	check_anon_vma_clone(dst, src, operation);

	if (!active_anon_vma)
		return 0;

	/*
	 * Allocate AVCs. We don't need an anon_vma lock for this as we
	 * are not updating the anon_vma rbtree nor are we changing
	 * anon_vma statistics.
	 *
	 * Either src, dst have the same mm for which we hold an exclusive mmap
	 * write lock, or we are forking and we hold it on src->vm_mm and dst is
	 * not yet accessible to other threads so there's no possibliity of the
	 * unlinked AVC's being observed yet.
	 */
	list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) {
		avc = anon_vma_chain_alloc(GFP_KERNEL);
		if (!avc)
			goto enomem_failure;

		anon_vma_chain_assign(dst, avc, pavc->anon_vma);
	}

	/*
	 * Now link the anon_vma's back to the newly inserted AVCs.
	 * Note that all anon_vma's share the same root.
	 */
	anon_vma_lock_write(active_anon_vma);
	list_for_each_entry_reverse(avc, &dst->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma = avc->anon_vma;

		anon_rmap_tree_insert(avc, anon_vma);
		if (operation == VMA_OP_FORK)
			maybe_reuse_anon_vma(dst, anon_vma);
	}

	if (operation != VMA_OP_FORK)
		dst->anon_vma->num_active_vmas++;

	anon_vma_unlock_write(active_anon_vma);
	return 0;

 enomem_failure:
	cleanup_partial_anon_vmas(dst);
	return -ENOMEM;
}

/*
 * Attach vma to its own anon_vma, as well as to the anon_vmas that
 * the corresponding VMA in the parent process is attached to.
 * Returns 0 on success, non-zero on failure.
 */
int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
{
	struct anon_vma_chain *avc;
	struct anon_vma *anon_vma;
	int rc;

	/* Don't bother if the parent process has no anon_vma here. */
	if (!pvma->anon_vma)
		return 0;

	/* Drop inherited anon_vma, we'll reuse existing or allocate new. */
	vma->anon_vma = NULL;

	anon_vma = anon_vma_alloc();
	if (!anon_vma)
		return -ENOMEM;
	avc = anon_vma_chain_alloc(GFP_KERNEL);
	if (!avc) {
		put_anon_vma(anon_vma);
		return -ENOMEM;
	}

	/*
	 * First, attach the new VMA to the parent VMA's anon_vmas,
	 * so rmap can find non-COWed pages in child processes.
	 */
	rc = anon_vma_clone(vma, pvma, VMA_OP_FORK);
	/* An error arose or an existing anon_vma was reused, all done then. */
	if (rc || vma->anon_vma) {
		put_anon_vma(anon_vma);
		anon_vma_chain_free(avc);
		return rc;
	}

	/*
	 * OK no reuse, so add our own anon_vma.
	 *
	 * Since it is not linked anywhere we can safely manipulate anon_vma
	 * fields without a lock.
	 */

	anon_vma->num_active_vmas = 1;
	/*
	 * The root anon_vma's rwsem is the lock actually used when we
	 * lock any of the anon_vmas in this anon_vma tree.
	 */
	anon_vma->root = pvma->anon_vma->root;
	anon_vma->parent = pvma->anon_vma;
	/*
	 * With refcounts, an anon_vma can stay around longer than the
	 * process it belongs to. The root anon_vma needs to be pinned until
	 * this anon_vma is freed, because the lock lives in the root.
	 */
	get_anon_vma(anon_vma->root);
	/* Mark this anon_vma as the one where our new (COWed) pages go. */
	vma->anon_vma = anon_vma;
	anon_vma_chain_assign(vma, avc, anon_vma);
	/* Now let rmap see it. */
	anon_vma_lock_write(anon_vma);
	anon_rmap_tree_insert(avc, anon_vma);
	anon_vma->parent->num_children++;
	anon_vma_unlock_write(anon_vma);

	return 0;
}

/*
 * In the unfortunate case of anon_vma_clone() failing to allocate memory we
 * have to clean things up.
 *
 * Since we allocate anon_vma_chain's before we insert them into the interval
 * trees, we simply have to free up the AVC's and remove the entries from the
 * VMA's anon_vma_chain.
 */
static void cleanup_partial_anon_vmas(struct vm_area_struct *vma)
{
	struct anon_vma_chain *avc, *next;

	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
		list_del(&avc->same_vma);
		anon_vma_chain_free(avc);
	}

	/*
	 * The anon_vma assigned to this VMA is no longer valid, as we were not
	 * able to correctly clone AVC state. Avoid inconsistent anon_vma tree
	 * state by resetting.
	 */
	vma->anon_vma = NULL;
}

/**
 * unlink_anon_vmas() - remove all links between a VMA and anon_vma's, freeing
 * anon_vma_chain objects.
 * @vma: The VMA whose links to anon_vma objects is to be severed.
 *
 * As part of the process anon_vma_chain's are freed,
 * anon_vma->num_children,num_active_vmas is updated as required and, if the
 * relevant anon_vma references no further VMAs, its reference count is
 * decremented.
 */
void unlink_anon_vmas(struct vm_area_struct *vma)
{
	struct anon_vma_chain *avc, *next;
	struct anon_vma *active_anon_vma = vma->anon_vma;

	/* Always hold mmap lock, read-lock on unmap possibly. */
	mmap_assert_locked(vma->vm_mm);

	/* Unfaulted is a no-op. */
	if (!active_anon_vma) {
		VM_WARN_ON_ONCE(!list_empty(&vma->anon_vma_chain));
		return;
	}

	anon_vma_lock_write(active_anon_vma);

	/*
	 * Unlink each anon_vma chained to the VMA.  This list is ordered
	 * from newest to oldest, ensuring the root anon_vma gets freed last.
	 */
	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma = avc->anon_vma;

		anon_rmap_tree_remove(avc, anon_vma);

		/*
		 * Leave empty anon_vmas on the list - we'll need
		 * to free them outside the lock.
		 */
		if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) {
			anon_vma->parent->num_children--;
			continue;
		}

		list_del(&avc->same_vma);
		anon_vma_chain_free(avc);
	}

	active_anon_vma->num_active_vmas--;
	/*
	 * vma would still be needed after unlink, and anon_vma will be prepared
	 * when handle fault.
	 */
	vma->anon_vma = NULL;
	anon_vma_unlock_write(active_anon_vma);


	/*
	 * Iterate the list once more, it now only contains empty and unlinked
	 * anon_vmas, destroy them. Could not do before due to __put_anon_vma()
	 * needing to write-acquire the anon_vma->root->rwsem.
	 */
	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma = avc->anon_vma;

		VM_WARN_ON(anon_vma->num_children);
		VM_WARN_ON(anon_vma->num_active_vmas);
		put_anon_vma(anon_vma);

		list_del(&avc->same_vma);
		anon_vma_chain_free(avc);
	}
}

static void anon_vma_ctor(void *data)
{
	struct anon_vma *anon_vma = data;

	init_rwsem(&anon_vma->rwsem);
	atomic_set(&anon_vma->refcount, 0);
	anon_vma->rb_root = RB_ROOT_CACHED;
}

void __init anon_vma_init(void)
{
	anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
			0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT,
			anon_vma_ctor);
	anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain,
			SLAB_PANIC|SLAB_ACCOUNT);
}

/*
 * Getting a lock on a stable anon_vma from a page off the LRU is tricky!
 *
 * Since there is no serialization what so ever against folio_remove_rmap_*()
 * the best this function can do is return a refcount increased anon_vma
 * that might have been relevant to this page.
 *
 * The page might have been remapped to a different anon_vma or the anon_vma
 * returned may already be freed (and even reused).
 *
 * In case it was remapped to a different anon_vma, the new anon_vma will be a
 * child of the old anon_vma, and the anon_vma lifetime rules will therefore
 * ensure that any anon_vma obtained from the page will still be valid for as
 * long as we observe folio_mapped() [ hence all those folio_mapped() tests ].
 *
 * All users of this function must be very careful when walking the anon_vma
 * chain and verify that the page in question is indeed mapped in it
 * [ something equivalent to page_mapped_in_vma() ].
 *
 * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from
 * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid
 * if there is a mapcount, we can dereference the anon_vma after observing
 * those.
 *
 * NOTE: the caller should hold folio lock when calling this.
 */
struct anon_vma *folio_get_anon_vma(const struct folio *folio)
{
	struct anon_vma *anon_vma = NULL;
	unsigned long anon_mapping;

	VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);

	rcu_read_lock();
	anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
	if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON)
		goto out;
	if (!folio_mapped(folio))
		goto out;

	anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON);
	if (!atomic_inc_not_zero(&anon_vma->refcount)) {
		anon_vma = NULL;
		goto out;
	}

	/*
	 * If this folio is still mapped, then its anon_vma cannot have been
	 * freed.  But if it has been unmapped, we have no security against the
	 * anon_vma structure being freed and reused (for another anon_vma:
	 * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero()
	 * above cannot corrupt).
	 */
	if (!folio_mapped(folio)) {
		rcu_read_unlock();
		put_anon_vma(anon_vma);
		return NULL;
	}
out:
	rcu_read_unlock();

	return anon_vma;
}

/*
 * Similar to folio_get_anon_vma() except it locks the anon_vma.
 *
 * Its a little more complex as it tries to keep the fast path to a single
 * atomic op -- the trylock. If we fail the trylock, we fall back to getting a
 * reference like with folio_get_anon_vma() and then block on the mutex
 * on !rwc->try_lock case.
 */
struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio,
					  struct rmap_walk_control *rwc)
{
	struct anon_vma *anon_vma = NULL;
	struct anon_vma *root_anon_vma;
	unsigned long anon_mapping;

	VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);

	rcu_read_lock();
	anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
	if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON)
		goto out;
	if (!folio_mapped(folio))
		goto out;

	anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON);
	root_anon_vma = READ_ONCE(anon_vma->root);
	if (down_read_trylock(&root_anon_vma->rwsem)) {
		/*
		 * If the folio is still mapped, then this anon_vma is still
		 * its anon_vma, and holding the mutex ensures that it will
		 * not go away, see anon_vma_free().
		 */
		if (!folio_mapped(folio)) {
			up_read(&root_anon_vma->rwsem);
			anon_vma = NULL;
		}
		goto out;
	}

	if (rwc && rwc->try_lock) {
		anon_vma = NULL;
		rwc->contended = true;
		goto out;
	}

	/* trylock failed, we got to sleep */
	if (!atomic_inc_not_zero(&anon_vma->refcount)) {
		anon_vma = NULL;
		goto out;
	}

	if (!folio_mapped(folio)) {
		rcu_read_unlock();
		put_anon_vma(anon_vma);
		return NULL;
	}

