dax.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * fs/dax.c - Direct Access filesystem code
 * Copyright (c) 2013-2014 Intel Corporation
 * Author: Matthew Wilcox <matthew.r.wilcox@intel.com>
 * Author: Ross Zwisler <ross.zwisler@linux.intel.com>
 */

#include <linux/atomic.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/pagevec.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
#include <linux/pfn_t.h>
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
#include <asm/pgalloc.h>

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

static inline unsigned int pe_order(enum page_entry_size pe_size)
{
	if (pe_size == PE_SIZE_PTE)
		return PAGE_SHIFT - PAGE_SHIFT;
	if (pe_size == PE_SIZE_PMD)
		return PMD_SHIFT - PAGE_SHIFT;
	if (pe_size == PE_SIZE_PUD)
		return PUD_SHIFT - PAGE_SHIFT;
	return ~0;
}

/* We choose 4096 entries - same as per-zone page wait tables */
#define DAX_WAIT_TABLE_BITS 12
#define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)

/* The 'colour' (ie low bits) within a PMD of a page offset.  */
#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
#define PG_PMD_NR	(PMD_SIZE >> PAGE_SHIFT)

/* The order of a PMD entry */
#define PMD_ORDER	(PMD_SHIFT - PAGE_SHIFT)

static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];

static int __init init_dax_wait_table(void)
{
	int i;

	for (i = 0; i < DAX_WAIT_TABLE_ENTRIES; i++)
		init_waitqueue_head(wait_table + i);
	return 0;
}
fs_initcall(init_dax_wait_table);

/*
 * DAX pagecache entries use XArray value entries so they can't be mistaken
 * for pages.  We use one bit for locking, one bit for the entry size (PMD)
 * and two more to tell us if the entry is a zero page or an empty entry that
 * is just used for locking.  In total four special bits.
 *
 * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
 * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
 * block allocation.
 */
#define DAX_SHIFT	(4)
#define DAX_LOCKED	(1UL << 0)
#define DAX_PMD		(1UL << 1)
#define DAX_ZERO_PAGE	(1UL << 2)
#define DAX_EMPTY	(1UL << 3)

static unsigned long dax_to_pfn(void *entry)
{
	return xa_to_value(entry) >> DAX_SHIFT;
}

static void *dax_make_entry(pfn_t pfn, unsigned long flags)
{
	return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
}

static bool dax_is_locked(void *entry)
{
	return xa_to_value(entry) & DAX_LOCKED;
}

static unsigned int dax_entry_order(void *entry)
{
	if (xa_to_value(entry) & DAX_PMD)
		return PMD_ORDER;
	return 0;
}

static unsigned long dax_is_pmd_entry(void *entry)
{
	return xa_to_value(entry) & DAX_PMD;
}

static bool dax_is_pte_entry(void *entry)
{
	return !(xa_to_value(entry) & DAX_PMD);
}

static int dax_is_zero_entry(void *entry)
{
	return xa_to_value(entry) & DAX_ZERO_PAGE;
}

static int dax_is_empty_entry(void *entry)
{
	return xa_to_value(entry) & DAX_EMPTY;
}

/*
 * true if the entry that was found is of a smaller order than the entry
 * we were looking for
 */
static bool dax_is_conflict(void *entry)
{
	return entry == XA_RETRY_ENTRY;
}

/*
 * DAX page cache entry locking
 */
struct exceptional_entry_key {
	struct xarray *xa;
	pgoff_t entry_start;
};

struct wait_exceptional_entry_queue {
	wait_queue_entry_t wait;
	struct exceptional_entry_key key;
};

/**
 * enum dax_wake_mode: waitqueue wakeup behaviour
 * @WAKE_ALL: wake all waiters in the waitqueue
 * @WAKE_NEXT: wake only the first waiter in the waitqueue
 */
enum dax_wake_mode {
	WAKE_ALL,
	WAKE_NEXT,
};

static wait_queue_head_t *dax_entry_waitqueue(struct xa_state *xas,
		void *entry, struct exceptional_entry_key *key)
{
	unsigned long hash;
	unsigned long index = xas->xa_index;

