dax.c

/*
 * 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>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */

#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 "internal.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_locked(unsigned long pfn, unsigned long flags)
{
	return xa_mk_value(flags | ((unsigned long)pfn << DAX_SHIFT) |
			DAX_LOCKED);
}

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 int dax_is_pmd_entry(void *entry)
{
	return xa_to_value(entry) & DAX_PMD;
}

static int 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;
}

/*
 * 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;
};

static wait_queue_head_t *dax_entry_waitqueue(struct xarray *xa,
		pgoff_t index, void *entry, struct exceptional_entry_key *key)
{
	unsigned long hash;

	/*
	 * 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 = xa;
	key->entry_start = index;

	hash = hash_long((unsigned long)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_mapping_entry_waiter(struct xarray *xa,
		pgoff_t index, void *entry, bool wake_all)
{
	struct exceptional_entry_key key;
	wait_queue_head_t *wq;

	wq = dax_entry_waitqueue(xa, index, 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, wake_all ? 0 : 1, &key);
}

static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all)
{
	return dax_wake_mapping_entry_waiter(xas->xa, xas->xa_index, entry,
								wake_all);
}

/*
 * 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.
 *
 * Must be called with the i_pages lock held.
 */
static void *get_unlocked_entry(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;

	for (;;) {
		entry = xas_load(xas);
		if (!entry || xa_is_internal(entry) ||
				WARN_ON_ONCE(!xa_is_value(entry)) ||
				!dax_is_locked(entry))
			return entry;

		wq = dax_entry_waitqueue(xas->xa, xas->xa_index, 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);
	}
}

static void put_unlocked_entry(struct xa_state *xas, void *entry)
{
	/* If we were the only waiter woken, wake the next one */
	if (entry)
		dax_wake_entry(xas, entry, false);
}

/*
 * 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;

	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, false);
}

/*
 * 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));
}

/*
 * Check whether the given slot is locked.  Must be called with the i_pages
 * lock held.
 */
static inline int slot_locked(struct address_space *mapping, void **slot)
{
	unsigned long entry = xa_to_value(
		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
	return entry & DAX_LOCKED;
}

/*
 * Mark the given slot as locked.  Must be called with the i_pages lock held.
 */
static inline void *lock_slot(struct address_space *mapping, void **slot)
{
	unsigned long v = xa_to_value(
		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
	void *entry = xa_mk_value(v | DAX_LOCKED);
	radix_tree_replace_slot(&mapping->i_pages, slot, entry);
	return entry;
}

/*
 * Mark the given slot as unlocked.  Must be called with the i_pages lock held.
 */
static inline void *unlock_slot(struct address_space *mapping, void **slot)
{
	unsigned long v = xa_to_value(
		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
	void *entry = xa_mk_value(v & ~DAX_LOCKED);
	radix_tree_replace_slot(&mapping->i_pages, slot, entry);
	return entry;
}

/*
 * Lookup entry in page cache, wait for it to become unlocked if it is
 * a DAX entry and return it. The caller must call
 * put_unlocked_mapping_entry() when he decided not to lock the entry or
 * put_locked_mapping_entry() when he locked the entry and now wants to
 * unlock it.
 *
 * Must be called with the i_pages lock held.
 */
static void *__get_unlocked_mapping_entry(struct address_space *mapping,
		pgoff_t index, void ***slotp, bool (*wait_fn)(void))
{
	void *entry, **slot;
	struct wait_exceptional_entry_queue ewait;
	wait_queue_head_t *wq;

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

	for (;;) {
		bool revalidate;

		entry = __radix_tree_lookup(&mapping->i_pages, index, NULL,
					  &slot);
		if (!entry ||
		    WARN_ON_ONCE(!xa_is_value(entry)) ||
		    !slot_locked(mapping, slot)) {
			if (slotp)
				*slotp = slot;
			return entry;
		}

		wq = dax_entry_waitqueue(&mapping->i_pages, index, entry,
				&ewait.key);
		prepare_to_wait_exclusive(wq, &ewait.wait,
					  TASK_UNINTERRUPTIBLE);
		xa_unlock_irq(&mapping->i_pages);
		revalidate = wait_fn();
		finish_wait(wq, &ewait.wait);
		xa_lock_irq(&mapping->i_pages);
		if (revalidate)
			return ERR_PTR(-EAGAIN);
	}
}

static bool entry_wait(void)
{
	schedule();
	/*
	 * Never return an ERR_PTR() from
	 * __get_unlocked_mapping_entry(), just keep looping.
	 */
	return false;
}

static void *get_unlocked_mapping_entry(struct address_space *mapping,
		pgoff_t index, void ***slotp)
{
	return __get_unlocked_mapping_entry(mapping, index, slotp, entry_wait);
}

static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
{
	void *entry, **slot;

	xa_lock_irq(&mapping->i_pages);
	entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot);
	if (WARN_ON_ONCE(!entry || !xa_is_value(entry) ||
			 !slot_locked(mapping, slot))) {
		xa_unlock_irq(&mapping->i_pages);
		return;
	}
	unlock_slot(mapping, slot);
	xa_unlock_irq(&mapping->i_pages);
	dax_wake_mapping_entry_waiter(&mapping->i_pages, index, entry, false);
}

static void put_locked_mapping_entry(struct address_space *mapping,
		pgoff_t index)
{
	unlock_mapping_entry(mapping, index);
}

