mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 10:50:53 +07:00
facb6011f3
This is a simpler, gentler variant of memory_failure() for soft page offlining controlled from user space. It doesn't kill anything, just tries to invalidate and if that doesn't work migrate the page away. This is useful for predictive failure analysis, where a page has a high rate of corrected errors, but hasn't gone bad yet. Instead it can be offlined early and avoided. The offlining is controlled from sysfs, including a new generic entry point for hard page offlining for symmetry too. We use the page isolate facility to prevent re-allocation race. Normally this is only used by memory hotplug. To avoid races with memory allocation I am using lock_system_sleep(). This avoids the situation where memory hotplug is about to isolate a page range and then hwpoison undoes that work. This is a big hammer currently, but the simplest solution currently. When the page is not free or LRU we try to free pages from slab and other caches. The slab freeing is currently quite dumb and does not try to focus on the specific slab cache which might own the page. This could be potentially improved later. Thanks to Fengguang Wu and Haicheng Li for some fixes. [Added fix from Andrew Morton to adapt to new migrate_pages prototype] Signed-off-by: Andi Kleen <ak@linux.intel.com>
136 lines
3.2 KiB
C
136 lines
3.2 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, 0);
|
|
/*
|
|
* 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-enable", 0600,
|
|
hwpoison_dir, &hwpoison_filter_enable);
|
|
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;
|
|
|
|
dentry = debugfs_create_u64("corrupt-filter-flags-mask", 0600,
|
|
hwpoison_dir, &hwpoison_filter_flags_mask);
|
|
if (!dentry)
|
|
goto fail;
|
|
|
|
dentry = debugfs_create_u64("corrupt-filter-flags-value", 0600,
|
|
hwpoison_dir, &hwpoison_filter_flags_value);
|
|
if (!dentry)
|
|
goto fail;
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
|
|
dentry = debugfs_create_u64("corrupt-filter-memcg", 0600,
|
|
hwpoison_dir, &hwpoison_filter_memcg);
|
|
if (!dentry)
|
|
goto fail;
|
|
#endif
|
|
|
|
return 0;
|
|
fail:
|
|
pfn_inject_exit();
|
|
return -ENOMEM;
|
|
}
|
|
|
|
module_init(pfn_inject_init);
|
|
module_exit(pfn_inject_exit);
|
|
MODULE_LICENSE("GPL");
|