	/*
	 * If 'entry' is a PMD, align the 'index' that we use for the wait
	 * queue to the start of that PMD.  This ensures that all offsets in
	 * the range covered by the PMD map to the same bit lock.
	 */
	if (dax_is_pmd_entry(entry))
		index &= ~PG_PMD_COLOUR;
	key->xa = xas->xa;
	key->entry_start = index;

	hash = hash_long((unsigned long)xas->xa ^ index, DAX_WAIT_TABLE_BITS);
	return wait_table + hash;
}

static int wake_exceptional_entry_func(wait_queue_entry_t *wait,
		unsigned int mode, int sync, void *keyp)
{
	struct exceptional_entry_key *key = keyp;
	struct wait_exceptional_entry_queue *ewait =
		container_of(wait, struct wait_exceptional_entry_queue, wait);

	if (key->xa != ewait->key.xa ||
	    key->entry_start != ewait->key.entry_start)
		return 0;
	return autoremove_wake_function(wait, mode, sync, NULL);
}

/*
 * @entry may no longer be the entry at the index in the mapping.
 * The important information it's conveying is whether the entry at
 * this index used to be a PMD entry.
 */
static void dax_wake_entry(struct xa_state *xas, void *entry,
			   enum dax_wake_mode mode)
{
	struct exceptional_entry_key key;
	wait_queue_head_t *wq;

	wq = dax_entry_waitqueue(xas, entry, &key);

	/*
	 * Checking for locked entry and prepare_to_wait_exclusive() happens
	 * under the i_pages lock, ditto for entry handling in our callers.
	 * So at this point all tasks that could have seen our entry locked
	 * must be in the waitqueue and the following check will see them.
	 */
	if (waitqueue_active(wq))
		__wake_up(wq, TASK_NORMAL, mode == WAKE_ALL ? 0 : 1, &key);
}

/*
 * Look up entry in page cache, wait for it to become unlocked if it
 * is a DAX entry and return it.  The caller must subsequently call
 * put_unlocked_entry() if it did not lock the entry or dax_unlock_entry()
 * if it did.  The entry returned may have a larger order than @order.
 * If @order is larger than the order of the entry found in i_pages, this
 * function returns a dax_is_conflict entry.
 *
 * Must be called with the i_pages lock held.
 */
static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
{
	void *entry;
	struct wait_exceptional_entry_queue ewait;
	wait_queue_head_t *wq;

	init_wait(&ewait.wait);
	ewait.wait.func = wake_exceptional_entry_func;

	for (;;) {
		entry = xas_find_conflict(xas);
		if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
			return entry;
		if (dax_entry_order(entry) < order)
			return XA_RETRY_ENTRY;
		if (!dax_is_locked(entry))
			return entry;

		wq = dax_entry_waitqueue(xas, entry, &ewait.key);
		prepare_to_wait_exclusive(wq, &ewait.wait,
					  TASK_UNINTERRUPTIBLE);
		xas_unlock_irq(xas);
		xas_reset(xas);
		schedule();
		finish_wait(wq, &ewait.wait);
		xas_lock_irq(xas);
	}
}

/*
 * The only thing keeping the address space around is the i_pages lock
 * (it's cycled in clear_inode() after removing the entries from i_pages)
 * After we call xas_unlock_irq(), we cannot touch xas->xa.
 */
static void wait_entry_unlocked(struct xa_state *xas, void *entry)
{
	struct wait_exceptional_entry_queue ewait;
	wait_queue_head_t *wq;

	init_wait(&ewait.wait);
	ewait.wait.func = wake_exceptional_entry_func;

	wq = dax_entry_waitqueue(xas, entry, &ewait.key);
	/*
	 * Unlike get_unlocked_entry() there is no guarantee that this
	 * path ever successfully retrieves an unlocked entry before an
	 * inode dies. Perform a non-exclusive wait in case this path
	 * never successfully performs its own wake up.
	 */
	prepare_to_wait(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
	xas_unlock_irq(xas);
	schedule();
	finish_wait(wq, &ewait.wait);
}

static void put_unlocked_entry(struct xa_state *xas, void *entry,
			       enum dax_wake_mode mode)
{
	if (entry && !dax_is_conflict(entry))
		dax_wake_entry(xas, entry, mode);
}

/*
 * We used the xa_state to get the entry, but then we locked the entry and
 * dropped the xa_lock, so we know the xa_state is stale and must be reset
 * before use.
 */
static void dax_unlock_entry(struct xa_state *xas, void *entry)
{
	void *old;