	/* we pinned the anon_vma, its safe to sleep */
	rcu_read_unlock();
	anon_vma_lock_read(anon_vma);

	if (atomic_dec_and_test(&anon_vma->refcount)) {
		/*
		 * Oops, we held the last refcount, release the lock
		 * and bail -- can't simply use put_anon_vma() because
		 * we'll deadlock on the anon_vma_lock_write() recursion.
		 */
		anon_vma_unlock_read(anon_vma);
		__put_anon_vma(anon_vma);
		anon_vma = NULL;
	}

	return anon_vma;

out:
	rcu_read_unlock();
	return anon_vma;
}

#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
/*
 * Flush TLB entries for recently unmapped pages from remote CPUs. It is
 * important if a PTE was dirty when it was unmapped that it's flushed
 * before any IO is initiated on the page to prevent lost writes. Similarly,
 * it must be flushed before freeing to prevent data leakage.
 */
void try_to_unmap_flush(void)
{
	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;

	if (!tlb_ubc->flush_required)
		return;

	arch_tlbbatch_flush(&tlb_ubc->arch);
	tlb_ubc->flush_required = false;
	tlb_ubc->writable = false;
}

/* Flush iff there are potentially writable TLB entries that can race with IO */
void try_to_unmap_flush_dirty(void)
{
	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;

	if (tlb_ubc->writable)
		try_to_unmap_flush();
}

/*
 * Bits 0-14 of mm->tlb_flush_batched record pending generations.
 * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations.
 */
#define TLB_FLUSH_BATCH_FLUSHED_SHIFT	16
#define TLB_FLUSH_BATCH_PENDING_MASK			\
	((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1)
#define TLB_FLUSH_BATCH_PENDING_LARGE			\
	(TLB_FLUSH_BATCH_PENDING_MASK / 2)

static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
		unsigned long start, unsigned long end)
{
	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
	int batch;
	bool writable = pte_dirty(pteval);

	if (!pte_accessible(mm, pteval))
		return;

	arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, start, end);
	tlb_ubc->flush_required = true;

	/*
	 * Ensure compiler does not re-order the setting of tlb_flush_batched
	 * before the PTE is cleared.
	 */
	barrier();
	batch = atomic_read(&mm->tlb_flush_batched);
retry:
	if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) {
		/*
		 * Prevent `pending' from catching up with `flushed' because of
		 * overflow.  Reset `pending' and `flushed' to be 1 and 0 if
		 * `pending' becomes large.
		 */
		if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1))
			goto retry;
	} else {
		atomic_inc(&mm->tlb_flush_batched);
	}

	/*
	 * If the PTE was dirty then it's best to assume it's writable. The
	 * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush()
	 * before the page is queued for IO.
	 */
	if (writable)
		tlb_ubc->writable = true;
}

/*
 * Returns true if the TLB flush should be deferred to the end of a batch of
 * unmap operations to reduce IPIs.
 */
static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
{
	if (!(flags & TTU_BATCH_FLUSH))
		return false;

	return arch_tlbbatch_should_defer(mm);
}

/*
 * Reclaim unmaps pages under the PTL but do not flush the TLB prior to
 * releasing the PTL if TLB flushes are batched. It's possible for a parallel
 * operation such as mprotect or munmap to race between reclaim unmapping
 * the page and flushing the page. If this race occurs, it potentially allows
 * access to data via a stale TLB entry. Tracking all mm's that have TLB
 * batching in flight would be expensive during reclaim so instead track
 * whether TLB batching occurred in the past and if so then do a flush here
 * if required. This will cost one additional flush per reclaim cycle paid
 * by the first operation at risk such as mprotect and mumap.
 *
 * This must be called under the PTL so that an access to tlb_flush_batched
 * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise
 * via the PTL.
 */
void flush_tlb_batched_pending(struct mm_struct *mm)
{
	int batch = atomic_read(&mm->tlb_flush_batched);
	int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK;
	int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT;

	if (pending != flushed) {
		flush_tlb_mm(mm);
		/*
		 * If the new TLB flushing is pending during flushing, leave
		 * mm->tlb_flush_batched as is, to avoid losing flushing.
		 */
		atomic_cmpxchg(&mm->tlb_flush_batched, batch,
			       pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT));
	}
}
#else
static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
		unsigned long start, unsigned long end)
{
}

static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
{
	return false;
}
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */

/**
 * page_address_in_vma - The virtual address of a page in this VMA.
 * @folio: The folio containing the page.
 * @page: The page within the folio.
 * @vma: The VMA we need to know the address in.
 *
 * Calculates the user virtual address of this page in the specified VMA.
 * It is the caller's responsibility to check the page is actually
 * within the VMA.  There may not currently be a PTE pointing at this
 * page, but if a page fault occurs at this address, this is the page
 * which will be accessed.
 *
 * Context: Caller should hold a reference to the folio.  Caller should
 * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the
 * VMA from being altered.
 *
 * Return: The virtual address corresponding to this page in the VMA.
 */
unsigned long page_address_in_vma(const struct folio *folio,
		const struct page *page, const struct vm_area_struct *vma)
{
	if (folio_test_anon(folio)) {
		struct anon_vma *anon_vma = folio_anon_vma(folio);
		/*
		 * Note: swapoff's unuse_vma() is more efficient with this
		 * check, and needs it to match anon_vma when KSM is active.
		 */
		if (!vma->anon_vma || !anon_vma ||
		    vma->anon_vma->root != anon_vma->root)
			return -EFAULT;
		/* KSM folios don't reach here because of the !anon_vma check */
		return vma_anon_address(vma, page_pgoff(folio, page), 1);
	} else if (!vma->vm_file) {
		return -EFAULT;
	} else if (vma->vm_file->f_mapping != folio->mapping) {
		return -EFAULT;
	}

	return vma_filebacked_address(vma, page_pgoff(folio, page), 1);
}

/*
 * Returns the actual pmd_t* where we expect 'address' to be mapped from, or
 * NULL if it doesn't exist.  No guarantees / checks on what the pmd_t*
 * represents.
 */
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd = NULL;

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		goto out;

	p4d = p4d_offset(pgd, address);
	if (!p4d_present(*p4d))
		goto out;

	pud = pud_offset(p4d, address);
	if (!pud_present(*pud))
		goto out;

	pmd = pmd_offset(pud, address);
out:
	return pmd;
}

struct folio_referenced_arg {
	int mapcount;
	int referenced;
	vma_flags_t vma_flags;
	struct mem_cgroup *memcg;
};

/*
 * arg: folio_referenced_arg will be passed
 */
static bool folio_referenced_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long address, void *arg)
{
	struct folio_referenced_arg *pra = arg;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
	int ptes = 0, referenced = 0;
	unsigned int nr;

	while (page_vma_mapped_walk(&pvmw)) {
		address = pvmw.address;
		nr = 1;

		if (vma_test(vma, VMA_LOCKED_BIT)) {
			ptes++;
			pra->mapcount--;

			/* Only mlock fully mapped pages */
			if (pvmw.pte && ptes != pvmw.nr_pages)
				continue;

			/*
			 * All PTEs must be protected by page table lock in
			 * order to mlock the page.
			 *
			 * If page table boundary has been cross, current ptl
			 * only protect part of ptes.
			 */
			if (pvmw.flags & PVMW_PGTABLE_CROSSED)
				continue;

			/* Restore the mlock which got missed */
			mlock_vma_folio(folio, vma);
			page_vma_mapped_walk_done(&pvmw);
			vma_flags_set(&pra->vma_flags, VMA_LOCKED_BIT);
			return false; /* To break the loop */
		}

		/*
		 * Skip the non-shared swapbacked folio mapped solely by
		 * the exiting or OOM-reaped process. This avoids redundant
		 * swap-out followed by an immediate unmap.
		 */
		if ((!atomic_read(&vma->vm_mm->mm_users) ||
		    check_stable_address_space(vma->vm_mm)) &&
		    folio_test_anon(folio) && folio_test_swapbacked(folio) &&
		    !folio_maybe_mapped_shared(folio)) {
			pra->referenced = -1;
			page_vma_mapped_walk_done(&pvmw);
			return false;
		}

		if (pvmw.pte && folio_test_large(folio)) {
			const unsigned long end_addr = pmd_addr_end(address, vma->vm_end);
			const unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT;
			pte_t pteval = ptep_get(pvmw.pte);

			nr = folio_pte_batch(folio, pvmw.pte, pteval, max_nr);
		}

		/*
		 * When LRU is switching, we don’t know where the surrounding folios
		 * are. —they could be on active/inactive lists or on MGLRU. So the
		 * simplest approach is to disable this look-around optimization.
		 */
		if (lru_gen_enabled() && !lru_gen_switching() && pvmw.pte) {
			if (lru_gen_look_around(&pvmw, nr))
				referenced++;
		} else if (pvmw.pte) {
			if (clear_flush_young_ptes_notify(vma, address, pvmw.pte, nr))
				referenced++;
		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
			if (pmdp_clear_flush_young_notify(vma, address,
						pvmw.pmd))
				referenced++;
		} else {
			/* unexpected pmd-mapped folio? */
			WARN_ON_ONCE(1);
		}

		ptes += nr;
		pra->mapcount -= nr;
		/*
		 * If we are sure that we batched the entire folio,
		 * we can just optimize and stop right here.
		 */
		if (ptes == pvmw.nr_pages) {
			page_vma_mapped_walk_done(&pvmw);
			break;
		}

		/* Skip the batched PTEs */
		pvmw.pte += nr - 1;
		pvmw.address += (nr - 1) * PAGE_SIZE;
	}

	if (referenced)
		folio_clear_idle(folio);
	if (folio_test_clear_young(folio))
		referenced++;

	if (referenced) {
		vma_flags_t vma_flags = vma->flags;

		pra->referenced++;
		vma_flags_clear(&vma_flags, VMA_LOCKED_BIT);
		vma_flags_set_mask(&pra->vma_flags, vma_flags);
	}

	if (!pra->mapcount)
		return false; /* To break the loop */

	return true;
}

static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg)
{
	struct folio_referenced_arg *pra = arg;
	struct mem_cgroup *memcg = pra->memcg;

	/*
	 * Ignore references from this mapping if it has no recency. If the
	 * folio has been used in another mapping, we will catch it; if this
	 * other mapping is already gone, the unmap path will have set the
	 * referenced flag or activated the folio in zap_pte_range().
	 */
	if (!vma_has_recency(vma))
		return true;

	/*
	 * If we are reclaiming on behalf of a cgroup, skip counting on behalf
	 * of references from different cgroups.
	 */
	if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
		return true;

	return false;
}

/**
 * folio_referenced() - Test if the folio was referenced.
 * @folio: The folio to test.
 * @is_locked: Caller holds lock on the folio.
 * @memcg: target memory cgroup
 * @vma_flags: A combination of all the vma->flags which referenced the folio.
 *
 * Quick test_and_clear_referenced for all mappings of a folio,
 *
 * Return: The number of mappings which referenced the folio. Return -1 if
 * the function bailed out due to rmap lock contention.
 */
int folio_referenced(struct folio *folio, int is_locked,
		struct mem_cgroup *memcg, vma_flags_t *vma_flags)
{
	bool we_locked = false;
	struct folio_referenced_arg pra = {
		.mapcount = folio_mapcount(folio),
		.memcg = memcg,
	};
	struct rmap_walk_control rwc = {
		.rmap_one = folio_referenced_one,
		.arg = (void *)&pra,
		.anon_lock = folio_lock_anon_vma_read,
		.try_lock = true,
		.invalid_vma = invalid_folio_referenced_vma,
	};

