mirror of
https://github.com/rd-stuffs/msm-4.14.git
synced 2025-02-20 11:45:48 +08:00
31d3d3484f
__memory_failure()'s workflow is set PG_hwpoison //... unset PG_hwpoison if didn't pass hwpoison filter That could kill unrelated process if it happens to page fault on the page with the (temporary) PG_hwpoison. The race should be big enough to appear in stress tests. Fix it by grabbing the page and checking filter at inject time. This also avoids the very noisy "Injecting memory failure..." messages. - we don't touch madvise() based injection, because the filters are generally not necessary for it. - if we want to apply the filters to h/w aided injection, we'd better to rearrange the logic in __memory_failure() instead of this patch. AK: fix documentation, use drain all, cleanups CC: Haicheng Li <haicheng.li@intel.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andi Kleen <ak@linux.intel.com>
114 lines
2.6 KiB
C
114 lines
2.6 KiB
C
/* Inject a hwpoison memory failure on a arbitary 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 "internal.h"
|
|
|
|
static struct dentry *hwpoison_dir;
|
|
|
|
static int hwpoison_inject(void *data, u64 val)
|
|
{
|
|
unsigned long pfn = val;
|
|
struct page *p;
|
|
int err;
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
if (!pfn_valid(pfn))
|
|
return -ENXIO;
|
|
|
|
p = pfn_to_page(pfn);
|
|
/*
|
|
* This implies unable to support free buddy pages.
|
|
*/
|
|
if (!get_page_unless_zero(p))
|
|
return 0;
|
|
|
|
if (!PageLRU(p))
|
|
shake_page(p);
|
|
/*
|
|
* This implies unable to support non-LRU pages.
|
|
*/
|
|
if (!PageLRU(p))
|
|
return 0;
|
|
|
|
/*
|
|
* 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).
|
|
* We temporarily take page lock for try_get_mem_cgroup_from_page().
|
|
* __memory_failure() will redo the check reliably inside page lock.
|
|
*/
|
|
lock_page(p);
|
|
err = hwpoison_filter(p);
|
|
unlock_page(p);
|
|
if (err)
|
|
return 0;
|
|
|
|
printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn);
|
|
return __memory_failure(pfn, 18, MF_COUNT_INCREASED);
|
|
}
|
|
|
|
static int hwpoison_unpoison(void *data, u64 val)
|
|
{
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
return unpoison_memory(val);
|
|
}
|
|
|
|
DEFINE_SIMPLE_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
|
|
DEFINE_SIMPLE_ATTRIBUTE(unpoison_fops, NULL, hwpoison_unpoison, "%lli\n");
|
|
|
|
static void pfn_inject_exit(void)
|
|
{
|
|
if (hwpoison_dir)
|
|
debugfs_remove_recursive(hwpoison_dir);
|
|
}
|
|
|
|
static int pfn_inject_init(void)
|
|
{
|
|
struct dentry *dentry;
|
|
|
|
hwpoison_dir = debugfs_create_dir("hwpoison", NULL);
|
|
if (hwpoison_dir == NULL)
|
|
return -ENOMEM;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
dentry = debugfs_create_file("corrupt-pfn", 0600, hwpoison_dir,
|
|
NULL, &hwpoison_fops);
|
|
if (!dentry)
|
|
goto fail;
|
|
|
|
dentry = debugfs_create_file("unpoison-pfn", 0600, hwpoison_dir,
|
|
NULL, &unpoison_fops);
|
|
if (!dentry)
|
|
goto fail;
|
|
|
|
dentry = debugfs_create_u32("corrupt-filter-dev-major", 0600,
|
|
hwpoison_dir, &hwpoison_filter_dev_major);
|
|
if (!dentry)
|
|
goto fail;
|
|
|
|
dentry = debugfs_create_u32("corrupt-filter-dev-minor", 0600,
|
|
hwpoison_dir, &hwpoison_filter_dev_minor);
|
|
if (!dentry)
|
|
goto fail;
|
|
|
|
return 0;
|
|
fail:
|
|
pfn_inject_exit();
|
|
return -ENOMEM;
|
|
}
|
|
|
|
module_init(pfn_inject_init);
|
|
module_exit(pfn_inject_exit);
|
|
MODULE_LICENSE("GPL");
|