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)
 */

#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/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>

#include <asm/tlbflush.h>

#include "internal.h"

static struct kmem_cache *anon_vma_cachep;

static inline struct anon_vma *anon_vma_alloc(void)
{
	return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
}

static inline void anon_vma_free(struct anon_vma *anon_vma)
{
	kmem_cache_free(anon_vma_cachep, anon_vma);
}

/**
 * anon_vma_prepare - attach an anon_vma to a memory region
 * @vma: the memory region in question
 *
 * This makes sure the memory mapping described by 'vma' has
 * an 'anon_vma' attached to it, so that we can associate the
 * anonymous pages mapped into it with that anon_vma.
 *
 * The common case will be that we already have one, but if
 * if not we either need to find an adjacent mapping that we
 * can re-use the anon_vma from (very common when the only
 * reason for splitting a vma has been mprotect()), or we
 * allocate a new one.
 *
 * Anon-vma allocations are very subtle, because we may have
 * optimistically looked up an anon_vma in page_lock_anon_vma()
 * and that may actually touch the spinlock even in the newly
 * allocated vma (it depends on RCU to make sure that the
 * anon_vma isn't actually destroyed).
 *
 * As a result, we need to do proper anon_vma locking even
 * for the new allocation. At the same time, we do not want
 * to do any locking for the common case of already having
 * an anon_vma.
 *
 * This must be called with the mmap_sem held for reading.
 */
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;

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

		/* 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);

		spin_unlock(&anon_vma->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 =<