	VM_WARN_ON_ONCE_FOLIO(folio_is_zone_device(folio), folio);
	vma_flags_clear_all(vma_flags);
	if (!pra.mapcount)
		return 0;

	if (!folio_raw_mapping(folio))
		return 0;

	if (!is_locked) {
		we_locked = folio_trylock(folio);
		if (!we_locked)
			return 1;
	}

	rmap_walk(folio, &rwc);
	vma_flags_set_mask(vma_flags, pra.vma_flags);

	if (we_locked)
		folio_unlock(folio);

	return rwc.contended ? -1 : pra.referenced;
}

static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
{
	int cleaned = 0;
	struct vm_area_struct *vma = pvmw->vma;
	struct mmu_notifier_range range;
	unsigned long address = pvmw->address;

	/*
	 * We have to assume the worse case ie pmd for invalidation. Note that
	 * the folio can not be freed from this function.
	 */
	mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0,
				vma->vm_mm, address, vma_address_end(pvmw));
	mmu_notifier_invalidate_range_start(&range);

	while (page_vma_mapped_walk(pvmw)) {
		int ret = 0;

		address = pvmw->address;
		if (pvmw->pte) {
			pte_t *pte = pvmw->pte;
			pte_t entry = ptep_get(pte);

			/*
			 * PFN swap PTEs, such as device-exclusive ones, that
			 * actually map pages are clean and not writable from a
			 * CPU perspective. The MMU notifier takes care of any
			 * device aspects.
			 */
			if (!pte_present(entry))
				continue;
			if (!pte_dirty(entry) && !pte_write(entry))
				continue;

			flush_cache_page(vma, address, pte_pfn(entry));
			entry = ptep_clear_flush(vma, address, pte);
			entry = pte_wrprotect(entry);
			entry = pte_mkclean(entry);
			set_pte_at(vma->vm_mm, address, pte, entry);
			ret = 1;
		} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
			pmd_t *pmd = pvmw->pmd;
			pmd_t entry = pmdp_get(pmd);

			/*
			 * Please see the comment above (!pte_present).
			 * A non present PMD is not writable from a CPU
			 * perspective.
			 */
			if (!pmd_present(entry))
				continue;
			if (!pmd_dirty(entry) && !pmd_write(entry))
				continue;

			flush_cache_range(vma, address,
					  address + HPAGE_PMD_SIZE);
			entry = pmdp_invalidate(vma, address, pmd);
			entry = pmd_wrprotect(entry);
			entry = pmd_mkclean(entry);
			set_pmd_at(vma->vm_mm, address, pmd, entry);
			ret = 1;
#else
			/* unexpected pmd-mapped folio? */
			WARN_ON_ONCE(1);
#endif
		}

		if (ret)
			cleaned++;
	}

	mmu_notifier_invalidate_range_end(&range);

	return cleaned;
}

static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
			     unsigned long address, void *arg)
{
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
	int *cleaned = arg;

	*cleaned += page_vma_mkclean_one(&pvmw);

	return true;
}

static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg)
{
	if (vma->vm_flags & VM_SHARED)
		return false;

	return true;
}

int folio_mkclean(struct folio *folio)
{
	int cleaned = 0;
	struct address_space *mapping;
	struct rmap_walk_control rwc = {
		.arg = (void *)&cleaned,
		.rmap_one = page_mkclean_one,
		.invalid_vma = invalid_mkclean_vma,
	};

	BUG_ON(!folio_test_locked(folio));

	if (!folio_mapped(folio))
		return 0;

	mapping = folio_mapping(folio);
	if (!mapping)
		return 0;

	rmap_walk(folio, &rwc);

	return cleaned;
}
EXPORT_SYMBOL_GPL(folio_mkclean);

struct wrprotect_file_state {
	int cleaned;
	pgoff_t pgoff;
	unsigned long pfn;
	unsigned long nr_pages;
};

static bool mapping_wrprotect_range_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long address, void *arg)
{
	struct wrprotect_file_state *state = (struct wrprotect_file_state *)arg;
	struct page_vma_mapped_walk pvmw = {
		.pfn		= state->pfn,
		.nr_pages	= state->nr_pages,
		.pgoff		= state->pgoff,
		.vma		= vma,
		.address	= address,
		.flags		= PVMW_SYNC,
		.pgoff_is_anon	= false,
	};

	state->cleaned += page_vma_mkclean_one(&pvmw);

	return true;
}

static void __rmap_walk_file(struct folio *folio, struct address_space *mapping,
			     pgoff_t pgoff_start, unsigned long nr_pages,
			     struct rmap_walk_control *rwc, bool locked);

/**
 * mapping_wrprotect_range() - Write-protect all mappings in a specified range.
 *
 * @mapping:	The mapping whose reverse mapping should be traversed.
 * @pgoff:	The page offset at which @pfn is mapped within @mapping.
 * @pfn:	The PFN of the page mapped in @mapping at @pgoff.
 * @nr_pages:	The number of physically contiguous base pages spanned.
 *
 * Traverses the reverse mapping, finding all VMAs which contain a shared
 * mapping of the pages in the specified range in @mapping, and write-protects
 * them (that is, updates the page tables to mark the mappings read-only such
 * that a write protection fault arises when the mappings are written to).
 *
 * The @pfn value need not refer to a folio, but rather can reference a kernel
 * allocation which is mapped into userland. We therefore do not require that
 * the page maps to a folio with a valid mapping or index field, rather the
 * caller specifies these in @mapping and @pgoff.
 *
 * Return: the number of write-protected PTEs, or an error.
 */
int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff,
		unsigned long pfn, unsigned long nr_pages)
{
	struct wrprotect_file_state state = {
		.cleaned = 0,
		.pgoff = pgoff,
		.pfn = pfn,
		.nr_pages = nr_pages,
	};
	struct rmap_walk_control rwc = {
		.arg = (void *)&state,
		.rmap_one = mapping_wrprotect_range_one,
		.invalid_vma = invalid_mkclean_vma,
	};

	if (!mapping)
		return 0;

	__rmap_walk_file(/* folio = */NULL, mapping, pgoff, nr_pages, &rwc,
			 /* locked = */false);

	return state.cleaned;
}
EXPORT_SYMBOL_GPL(mapping_wrprotect_range);

/**
 * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of
 *                     [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff)
 *                     within the @vma of shared mappings. And since clean PTEs
 *                     should also be readonly, write protects them too.
 * @pfn: start pfn.
 * @nr_pages: number of physically contiguous pages srarting with @pfn.
 * @pgoff: page offset that the @pfn mapped with.
 * @vma: vma that @pfn mapped within.
 *
 * Returns the number of cleaned PTEs (including PMDs).
 */
int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
		      struct vm_area_struct *vma)
{
	struct page_vma_mapped_walk pvmw = {
		.pfn		= pfn,
		.nr_pages	= nr_pages,
		.pgoff		= pgoff,
		.vma		= vma,
		.flags		= PVMW_SYNC,
		.pgoff_is_anon	= false,
	};

	if (invalid_mkclean_vma(vma, NULL))
		return 0;

	pvmw.address = vma_filebacked_address(vma, pgoff, nr_pages);
	VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma);

	return page_vma_mkclean_one(&pvmw);
}

static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped)
{
	int idx;

	if (nr) {
		idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED;
		lruvec_stat_mod_folio(folio, idx, nr);
	}
	if (nr_pmdmapped) {
		if (folio_test_anon(folio)) {
			idx = NR_ANON_THPS;
			lruvec_stat_mod_folio(folio, idx, nr_pmdmapped);
		} else {
			/* NR_*_PMDMAPPED are not maintained per-memcg */
			idx = folio_test_swapbacked(folio) ?
				NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED;
			__mod_node_page_state(folio_pgdat(folio), idx,
					      nr_pmdmapped);
		}
	}
}

static __always_inline void __folio_add_rmap(struct folio *folio,
		struct page *page, int nr_pages, struct vm_area_struct *vma,
		enum pgtable_level level)
{
	atomic_t *mapped = &folio->_nr_pages_mapped;
	const int orig_nr_pages = nr_pages;
	int first = 0, nr = 0, nr_pmdmapped = 0;

	__folio_rmap_sanity_checks(folio, page, nr_pages, level);

	switch (level) {
	case PGTABLE_LEVEL_PTE:
		if (!folio_test_large(folio)) {
			nr = atomic_inc_and_test(&folio->_mapcount);
			break;
		}

		if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
			nr = folio_add_return_large_mapcount(folio, orig_nr_pages, vma);
			if (nr == orig_nr_pages)
				/* Was completely unmapped. */
				nr = folio_large_nr_pages(folio);
			else
				nr = 0;
			break;
		}

		do {
			first += atomic_inc_and_test(&page->_mapcount);
		} while (page++, --nr_pages > 0);

		if (first &&
		    atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED)
			nr = first;

		folio_add_large_mapcount(folio, orig_nr_pages, vma);
		break;
	case PGTABLE_LEVEL_PMD:
	case PGTABLE_LEVEL_PUD:
		first = atomic_inc_and_test(&folio->_entire_mapcount);
		if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
			if (level == PGTABLE_LEVEL_PMD && first)
				nr_pmdmapped = folio_large_nr_pages(folio);
			nr = folio_inc_return_large_mapcount(folio, vma);
			if (nr == 1)
				/* Was completely unmapped. */
				nr = folio_large_nr_pages(folio);
			else
				nr = 0;
			break;
		}

		if (first) {
			nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped);
			if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) {
				nr_pages = folio_large_nr_pages(folio);
				/*
				 * We only track PMD mappings of PMD-sized
				 * folios separately.
				 */
				if (level == PGTABLE_LEVEL_PMD)
					nr_pmdmapped = nr_pages;
				nr = nr_pages - (nr & FOLIO_PAGES_MAPPED);
				/* Raced ahead of a remove and another add? */
				if (unlikely(nr < 0))
					nr = 0;
			} else {
				/* Raced ahead of a remove of ENTIRELY_MAPPED */
				nr = 0;
			}
		}
		folio_inc_large_mapcount(folio, vma);
		break;
	default:
		BUILD_BUG();
	}
	__folio_mod_stat(folio, nr, nr_pmdmapped);
}

/**
 * folio_move_anon_rmap - move a folio to our anon_vma
 * @folio:	The folio to move to our anon_vma
 * @vma:	The vma the folio belongs to
 *
 * When a folio belongs exclusively to one process after a COW event,
 * that folio can be moved into the anon_vma that belongs to just that
 * process, so the rmap code will not search the parent or sibling processes.
 */
void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma)
{
	void *anon_vma = vma->anon_vma;

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_VMA(!anon_vma, vma);

	anon_vma += FOLIO_MAPPING_ANON;
	/*
	 * Ensure that anon_vma and the FOLIO_MAPPING_ANON bit are written
	 * simultaneously, so a concurrent reader (eg folio_referenced()'s
	 * folio_test_anon()) will not see one without the other.
	 */
	WRITE_ONCE(folio->mapping, anon_vma);
}

/**
 * __folio_set_anon - set up a new anonymous rmap for a folio
 * @folio:	The folio to set up the new anonymous rmap for.
 * @vma:	VM area to add the folio to.
 * @address:	User virtual address of the mapping
 * @exclusive:	Whether the folio is exclusive to the process.
 */
static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma,
			     unsigned long address, bool exclusive)
{
	struct anon_vma *anon_vma = vma->anon_vma;