	BUG_ON(dax_is_locked(entry));
	xas_reset(xas);
	xas_lock_irq(xas);
	old = xas_store(xas, entry);
	xas_unlock_irq(xas);
	BUG_ON(!dax_is_locked(old));
	dax_wake_entry(xas, entry, WAKE_NEXT);
}

/*
 * Return: The entry stored at this location before it was locked.
 */
static void *dax_lock_entry(struct xa_state *xas, void *entry)
{
	unsigned long v = xa_to_value(entry);
	return xas_store(xas, xa_mk_value(v | DAX_LOCKED));
}

static unsigned long dax_entry_size(void *entry)
{
	if (dax_is_zero_entry(entry))
		return 0;
	else if (dax_is_empty_entry(entry))
		return 0;
	else if (dax_is_pmd_entry(entry))
		return PMD_SIZE;
	else
		return PAGE_SIZE;
}

static unsigned long dax_end_pfn(void *entry)
{
	return dax_to_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
}

/*
 * Iterate through all mapped pfns represented by an entry, i.e. skip
 * 'empty' and 'zero' entries.
 */
#define for_each_mapped_pfn(entry, pfn) \
	for (pfn = dax_to_pfn(entry); \
			pfn < dax_end_pfn(entry); pfn++)

/*
 * TODO: for reflink+dax we need a way to associate a single page with
 * multiple address_space instances at different linear_page_index()
 * offsets.
 */
static void dax_associate_entry(void *entry, struct address_space *mapping,
		struct vm_area_struct *vma, unsigned long address)
{
	unsigned long size = dax_entry_size(entry), pfn, index;
	int i = 0;

	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
		return;

	index = linear_page_index(vma, address & ~(size - 1));
	for_each_mapped_pfn(entry, pfn) {
		struct page *page = pfn_to_page(pfn);

		WARN_ON_ONCE(page->mapping);
		page->mapping = mapping;
		page->index = index + i++;
	}
}

static void dax_disassociate_entry(void *entry, struct address_space *mapping,
		bool trunc)
{
	unsigned long pfn;

	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
		return;

	for_each_mapped_pfn(entry, pfn) {
		struct page *page = pfn_to_page(pfn);

		WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
		WARN_ON_ONCE(page->mapping && page->mapping != mapping);
		page->mapping = NULL;
		page->index = 0;
	}
}

static struct page *dax_busy_page(void *entry)
{
	unsigned long pfn;

	for_each_mapped_pfn(entry, pfn) {
		struct page *page = pfn_to_page(pfn);

		if (page_ref_count(page) > 1)
			return page;
	}
	return NULL;
}

/*
 * dax_lock_mapping_entry - Lock the DAX entry corresponding to a page
 * @page: The page whose entry we want to lock
 *
 * Context: Process context.
 * Return: A cookie to pass to dax_unlock_page() or 0 if the entry could
 * not be locked.
 */
dax_entry_t dax_lock_page(struct page *page)
{
	XA_STATE(xas, NULL, 0);
	void *entry;

	/* Ensure page->mapping isn't freed while we look at it */
	rcu_read_lock();
	for (;;) {
		struct address_space *mapping = READ_ONCE(page->mapping);

		entry = NULL;
		if (!mapping || !dax_mapping(mapping))
			break;

		/*
		 * In the device-dax case there's no need to lock, a
		 * struct dev_pagemap pin is sufficient to keep the
		 * inode alive, and we assume we have dev_pagemap pin
		 * otherwise we would not have a valid pfn_to_page()
		 * translation.
		 */
		entry = (void *)~0UL;
		if (S_ISCHR(mapping->host->i_mode))
			break;

		xas.xa = &mapping->i_pages;
		xas_lock_irq(&xas);
		if (mapping != page->mapping) {
			xas_unlock_irq(&xas);
			continue;
		}
		xas_set(&xas, page->index);
		entry = xas_load(&xas);
		if (dax_is_locked(entry)) {
			rcu_read_unlock();
			wait_entry_unlocked(&xas, entry);
			rcu_read_lock();
			continue;
		}
		dax_lock_entry(&xas, entry);
		xas_unlock_irq(&xas);
		break;
	}
	rcu_read_unlock();
	return (dax_entry_t)entry;
}

void dax_unlock_page(struct page *page, dax_entry_t cookie)
{
	struct address_space *mapping = page->mapping;
	XA_STATE(xas, &mapping->i_pages, page->index);

