path: root/mm/memory-failure.c

/*
 * Copyright (C) 2008, 2009 Intel Corporation
 * Authors: Andi Kleen, Fengguang Wu
 *
 * This software may be redistributed and/or modified under the terms of
 * the GNU General Public License ("GPL") version 2 only as published by the
 * Free Software Foundation.
 *
 * High level machine check handler. Handles pages reported by the
 * hardware as being corrupted usually due to a multi-bit ECC memory or cache
 * failure.
 * 
 * In addition there is a "soft offline" entry point that allows stop using
 * not-yet-corrupted-by-suspicious pages without killing anything.
 *
 * Handles page cache pages in various states.	The tricky part
 * here is that we can access any page asynchronously in respect to 
 * other VM users, because memory failures could happen anytime and 
 * anywhere. This could violate some of their assumptions. This is why 
 * this code has to be extremely careful. Generally it tries to use 
 * normal locking rules, as in get the standard locks, even if that means 
 * the error handling takes potentially a long time.
 * 
 * There are several operations here with exponential complexity because
 * of unsuitable VM data structures. For example the operation to map back 
 * from RMAP chains to processes has to walk the complete process list and 
 * has non linear complexity with the number. But since memory corruptions
 * are rare we hope to get away with this. This avoids impacting the core 
 * VM.
 */

/*
 * Notebook:
 * - hugetlb needs more code
 * - kcore/oldmem/vmcore/mem/kmem check for hwpoison pages
 * - pass bad pages to kdump next kernel
 */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/kernel-page-flags.h>
#include <linux/sched.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/backing-dev.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/suspend.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memory_hotplug.h>
#include <linux/mm_inline.h>
#include <linux/kfifo.h>
#include "internal.h"

int sysctl_memory_failure_early_kill __read_mostly = 0;

int sysctl_memory_failure_recovery __read_mostly = 1;

atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);

#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)

u32 hwpoison_filter_enable = 0;
u32 hwpoison_filter_dev_major = ~0U;
u32 hwpoison_filter_dev_minor = ~0U;
u64 hwpoison_filter_flags_mask;
u64 hwpoison_filter_flags_value;
EXPORT_SYMBOL_GPL(hwpoison_filter_enable);
EXPORT_SYMBOL_GPL(hwpoison_filter_dev_major);
EXPORT_SYMBOL_GPL(hwpoison_filter_dev_minor);
EXPORT_SYMBOL_GPL(hwpoison_filter_flags_mask);
EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value);

static int hwpoison_filter_dev(struct page *p)
{
	struct address_space *mapping;
	dev_t dev;

	if (hwpoison_filter_dev_major == ~0U &&
	    hwpoison_filter_dev_minor == ~0U)
		return 0;

	/*
	 * page_mapping() does not accept slab pages.
	 */
	if (PageSlab(p))
		return -EINVAL;

	mapping = page_mapping(p);
	if (mapping == NULL || mapping->host == NULL)
		return -EINVAL;

	dev = mapping->host->i_sb->s_dev;
	if (hwpoison_filter_dev_major != ~0U &&
	    hwpoison_filter_dev_major != MAJOR(dev))
		return -EINVAL;
	if (hwpoison_filter_dev_minor != ~0U &&
	    hwpoison_filter_dev_minor != MINOR(dev))
		return -EINVAL;

	return 0;
}

static int hwpoison_filter_flags(struct page *p)
{
	if (!hwpoison_filter_flags_mask)
		return 0;

	if ((stable_page_flags(p) & hwpoison_filter_flags_mask) ==
				    hwpoison_filter_flags_value)
		return 0;
	else
		return -EIN