@@ -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, the feature is disabled.
Note these injection interfaces are not stable and might change between
kernel versions
@@ -7,6 +7,7 @@
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/hugetlb.h>
+#include <linux/swapops.h>
#include "internal.h"
static struct dentry *hwpoison_dir;
@@ -65,6 +66,11 @@ static int hwpoison_unpoison(void *data, u64 val)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (atomic_read(&hwpoisoned_pages) != atomic_long_read(&num_poisoned_pages)) {
+ pr_info("Unpoison is disabled after hardware memory failure happened\n");
+ return -EOPNOTSUPP;
+ }
+
ret = unpoison_memory(val);
if (!ret) {
atomic_dec(&hwpoisoned_pages);
@@ -68,6 +68,7 @@ int sysctl_memory_failure_early_kill __read_mostly = 0;
int sysctl_memory_failure_recovery __read_mostly = 1;
atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
+EXPORT_SYMBOL_GPL(num_poisoned_pages);
static bool __page_handle_poison(struct page *page)
{
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. Do not allow to unpoison hardware corrupted page in unpoison_memory() 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 Suggested by David&Naoya, disable unpoison mechanism when a real HW error happens. Fixes: 847ce401df392 ("HWPOISON: Add unpoisoning support") Fixes: 17fae1294ad9d ("x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned") Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: David Hildenbrand <david@redhat.com> Signed-off-by: zhenwei pi <pizhenwei@bytedance.com> --- Documentation/vm/hwpoison.rst | 3 ++- mm/hwpoison-inject.c | 6 ++++++ mm/memory-failure.c | 1 + 3 files changed, 9 insertions(+), 1 deletion(-)