	BUG_ON(!anon_vma);

	/*
	 * If the folio isn't exclusive to this vma, we must use the _oldest_
	 * possible anon_vma for the folio mapping!
	 */
	if (!exclusive)
		anon_vma = anon_vma->root;

	/*
	 * page_idle does a lockless/optimistic rmap scan on folio->mapping.
	 * Make sure the compiler doesn't split the stores of anon_vma and
	 * the FOLIO_MAPPING_ANON type identifier, otherwise the rmap code
	 * could mistake the mapping for a struct address_space and crash.
	 */
	anon_vma = (void *) anon_vma + FOLIO_MAPPING_ANON;
	WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma);
	folio->index = linear_anon_page_index(vma, address);
}

/**
 * __page_check_anon_rmap - sanity check anonymous rmap addition
 * @folio:	The folio containing @page.
 * @page:	the page to check the mapping of
 * @vma:	the vm area in which the mapping is added
 * @address:	the user virtual address mapped
 */
static void __page_check_anon_rmap(const struct folio *folio,
		const struct page *page, struct vm_area_struct *vma,
		unsigned long address)
{
	/*
	 * The page's anon-rmap details (mapping and index) are guaranteed to
	 * be set up correctly at this point.
	 *
	 * We have exclusion against folio_add_anon_rmap_*() because the caller
	 * always holds the page locked.
	 *
	 * We have exclusion against folio_add_new_anon_rmap because those pages
	 * are initially only visible via the pagetables, and the pte is locked
	 * over the call to folio_add_new_anon_rmap.
	 */
	VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root,
			folio);
	VM_BUG_ON_PAGE(page_pgoff(folio, page) !=
		       linear_anon_page_index(vma, address), page);
}

static __always_inline void __folio_add_anon_rmap(struct folio *folio,
		struct page *page, int nr_pages, struct vm_area_struct *vma,
		unsigned long address, rmap_t flags, enum pgtable_level level)
{
	int i;

	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);

	__folio_add_rmap(folio, page, nr_pages, vma, level);

	if (likely(!folio_test_ksm(folio)))
		__page_check_anon_rmap(folio, page, vma, address);

	if (flags & RMAP_EXCLUSIVE) {
		switch (level) {
		case PGTABLE_LEVEL_PTE:
			for (i = 0; i < nr_pages; i++)
				SetPageAnonExclusive(page + i);
			break;
		case PGTABLE_LEVEL_PMD:
			SetPageAnonExclusive(page);
			break;
		case PGTABLE_LEVEL_PUD:
			/*
			 * Keep the compiler happy, we don't support anonymous
			 * PUD mappings.
			 */
			WARN_ON_ONCE(1);
			break;
		default:
			BUILD_BUG();
		}
	}

	VM_WARN_ON_FOLIO(!folio_test_large(folio) && PageAnonExclusive(page) &&
			 atomic_read(&folio->_mapcount) > 0, folio);
	for (i = 0; i < nr_pages; i++) {
		struct page *cur_page = page + i;

		VM_WARN_ON_FOLIO(folio_test_large(folio) &&
				 folio_entire_mapcount(folio) > 1 &&
				 PageAnonExclusive(cur_page), folio);
		if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT))
			continue;

		/*
		 * While PTE-mapping a THP we have a PMD and a PTE
		 * mapping.
		 */
		VM_WARN_ON_FOLIO(atomic_read(&cur_page->_mapcount) > 0 &&
				 PageAnonExclusive(cur_page), folio);
	}

	/*
	 * Only mlock it if the folio is fully mapped to the VMA.
	 *
	 * Partially mapped folios can be split on reclaim and part outside
	 * of mlocked VMA can be evicted or freed.
	 */
	if (folio_nr_pages(folio) == nr_pages)
		mlock_vma_folio(folio, vma);
}

/**
 * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio
 * @folio:	The folio to add the mappings to
 * @page:	The first page to add
 * @nr_pages:	The number of pages which will be mapped
 * @vma:	The vm area in which the mappings are added
 * @address:	The user virtual address of the first page to map
 * @flags:	The rmap flags
 *
 * The page range of folio is defined by [first_page, first_page + nr_pages)
 *
 * The caller needs to hold the page table lock, and the page must be locked in
 * the anon_vma case: to serialize mapping,index checking after setting,
 * and to ensure that an anon folio is not being upgraded racily to a KSM folio
 * (but KSM folios are never downgraded).
 */
void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page,
		int nr_pages, struct vm_area_struct *vma, unsigned long address,
		rmap_t flags)
{
	__folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags,
			      PGTABLE_LEVEL_PTE);
}

/**
 * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio
 * @folio:	The folio to add the mapping to
 * @page:	The first page to add
 * @vma:	The vm area in which the mapping is added
 * @address:	The user virtual address of the first page to map
 * @flags:	The rmap flags
 *
 * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR)
 *
 * The caller needs to hold the page table lock, and the page must be locked in
 * the anon_vma case: to serialize mapping,index checking after setting.
 */
void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page,
		struct vm_area_struct *vma, unsigned long address, rmap_t flags)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	__folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags,
			      PGTABLE_LEVEL_PMD);
#else
	WARN_ON_ONCE(true);
#endif
}

/**
 * folio_add_new_anon_rmap - Add mapping to a new anonymous folio.
 * @folio:	The folio to add the mapping to.
 * @vma:	the vm area in which the mapping is added
 * @address:	the user virtual address mapped
 * @flags:	The rmap flags
 *
 * Like folio_add_anon_rmap_*() but must only be called on *new* folios.
 * This means the inc-and-test can be bypassed.
 * The folio doesn't necessarily need to be locked while it's exclusive
 * unless two threads map it concurrently. However, the folio must be
 * locked if it's shared.
 *
 * If the folio is pmd-mappable, it is accounted as a THP.
 */
void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
		unsigned long address, rmap_t flags)
{
	const bool exclusive = flags & RMAP_EXCLUSIVE;
	int nr = 1, nr_pmdmapped = 0;

	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
	VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio);

	/*
	 * VM_DROPPABLE mappings don't swap; instead they're just dropped when
	 * under memory pressure.
	 */
	if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE))
		__folio_set_swapbacked(folio);
	__folio_set_anon(folio, vma, address, exclusive);

	if (likely(!folio_test_large(folio))) {
		/* increment count (starts at -1) */
		atomic_set(&folio->_mapcount, 0);
		if (exclusive)
			SetPageAnonExclusive(&folio->page);
	} else if (!folio_test_pmd_mappable(folio)) {
		int i;

		nr = folio_large_nr_pages(folio);
		for (i = 0; i < nr; i++) {
			struct page *page = folio_page(folio, i);

			if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
				/* increment count (starts at -1) */
				atomic_set(&page->_mapcount, 0);
			if (exclusive)
				SetPageAnonExclusive(page);
		}

		folio_set_large_mapcount(folio, nr, vma);
		if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
			atomic_set(&folio->_nr_pages_mapped, nr);
	} else {
		nr = folio_large_nr_pages(folio);
		/* increment count (starts at -1) */
		atomic_set(&folio->_entire_mapcount, 0);
		folio_set_large_mapcount(folio, 1, vma);
		if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
			atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED);
		if (exclusive)
			SetPageAnonExclusive(&folio->page);
		nr_pmdmapped = nr;
	}

	VM_WARN_ON_ONCE(address < vma->vm_start ||
			address + (nr << PAGE_SHIFT) > vma->vm_end);

	__folio_mod_stat(folio, nr, nr_pmdmapped);
	mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1);
}

static __always_inline void __folio_add_file_rmap(struct folio *folio,
		struct page *page, int nr_pages, struct vm_area_struct *vma,
		enum pgtable_level level)
{
	VM_WARN_ON_FOLIO(folio_test_anon(folio), folio);

	__folio_add_rmap(folio, page, nr_pages, vma, level);

	/*
	 * Only mlock it if the folio is fully mapped to the VMA.
	 *
	 * Partially mapped folios can be split on reclaim and part outside
	 * of mlocked VMA can be evicted or freed.
	 */
	if (folio_nr_pages(folio) == nr_pages)
		mlock_vma_folio(folio, vma);
}

/**
 * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio
 * @folio:	The folio to add the mappings to
 * @page:	The first page to add
 * @nr_pages:	The number of pages that will be mapped using PTEs
 * @vma:	The vm area in which the mappings are added
 *
 * The page range of the folio is defined by [page, page + nr_pages)
 *
 * The caller needs to hold the page table lock.
 */
void folio_add_file_rmap_ptes(struct folio *folio, struct page *page,
		int nr_pages, struct vm_area_struct *vma)
{
	__folio_add_file_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE);
}

/**
 * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio
 * @folio:	The folio to add the mapping to
 * @page:	The first page to add
 * @vma:	The vm area in which the mapping is added
 *
 * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
 *
 * The caller needs to hold the page table lock.
 */
void folio_add_file_rmap_pmd(struct folio *folio, struct page *page,
		struct vm_area_struct *vma)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	__folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD);
#else
	WARN_ON_ONCE(true);
#endif
}

/**
 * folio_add_file_rmap_pud - add a PUD mapping to a page range of a folio
 * @folio:	The folio to add the mapping to
 * @page:	The first page to add
 * @vma:	The vm area in which the mapping is added
 *
 * The page range of the folio is defined by [page, page + HPAGE_PUD_NR)
 *
 * The caller needs to hold the page table lock.
 */
void folio_add_file_rmap_pud(struct folio *folio, struct page *page,
		struct vm_area_struct *vma)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
	__folio_add_file_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD);
#else
	WARN_ON_ONCE(true);
#endif
}

static __always_inline void __folio_remove_rmap(struct folio *folio,
		struct page *page, int nr_pages, struct vm_area_struct *vma,
		enum pgtable_level level)
{
	atomic_t *mapped = &folio->_nr_pages_mapped;
	int last = 0, nr = 0, nr_pmdmapped = 0;
	bool partially_mapped = false;