	if (S_ISCHR(mapping->host->i_mode))
		return;

	dax_unlock_entry(&xas, (void *)cookie);
}

/*
 * Find page cache entry at given index. If it is a DAX entry, return it
 * with the entry locked. If the page cache doesn't contain an entry at
 * that index, add a locked empty entry.
 *
 * When requesting an entry with size DAX_PMD, grab_mapping_entry() will
 * either return that locked entry or will return VM_FAULT_FALLBACK.
 * This will happen if there are any PTE entries within the PMD range
 * that we are requesting.
 *
 * We always favor PTE entries over PMD entries. There isn't a flow where we
 * evict PTE entries in order to 'upgrade' them to a PMD entry.  A PMD
 * insertion will fail if it finds any PTE entries already in the tree, and a
 * PTE insertion will cause an existing PMD entry to be unmapped and
 * downgraded to PTE entries.  This happens for both PMD zero pages as
 * well as PMD empty entries.
 *
 * The exception to this downgrade path is for PMD entries that have
 * real storage backing them.  We will leave these real PMD entries in
 * the tree, and PTE writes will simply dirty the entire PMD entry.
 *
 * Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For
 * persistent memory the benefit is doubtful. We can add that later if we can
 * show it helps.
 *
 * On error, this function does not return an ERR_PTR.  Instead it returns
 * a VM_FAULT code, encoded as an xarray internal entry.  The ERR_PTR values
 * overlap with xarray value entries.
 */
static void *grab_mapping_entry(struct xa_state *xas,
		struct address_space *mapping, unsigned int order)
{
	unsigned long index = xas->xa_index;
	bool pmd_downgrade;	/* splitting PMD entry into PTE entries? */
	void *entry;

retry:
	pmd_downgrade = false;
	xas_lock_irq(xas);
	entry = get_unlocked_entry(xas, order);

	if (entry) {
		if (dax_is_conflict(entry))
			goto fallback;
		if (!xa_is_value(entry)) {
			xas_set_err(xas, -EIO);
			goto out_unlock;
		}

		if (order == 0) {
			if (dax_is_pmd_entry(entry) &&
			    (dax_is_zero_entry(entry) ||
			     dax_is_empty_entry(entry))) {
				pmd_downgrade = true;
			}
		}
	}

	if (pmd_downgrade) {
		/*
		 * Make sure 'entry' remains valid while we drop
		 * the i_pages lock.
		 */
		dax_lock_entry(xas, entry);

		/*
		 * Besides huge zero pages the only other thing that gets
		 * downgraded are empty entries which don't need to be
		 * unmapped.
		 */
		if (dax_is_zero_entry(entry)) {
			xas_unlock_irq(xas);
			unmap_mapping_pages(mapping,
					xas->xa_index & ~PG_PMD_COLOUR,
					PG_PMD_NR, false);
			xas_reset(xas);
			xas_lock_irq(xas);
		}

		dax_disassociate_entry(entry, mapping, false);
		xas_store(xas, NULL);	/* undo the PMD join */
		dax_wake_entry(xas, entry, WAKE_ALL);
		mapping->nrpages -= PG_PMD_NR;
		entry = NULL;
		xas_set(xas, index);
	}

	if (entry) {
		dax_lock_entry(xas, entry);
	} else {
		unsigned long flags = DAX_EMPTY;

		if (order > 0)
			flags |= DAX_PMD;
		entry = dax_make_entry(pfn_to_pfn_t(0), flags);
		dax_lock_entry(xas, entry);
		if (xas_error(xas))
			goto out_unlock;
		mapping->nrpages += 1UL << order;
	}

out_unlock:
	xas_unlock_irq(xas);
	if (xas_nomem(xas, mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM))
		goto retry;
	if (xas->xa_node == XA_ERROR(-ENOMEM))
		return xa_mk_internal(VM_FAULT_OOM);
	if (xas_error(xas))
		return xa_mk_internal(VM_FAULT_SIGBUS);
	return entry;
fallback:
	xas_unlock_irq(xas);
	return xa_mk_internal(VM_FAULT_FALLBACK);
}

