mirrors
/
linux-stable
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
1
0
Fork 0
Code Issues Releases Wiki Activity

mm/memory-failure: disable unpoison once hw error happens 

Currently unpoison_memory(unsigned long pfn) is designed for soft
poison(hwpoison-inject) only.  Since 17fae1294a, 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: 847ce401df ("HWPOISON: Add unpoisoning support")
Fixes: 17fae1294a ("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>
This commit is contained in:
zhenwei pi 2022-06-15 17:32:09 +08:00 committed by akpm
parent 68d32527d3
commit 67f22ba775
6 changed files with 18 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
Documentation/vm/hwpoison.rst
View File

@ -120,7 +120,8 @@ Testing
unpoison-pfn
Software-unpoison page at PFN echoed into this file. This way
a page can be reused again. This only works for Linux
injected failures, not for real memory failures.
injected failures, not for real memory failures. Once any hardware
memory failure happens, this feature is disabled.
Note these injection interfaces are not stable and might change between
kernel versions

2
drivers/base/memory.c
View File

@ -558,7 +558,7 @@ static ssize_t hard_offline_page_store(struct device *dev,
if (kstrtoull(buf, 0, &pfn) < 0)
return -EINVAL;
pfn >>= PAGE_SHIFT;
ret = memory_failure(pfn, 0);
ret = memory_failure(pfn, MF_SW_SIMULATED);
if (ret == -EOPNOTSUPP)
ret = 0;
return ret ? ret : count;

1
include/linux/mm.h
View File

@ -3232,6 +3232,7 @@ enum mf_flags {
MF_MUST_KILL = 1 << 2,
MF_SOFT_OFFLINE = 1 << 3,
MF_UNPOISON = 1 << 4,
MF_SW_SIMULATED = 1 << 5,
};
extern int memory_failure(unsigned long pfn, int flags);
extern void memory_failure_queue(unsigned long pfn, int flags);

2
mm/hwpoison-inject.c
View File

@ -48,7 +48,7 @@ static int hwpoison_inject(void *data, u64 val)
inject:
pr_info("Injecting memory failure at pfn %#lx\n", pfn);
err = memory_failure(pfn, 0);
err = memory_failure(pfn, MF_SW_SIMULATED);
return (err == -EOPNOTSUPP) ? 0 : err;
}

2
mm/madvise.c
View File

@ -1112,7 +1112,7 @@ static int madvise_inject_error(int behavior,
} else {
pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
pfn, start);
ret = memory_failure(pfn, MF_COUNT_INCREASED);
ret = memory_failure(pfn, MF_COUNT_INCREASED | MF_SW_SIMULATED);
if (ret == -EOPNOTSUPP)
ret = 0;
}

12
mm/memory-failure.c
View File

@ -69,6 +69,8 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool hw_memory_failure __read_mostly = false;
static bool __page_handle_poison(struct page *page)
{
int ret;
@ -1768,6 +1770,9 @@ int memory_failure(unsigned long pfn, int flags)
mutex_lock(&mf_mutex);
if (!(flags & MF_SW_SIMULATED))
hw_memory_failure = true;
p = pfn_to_online_page(pfn);
if (!p) {
res = arch_memory_failure(pfn, flags);
@ -2103,6 +2108,13 @@ int unpoison_memory(unsigned long pfn)
mutex_lock(&mf_mutex);
if (hw_memory_failure) {
unpoison_pr_info("Unpoison: Disabled after HW memory failure %#lx\n",
pfn, &unpoison_rs);
ret = -EOPNOTSUPP;
goto unlock_mutex;
}
if (!PageHWPoison(p)) {
unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n",
pfn, &unpoison_rs);