	__folio_rmap_sanity_checks(folio, page, nr_pages, level);

	switch (level) {
	case PGTABLE_LEVEL_PTE:
		if (!folio_test_large(folio)) {
			nr = atomic_add_negative(-1, &folio->_mapcount);
			break;
		}

		if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
			nr = folio_sub_return_large_mapcount(folio, nr_pages, vma);
			if (!nr) {
				/* Now completely unmapped. */
				nr = folio_large_nr_pages(folio);
			} else {
				partially_mapped = nr < folio_large_nr_pages(folio) &&
						   !folio_entire_mapcount(folio);
				nr = 0;
			}
			break;
		}

		folio_sub_large_mapcount(folio, nr_pages, vma);
		do {
			last += atomic_add_negative(-1, &page->_mapcount);
		} while (page++, --nr_pages > 0);

		if (last &&
		    atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED)
			nr = last;

		partially_mapped = nr && atomic_read(mapped);
		break;
	case PGTABLE_LEVEL_PMD:
	case PGTABLE_LEVEL_PUD:
		if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
			last = atomic_add_negative(-1, &folio->_entire_mapcount);
			if (level == PGTABLE_LEVEL_PMD && last)
				nr_pmdmapped = folio_large_nr_pages(folio);
			nr = folio_dec_return_large_mapcount(folio, vma);
			if (!nr) {
				/* Now completely unmapped. */
				nr = folio_large_nr_pages(folio);
			} else {
				partially_mapped = last &&
						   nr < folio_large_nr_pages(folio);
				nr = 0;
			}
			break;
		}

		folio_dec_large_mapcount(folio, vma);
		last = atomic_add_negative(-1, &folio->_entire_mapcount);
		if (last) {
			nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped);
			if (likely(nr < ENTIRELY_MAPPED)) {
				nr_pages = folio_large_nr_pages(folio);
				if (level == PGTABLE_LEVEL_PMD)
					nr_pmdmapped = nr_pages;
				nr = nr_pages - nr;
				/* Raced ahead of another remove and an add? */
				if (unlikely(nr < 0))
					nr = 0;
			} else {
				/* An add of ENTIRELY_MAPPED raced ahead */
				nr = 0;
			}
		}

		partially_mapped = nr && nr < nr_pmdmapped;
		break;
	default:
		BUILD_BUG();
	}

	/*
	 * Queue anon large folio for deferred split if at least one page of
	 * the folio is unmapped and at least one page is still mapped.
	 *
	 * Check partially_mapped first to ensure it is a large folio.
	 *
	 * Device private folios do not support deferred splitting and
	 * shrinker based scanning of the folios to free.
	 */
	if (partially_mapped && folio_test_anon(folio) &&
	    !folio_test_partially_mapped(folio) &&
	    !folio_is_device_private(folio))
		deferred_split_folio(folio, true);

	__folio_mod_stat(folio, -nr, -nr_pmdmapped);

	/*
	 * It would be tidy to reset folio_test_anon mapping when fully
	 * unmapped, but that might overwrite a racing folio_add_anon_rmap_*()
	 * which increments mapcount after us but sets mapping before us:
	 * so leave the reset to free_pages_prepare, and remember that
	 * it's only reliable while mapped.
	 */

	munlock_vma_folio(folio, vma);
}

/**
 * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio
 * @folio:	The folio to remove the mappings from
 * @page:	The first page to remove
 * @nr_pages:	The number of pages that will be removed from the mapping
 * @vma:	The vm area from which the mappings are removed
 *
 * The page range of the folio is defined by [page, page + nr_pages)
 *
 * The caller needs to hold the page table lock.
 */
void folio_remove_rmap_ptes(struct folio *folio, struct page *page,
		int nr_pages, struct vm_area_struct *vma)
{
	__folio_remove_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE);
}

/**
 * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio
 * @folio:	The folio to remove the mapping from
 * @page:	The first page to remove
 * @vma:	The vm area from which the mapping is removed
 *
 * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
 *
 * The caller needs to hold the page table lock.
 */
void folio_remove_rmap_pmd(struct folio *folio, struct page *page,
		struct vm_area_struct *vma)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	__folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD);
#else
	WARN_ON_ONCE(true);
#endif
}

/**
 * folio_remove_rmap_pud - remove a PUD mapping from a page range of a folio
 * @folio:	The folio to remove the mapping from
 * @page:	The first page to remove
 * @vma:	The vm area from which the mapping is removed
 *
 * The page range of the folio is defined by [page, page + HPAGE_PUD_NR)
 *
 * The caller needs to hold the page table lock.
 */
void folio_remove_rmap_pud(struct folio *folio, struct page *page,
		struct vm_area_struct *vma)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
	__folio_remove_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD);
#else
	WARN_ON_ONCE(true);
#endif
}

static inline unsigned int folio_unmap_pte_batch(struct folio *folio,
			struct page_vma_mapped_walk *pvmw,
			enum ttu_flags flags, pte_t pte)
{
	unsigned long end_addr, addr = pvmw->address;
	struct vm_area_struct *vma = pvmw->vma;
	unsigned int max_nr;

	if (flags & TTU_HWPOISON)
		return 1;
	if (!folio_test_large(folio))
		return 1;

	/* We may only batch within a single VMA and a single page table. */
	end_addr = pmd_addr_end(addr, vma->vm_end);
	max_nr = (end_addr - addr) >> PAGE_SHIFT;

	/* We only support lazyfree or file folios batching for now ... */
	if (folio_test_anon(folio) && folio_test_swapbacked(folio))
		return 1;

	if (pte_unused(pte))
		return 1;

	/*
	 * If unmap fails, we need to restore the ptes. To avoid accidentally
	 * upgrading write permissions for ptes that were not originally
	 * writable, and to avoid losing the soft-dirty bit, use the
	 * appropriate FPB flags.
	 */
	return folio_pte_batch_flags(folio, vma, pvmw->pte, &pte, max_nr,
				     FPB_RESPECT_WRITE | FPB_RESPECT_SOFT_DIRTY);
}

static bool try_to_unmap_poisoned_hugetlb_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long address, void *arg)
{
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
	const unsigned long hsz = huge_page_size(hstate_vma(vma));
	const enum ttu_flags flags = (enum ttu_flags)(long)arg;
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_notifier_range range;
	bool ret = true;
	pte_t pteval;

	/*
	 * The try_to_unmap() is only passed a hugetlb folio in the case
	 * where the hugetlb folio is poisoned.
	 */
	VM_WARN_ON_ONCE_FOLIO(!folio_test_hwpoison(folio), folio);
	VM_WARN_ON_ONCE(!(flags & TTU_HWPOISON));

	range.end = vma_address_end(&pvmw);
	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
				address, range.end);
	adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
	mmu_notifier_invalidate_range_start(&range);

	/* There is only a single mapping in a VMA. */
	if (!page_vma_mapped_walk(&pvmw))
		goto range_end;

	VM_WARN_ON_ONCE(address != pvmw.address);

	pteval = huge_ptep_get(mm, address, pvmw.pte);
	VM_WARN_ON_ONCE(!pte_present(pteval));
	VM_WARN_ON_ONCE(pte_pfn(pteval) != folio_pfn(folio));

	/*
	 * huge_pmd_unshare may unmap an entire PMD page. There is no way of
	 * knowing exactly which PMDs may be cached for this mm, so we must
	 * flush them all. start/end were already adjusted above to cover this
	 * range.
	 */
	flush_cache_range(vma, range.start, range.end);

	/*
	 * To call huge_pmd_unshare, i_mmap_rwsem must be held in write mode.
	 * Caller needs to explicitly do this outside rmap routines.
	 *
	 * We also must hold hugetlb vma_lock in write mode. Lock order dictates
	 * acquiring vma_lock BEFORE i_mmap_rwsem. We can only try lock here and
	 * fail if unsuccessful.
	 */
	if (!folio_test_anon(folio)) {
		struct mmu_gather tlb;

		VM_WARN_ON_ONCE(!(flags & TTU_RMAP_LOCKED));
		if (!hugetlb_vma_trylock_write(vma)) {
			ret = false;
			goto walk_done;
		}

		tlb_gather_mmu_vma(&tlb, vma);
		if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) {
			hugetlb_vma_unlock_write(vma);
			huge_pmd_unshare_flush(&tlb, vma);
			tlb_finish_mmu(&tlb);
			/*
			 * The PMD table was unmapped, consequently unmapping
			 * the folio.
			 */
			goto walk_done;
		}
		hugetlb_vma_unlock_write(vma);
		tlb_finish_mmu(&tlb);
	}
	pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
	if (huge_pte_dirty(pteval))
		folio_mark_dirty(folio);

	pteval = swp_entry_to_pte(make_hwpoison_entry(folio_page(folio, 0)));
	hugetlb_count_sub(folio_nr_pages(folio), mm);
	set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz);
	hugetlb_remove_rmap(folio);
	folio_put_refs(folio, 1);

walk_done:
	page_vma_mapped_walk_done(&pvmw);
range_end:
	mmu_notifier_invalidate_range_end(&range);
	return ret;
}

static bool ttu_anon_lazyfree_folio(struct vm_area_struct *vma,
		struct folio *folio, unsigned long nr_pages)
{
	int ref_count, map_count;

	/*
	 * Synchronize with gup_pte_range():
	 * - clear PTE; barrier; read refcount
	 * - inc refcount; barrier; read PTE
	 */
	smp_mb();

	ref_count = folio_ref_count(folio);
	map_count = folio_mapcount(folio);

	/*
	 * Order reads for page refcount and dirty flag
	 * (see comments in __remove_mapping()).
	 */
	smp_rmb();

	if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) {
		/*
		 * redirtied either using the page table or a previously
		 * obtained GUP reference.
		 */
		folio_set_swapbacked(folio);
		return false;
	}

	/*
	 * Additional references could be due to GUP or speculative lookups.
	 * GUP users must mark the folio dirty if there was a modification.
	 * This folio cannot be reclaimed right now either way, so act just
	 * like nothing happened. We'll come back here later and detect if the
	 * folio was dirtied when the additional reference is gone.
	 */
	if (ref_count != 1 + map_count)
		return false;

	add_mm_counter(vma->vm_mm, MM_ANONPAGES, -nr_pages);
	return true;
}

static pte_t swp_pte_prepare(swp_entry_t entry, pte_t old_pte,
		bool anon_exclusive)
{
	pte_t swp_pte = swp_entry_to_pte(entry);

	if (anon_exclusive)
		swp_pte = pte_swp_mkexclusive(swp_pte);

	if (likely(pte_present(old_pte))) {
		if (pte_soft_dirty(old_pte))
			swp_pte = pte_swp_mksoft_dirty(swp_pte);
		if (pte_uffd(old_pte))
			swp_pte = pte_swp_mkuffd(swp_pte);
	} else {
		/* Device-exclusive entry */
		if (pte_swp_soft_dirty(old_pte))
			swp_pte = pte_swp_mksoft_dirty(swp_pte);
		if (pte_swp_uffd(old_pte))
			swp_pte = pte_swp_mkuffd(swp_pte);
	}

	return swp_pte;
}

static bool ttu_anon_swapbacked_folio(struct vm_area_struct *vma,
		struct folio *folio, struct page *page, unsigned long address,
		pte_t *ptep, pte_t pteval)
{
	const bool anon_exclusive = folio_test_anon(folio) &&
				    PageAnonExclusive(page);
	swp_entry_t entry = page_swap_entry(page);
	struct mm_struct *mm = vma->vm_mm;

	if (folio_dup_swap(folio, page) < 0)
		return false;

	/*
	 * arch_unmap_one() is expected to be a NOP on
	 * architectures where we could have PFN swap PTEs,
	 * so we'll not check/care.
	 */
	if (arch_unmap_one(mm, vma, address, pteval) < 0) {
		folio_put_swap(folio, page);
		return false;
	}

	/* See folio_try_share_anon_rmap(): clear PTE first. */
	if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, page)) {
		folio_put_swap(folio, page);
		return false;
	}

	mm_prepare_for_swap_entries(mm);
	dec_mm_counter(mm, MM_ANONPAGES);
	inc_mm_counter(mm, MM_SWAPENTS);
	set_pte_at(mm, address, ptep,
		   swp_pte_prepare(entry, pteval, anon_exclusive));
	return true;
}

static bool ttu_anon_folio(struct vm_area_struct *vma, struct folio *folio,
		struct page *page, unsigned long address, pte_t *ptep,
		pte_t pteval, unsigned long nr_pages)
{
	/*
	 * Store the swap location in the pte.
	 * See handle_pte_fault() ...
	 */
	if (WARN_ON_ONCE(folio_test_swapbacked(folio) !=
			 folio_test_swapcache(folio)))
		return false;

	if (!folio_test_swapbacked(folio))
		return ttu_anon_lazyfree_folio(vma, folio, nr_pages);