/*
 * Called when we are done with page cache entry we looked up via
 * get_unlocked_mapping_entry() and which we didn't lock in the end.
 */
static void put_unlocked_mapping_entry(struct address_space *mapping,
				       pgoff_t index, void *entry)
{
	if (!entry)
		return;

	/* We have to wake up next waiter for the page cache entry lock */
	dax_wake_mapping_entry_waiter(&mapping->i_pages, index, entry, false);
}

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;
}

static bool entry_wait_revalidate(void)
{
	rcu_read_unlock();
	schedule();
	rcu_read_lock();

	/*
	 * Tell __get_unlocked_mapping_entry() to take a break, we need
	 * to revalidate page->mapping after dropping locks
	 */
	return true;
}

bool dax_lock_mapping_entry(struct page *page)
{
	pgoff_t index;
	struct inode *inode;
	bool did_lock = false;
	void *entry = NULL, **slot;
	struct address_space *mapping;

	rcu_read_lock();
	for (;;) {
		mapping = READ_ONCE(page->mapping);

		if (!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.
		 */
		inode = mapping->host;
		if (S_ISCHR(inode->i_mode)) {
			did_lock = true;
			break;
		}

		xa_lock_irq(&mapping->i_pages);
		if (mapping != page->mapping) {
			xa_unlock_irq(&mapping->i_pages);
			continue;
		}
		index = page->index;

		entry = __get_unlocked_mapping_entry(mapping, index, &slot,
				entry_wait_revalidate);
		if (!entry) {
			xa_unlock_irq(&mapping->i_pages);
			break;
		} else if (IS_ERR(entry)) {
			WARN_ON_ONCE(PTR_ERR(entry) != -EAGAIN);
			continue;
		}
		lock_slot(mapping, slot);
		did_lock = true;
		xa_unlock_irq(&mapping->i_pages);
		break;
	}
	rcu_read_unlock();

	return did_lock;
}

void dax_unlock_mapping_entry(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode = mapping->host;

	if (S_ISCHR(inode->i_mode))
		return;

	unlock_mapping_entry(mapping, page->index);
}

/*
 * 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 an error.  This error will
 * happen if there are any 4k entries within the 2MiB range that we are
 * requesting.
 *
 * We always favor 4k entries over 2MiB entries. There isn't a flow where we
 * evict 4k entries in order to 'upgrade' them to a 2MiB entry.  A 2MiB
 * insertion will fail if it finds any 4k entries already in the tree, and a
 * 4k insertion will cause an existing 2MiB entry to be unmapped and
 * downgraded to 4k entries.  This happens for both 2MiB huge zero pages as
 * well as 2MiB empty entries.
 *
 * The exception to this downgrade path is for 2MiB DAX PMD entries that have
 * real storage backing them.  We will leave these real 2MiB DAX entries in
 * the tree, and PTE writes will simply dirty the entire 2MiB DAX 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.
 */
static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
		unsigned long size_flag)
{
	bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */
	void *entry, **slot;

restart:
	xa_lock_irq(&mapping->i_pages);
	entry = get_unlocked_mapping_entry(mapping, index, &slot);

	if (WARN_ON_ONCE(entry && !xa_is_value(entry))) {
		entry = ERR_PTR(-EIO);
		goto out_unlock;
	}

	if (entry) {
		if (size_flag & DAX_PMD) {
			if (dax_is_pte_entry(entry)) {
				put_unlocked_mapping_entry(mapping, index,
						entry);
				entry = ERR_PTR(-EEXIST);
				goto out_unlock;
			}
		} else { /* trying to grab a PTE entry */
			if (dax_is_pmd_entry(entry) &&
			    (dax_is_zero_entry(entry) ||
			     dax_is_empty_entry(entry))) {
				pmd_downgrade = true;
			}
		}
	}

