linux/mm/hwpoison-inject.c

119 lines
2.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/* Inject a hwpoison memory failure on a arbitrary pfn */
#include <linux/module.h>
#include <linux/debugfs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/hugetlb.h>
#include "internal.h"
static struct dentry *hwpoison_dir;
static int hwpoison_inject(void *data, u64 val)
{
unsigned long pfn = val;
struct page *p;
struct page *hpage;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!pfn_valid(pfn))
return -ENXIO;
p = pfn_to_page(pfn);
hpage = compound_head(p);
/*
* This implies unable to support free buddy pages.
*/
mm/memory-failure: introduce get_hwpoison_page() for consistent refcount handling memory_failure() can run in 2 different mode (specified by MF_COUNT_INCREASED) in page refcount perspective. When MF_COUNT_INCREASED is set, memory_failure() assumes that the caller takes a refcount of the target page. And if cleared, memory_failure() takes it in it's own. In current code, however, refcounting is done differently in each caller. For example, madvise_hwpoison() uses get_user_pages_fast() and hwpoison_inject() uses get_page_unless_zero(). So this inconsistent refcounting causes refcount failure especially for thp tail pages. Typical user visible effects are like memory leak or VM_BUG_ON_PAGE(!page_count(page)) in isolate_lru_page(). To fix this refcounting issue, this patch introduces get_hwpoison_page() to handle thp tail pages in the same manner for each caller of hwpoison code. memory_failure() might fail to split thp and in such case it returns without completing page isolation. This is not good because PageHWPoison on the thp is still set and there's no easy way to unpoison such thps. So this patch try to roll back any action to the thp in "non anonymous thp" case and "thp split failed" case, expecting an MCE(SRAR) generated by later access afterward will properly free such thps. [akpm@linux-foundation.org: fix CONFIG_HWPOISON_INJECT=m] Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Tony Luck <tony.luck@intel.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:56:48 +08:00
if (!get_hwpoison_page(p))
return 0;
if (!hwpoison_filter_enable)
goto inject;
shake_page(hpage, 0);
/*
* This implies unable to support non-LRU pages.
*/
if (!PageLRU(hpage) && !PageHuge(p))
goto put_out;
/*
* do a racy check with elevated page count, to make sure PG_hwpoison
* will only be set for the targeted owner (or on a free page).
* memory_failure() will redo the check reliably inside page lock.
*/
err = hwpoison_filter(hpage);
if (err)
goto put_out;
inject:
pr_info("Injecting memory failure at pfn %#lx\n", pfn);
return memory_failure(pfn, MF_COUNT_INCREASED);
put_out:
put_hwpoison_page(p);
return 0;
}
static int hwpoison_unpoison(void *data, u64 val)
{
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return unpoison_memory(val);
}
DEFINE_DEBUGFS_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
DEFINE_DEBUGFS_ATTRIBUTE(unpoison_fops, NULL, hwpoison_unpoison, "%lli\n");
static void pfn_inject_exit(void)
{
debugfs_remove_recursive(hwpoison_dir);
}
static int pfn_inject_init(void)
{
hwpoison_dir = debugfs_create_dir("hwpoison", NULL);
/*
* Note that the below poison/unpoison interfaces do not involve
* hardware status change, hence do not require hardware support.
* They are mainly for testing hwpoison in software level.
*/
debugfs_create_file("corrupt-pfn", 0200, hwpoison_dir, NULL,
&hwpoison_fops);
debugfs_create_file("unpoison-pfn", 0200, hwpoison_dir, NULL,
&unpoison_fops);
debugfs_create_u32("corrupt-filter-enable", 0600, hwpoison_dir,
&hwpoison_filter_enable);
debugfs_create_u32("corrupt-filter-dev-major", 0600, hwpoison_dir,
&hwpoison_filter_dev_major);
debugfs_create_u32("corrupt-filter-dev-minor", 0600, hwpoison_dir,
&hwpoison_filter_dev_minor);
debugfs_create_u64("corrupt-filter-flags-mask", 0600, hwpoison_dir,
&hwpoison_filter_flags_mask);
debugfs_create_u64("corrupt-filter-flags-value", 0600, hwpoison_dir,
&hwpoison_filter_flags_value);
#ifdef CONFIG_MEMCG
debugfs_create_u64("corrupt-filter-memcg", 0600, hwpoison_dir,
&hwpoison_filter_memcg);
HWPOISON: add memory cgroup filter The hwpoison test suite need to inject hwpoison to a collection of selected task pages, and must not touch pages not owned by them and thus kill important system processes such as init. (But it's OK to mis-hwpoison free/unowned pages as well as shared clean pages. Mis-hwpoison of shared dirty pages will kill all tasks, so the test suite will target all or non of such tasks in the first place.) The memory cgroup serves this purpose well. We can put the target processes under the control of a memory cgroup, and tell the hwpoison injection code to only kill pages associated with some active memory cgroup. The prerequisite for doing hwpoison stress tests with mem_cgroup is, the mem_cgroup code tracks task pages _accurately_ (unless page is locked). Which we believe is/should be true. The benefits are simplification of hwpoison injector code. Also the mem_cgroup code will automatically be tested by hwpoison test cases. The alternative interfaces pin-pfn/unpin-pfn can also delegate the (process and page flags) filtering functions reliably to user space. However prototype implementation shows that this scheme adds more complexity than we wanted. Example test case: mkdir /cgroup/hwpoison usemem -m 100 -s 1000 & echo `jobs -p` > /cgroup/hwpoison/tasks memcg_ino=$(ls -id /cgroup/hwpoison | cut -f1 -d' ') echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg page-types -p `pidof init` --hwpoison # shall do nothing page-types -p `pidof usemem` --hwpoison # poison its pages [AK: Fix documentation] [Add fix for problem noticed by Li Zefan <lizf@cn.fujitsu.com>; dentry in the css could be NULL] CC: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> CC: Hugh Dickins <hugh.dickins@tiscali.co.uk> CC: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> CC: Balbir Singh <balbir@linux.vnet.ibm.com> CC: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> CC: Li Zefan <lizf@cn.fujitsu.com> CC: Paul Menage <menage@google.com> CC: Nick Piggin <npiggin@suse.de> CC: Andi Kleen <andi@firstfloor.org> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andi Kleen <ak@linux.intel.com>
2009-12-16 19:19:59 +08:00
#endif
return 0;
}
module_init(pfn_inject_init);
module_exit(pfn_inject_exit);
MODULE_LICENSE("GPL");