path: root/fs/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