/**
 * dax_layout_busy_page_range - find first pinned page in @mapping
 * @mapping: address space to scan for a page with ref count > 1
 * @start: Starting offset. Page containing 'start' is included.
 * @end: End offset. Page containing 'end' is included. If 'end' is LLONG_MAX,
 *       pages from 'start' till the end of file are included.
 *
 * DAX requires ZONE_DEVICE mapped pages. These pages are never
 * 'onlined' to the page allocator so they are considered idle when
 * page->count == 1. A filesystem uses this interface to determine if
 * any page in the mapping is busy, i.e. for DMA, or other
 * get_user_pages() usages.
 *
 * It is expected that the filesystem is holding locks to block the
 * establishment of new mappings in this address_space. I.e. it expects
 * to be able to run unmap_mapping_range() and subsequently not race
 * mapping_mapped() becoming true.
 */
struct page *dax_layout_busy_page_range(struct address_space *mapping,
					loff_t start, loff_t end)
{
	void *entry;
	unsigned int scanned = 0;
	struct page *page = NULL;
	pgoff_t start_idx = start >> PAGE_SHIFT;
	pgoff_t end_idx;
	XA_STATE(xas, &mapping->i_pages, start_idx);

	/*
	 * In the 'limited' case get_user_pages() for dax is disabled.
	 */
	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
		return NULL;

	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
		return NULL;

	/* If end == LLONG_MAX, all pages from start to till end of file */
	if (end == LLONG_MAX)
		end_idx = ULONG_MAX;
	else
		end_idx = end >> PAGE_SHIFT;
	/*
	 * If we race get_user_pages_fast() here either we'll see the
	 * elevated page count in the iteration and wait, or
	 * get_user_pages_fast() will see that the page it took a reference
	 * against is no longer mapped in the page tables and bail to the
	 * get_user_pages() slow path.  The slow path is protected by
	 * pte_lock() and pmd_lock(). New references are not taken without
	 * holding those locks, and unmap_mapping_pages() will not zero the
	 * pte or pmd without holding the respective lock, so we are
	 * guaranteed to either see new references or prevent new
	 * references from being established.
	 */
	unmap_mapping_pages(mapping, start_idx, end_idx - start_idx + 1, 0);

	xas_lock_irq(&xas);
	xas_for_each(&xas, entry, end_idx) {
		if (WARN_ON_ONCE(!xa_is_value(entry)))
			continue;
		if (unlikely(dax_is_locked(entry)))
			entry = get_unlocked_entry(&xas, 0);
		if (entry)
			page = dax_busy_page(entry);
		put_unlocked_entry(&xas, entry, WAKE_NEXT);
		if (page)
			break;
		if (++scanned % XA_CHECK_SCHED)
			continue;

		xas_pause(&xas);
		xas_unlock_irq(&xas);
		cond_resched();
		xas_lock_irq(&xas);
	}
	xas_unlock_irq(&xas);
	return page;
}
EXPORT_SYMBOL_GPL(dax_layout_busy_page_range);

struct page *dax_layout_busy_page(struct address_space *mapping)
{
	return dax_layout_busy_page_range(mapping, 0, LLONG_MAX);
}
EXPORT_SYMBOL_GPL(dax_layout_busy_page);

static int __dax_invalidate_entry(struct address_space *mapping,
					  pgoff_t index, bool trunc)
{
	XA_STATE(xas, &mapping->i_pages, index);
	int ret = 0;
	void *entry;

	xas_lock_irq(&xas);
	entry = get_unlocked_entry(&xas, 0);
	if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
		goto out;
	if (!trunc &&
	    (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY) ||
	     xas_get_mark(&xas, PAGECACHE_TAG_TOWRITE)))
		goto out;
	dax_disassociate_entry(entry, mapping, trunc);
	xas_store(&xas, NULL);
	mapping->nrpages -= 1UL << dax_entry_order(entry);
	ret = 1;
out:
	put_unlocked_entry(&xas, entry, WAKE_ALL);
	xas_unlock_irq(&xas);
	return ret;
}

/*
 * Delete DAX entry at @index from @mapping.  Wait for it
 * to be unlocked before deleting it.
 */
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
{
	int ret = __dax_invalidate_entry(mapping, index, true);

	/*
	 * This gets called from truncate / punch_hole path. As such, the caller
	 * must hold locks protecting against concurrent modifications of the
	 * page cache (usually fs-private i_mmap_sem for writing). Since the
	 * caller has seen a DAX entry for this index, we better find it
	 * at that index as well...
	 */
	WARN_ON_ONCE(!ret);
	return ret;
}

