/*
* 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>
/* 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)
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);
/*
* We use lowest available bit in exceptional entry 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 RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
static unsigned long dax_radix_pfn(void *entry)
{
return (unsigned long)entry >> RADIX_DAX_SHIFT;
}
static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags)
{
return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
(pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK);
}
static unsigned int dax_radix_order(void *entry)
{
if ((unsigned long)entry & RADIX_DAX_PMD)
return PMD_SHIFT - PAGE_SHIFT;
return 0;
}
static int dax_is_pmd_entry(void *entry)
{
return (unsigned long)entry & RADIX_DAX_PMD;
}
static int dax_is_pte_entry(void *entry)
{
return !((unsigned long)entry & RADIX_DAX_PMD);
}
static int dax_is_zero_entry(void *entry)
{
return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
}
static int dax_is_empty_entry(void *entry)
{
return (unsigned long)entry & RADIX_DAX_EMPTY;
}
/*
* DAX radix tree locking
*/
struct exceptional_entry_key {
struct address_space *mapping;
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 address_space *mapping,
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->mapping = mapping;
key->entry_start = index;
|