rmap.c

/*
 * mm/rmap.c - physical to virtual reverse mappings
 *
 * Copyright 2001, Rik van Riel <riel@conectiva.com.br>
 * Released under the General Public License (GPL).
 *
 * 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_mutex	(while writing or truncating, not reading or faulting)
 *   mm->mmap_lock
 *     page->flags PG_locked (lock_page)   * (see huegtlbfs below)
 *       hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
 *         mapping->i_mmap_rwsem
 *           hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
 *           anon_vma->rwsem
 *             mm->page_table_lock or pte_lock
 *               pgdat->lru_lock (in mark_page_accessed, isolate_lru_page)
 *               swap_lock (in swap_duplicate, swap_info_get)
 *                 mmlist_lock (in mmput, drain_mmlist and others)
 *                 mapping->private_lock (in __set_page_dirty_buffers)
 *                   mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
 *                     i_pages lock (widely used)
 *                 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_mutex      (memory_failure, collect_procs_anon)
 *   ->tasklist_lock
 *     pte map lock
 *
 * * hugetlbfs PageHuge() pages take locks in this order:
 *         mapping->i_mmap_rwsem
 *           hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
 *             page->flags PG_locked (lock_page)
 */

#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/swapops.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 <asm/tlbflush.h>

#include <trace/events/tlb.h>

#include "internal.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->degree = 1;	/* Reference for first vma */
		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 page_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 page_lock_anon_vma_read(). This orders:
	 *
	 * page_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_link(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_interval_tree_insert(avc, &anon_vma->rb_root);
}

/**
 * __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 page_lock_anon_vma_read()
 * and that may actually touch the spinlock 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.
 *
 * This must be called with the mmap_lock held for reading.
 */
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;

	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;
		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)) {
		vma->anon_vma = anon_vma;
		anon_vma_chain_link(vma, avc, anon_vma);
		/* vma reference or self-parent link for new root */
		anon_vma->degree++;
		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;
}

/*
 * This is a useful helper function for locking the anon_vma root as
 * we traverse the vma->anon_vma_chain, looping over anon_vma's that
 * have the same vma.
 *
 * Such anon_vma's should have the same root, so you'd expect to see
 * just a single mutex_lock for the whole traversal.
 */
static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma)
{
	struct anon_vma *new_root = anon_vma->root;
	if (new_root != root) {
		if (WARN_ON_ONCE(root))
			up_write(&root->rwsem);
		root = new_root;
		down_write(&root->rwsem);
	}
	return root;
}

static inline void unlock_anon_vma_root(struct anon_vma *root)
{
	if (root)
		up_write(&root->rwsem);
}

/*
 * Attach the anon_vmas from src to dst.
 * Returns 0 on success, -ENOMEM on failure.
 *
 * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and
 * anon_vma_fork(). The first three want an exact copy of src, while the last
 * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent
 * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call,
 * we can identify this case by checking (!dst->anon_vma && src->anon_vma).
 *
 * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find
 * and reuse existing anon_vma which has no vmas and only one child anon_vma.
 * This prevents degradation of anon_vma hierarchy to endless linear chain in
 * case of constantly forking task. On the other hand, an anon_vma with more
 * than one child isn't reused even if there was no alive vma, thus rmap
 * walker has a good chance of avoiding scanning the whole hierarchy when it
 * searches where page is mapped.
 */
int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
{
	struct anon_vma_chain *avc, *pavc;
	struct anon_vma *root = NULL;

	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma;

		avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN);
		if (unlikely(!avc)) {
			unlock_anon_vma_root(root);
			root = NULL;
			avc = anon_vma_chain_alloc(GFP_KERNEL);
			if (!avc)
				goto enomem_failure;
		}
		anon_vma = pavc->anon_vma;
		root = lock_anon_vma_root(root, anon_vma);
		anon_vma_chain_link(dst, avc, anon_vma);

		/*
		 * Reuse existing anon_vma if its degree lower than two,
		 * that means it has no vma and only one anon_vma child.
		 *
		 * Do not chose parent anon_vma, otherwise first child
		 * will always reuse it. Root anon_vma is never reused:
		 * it has self-parent reference and at least one child.
		 */
		if (!dst->anon_vma && src->anon_vma &&
		    anon_vma != src->anon_vma && anon_vma->degree < 2)
			dst->anon_vma = anon_vma;
	}
	if (dst->anon_vma)
		dst->anon_vma->degree++;
	unlock_anon_vma_root(root);
	return 0;

 enomem_failure:
	/*
	 * dst->anon_vma is dropped here otherwise its degree can be incorrectly
	 * decremented in unlink_anon_vmas().
	 * We can safely do this because callers of anon_vma_clone() don't care
	 * about dst->anon_vma if anon_vma_clone() failed.
	 */
	dst->anon_vma = NULL;
	unlink_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 error;

	/* 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;

	/*
	 * First, attach the new VMA to the parent VMA's anon_vmas,
	 * so rmap can find non-COWed pages in child processes.
	 */
	error = anon_vma_clone(vma, pvma);
	if (error)
		return error;

