path: root/mm/rmap.c

/*
 * mm/rmap.c - physical to virtual reverse mappings
 *
 * Copyright 2001, Rik van Riel <riel@conectiva.com.br>
 * Released under the General Public License (GPL).
 *
 * Simple, low overhead reverse mapping scheme.
 * Please try to keep this thing as modular as possible.
 *
 * Provides methods for unmapping each kind of mapped page:
 * the anon methods track anonymous pages, and
 * the file methods track pages belonging to an inode.
 *
 * Original design by Rik van Riel <riel@conectiva.com.br> 2001
 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
 * Contributions by Hugh Dickins <hugh@veritas.com> 2003, 2004
 */

/*
 * Lock ordering in mm:
 *
 * inode->i_mutex	(while writing or truncating, not reading or faulting)
 *   inode->i_alloc_sem (vmtruncate_range)
 *   mm->mmap_sem
 *     page->flags PG_locked (lock_page)
 *       mapping->i_mmap_lock
 *         anon_vma->lock
 *           mm->page_table_lock or pte_lock
 *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
 *             swap_lock (in swap_duplicate, swap_info_get)
 *               mmlist_lock (in mmput, drain_mmlist and others)
 *               mapping->private_lock (in __set_page_dirty_buffers)
 *               inode_lock (in set_page_dirty's __mark_inode_dirty)
 *                 sb_lock (within inode_lock in fs/fs-writeback.c)
 *                 mapping->tree_lock (widely used, in set_page_dirty,
 *                           in arch-dependent flush_dcache_mmap_lock,
 *                           within inode_lock in __sync_single_inode)
 *                   zone->lock (within radix tree node alloc)
 */

#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/module.h>
#include <linux/kallsyms.h>

#include <asm/tlbflush.h>

struct kmem_cache *anon_vma_cachep;

/* This must be called under the mmap_sem. */
int anon_vma_prepare(struct vm_area_struct *vma)
{
	struct anon_vma *anon_vma = vma->anon_vma;

	might_sleep();
	if (unlikely(!anon_vma)) {
		struct mm_struct *mm = vma->vm_mm;
		struct anon_vma *allocated, *locked;

		anon_vma = find_mergeable_anon_vma(vma);
		if (anon_vma) {
			allocated = NULL;
			locked = anon_vma;
			spin_lock(&locked->lock);
		} else {
			anon_vma = anon_vma_alloc();
			if (unlikely(!anon_vma))
				return -ENOMEM;
			allocated = anon_vma;
			locked = NULL;
		}

		/* page_table_lock to protect against threads */
		spin_lock(&mm->page_table_lock);
		if (likely(!vma->anon_vma)) {
			vma->anon_vma = anon_vma;
			list_add_tail(&vma->anon_vma_node, &anon_vma->head);
			allocated = NULL;
		}
		spin_unlock(&mm->page_table_lock);

		if (locked)
			spin_unlock(&locked->lock);
		if (unlikely(allocated))
			anon_vma_free(allocated);
	}
	return 0;
}

void __anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next)
{
	BUG_ON(vma->anon_vma != next->anon_vma);
	list_del(&next->anon_vma_node);
}

void __anon_vma_link(struct vm_area_struct *vma)
{
	struct anon_vma *anon_vma = vma->anon_vma;

	if (anon_vma)
		list_add_tail(&vma->anon_vma_node, &anon_vma->head);
}

void anon_vma_link(struct vm_area_struct *vma)
{
	struct anon_vma *anon_vma = vma->anon_vma;

	if (anon_vma) {
		spin_lock(&anon_vma->lock);
		list_add_tail(&vma->anon_vma_node, &anon_vma->head);
		spin_unlock(&anon_vma->lock);
	}
}

void anon_vma_unlink(struct vm_area_struct *vma)
{
	struct anon_vma *anon_vma = vma->anon_vma;
	int empty;

	if (!anon_vma)
		return;

	spin_lock(&anon_vma->lock);
	list_del(&vma->anon_vma_node);

	/* We must garbage collect the anon_vma if it's empty */
	empty = list_empty(&anon_vma->head);
	spin_unlock(&anon_vma->lock);

	if (empty)
		anon_vma_free(anon_vma);
}

static void anon_vma_ctor(struct kmem_cache *cachep, void *data)
{
	struct anon_vma *anon_vma = data;

	spin_lock_init(&anon_vma->lock);
	INIT_LIST_HEAD(&anon_vma->head);
}

void __init anon_vma_init(void)
{
	anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
			0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor);
}

/*
 * Getting a lock on a stable anon_vma from a page off the LRU is
 * tricky: page_lock_anon_vma rely on RCU to guard against the races.
 */
static struct anon_vma *page_lock_anon_vma(struct page *page)
{
	struct anon_vma *anon_vma;
	unsigned long anon_mapping;

	rcu_read_lock();
	anon_mapping = (unsigned long) page->mapping;
	if (!(anon_mapping & PAGE_MAPPING_ANON))
		goto out;
	if (!page_mapped(page))
		goto out;

	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
	spin_lock(&anon_vma->lock);
	return anon_vma;
out:
	rcu_read_unlock();
	return NULL;
}

static void page_unlock_anon_vma(struct anon_vma *anon_vma)
{
	spin_unlock(&anon_vma->lock);
	rcu_read_unlock();
}

/*<