/*
 * Invalidate DAX entry if it is clean.
 */
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
				      pgoff_t index)
{
	return __dax_invalidate_entry(mapping, index, false);
}

static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos)
{
	return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset);
}

static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
{
	pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos);
	void *vto, *kaddr;
	long rc;
	int id;

	id = dax_read_lock();
	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL);
	if (rc < 0) {
		dax_read_unlock(id);
		return rc;
	}
	vto = kmap_atomic(vmf->cow_page);
	copy_user_page(vto, kaddr, vmf->address, vmf->cow_page);
	kunmap_atomic(vto);
	dax_read_unlock(id);
	return 0;
}

/*
 * By this point grab_mapping_entry() has ensured that we have a locked entry
 * of the appropriate size so we don't have to worry about downgrading PMDs to
 * PTEs.  If we happen to be trying to insert a PTE and there is a PMD
 * already in the tree, we will skip the insertion and just dirty the PMD as
 * appropriate.
 */
static void *dax_insert_entry(struct xa_state *xas,
		struct address_space *mapping, struct vm_fault *vmf,
		void *entry, pfn_t pfn, unsigned long flags, bool dirty)
{
	void *new_entry = dax_make_entry(pfn, flags);

	if (dirty)
		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);

	if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
		unsigned long index = xas->xa_index;
		/* we are replacing a zero page with block mapping */
		if (dax_is_pmd_entry(entry))
			unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
					PG_PMD_NR, false);
		else /* pte entry */
			unmap_mapping_pages(mapping, index, 1, false);
	}

	xas_reset(xas);
	xas_lock_irq(xas);
	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
		void *old;

		dax_disassociate_entry(entry, mapping, false);
		dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address);
		/*
		 * Only swap our new entry into the page cache if the current
		 * entry is a zero page or an empty entry.  If a normal PTE or
		 * PMD entry is already in the cache, we leave it alone.  This
		 * means that if we are trying to insert a PTE and the
		 * existing entry is a PMD, we will just leave the PMD in the
		 * tree and dirty it if necessary.
		 */
		old = dax_lock_entry(xas, new_entry);
		WARN_ON_ONCE(old != xa_mk_value(xa_to_value(entry) |
					DAX_LOCKED));
		entry = new_entry;
	} else {
		xas_load(xas);	/* Walk the xa_state */
	}

	if (dirty)
		xas_set_mark(xas, PAGECACHE_TAG_DIRTY);

	xas_unlock_irq(xas);
	return entry;
}

static inline
unsigned long pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
{
	unsigned long address;

	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
	return address;
}

/* Walk all mappings of a given index of a file and writeprotect them */
static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
		unsigned long pfn)
{
	struct vm_area_struct *vma;
	pte_t pte, *ptep = NULL;
	pmd_t *pmdp = NULL;
	spinlock_t *ptl;

	i_mmap_lock_read(mapping);
	vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
		struct mmu_notifier_range range;
		unsigned long address;

		cond_resched();

		if (!(vma->vm_flags & VM_SHARED))
			continue;

		address = pgoff_address(index, vma);

		/*
		 * follow_invalidate_pte() will use the range to call
		 * mmu_notifier_invalidate_range_start() on our behalf before
		 * taking any lock.
		 */
		if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep,
					  &pmdp, &ptl))
			continue;

		/*
		 * 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 (pmdp) {
#ifdef CONFIG_FS_DAX_PMD
			pmd_t pmd;

			if (pfn != pmd_pfn(*pmdp))
				goto unlock_pmd;
			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
				goto unlock_pmd;

			flush_cache_page(vma, address, pfn);
			pmd = pmdp_invalidate(vma, address, pmdp);
			pmd = pmd_wrprotect(pmd);
			pmd = pmd_mkclean(pmd);
			set_pmd_at(vma->vm_mm, address, pmdp, pmd);
unlock_pmd:
#endif
			spin_unlock(ptl);
		} else {
			if (pfn != pte_pfn(*ptep))
				goto unlock_pte;
			if (!pte_dirty(*ptep) && !pte_write(*ptep))
				goto unlock_pte;

			flush_cache_page(vma, address, pfn);
			pte = ptep_clear_flush(vma, address, ptep);
			pte = pte_wrprotect(pte);
			pte = pte_mkclean(pte);
			set_pte_at(vma->vm_mm, address, ptep, pte);
unlock_pte:
			pte_unmap_unlock(ptep, ptl);
		}

		mmu_notifier_invalidate_range_end(&range);
	}
	i_mmap_unlock_read(mapping);
}

static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
		struct address_space *mapping, void *entry)
{
	unsigned long pfn, index, count;
	long ret = 0;