	/* An existing anon_vma has been reused, all done then. */
	if (vma->anon_vma)
		return 0;

	/* Then add our own anon_vma. */
	anon_vma = anon_vma_alloc();
	if (!anon_vma)
		goto out_error;
	avc = anon_vma_chain_alloc(GFP_KERNEL);
	if (!avc)
		goto out_error_free_anon_vma;

	/*
	 * The root anon_vma's spinlock 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_lock_write(anon_vma);
	anon_vma_chain_link(vma, avc, anon_vma);
	anon_vma->parent->degree++;
	anon_vma_unlock_write(anon_vma);

	return 0;

 out_error_free_anon_vma:
	put_anon_vma(anon_vma);
 out_error:
	unlink_anon_vmas(vma);
	return -ENOMEM;
}

void unlink_anon_vmas(struct vm_area_struct *vma)
{
	struct anon_vma_chain *avc, *next;
	struct anon_vma *root = NULL;

	/*
	 * 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;

		root = lock_anon_vma_root(root, anon_vma);
		anon_vma_interval_tree_remove(avc, &anon_vma->rb_root);

		/*
		 * 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->degree--;
			continue;
		}

		list_del(&avc->same_vma);
		anon_vma_chain_free(avc);
	}
	if (vma->anon_vma)
		vma->anon_vma->degree--;
	unlock_anon_vma_root(root);

	/*
	 * 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->degree);
		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 page_remove_rmap()
 * the best this function can do is return a locked 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 page_mapped() [ hence all those page_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
 * page_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.
 */
struct anon_vma *page_get_anon_vma(struct page *page)
{
	struct anon_vma *anon_vma = NULL;
	unsigned long anon_mapping;

	rcu_read_lock();
	anon_mapping = (unsigned long)READ_ONCE(page->mapping);
	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
		goto out;
	if (!page_mapped(page))
		goto out;

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

	/*
	 * If this page 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 (!page_mapped(page)) {
		rcu_read_unlock();
		put_anon_vma(anon_vma);
		return NULL;
	}
out:
	rcu_read_unlock();

	return anon_vma;
}

/*
 * Similar to page_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 page_get_anon_vma() and then block on the mutex.
 */
struct anon_vma *page_lock_anon_vma_read(struct page *page)
{
	struct anon_vma *anon_vma = NULL;
	struct anon_vma *root_anon_vma;
	unsigned long anon_mapping;

	rcu_read_lock();
	anon_mapping = (unsigned long)READ_ONCE(page->mapping);
	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
		goto out;
	if (!page_mapped(page))
		goto out;

	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
	root_anon_vma = READ_ONCE(anon_vma->root);
	if (down_read_trylock(&root_anon_vma->rwsem)) {
		/*
		 * If the page 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 (!page_mapped(page)) {
			up_read(&root_anon_vma->rwsem);
			anon_vma = NULL;
		}
		goto out;
	}

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

	if (!page_mapped(page)) {
		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;
}

void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
{
	anon_vma_unlock_read(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();
}

static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
{
	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;

	arch_tlbbatch_add_mm(&tlb_ubc->arch, mm);
	tlb_ubc->flush_required = true;

	/*
	 * Ensure compiler does not re-order the setting of tlb_flush_batched
	 * before the PTE is cleared.
	 */
	barrier();
	mm->tlb_flush_batched = true;

	/*
	 * 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)
{
	bool should_defer = false;

	if (!(flags & TTU_BATCH_FLUSH))
		return false;

	/* If remote CPUs need to be flushed then defer batch the flush */
	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
		should_defer = true;
	put_cpu();

	return should_defer;
}

/*
 * 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)
{
	if (data_race(mm->tlb_flush_batched)) {
		flush_tlb_mm(mm);

		/*
		 * Do not allow the compiler to re-order the clearing of
		 * tlb_flush_batched before the tlb is flushed.
		 */
		barrier();
		mm->tlb_flush_batched = false;
	}
}
#else
static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
{
}

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

/*
 * At what user virtual address is page expected in vma?
 * Caller should check the page is actually part of the vma.
 */
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
	unsigned long address;
	if (PageAnon(page)) {
		struct anon_vma *page__anon_vma = page_anon_vma(page);
		/*
		 * 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 || !page__anon_vma ||
		    vma->anon_vma->root != page__anon_vma->root)
			return -EFAULT;
	} else if (page->mapping) {
		if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping)
			return -EFAULT;
	} else
		return -EFAULT;
	address = __vma_address(page, vma);
	if (unlikely(address < vma->vm_start || address >= vma->vm_end))
		return -EFAULT;
	return address;
}

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;
	pmd_t pmde;