	/* No entry for given index? Make sure radix tree is big enough. */
	if (!entry || pmd_downgrade) {
		int err;

		if (pmd_downgrade) {
			/*
			 * Make sure 'entry' remains valid while we drop
			 * the i_pages lock.
			 */
			entry = lock_slot(mapping, slot);
		}

		xa_unlock_irq(&mapping->i_pages);
		/*
		 * Besides huge zero pages the only other thing that gets
		 * downgraded are empty entries which don't need to be
		 * unmapped.
		 */
		if (pmd_downgrade && dax_is_zero_entry(entry))
			unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
							PG_PMD_NR, false);

		err = radix_tree_preload(
				mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
		if (err) {
			if (pmd_downgrade)
				put_locked_mapping_entry(mapping, index);
			return ERR_PTR(err);
		}
		xa_lock_irq(&mapping->i_pages);

		if (!entry) {
			/*
			 * We needed to drop the i_pages lock while calling
			 * radix_tree_preload() and we didn't have an entry to
			 * lock.  See if another thread inserted an entry at
			 * our index during this time.
			 */
			entry = __radix_tree_lookup(&mapping->i_pages, index,
					NULL, &slot);
			if (entry) {
				radix_tree_preload_end();
				xa_unlock_irq(&mapping->i_pages);
				goto restart;
			}
		}

		if (pmd_downgrade) {
			dax_disassociate_entry(entry, mapping, false);
			radix_tree_delete(&mapping->i_pages, index);
			mapping->nrexceptional--;
			dax_wake_mapping_entry_waiter(&mapping->i_pages,
					index, entry, true);
		}

		entry = dax_make_locked(0, size_flag | DAX_EMPTY);

		err = __radix_tree_insert(&mapping->i_pages, index,
				dax_entry_order(entry), entry);
		radix_tree_preload_end();
		if (err) {
			xa_unlock_irq(&mapping->i_pages);
			/*
			 * Our insertion of a DAX entry failed, most likely
			 * because we were inserting a PMD entry and it
			 * collided with a PTE sized entry at a different
			 * index in the PMD range.  We haven't inserted
			 * anything into the radix tree and have no waiters to
			 * wake.
			 */
			return ERR_PTR(err);
		}
		/* Good, we have inserted empty locked entry into the tree. */
		mapping->nrexceptional++;
		xa_unlock_irq(&mapping->i_pages);
		return entry;
	}
	entry = lock_slot(mapping, slot);
 out_unlock:
	xa_unlock_irq(&mapping->i_pages);
	return entry;
}

/**
 * dax_layout_busy_page - find first pinned page in @mapping
 * @mapping: address space to scan for a page with ref count > 1
 *
 * 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(struct address_space *mapping)
{
	XA_STATE(xas, &mapping->i_pages, 0);
	void *entry;
	unsigned int scanned = 0;
	struct page *page = NULL;

	/*
	 * 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 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_range() 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_range(mapping, 0, 0, 1);

	xas_lock_irq(&xas);
	xas_for_each(&xas, entry, ULONG_MAX) {
		if (WARN_ON_ONCE(!xa_is_value(entry)))
			continue;
		if (unlikely(dax_is_locked(entry)))
			entry = get_unlocked_entry(&xas);
		if (entry)
			page = dax_busy_page(entry);
		put_unlocked_entry(&xas, entry);
		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);

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);
	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->nrexceptional--;
	ret = 1;
out:
	put_unlocked_entry(&xas, entry);
	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 int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
		sector_t sector, size_t size, struct page *to,
		unsigned long vaddr)
{
	void *vto, *kaddr;
	pgoff_t pgoff;
	long rc;
	int id;

	rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
	if (rc)
		return rc;

	id = dax_read_lock();
	rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, NULL);
	if (rc < 0) {
		dax_read_unlock(id);
		return rc;
	}
	vto = kmap_atomic(to);
	copy_user_page(vto, (void __force *)kaddr, vaddr, to);
	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 address_space *mapping,
		struct vm_fault *vmf,
		void *entry, pfn_t pfn_t, unsigned long flags, bool dirty)
{
	struct radix_tree_root *pages = &mapping->i_pages;
	unsigned long pfn = pfn_t_to_pfn(pfn_t);
	pgoff_t index = vmf->pgoff;
	void *new_entry;

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

	if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
		/* 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, vmf->pgoff, 1, false);
	}

	xa_lock_irq(pages);
	new_entry = dax_make_locked(pfn, flags);
	if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
		dax_disassociate_entry(entry, mapping, false);
		dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address);
	}

	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
		/*
		 * 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.
		 */
		struct radix_tree_node *node;
		void **slot;
		void *ret;

		ret = __radix_tree_lookup(pages, index, &node, &slot);
		WARN_ON_ONCE(ret != entry);
		__radix_tree_replace(pages, node, slot,
				     new_entry, NULL);
		entry = new_entry;
	}

	if (dirty)
		radix_tree_tag_set(pages, index, PAGECACHE_TAG_DIRTY);

	xa_unlock_irq(pages);
	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) {
		unsigned long address, start, end;

		cond_resched();

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

		address = pgoff_address(index, vma);

		/*
		 * Note because we provide start/end to follow_pte_pmd it will
		 * call mmu_notifier_invalidate_range_start() on our behalf
		 * before taking any lock.
		 */
		if (follow_pte_pmd(vma->vm_mm, address, &start, &end, &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_huge_clear_flush(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(vma->vm_mm, start, end);
	}
	i_mmap_unlock_read(mapping);
}

static int dax_writeback_one(struct dax_device *dax_dev,