	/* nr_pages > 1 not supported yet */
	return ttu_anon_swapbacked_folio(vma, folio, page, address, ptep,
					 pteval);
}

/*
 * @arg: enum ttu_flags will be passed to this argument
 */
static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
		     unsigned long address, void *arg)
{
	struct mm_struct *mm = vma->vm_mm;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
	bool ret = true;
	pte_t pteval;
	struct page *page;
	struct mmu_notifier_range range;
	enum ttu_flags flags = (enum ttu_flags)(long)arg;
	unsigned long nr_pages = 1, end_addr;
	unsigned long pfn;
	int ptes = 0;

	/*
	 * When racing against e.g. zap_pte_range() on another cpu,
	 * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(),
	 * try_to_unmap() may return before folio_mapped() has become false,
	 * if page table locking is skipped: use TTU_SYNC to wait for that.
	 */
	if (flags & TTU_SYNC)
		pvmw.flags = PVMW_SYNC;

	/*
	 * For THP, we have to assume the worse case ie pmd for invalidation.
	 *
	 * Note that the folio can not be freed in this function as call of
	 * try_to_unmap() must hold a reference on the folio.
	 */
	range.end = vma_address_end(&pvmw);
	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
				address, range.end);
	mmu_notifier_invalidate_range_start(&range);

	while (page_vma_mapped_walk(&pvmw)) {
		nr_pages = 1;

		/*
		 * If the folio is in an mlock()d vma, we must not swap it out.
		 */
		if (!(flags & TTU_IGNORE_MLOCK) &&
		    (vma->vm_flags & VM_LOCKED)) {
			ptes++;

			/*
			 * Set 'ret' to indicate the page cannot be unmapped.
			 *
			 * Do not jump to walk_abort immediately as additional
			 * iteration might be required to detect fully mapped
			 * folio an mlock it.
			 */
			ret = false;

			/* Only mlock fully mapped pages */
			if (pvmw.pte && ptes != pvmw.nr_pages)
				continue;

			/*
			 * All PTEs must be protected by page table lock in
			 * order to mlock the page.
			 *
			 * If page table boundary has been cross, current ptl
			 * only protect part of ptes.
			 */
			if (pvmw.flags & PVMW_PGTABLE_CROSSED)
				goto walk_done;

			/* Restore the mlock which got missed */
			mlock_vma_folio(folio, vma);
			goto walk_done;
		}

		if (!pvmw.pte) {
			if (folio_test_lazyfree(folio)) {
				if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio))
					goto walk_done;
				/*
				 * unmap_huge_pmd_locked has either already marked
				 * the folio as swap-backed or decided to retain it
				 * due to GUP or speculative references.
				 */
				goto walk_abort;
			}

			if (flags & TTU_SPLIT_HUGE_PMD) {
				/*
				 * We temporarily have to drop the PTL and
				 * restart so we can process the PTE-mapped THP.
				 */
				split_huge_pmd_locked(vma, pvmw.address,
						      pvmw.pmd, false);
				flags &= ~TTU_SPLIT_HUGE_PMD;
				page_vma_mapped_walk_restart(&pvmw);
				continue;
			}
		}

		/* Unexpected PMD-mapped THP? */
		VM_BUG_ON_FOLIO(!pvmw.pte, folio);

		address = pvmw.address;
		if (folio_test_hugetlb(folio)) {
			pteval = huge_ptep_get(mm, address, pvmw.pte);
		} else {
			pteval = ptep_get(pvmw.pte);
		}
		if (likely(pte_present(pteval))) {
			pfn = pte_pfn(pteval);
		} else {
			/*
			 * Handle PFN swap PTEs, such as device-exclusive ones,
			 * that actually map pages.
			 */
			const softleaf_t entry = softleaf_from_pte(pteval);

			pfn = softleaf_to_pfn(entry);
		}

		page = folio_page(folio, pfn - folio_pfn(folio));

		if (likely(pte_present(pteval))) {
			nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval);
			end_addr = address + nr_pages * PAGE_SIZE;
			flush_cache_range(vma, address, end_addr);

			/* Nuke the page table entry. */
			pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages);
			/*
			 * We clear the PTE but do not flush so potentially
			 * a remote CPU could still be writing to the folio.
			 * If the entry was previously clean then the
			 * architecture must guarantee that a clear->dirty
			 * transition on a cached TLB entry is written through
			 * and traps if the PTE is unmapped.
			 */
			if (should_defer_flush(mm, flags))
				set_tlb_ubc_flush_pending(mm, pteval, address, end_addr);
			else
				flush_tlb_range(vma, address, end_addr);
			if (pte_dirty(pteval))
				folio_mark_dirty(folio);
		} else {
			pte_clear(mm, address, pvmw.pte);
		}

		/*
		 * Now the pte is cleared. If this pte was uffd-wp armed,
		 * we may want to replace a none pte with a marker pte if
		 * it's file-backed, so we don't lose the tracking info.
		 */
		cond_install_uffd_wp_ptes(vma, address, pvmw.pte, pteval,
					  nr_pages);

		/* Update high watermark before we lower rss */
		update_hiwater_rss(mm);

		/* unmap_poisoned_folio() only refs order-0 folios */
		if (folio_test_hwpoison(folio) && (flags & TTU_HWPOISON)) {
			pteval = swp_entry_to_pte(make_hwpoison_entry(page));
			dec_mm_counter(mm, mm_counter(folio));
			set_pte_at(mm, address, pvmw.pte, pteval);
		} else if (likely(pte_present(pteval)) && pte_unused(pteval) &&
			   !userfaultfd_armed(vma)) {
			/*
			 * The guest indicated that the page content is of no
			 * interest anymore. Simply discard the pte, vmscan
			 * will take care of the rest.
			 * A future reference will then fault in a new zero
			 * page. When userfaultfd is active, we must not drop
			 * this page though, as its main user (postcopy
			 * migration) will not expect userfaults on already
			 * copied pages.
			 */
			dec_mm_counter(mm, mm_counter(folio));
		} else if (folio_test_anon(folio)) {
			if (!ttu_anon_folio(vma, folio, page, address,
					    pvmw.pte, pteval, nr_pages)) {
				set_ptes(mm, address, pvmw.pte, pteval, nr_pages);
				goto walk_abort;
			}

			goto finish_unmap;
		} else {
			/*
			 * This is a locked file-backed folio,
			 * so it cannot be removed from the page
			 * cache and replaced by a new folio before
			 * mmu_notifier_invalidate_range_end, so no
			 * concurrent thread might update its page table
			 * to point at a new folio while a device is
			 * still using this folio.
			 *
			 * See Documentation/mm/mmu_notifier.rst
			 */
			add_mm_counter(mm, mm_counter_file(folio), -nr_pages);
		}
finish_unmap:
		folio_remove_rmap_ptes(folio, page, nr_pages, vma);
		if (vma->vm_flags & VM_LOCKED)
			mlock_drain_local();
		folio_put_refs(folio, nr_pages);

		/*
		 * If we are sure that we batched the entire folio and cleared
		 * all PTEs, we can just optimize and stop right here.
		 */
		if (nr_pages == folio_nr_pages(folio))
			goto walk_done;
		continue;
walk_abort:
		ret = false;
walk_done:
		page_vma_mapped_walk_done(&pvmw);
		break;
	}

	mmu_notifier_invalidate_range_end(&range);

	return ret;
}

static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg)
{
	return vma_is_temporary_stack(vma);
}

static int folio_not_mapped(struct folio *folio)
{
	return !folio_mapped(folio);
}

/**
 * try_to_unmap - Try to remove all page table mappings to a folio.
 * @folio: The folio to unmap.
 * @flags: action and flags
 *
 * Tries to remove all the page table entries which are mapping this
 * folio.  It is the caller's responsibility to check if the folio is
 * still mapped if needed (use TTU_SYNC to prevent accounting races).
 *
 * Context: Caller must hold the folio lock.
 */
void try_to_unmap(struct folio *folio, enum ttu_flags flags)
{
	struct rmap_walk_control rwc = {
		.rmap_one = folio_test_hugetlb(folio) ?
				try_to_unmap_poisoned_hugetlb_one : try_to_unmap_one,
		.arg = (void *)flags,
		.done = folio_not_mapped,
		.anon_lock = folio_lock_anon_vma_read,
	};

	if (flags & TTU_RMAP_LOCKED)
		rmap_walk_locked(folio, &rwc);
	else
		rmap_walk(folio, &rwc);
}

/*
 * @arg: enum ttu_flags will be passed to this argument.
 *
 * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs
 * containing migration entries.
 */
static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
		     unsigned long address, void *arg)
{
	struct mm_struct *mm = vma->vm_mm;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
	bool anon_exclusive, writable, ret = true;
	pte_t pteval;
	struct page *subpage;
	struct mmu_notifier_range range;
	enum ttu_flags flags = (enum ttu_flags)(long)arg;
	unsigned long pfn;
	unsigned long hsz = 0;

	/*
	 * When racing against e.g. zap_pte_range() on another cpu,
	 * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(),
	 * try_to_migrate() may return before folio_mapped() has become false,
	 * if page table locking is skipped: use TTU_SYNC to wait for that.
	 */
	if (flags & TTU_SYNC)
		pvmw.flags = PVMW_SYNC;

	/*
	 * For THP, we have to assume the worse case ie pmd for invalidation.
	 * For hugetlb, it could be much worse if we need to do pud
	 * invalidation in the case of pmd sharing.
	 *
	 * Note that the page can not be free in this function as call of
	 * try_to_unmap() must hold a reference on the page.
	 */
	range.end = vma_address_end(&pvmw);
	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
				address, range.end);
	if (folio_test_hugetlb(folio)) {
		/*
		 * If sharing is possible, start and end will be adjusted
		 * accordingly.
		 */
		adjust_range_if_pmd_sharing_possible(vma, &range.start,
						     &range.end);

		/* We need the huge page size for set_huge_pte_at() */
		hsz = huge_page_size(hstate_vma(vma));
	}
	mmu_notifier_invalidate_range_start(&range);

	while (page_vma_mapped_walk(&pvmw)) {
		/* PMD-mapped THP migration entry */
		if (!pvmw.pte) {
			__maybe_unused unsigned long pfn;
			__maybe_unused pmd_t pmdval;

			if (flags & TTU_SPLIT_HUGE_PMD) {
				/*
				 * split_huge_pmd_locked() might leave the
				 * folio mapped through PTEs. Retry the walk
				 * so we can detect this scenario and properly
				 * abort the walk.
				 */
				split_huge_pmd_locked(vma, pvmw.address,
						      pvmw.pmd, true);
				flags &= ~TTU_SPLIT_HUGE_PMD;
				page_vma_mapped_walk_restart(&pvmw);
				continue;
			}
#ifdef CONFIG_ARCH_HAS_PMD_SOFTLEAVES
			pmdval = pmdp_get(pvmw.pmd);
			if (likely(pmd_present(pmdval)))
				pfn = pmd_pfn(pmdval);
			else
				pfn = softleaf_to_pfn(softleaf_from_pmd(pmdval));

			subpage = folio_page(folio, pfn - folio_pfn(folio));

			VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
					!folio_test_pmd_mappable(folio), folio);

			if (set_pmd_migration_entry(&pvmw, subpage)) {
				ret = false;
				page_vma_mapped_walk_done(&pvmw);
				break;
			}
			continue;
#endif
		}

		/* Unexpected PMD-mapped THP? */
		VM_BUG_ON_FOLIO(!pvmw.pte, folio);

		address = pvmw.address;
		if (folio_test_hugetlb(folio))
			pteval = huge_ptep_get(mm, address, pvmw.pte);
		else
			pteval = ptep_get(pvmw.pte);
		if (likely(pte_present(pteval))) {
			pfn = pte_pfn(pteval);
		} else {
			/*
			 * Handle PFN swap PTEs, such as device-exclusive ones,
			 * that actually map pages.
			 */
			const softleaf_t entry = softleaf_from_pte(pteval);

			pfn = softleaf_to_pfn(entry);
			VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
		}

		subpage = folio_page(folio, pfn - folio_pfn(folio));
		anon_exclusive = folio_test_anon(folio) &&
				 PageAnonExclusive(subpage);

		if (folio_test_hugetlb(folio)) {
			bool anon = folio_test_anon(folio);

			/*
			 * huge_pmd_unshare may unmap an entire PMD page.
			 * There is no way of knowing exactly which PMDs may
			 * be cached for this mm, so we must flush them all.
			 * start/end were already adjusted above to cover this
			 * range.
			 */
			flush_cache_range(vma, range.start, range.end);

			/*
			 * To call huge_pmd_unshare, i_mmap_rwsem must be
			 * held in write mode.  Caller needs to explicitly
			 * do this outside rmap routines.
			 *
			 * We also must hold hugetlb vma_lock in write mode.
			 * Lock order dictates acquiring vma_lock BEFORE
			 * i_mmap_rwsem.  We can only try lock here and
			 * fail if unsuccessful.
			 */
			if (!anon) {
				struct mmu_gather tlb;

				VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
				if (!hugetlb_vma_trylock_write(vma)) {
					page_vma_mapped_walk_done(&pvmw);
					ret = false;
					break;
				}

				tlb_gather_mmu_vma(&tlb, vma);
				if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) {
					hugetlb_vma_unlock_write(vma);
					huge_pmd_unshare_flush(&tlb, vma);
					tlb_finish_mmu(&tlb);
					/*
					 * The PMD table was unmapped,
					 * consequently unmapping the folio.
					 */
					page_vma_mapped_walk_done(&pvmw);
					break;
				}
				hugetlb_vma_unlock_write(vma);
				tlb_finish_mmu(&tlb);
			}
			/* Nuke the hugetlb page table entry */
			pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
			if (pte_dirty(pteval))
				folio_mark_dirty(folio);
			writable = pte_write(pteval);
		} else if (likely(pte_present(pteval))) {
			flush_cache_page(vma, address, pfn);
			/* Nuke the page table entry. */
			if (should_defer_flush(mm, flags)) {
				/*
				 * We clear the PTE but do not flush so potentially
				 * a remote CPU could still be writing to the folio.
				 * If the entry was previously clean then the
				 * architecture must guarantee that a clear->dirty
				 * transition on a cached TLB entry is written through
				 * and traps if the PTE is unmapped.
				 */
				pteval = ptep_get_and_clear(mm, address, pvmw.pte);

				set_tlb_ubc_flush_pending(mm, pteval, address, address + PAGE_SIZE);
			} else {
				pteval = ptep_clear_flush(vma, address, pvmw.pte);
			}
			if (pte_dirty(pteval))
				folio_mark_dirty(folio);
			writable = pte_write(pteval);
		} else {
			const softleaf_t entry = softleaf_from_pte(pteval);

			pte_clear(mm, address, pvmw.pte);

			writable = softleaf_is_device_private_write(entry);
		}

		VM_WARN_ON_FOLIO(writable && folio_test_anon(folio) &&
				!anon_exclusive, folio);

		/* Update high watermark before we lower rss */
		update_hiwater_rss(mm);

		if (PageHWPoison(subpage)) {
			VM_WARN_ON_FOLIO(folio_is_device_private(folio), folio);

			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
			if (folio_test_hugetlb(folio)) {
				hugetlb_count_sub(folio_nr_pages(folio), mm);
				set_huge_pte_at(mm, address, pvmw.pte, pteval,
						hsz);
			} else {
				dec_mm_counter(mm, mm_counter(folio));
				set_pte_at(mm, address, pvmw.pte, pteval);
			}
		} else if (likely(pte_present(pteval)) && pte_unused(pteval) &&
			   !userfaultfd_armed(vma)) {
			/*
			 * The guest indicated that the page content is of no
			 * interest anymore. Simply discard the pte, vmscan
			 * will take care of the rest.
			 * A future reference will then fault in a new zero
			 * page. When userfaultfd is active, we must not drop
			 * this page though, as its main user (postcopy
			 * migration) will not expect userfaults on already
			 * copied pages.
			 */
			dec_mm_counter(mm, mm_counter(folio));
		} else {
			swp_entry_t entry;
			pte_t swp_pte;

			/*
			 * arch_unmap_one() is expected to be a NOP on
			 * architectures where we could have PFN swap PTEs,
			 * so we'll not check/care.
			 */
			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
				if (folio_test_hugetlb(folio))
					set_huge_pte_at(mm, address, pvmw.pte,
							pteval, hsz);
				else
					set_pte_at(mm, address, pvmw.pte, pteval);
				ret = false;
				page_vma_mapped_walk_done(&pvmw);
				break;
			}

			/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
			if (folio_test_hugetlb(folio)) {
				if (anon_exclusive &&
				    hugetlb_try_share_anon_rmap(folio)) {
					set_huge_pte_at(mm, address, pvmw.pte,
							pteval, hsz);
					ret = false;
					page_vma_mapped_walk_done(&pvmw);
					break;
				}
			} else if (anon_exclusive &&
				   folio_try_share_anon_rmap_pte(folio, subpage)) {
				set_pte_at(mm, address, pvmw.pte, pteval);
				ret = false;
				page_vma_mapped_walk_done(&pvmw);
				break;
			}

			/*
			 * Store the pfn of the page in a special migration
			 * pte. do_swap_page() will wait until the migration
			 * pte is removed and then restart fault handling.
			 */
			if (writable)
				entry = make_writable_migration_entry(
							page_to_pfn(subpage));
			else if (anon_exclusive)
				entry = make_readable_exclusive_migration_entry(
							page_to_pfn(subpage));
			else
				entry = make_readable_migration_entry(
							page_to_pfn(subpage));
			if (likely(pte_present(pteval))) {
				if (pte_young(pteval))
					entry = make_migration_entry_young(entry);
				if (pte_dirty(pteval))
					entry = make_migration_entry_dirty(entry);
				swp_pte = swp_entry_to_pte(entry);
				if (pte_soft_dirty(pteval))
					swp_pte = pte_swp_mksoft_dirty(swp_pte);
				if (pte_uffd(pteval))
					swp_pte = pte_swp_mkuffd(swp_pte);
			} else {
				swp_pte = swp_entry_to_pte(entry);
				if (pte_swp_soft_dirty(pteval))
					swp_pte = pte_swp_mksoft_dirty(swp_pte);
				if (pte_swp_uffd(pteval))
					swp_pte = pte_swp_mkuffd(swp_pte);
			}
			if (folio_test_hugetlb(folio))
				set_huge_pte_at(mm, address, pvmw.pte, swp_pte,
						hsz);
			else
				set_pte_at(mm, address, pvmw.pte, swp_pte);
			trace_set_migration_pte(address, pte_val(swp_pte),
						folio_order(folio));
			/*
			 * No need to invalidate here it will synchronize on
			 * against the special swap migration pte.
			 */
		}

		if (unlikely(folio_test_hugetlb(folio)))
			hugetlb_remove_rmap(folio);
		else
			folio_remove_rmap_pte(folio, subpage, vma);
		if (vma->vm_flags & VM_LOCKED)
			mlock_drain_local();
		folio_put(folio);
	}

	mmu_notifier_invalidate_range_end(&range);

	return ret;
}

/**
 * try_to_migrate - try to replace all page table mappings with swap entries
 * @folio: the folio to replace page table entries for
 * @flags: action and flags
 *
 * Tries to remove all the page table entries which are mapping this folio and
 * replace them with special swap entries. Caller must hold the folio lock.
 */
void try_to_migrate(struct folio *folio, enum ttu_flags flags)
{
	struct rmap_walk_control rwc = {
		.rmap_one = try_to_migrate_one,
		.arg = (void *)flags,
		.done = folio_not_mapped,
		.anon_lock = folio_lock_anon_vma_read,
	};

	/*
	 * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and
	 * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags.
	 */
	if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
					TTU_SYNC | TTU_BATCH_FLUSH)))
		return;

	if (folio_is_zone_device(folio) &&
	    (!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
		return;

	/*
	 * During exec, a temporary VMA is setup and later moved.
	 * The VMA is moved under the anon_vma lock but not the
	 * page tables leading to a race where migration cannot
	 * find the migration ptes. Rather than increasing the
	 * locking requirements of exec(), migration skips
	 * temporary VMAs until after exec() completes.
	 */
	if (!folio_test_ksm(folio) && folio_test_anon(folio))
		rwc.invalid_vma = invalid_migration_vma;

	if (flags & TTU_RMAP_LOCKED)
		rmap_walk_locked(folio, &rwc);
	else
		rmap_walk(folio, &rwc);
}

#ifdef CONFIG_DEVICE_PRIVATE
/**
 * make_device_exclusive() - Mark a page for exclusive use by a device
 * @mm: mm_struct of associated target process
 * @addr: the virtual address to mark for exclusive device access
 * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering
 * @foliop: folio pointer will be stored here on success.
 *
 * This function looks up the page mapped at the given address, grabs a
 * folio reference, locks the folio and replaces the PTE with special
 * device-exclusive PFN swap entry, preventing access through the process
 * page tables. The function will return with the folio locked and referenced.
 *
 * On fault, the device-exclusive entries are replaced with the original PTE
 * under folio lock, after calling MMU notifiers.
 *
 * Only anonymous non-hugetlb folios are supported and the VMA must have
 * write permissions such that we can fault in the anonymous page writable
 * in order to mark it exclusive. The caller must hold the mmap_lock in read
 * mode.
 *
 * A driver using this to program access from a device must use a mmu notifier
 * critical section to hold a device specific lock during programming. Once
 * programming is complete it should drop the folio lock and reference after
 * which point CPU access to the page will revoke the exclusive access.
 *
 * Notes:
 *   #. This function always operates on individual PTEs mapping individual
 *      pages. PMD-sized THPs are first remapped to be mapped by PTEs before
 *      the conversion happens on a single PTE corresponding to @addr.
 *   #. While concurrent access through the process page tables is prevented,
 *      concurrent access through other page references (e.g., earlier GUP
 *      invocation) is not handled and not supported.
 *   #. device-exclusive entries are considered "clean" and "old" by core-mm.
 *      Device drivers must update the folio state when informed by MMU
 *      notifiers.
 *
 * Returns: pointer to mapped page on success, otherwise a negative error.
 */
struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr,
		void *owner, struct folio **foliop)
{
	struct mmu_notifier_range range;
	struct folio *folio, *fw_folio;
	struct vm_area_struct *vma;
	struct folio_walk fw;
	struct page *page;
	swp_entry_t entry;
	pte_t swp_pte;
	int ret;

	mmap_assert_locked(mm);
	addr = PAGE_ALIGN_DOWN(addr);

