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 2003, 2004
 */

/*
 * Lock ordering in mm:
 *
 * inode->i_mutex	(while writing or truncating, not reading or faulting)
 *   mm->mmap_sem
 *     page->flags PG_locked (lock_page)
 *       hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
 *         mapping->i_mmap_rwsem
 *           anon_vma->rwsem
 *             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)
 *                   mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
 *                     mapping->tree_lock (widely used)
 *                 inode->i_lock (in set_page_dirty's __mark_inode_dirty)
 *                 bdi.wb->list_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 bdi.wb->list_lock in __sync_single_inode)
 *
 * anon_vma->rwsem,mapping->i_mutex      (memory_failure, collect_procs_anon)
 *   ->tasklist_lock
 *     pte map lock
 */

#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/ksm.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/backing-dev.h>
#include <linux/page_idle.h>

#include <asm/tlbflush.h>

#include <trace/events/tlb.h>

#include "internal.h"

static struct kmem_cache *anon_vma_cachep;
static struct kmem_cache *anon_vma_chain_cachep;

static inline struct anon_vma *anon_vma_alloc(void)
{
	struct anon_vma *anon_vma;

	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
	if (anon_vma) {
		atomic_set(&anon_vma->refcount, 1);
		anon_vma->degree = 1;	/* Reference for first vma */
		anon_vma->parent = anon_vma;
		/*
		 * Initialise the anon_vma root to point to itself. If called
		 * from fork, the root will be reset to the parents anon_vma.
		 */
		anon_vma->root = anon_vma;
	}

	return anon_vma;
}

static inline void anon_vma_free(struct anon_vma *anon_vma)
{
	VM_BUG_ON(atomic_read(&anon_vma->refcount));

	/*
	 * Synchronize against page_lock_anon_vma_read() such that
	 * we can safely hold the lock without the anon_vma getting
	 * freed.
	 *
	 * Relies on the full mb implied by the atomic_dec_and_test() from
	 * put_anon_vma() against the acquire barrier implied by
	 * down_read_trylock() from page_lock_anon_vma_read(). This orders:
	 *
	 * page_lock_anon_vma_read()	VS	put_anon_vma()
	 *   down_read_trylock()		  atomic_dec_and_test()
	 *   LOCK				  MB
	 *   atomic_read()			  rwsem_is_locked()
	 *
	 * LOCK should suffice since the actual taking of the lock must
	 * happen _before_ what follows.
	 */
	might_sleep();
	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
		anon_vma_lock_write(anon_vma);
		anon_vma_unlock_write(anon_vma);
	}

	kmem_cache_free(anon_vma_cachep, anon_vma);
}

static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp)
{
	return kmem_cache_alloc(anon_vma_chain_cachep, gfp);
}

static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
{
	kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
}

static void anon_vma_chain_link(struct vm_area_struct *vma,
				struct anon_vma_chain *avc,
				struct anon_vma *anon_vma)
{
	avc->vma = vma;
	avc->anon_vma = anon_vma;
	list_add(&avc->same_vma, &vma->anon_vma_chain);
	anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
}

/**
 * __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, which
 * is handled inline by anon_vma_prepare(). But 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_read()
 * 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 mm_struct *mm = vma->vm_mm;
	struct anon_vma *anon_vma, *allocated;
	struct anon_vma_chain *avc;

	might_sleep();

	avc = anon_vma_chain_alloc(GFP_KERNEL);
	if (!avc)
		goto out_enomem;

	anon_vma = find_mergeable_anon_vma(vma);
	allocated = NULL;
	if (!anon_vma) {
		anon_vma = anon_vma_alloc();
		if (unlikely(!anon_vma))
			goto out_enomem_free_avc;
		allocated = anon_vma;
	}

	anon_vma_lock_write(anon_vma);
	/* page_table_lock to protect against threads */
	spin_lock(&mm->page_table_lock);
	if (likely(!vma->anon_vma)) {
		vma->anon_vma = anon_vma;
		anon_vma_chain_link(vma, avc, anon_vma);
		/* vma reference or self-parent link for new root */
		anon_vma->degree++;
		allocated = NULL;