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 2bit ECC memory or cache
 * failure.
 *
 * Handles page cache pages in various states.	The tricky part
 * here is that we can access any page asynchronous to other VM
 * users, because memory failures could happen anytime and anywhere,
 * possibly violating 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.
 *
 * 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
 * mappings. In short it can be quite slow. But since memory corruptions
 * are rare we hope to get away with this.
 */

/*
 * Notebook:
 * - hugetlb needs more code
 * - kcore/oldmem/vmcore/mem/kmem check for hwpoison pages
 * - pass bad pages to kdump next kernel
 */
#define DEBUG 1		/* remove me in 2.6.34 */
#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/pagemap.h>
#include <linux/swap.h>
#include <linux/backing-dev.h>
#include "internal.h"

int sysctl_memory_failure_early_kill __read_mostly = 0;

int sysctl_memory_failure_recovery __read_mostly = 1;

atomic_long_t mce_bad_pages __read_mostly = ATOMIC_LONG_INIT(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_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 page
	 */
	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 -EINVAL;
}

/*
 * This allows stress tests to limit test scope to a collection of tasks
 * by putting them under some memcg. This prevents killing unrelated/important
 * processes such as /sbin/init. Note that the target task may share clean
 * pages with init (eg. libc text), which is harmless. If the target task
 * share _dirty_ pages with another task B, the test scheme must make sure B
 * is also included in the memcg. At last, due to race conditions this filter
 * can only guarantee that the page either belongs to the memcg tasks, or is
 * a freed page.
 */
#ifdef	CONFIG_CGROUP_MEM_RES_CTLR_SWAP
u64 hwpoison_filter_memcg;
EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
static int hwpoison_filter_task(struct page *p)
{
	struct mem_cgroup *mem;
	struct cgroup_subsys_state *css;
	unsigned long ino;

	if (!hwpoison_filter_memcg)
		return 0;

	mem = try_get_mem_cgroup_from_page(p);
	if (!mem)
		return -EINVAL;

	css = mem_cgroup_css(mem);
	/* root_mem_cgroup has NULL dentries */
	if (!css->cgroup->dentry)
		return -EINVAL;

	ino = css->cgroup->dentry->d_inode->i_ino;
	css_put(css);

	if (ino != hwpoison_filter_memcg)
		return -EINVAL;

	return 0;
}
#else
static int hwpoison_filter_task(struct page *p) { return 0; }
#endif

int hwpoison_filter(struct page *p)
{
	if (hwpoison_filter_dev(p))
		return -EINVAL;

	if (hwpoison_filter_flags(p))
		return -EINVAL;

	if (hwpoison_filter_task(p))
		return -EINVAL;

	return 0;
}
EXPORT_SYMBOL_GPL(hwpoison_filter);

/*
 * Send all the processes who have the page mapped an ``action optional''
 * signal.
 */
static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
			unsigned long pfn)
{
	struct siginfo si;
	int ret;

	printk(KERN_ERR