	/*
	 * A page got tagged dirty in DAX mapping? Something is seriously
	 * wrong.
	 */
	if (WARN_ON(!xa_is_value(entry)))
		return -EIO;

	if (unlikely(dax_is_locked(entry))) {
		void *old_entry = entry;

		entry = get_unlocked_entry(xas, 0);

		/* Entry got punched out / reallocated? */
		if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
			goto put_unlocked;
		/*
		 * Entry got reallocated elsewhere? No need to writeback.
		 * We have to compare pfns as we must not bail out due to
		 * difference in lockbit or entry type.
		 */
		if (dax_to_pfn(old_entry) != dax_to_pfn(entry))
			goto put_unlocked;
		if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
					dax_is_zero_entry(entry))) {
			ret = -EIO;
			goto put_unlocked;
		}

		/* Another fsync thread may have already done this entry */
		if (!xas_get_mark(xas, PAGECACHE_TAG_TOWRITE))
			goto put_unlocked;
	}

	/* Lock the entry to serialize with page faults */
	dax_lock_entry(xas, entry);

	/*
	 * We can clear the tag now but we have to be careful so that concurrent
	 * dax_writeback_one() calls for the same index cannot finish before we
	 * actually flush the caches. This is achieved as the calls will look
	 * at the entry only under the i_pages lock and once they do that
	 * they will see the entry locked and wait for it to unlock.
	 */
	xas_clear_mark(xas, PAGECACHE_TAG_TOWRITE);
	xas_unlock_irq(xas);

	/*
	 * If dax_writeback_mapping_range() was given a wbc->range_start
	 * in the middle of a PMD, the 'index' we use needs to be
	 * aligned to the start of the PMD.
	 * This allows us to flush for PMD_SIZE and not have to worry about
	 * partial PMD writebacks.
	 */
	pfn = dax_to_pfn(entry);
	count = 1UL << dax_entry_order(entry);
	index = xas->xa_index & ~(count - 1);

	dax_entry_mkclean(mapping, index, pfn);
	dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE);
	/*
	 * After we have flushed the cache, we can clear the dirty tag. There
	 * cannot be new dirty data in the pfn after the flush has completed as
	 * the pfn mappings are writeprotected and fault waits for mapping
	 * entry lock.
	 */
	xas_reset(xas);
	xas_lock_irq(xas);
	xas_store(xas, entry);
	xas_clear_mark(xas, PAGECACHE_TAG_DIRTY);
	dax_wake_entry(xas, entry, WAKE_NEXT);

	trace_dax_writeback_one(mapping->host, index, count);
	return ret;

 put_unlocked:
	put_unlocked_entry(xas, entry, WAKE_NEXT);
	return ret;
}

/*
 * Flush the mapping to the persistent domain within the byte range of [start,
 * end]. This is required by data integrity operations to ensure file data is
 * on persistent storage prior to completion of the operation.
 */
int dax_writeback_mapping_range(struct address_space *mapping,
		struct dax_device *dax_dev, struct writeback_control *wbc)
{
	XA_STATE(xas, &mapping->i_pages, wbc->range_start >> PAGE_SHIFT);
	struct inode *inode = mapping->host;
	pgoff_t end_index = wbc->range_end >> PAGE_SHIFT;
	void *entry;
	int ret = 0;
	unsigned int scanned = 0;

	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
		return -EIO;

	if (mapping_empty(mapping) || wbc->sync_mode != WB_SYNC_ALL)
		return 0;

	trace_dax_writeback_range(inode, xas.xa_index, end_index);

	tag_pages_for_writeback(mapping, xas.xa_index, end_index);

	xas_lock_irq(&xas);
	xas_for_each_marked(&xas, entry, end_index, PAGECACHE_TAG_TOWRITE) {
		ret = dax_writeback_one(&xas, dax_dev, mapping, entry);
		if (ret < 0) {
			mapping_set_error(mapping, ret);
			break;
		}
		if (++scanned % XA_CHECK_SCHED)
			continue;

		xas_pause(&xas);
		xas_unlock_irq(&xas);
		cond_resched();
		xas_lock_irq(&xas);