	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);
	/*
	 * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at()
	 * without holding anon_vma lock for write.  So when looking for a
	 * genuine pmde (in which to find pte), test present and !THP together.
	 */
	pmde = *pmd;
	barrier();
	if (!pmd_present(pmde) || pmd_trans_huge(pmde))
		pmd = NULL;
out:
	return pmd;
}

struct page_referenced_arg {
	int mapcount;
	int referenced;
	unsigned long vm_flags;
	struct mem_cgroup *memcg;
};
/*
 * arg: page_referenced_arg will be passed
 */
static bool page_referenced_one(struct page *page, struct vm_area_struct *vma,
			unsigned long address, void *arg)
{
	struct page_referenced_arg *pra = arg;
	struct page_vma_mapped_walk pvmw = {
		.page = page,
		.vma = vma,
		.address = address,
	};
	int referenced = 0;

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

		if (vma->vm_flags & VM_LOCKED) {
			page_vma_mapped_walk_done(&pvmw);
			pra->vm_flags |= VM_LOCKED;
			return false; /* To break the loop */
		}

		if (pvmw.pte) {
			if (ptep_clear_flush_young_notify(vma, address,
						pvmw.pte)) {
				/*
				 * Don't treat a reference through
				 * a sequentially read mapping as such.
				 * If the page has been used in another mapping,
				 * we will catch it; if this other mapping is
				 * already gone, the unmap path will have set
				 * PG_referenced or activated the page.
				 */
				if (likely(!(vma->vm_flags & VM_SEQ_READ)))
					referenced++;
			}
		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
			if (pmdp_clear_flush_young_notify(vma, address,
						pvmw.pmd))
				referenced++;
		} else {
			/* unexpected pmd-mapped page? */
			WARN_ON_ONCE(1);
		}

		pra->mapcount--;
	}

	if (referenced)
		clear_page_idle(page);
	if (test_and_clear_page_young(page))
		referenced++;

	if (referenced) {
		pra->referenced++;
		pra->vm_flags |= vma->vm_flags;
	}

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

	return true;
}

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

	if (!mm_match_cgroup(vma->vm_mm, memcg))
		return true;

	return false;
}

/**
 * page_referenced - test if the page was referenced
 * @page: the page to test
 * @is_locked: caller holds lock on the page
 * @memcg: target memory cgroup
 * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
 *
 * Quick test_and_clear_referenced for all mappings to a page,
 * returns the number of ptes which referenced the page.
 */
int page_referenced(struct page *page,
		    int is_locked,
		    struct mem_cgroup *memcg,
		    unsigned long *vm_flags)
{
	int we_locked = 0;
	struct page_referenced_arg pra = {
		.mapcount = total_mapcount(page),
		.memcg = memcg,
	};
	struct rmap_walk_control rwc = {
		.rmap_one = page_referenced_one,
		.arg = (void *)&pra,
		.anon_lock = page_lock_anon_vma_read,
	};

	*vm_flags = 0;
	if (!pra.mapcount)
		return 0;

	if (!page_rmapping(page))
		return 0;

	if (!is_locked && (!PageAnon(page) || PageKsm(page))) {
		we_locked = trylock_page(page);
		if (!we_locked)
			return 1;
	}

	/*
	 * If we are reclaiming on behalf of a cgroup, skip
	 * counting on behalf of references from different
	 * cgroups
	 */
	if (memcg) {
		rwc.invalid_vma = invalid_page_referenced_vma;
	}

	rmap_walk(page, &rwc);
	*vm_flags = pra.vm_flags;

	if (we_locked)
		unlock_page(page);

	return pra.referenced;
}

static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
			    unsigned long address, void *arg)
{
	struct page_vma_mapped_walk pvmw = {
		.page = page,
		.vma = vma,
		.address = address,
		.flags = PVMW_SYNC,
	};
	struct mmu_notifier_range range;
	int *cleaned = arg;

	/*
	 * We have to assume the worse case ie pmd for invalidation. Note that
	 * the page can not be free from this function.
	 */
	mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
				0, vma, vma->vm_mm, address,
				min(vma->vm_end, address + page_size(page)));
	mmu_notifier_invalidate_range_start(&range);

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

		address = pvmw.address;
		if (pvmw.pte) {
			pte_t entry;
			pte_t *pte = pvmw.pte;

			if (!pte_dirty(*pte) && !pte_write(*pte))
				continue;

			flush_cache_page(vma, address, pte_pfn(*pte));
			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;

			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
				continue;

			flush_cache_page(vma, address, page_to_pfn(page));
			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 page? */
			WARN_ON_ONCE(1);
#endif
		}

		/*
		 * No need to call mmu_notifier_invalidate_range() as we are
		 * downgrading page table protection not changing it to point
		 * to a new page.
		 *
		 * See Documentation/vm/mmu_notifier.rst
		 */
		if (ret)
			(*cleaned)++;
	}

	mmu_notifier_invalidate_range_end(&range);

	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 page_mkclean(struct page *page)
{
	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(!PageLocked(page));

	if (!page_mapped(page))
		return 0;

	mapping = page_mapping(page);
	if (!mapping)
		return 0;

	rmap_walk(page, &rwc);

	return cleaned;