linux-stable/mm/hwpoison-inject.c

115 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 folio *folio;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!pfn_valid(pfn))
return -ENXIO;
p = pfn_to_page(pfn);
folio = page_folio(p);
if (!hwpoison_filter_enable)
goto inject;
shake_folio(folio);
/*
* This implies unable to support non-LRU pages except free page.
*/
if (!folio_test_lru(folio) && !folio_test_hugetlb(folio) &&
!is_free_buddy_page(p))
return 0;
/*
* do a racy check 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(&folio->page);
if (err)
return 0;
inject:
pr_info("Injecting memory failure at pfn %#lx\n", pfn);
mm/memory-failure: disable unpoison once hw error happens Currently unpoison_memory(unsigned long pfn) is designed for soft poison(hwpoison-inject) only. Since 17fae1294ad9d, the KPTE gets cleared on a x86 platform once hardware memory corrupts. Unpoisoning a hardware corrupted page puts page back buddy only, the kernel has a chance to access the page with *NOT PRESENT* KPTE. This leads BUG during accessing on the corrupted KPTE. Suggested by David&Naoya, disable unpoison mechanism when a real HW error happens to avoid BUG like this: Unpoison: Software-unpoisoned page 0x61234 BUG: unable to handle page fault for address: ffff888061234000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 2c01067 P4D 2c01067 PUD 107267063 PMD 10382b063 PTE 800fffff9edcb062 Oops: 0002 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 26551 Comm: stress Kdump: loaded Tainted: G M OE 5.18.0.bm.1-amd64 #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ... RIP: 0010:clear_page_erms+0x7/0x10 Code: ... RSP: 0000:ffffc90001107bc8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000901 RCX: 0000000000001000 RDX: ffffea0001848d00 RSI: ffffea0001848d40 RDI: ffff888061234000 RBP: ffffea0001848d00 R08: 0000000000000901 R09: 0000000000001276 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: 0000000000000000 R14: 0000000000140dca R15: 0000000000000001 FS: 00007fd8b2333740(0000) GS:ffff88813fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff888061234000 CR3: 00000001023d2005 CR4: 0000000000770ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> prep_new_page+0x151/0x170 get_page_from_freelist+0xca0/0xe20 ? sysvec_apic_timer_interrupt+0xab/0xc0 ? asm_sysvec_apic_timer_interrupt+0x1b/0x20 __alloc_pages+0x17e/0x340 __folio_alloc+0x17/0x40 vma_alloc_folio+0x84/0x280 __handle_mm_fault+0x8d4/0xeb0 handle_mm_fault+0xd5/0x2a0 do_user_addr_fault+0x1d0/0x680 ? kvm_read_and_reset_apf_flags+0x3b/0x50 exc_page_fault+0x78/0x170 asm_exc_page_fault+0x27/0x30 Link: https://lkml.kernel.org/r/20220615093209.259374-2-pizhenwei@bytedance.com Fixes: 847ce401df392 ("HWPOISON: Add unpoisoning support") Fixes: 17fae1294ad9d ("x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned") Signed-off-by: zhenwei pi <pizhenwei@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Reviewed-by: Miaohe Lin <linmiaohe@huawei.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: <stable@vger.kernel.org> [5.8+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-15 09:32:09 +00:00
err = memory_failure(pfn, MF_SW_SIMULATED);
return (err == -EOPNOTSUPP) ? 0 : err;
}
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 __exit pfn_inject_exit(void)
{
hwpoison_filter_enable = 0;
debugfs_remove_recursive(hwpoison_dir);
}
static int __init 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 11:19:59 +00:00
#endif
return 0;
}
module_init(pfn_inject_init);
module_exit(pfn_inject_exit);
MODULE_DESCRIPTION("HWPoison pages injector");
MODULE_LICENSE("GPL");