v2 -> v3:
- David pointed out that virt_to_kpte() is broken(no pmd_large() test
on a PMD), so drop this API in this patch, walk kmap instead.
v1 -> v2:
- this change gets protected by mf_mutex
- use -EOPNOTSUPP instead of -EPERM
v1:
- check KPTE to avoid to unpoison hardware corrupted page
zhenwei pi (1):
mm/memory-failure: don't allow to unpoison hw corrupted page
mm/memory-failure.c | 59 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 59 insertions(+)
--
2.20.1
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
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 <[email protected]>
Cc: David Hildenbrand <[email protected]>
Signed-off-by: zhenwei pi <[email protected]>
---
mm/memory-failure.c | 59 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 59 insertions(+)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b85661cbdc4a..3124f428302c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -2068,6 +2068,58 @@ static int __init memory_failure_init(void)
}
core_initcall(memory_failure_init);
+/*
+ * Unpoisoning a hardware corrupted page with *NOT PRESENT* KPTE leads panic.
+ * Test a page is valid in the kernel mapping.
+ */
+static bool kmap_valid(struct page *page)
+{
+ unsigned long addr = (unsigned long)page_to_virt(page);
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = pgd_offset_k(addr);
+ if (pgd_none(*pgd))
+ return false;
+ if (pgd_leaf(*pgd))
+ return true;
+ if (pgd_bad(*pgd))
+ return false;
+
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d))
+ return false;
+ if (p4d_leaf(*p4d))
+ return true;
+ if (p4d_bad(*p4d))
+ return false;
+
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ return false;
+ if (pud_leaf(*pud))
+ return true;
+ if (pud_bad(*pud))
+ return false;
+
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ return false;
+ if (pmd_leaf(*pmd))
+ return true;
+ if (pmd_bad(*pmd))
+ return false;
+
+ pte = pte_offset_map(pmd, addr);
+ if (pte_none(*pte) || !pte_present(*pte))
+ return false;
+
+ return true;
+}
+
#define unpoison_pr_info(fmt, pfn, rs) \
({ \
if (__ratelimit(rs)) \
@@ -2109,6 +2161,13 @@ int unpoison_memory(unsigned long pfn)
goto unlock_mutex;
}
+ if (!kmap_valid(page)) {
+ unpoison_pr_info("Unpoison: Page was hardware poisoned %#lx\n",
+ pfn, &unpoison_rs);
+ ret = -EOPNOTSUPP;
+ goto unlock_mutex;
+ }
+
if (page_count(page) > 1) {
unpoison_pr_info("Unpoison: Someone grabs the hwpoison page %#lx\n",
pfn, &unpoison_rs);
--
2.20.1