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>

/* 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)

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);

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_HZP;
}

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 &= ~((1UL << (PMD_SHIFT - PAGE_SHIFT)) - 1);

	key->mapping = mapping;
	key->entry_start = index;

	hash = hash_long((unsigned long)mapping ^ 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->mapping != ewait->key.mapping ||
	    key->entry_start != ewait->key.entry_start)
		return 0;
	return autoremove_wake_function(wait, mode, sync, NULL);
}

/*
 * Check whether the given slot is locked. The function must be called with
 * mapping->tree_lock held
 */
static inline int slot_locked(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
	return entry & RADIX_DAX_ENTRY_LOCK;
}

/*
 * Mark the given slot is locked. The function must be called with
 * mapping->tree_lock held
 */
static inline void *lock_slot(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);

	entry |= RADIX_DAX_ENTRY_LOCK;
	radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry);
	return (void *)entry;
}

/*
 * Mark the given slot is unlocked. The function must be called with
 * mapping->tree_lock held
 */
static inline void *unlock_slot(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);

	entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
	radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry);
	return (void *)entry;
}

/*
 * Lookup entry in radix tree, wait for it to become unlocked if it is
 * exceptional 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.
 *
 * The function must be called with mapping->tree_lock held.
 */
static void *get_unlocked_mapping_entry(struct address_space *mapping,
					pgoff_t index, void ***slotp)
{
	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 (;;) {
		entry = __radix_tree_lookup(&mapping->page_tree, index, NULL,
					  &slot);
		if (!entry || !radix_tree_exceptional_entry(entry) ||
		    !slot_locked(mapping, slot)) {
			if (slotp)
				*slotp = slot;
			return entry;
		}

		wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key);
		prepare_to_wait_exclusive(wq, &ewait.wait,
					  TASK_UNINTERRUPTIBLE);
		spin_unlock_irq(&mapping->tree_lock);
		schedule();
		finish_wait(wq, &ewait.wait);
		spin_lock_irq(&mapping->tree_lock);
	}
}

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

	spin_lock_irq(&mapping->tree_lock);
	entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
			 !slot_locked(mapping, slot))) {
		spin_unlock_irq(&mapping->tree_lock);
		return;
	}
	unlock_slot(mapping, slot);
	spin_unlock_irq(&mapping->tree_lock);
	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}

static void put_locked_mapping_entry(struct address_space *mapping,
				     pgoff_t index, void *entry)
{
	if (!radix_tree_exceptional_entry(entry)) {
		unlock_page(entry);
		put_page(entry);
	} else {
		dax_unlock_mapping_entry(mapping, index);
	}
}

/*
 * Called when we are done with radix tree 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 (!radix_tree_exceptional_entry(entry))
		return;

	/* We have to wake up next waiter for the radix tree entry lock */
	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}

/*
 * Find radix tree entry at given index. If it points to a page, return with
 * the page locked. If it points to the exceptional entry, return with the
 * radix tree entry locked. If the radix tree doesn't contain given index,
 * create empty exceptional entry for the index and return with it locked.
 *
 * When requesting an entry with size RADIX_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 (either zero pages or DAX entri