linux-kernel - [RFCv2 11/13] mm: Replace hwpoison entry with present PTE if page got unpoisoned

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri, 16 Apr 2021 18:41:04 +0300
From:   "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To:     Dave Hansen <dave.hansen@...ux.intel.com>,
        Andy Lutomirski <luto@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Sean Christopherson <seanjc@...gle.com>,
        Jim Mattson <jmattson@...gle.com>
Cc:     David Rientjes <rientjes@...gle.com>,
        "Edgecombe, Rick P" <rick.p.edgecombe@...el.com>,
        "Kleen, Andi" <andi.kleen@...el.com>,
        "Yamahata, Isaku" <isaku.yamahata@...el.com>,
        Erdem Aktas <erdemaktas@...gle.com>,
        Steve Rutherford <srutherford@...gle.com>,
        Peter Gonda <pgonda@...gle.com>,
        David Hildenbrand <david@...hat.com>, x86@...nel.org,
        kvm@...r.kernel.org, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [RFCv2 11/13] mm: Replace hwpoison entry with present PTE if page got unpoisoned

If the page got unpoisoned we can replace hwpoison entry with a present
PTE on page fault instead of delivering SIGBUS.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
---
 mm/memory.c | 38 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/mm/memory.c b/mm/memory.c
index b15b0c582186..56f93e8e98f9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3280,7 +3280,43 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			vmf->page = device_private_entry_to_page(entry);
 			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
 		} else if (is_hwpoison_entry(entry)) {
-			ret = VM_FAULT_HWPOISON;
+			page = hwpoison_entry_to_page(entry);
+
+			locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags);
+			if (!locked) {
+				ret = VM_FAULT_RETRY;
+				goto out;
+			}
+
+			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+						       vmf->address, &vmf->ptl);
+
+			if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
+				ret = 0;
+			} else if (PageHWPoison(page)) {
+				ret = VM_FAULT_HWPOISON;
+			} else {
+				/*
+				 * The page is unpoisoned. Replace hwpoison
+				 * entry with a present PTE.
+				 */
+
+				inc_mm_counter(vma->vm_mm, mm_counter(page));
+				pte = mk_pte(page, vma->vm_page_prot);
+
+				if (PageAnon(page)) {
+					page_add_anon_rmap(page, vma,
+							   vmf->address, false);
+				} else {
+					page_add_file_rmap(page, false);
+				}
+
+				set_pte_at(vma->vm_mm, vmf->address,
+					   vmf->pte, pte);
+			}
+
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			unlock_page(page);
 		} else {
 			print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL);
 			ret = VM_FAULT_SIGBUS;
-- 
2.26.3