	/*
	 * Fault in the page writable and try to lock it; note that if the
	 * address would already be marked for exclusive use by a device,
	 * the GUP call would undo that first by triggering a fault.
	 *
	 * If any other device would already map this page exclusively, the
	 * fault will trigger a conversion to an ordinary
	 * (non-device-exclusive) PTE and issue a MMU_NOTIFY_EXCLUSIVE.
	 */
retry:
	page = get_user_page_vma_remote(mm, addr,
					FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD,
					&vma);
	if (IS_ERR(page))
		return page;
	folio = page_folio(page);

	if (!folio_test_anon(folio) || folio_test_hugetlb(folio)) {
		folio_put(folio);
		return ERR_PTR(-EOPNOTSUPP);
	}

	ret = folio_lock_killable(folio);
	if (ret) {
		folio_put(folio);
		return ERR_PTR(ret);
	}

	/*
	 * Inform secondary MMUs that we are going to convert this PTE to
	 * device-exclusive, such that they unmap it now. Note that the
	 * caller must filter this event out to prevent livelocks.
	 */
	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0,
				      mm, addr, addr + PAGE_SIZE, owner);
	mmu_notifier_invalidate_range_start(&range);

	/*
	 * Let's do a second walk and make sure we still find the same page
	 * mapped writable. Note that any page of an anonymous folio can
	 * only be mapped writable using exactly one PTE ("exclusive"), so
	 * there cannot be other mappings.
	 */
	fw_folio = folio_walk_start(&fw, vma, addr, 0);
	if (fw_folio != folio || fw.page != page ||
	    fw.level != FW_LEVEL_PTE || !pte_write(fw.pte)) {
		if (fw_folio)
			folio_walk_end(&fw, vma);
		mmu_notifier_invalidate_range_end(&range);
		folio_unlock(folio);
		folio_put(folio);
		goto retry;
	}

	/* Nuke the page table entry so we get the uptodate dirty bit. */
	flush_cache_page(vma, addr, page_to_pfn(page));
	fw.pte = ptep_clear_flush(vma, addr, fw.ptep);

	/* Set the dirty flag on the folio now the PTE is gone. */
	if (pte_dirty(fw.pte))
		folio_mark_dirty(folio);

	/*
	 * Store the pfn of the page in a special device-exclusive PFN swap PTE.
	 * do_swap_page() will trigger the conversion back while holding the
	 * folio lock.
	 */
	entry = make_device_exclusive_entry(page_to_pfn(page));
	swp_pte = swp_entry_to_pte(entry);
	if (pte_soft_dirty(fw.pte))
		swp_pte = pte_swp_mksoft_dirty(swp_pte);
	/* The pte is writable, uffd-wp does not apply. */
	set_pte_at(mm, addr, fw.ptep, swp_pte);

	folio_walk_end(&fw, vma);
	mmu_notifier_invalidate_range_end(&range);
	*foliop = folio;
	return page;
}
EXPORT_SYMBOL_GPL(make_device_exclusive);
#endif

void __put_anon_vma(struct anon_vma *anon_vma)
{
	struct anon_vma *root = anon_vma->root;

	anon_vma_free(anon_vma);
	if (root != anon_vma && atomic_dec_and_test(&root->refcount))
		anon_vma_free(root);
}

static struct anon_vma *rmap_walk_anon_lock(const struct folio *folio,
					    struct rmap_walk_control *rwc)
{
	struct anon_vma *anon_vma;

	if (rwc->anon_lock)
		return rwc->anon_lock(folio, rwc);

	/*
	 * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read()
	 * because that depends on folio_mapped(); but not all its usages
	 * are holding mmap_lock. Users without mmap_lock are required to
	 * take a reference count to prevent the anon_vma disappearing
	 */
	anon_vma = folio_anon_vma(folio);
	if (!anon_vma)
		return NULL;

	if (anon_vma_trylock_read(anon_vma))
		goto out;

	if (rwc->try_lock) {
		anon_vma = NULL;
		rwc->contended = true;
		goto out;
	}

	anon_vma_lock_read(anon_vma);
out:
	return anon_vma;
}

/*
 * rmap_walk_anon - do something to anonymous page using the object-based
 * rmap method
 * @folio: the folio to be handled
 * @rwc: control variable according to each walk type
 * @locked: caller holds relevant rmap lock
 *
 * Find all the mappings of a folio using the mapping pointer and the vma
 * chains contained in the anon_vma struct it points to.
 */
static void rmap_walk_anon(struct folio *folio,
		struct rmap_walk_control *rwc, bool locked)
{
	struct anon_vma *anon_vma;
	pgoff_t pgoff_start, pgoff_end;
	struct anon_vma_chain *avc;

	/*
	 * The folio lock ensures that folio->mapping can't be changed under us
	 * to an anon_vma with different root.
	 */
	VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);

	if (locked) {
		anon_vma = folio_anon_vma(folio);
		/* anon_vma disappear under us? */
		VM_BUG_ON_FOLIO(!anon_vma, folio);
	} else {
		anon_vma = rmap_walk_anon_lock(folio, rwc);
	}
	if (!anon_vma)
		return;

	pgoff_start = folio_pgoff(folio);
	pgoff_end = pgoff_start + folio_nr_pages(folio) - 1;
	anon_rmap_tree_foreach(avc, anon_vma, pgoff_start, pgoff_end) {
		struct vm_area_struct *vma = avc->vma;
		const unsigned long address = vma_anon_address(vma, pgoff_start,
				folio_nr_pages(folio));

		VM_WARN_ON_ONCE_VMA(address == -EFAULT, vma);
		cond_resched();

		if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
			continue;

		if (!rwc->rmap_one(folio, vma, address, rwc->arg))
			break;
		if (rwc->done && rwc->done(folio))
			break;
	}

	if (!locked)
		anon_vma_unlock_read(anon_vma);
}

/**
 * __rmap_walk_file() - Traverse the reverse mapping for a file-backed mapping
 * of a page mapped within a specified page cache object at a specified offset.
 *
 * @folio: 		Either the folio whose mappings to traverse, or if NULL,
 * 			the callbacks specified in @rwc will be configured such
 * 			as to be able to look up mappings correctly.
 * @mapping: 		The page cache object whose mapping VMAs we intend to
 * 			traverse. If @folio is non-NULL, this should be equal to
 *			folio_mapping(folio).
 * @pgoff_start:	The offset within @mapping of the page which we are
 * 			looking up. If @folio is non-NULL, this should be equal
 * 			to folio_pgoff(folio).
 * @nr_pages:		The number of pages mapped by the mapping. If @folio is
 *			non-NULL, this should be equal to folio_nr_pages(folio).
 * @rwc:		The reverse mapping walk control object describing how
 *			the traversal should proceed.
 * @locked:		Is the @mapping already locked? If not, we acquire the
 *			lock.
 */
static void __rmap_walk_file(struct folio *folio, struct address_space *mapping,
			     pgoff_t pgoff_start, unsigned long nr_pages,
			     struct rmap_walk_control *rwc, bool locked)
{
	pgoff_t pgoff_end = pgoff_start + nr_pages - 1;
	struct vm_area_struct *vma;

	VM_WARN_ON_FOLIO(folio && mapping != folio_mapping(folio), folio);
	VM_WARN_ON_FOLIO(folio && pgoff_start != folio_pgoff(folio), folio);
	VM_WARN_ON_FOLIO(folio && nr_pages != folio_nr_pages(folio), folio);

	if (!locked) {
		if (i_mmap_trylock_read(mapping))
			goto lookup;

		if (rwc->try_lock) {
			rwc->contended = true;
			return;
		}

		i_mmap_lock_read(mapping);
	}
lookup:
	mapping_rmap_tree_foreach(vma, mapping, pgoff_start, pgoff_end) {
		unsigned long address = vma_filebacked_address(vma, pgoff_start,
							       nr_pages);

		VM_BUG_ON_VMA(address == -EFAULT, vma);
		cond_resched();

		if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
			continue;

		if (!rwc->rmap_one(folio, vma, address, rwc->arg))
			goto done;
		if (rwc->done && rwc->done(folio))
			goto done;
	}
done:
	if (!locked)
		i_mmap_unlock_read(mapping);
}

/*
 * rmap_walk_file - do something to file page using the object-based rmap method
 * @folio: the folio to be handled
 * @rwc: control variable according to each walk type
 * @locked: caller holds relevant rmap lock
 *
 * Find all the mappings of a folio using the mapping pointer and the vma chains
 * contained in the address_space struct it points to.
 */
static void rmap_walk_file(struct folio *folio,
		struct rmap_walk_control *rwc, bool locked)
{
	/*
	 * The folio lock not only makes sure that folio->mapping cannot
	 * suddenly be NULLified by truncation, it makes sure that the structure
	 * at mapping cannot be freed and reused yet, so we can safely take
	 * mapping->i_mmap_rwsem.
	 */
	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);

	if (!folio->mapping)
		return;

	__rmap_walk_file(folio, folio->mapping, folio->index,
			 folio_nr_pages(folio), rwc, locked);
}

void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc)
{
	if (unlikely(folio_test_ksm(folio)))
		rmap_walk_ksm(folio, rwc);
	else if (folio_test_anon(folio))
		rmap_walk_anon(folio, rwc, false);
	else
		rmap_walk_file(folio, rwc, false);
}

/* Like rmap_walk, but caller holds relevant rmap lock */
void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc)
{
	/* no ksm support for now */
	VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio);
	if (folio_test_anon(folio))
		rmap_walk_anon(folio, rwc, true);
	else
		rmap_walk_file(folio, rwc, true);
}

#ifdef CONFIG_HUGETLB_PAGE
/*
 * The following two functions are for anonymous (private mapped) hugepages.
 * Unlike common anonymous pages, anonymous hugepages have no accounting code
 * and no lru code, because we handle hugepages differently from common pages.
 */
void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
		unsigned long address, rmap_t flags)
{
	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);

	atomic_inc(&folio->_entire_mapcount);
	atomic_inc(&folio->_large_mapcount);
	if (flags & RMAP_EXCLUSIVE)
		SetPageAnonExclusive(&folio->page);
	VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 &&
			 PageAnonExclusive(&folio->page), folio);
}

void hugetlb_add_new_anon_rmap(struct folio *folio,
		struct vm_area_struct *vma, unsigned long address)
{
	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);

	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
	/* increment count (starts at -1) */
	atomic_set(&folio->_entire_mapcount, 0);
	atomic_set(&folio->_large_mapcount, 0);
	folio_clear_hugetlb_restore_reserve(folio);
	__folio_set_anon(folio, vma, address, true);
	SetPageAnonExclusive(&folio->page);
}
#endif /* CONFIG_HUGETLB_PAGE */