linux-kernel - [PATCH v2 1/3] mm/swapfile: unuse_pte can map random data if swap read fails

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]

Message-ID: <20220421125348.62483-2-linmiaohe@huawei.com>
Date:   Thu, 21 Apr 2022 20:53:46 +0800
From:   Miaohe Lin <linmiaohe@...wei.com>
To:     <akpm@...ux-foundation.org>
CC:     <willy@...radead.org>, <vbabka@...e.cz>, <dhowells@...hat.com>,
        <neilb@...e.de>, <david@...hat.com>, <apopple@...dia.com>,
        <surenb@...gle.com>, <minchan@...nel.org>, <peterx@...hat.com>,
        <sfr@...b.auug.org.au>, <naoya.horiguchi@....com>,
        <linux-mm@...ck.org>, <linux-kernel@...r.kernel.org>,
        <linmiaohe@...wei.com>
Subject: [PATCH v2 1/3] mm/swapfile: unuse_pte can map random data if swap read fails

There is a bug in unuse_pte(): when swap page happens to be unreadable,
page filled with random data is mapped into user address space.  In case
of error, a special swap entry indicating swap read fails is set to the
page table.  So the swapcache page can be freed and the user won't end up
with a permanently mounted swap because a sector is bad.  And if the page
is accessed later, the user process will be killed so that corrupted data
is never consumed.  On the other hand, if the page is never accessed, the
user won't even notice it.

Signed-off-by: Miaohe Lin <linmiaohe@...wei.com>
Acked-by: David Hildenbrand <david@...hat.com>
---
 include/linux/swap.h    |  7 ++++++-
 include/linux/swapops.h | 10 ++++++++++
 mm/memory.c             |  5 ++++-
 mm/swapfile.c           | 11 +++++++++++
 4 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5553189d0215..b82c196d8867 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -55,6 +55,10 @@ static inline int current_is_kswapd(void)
  * actions on faults.
  */
 
+#define SWP_SWAPIN_ERROR_NUM 1
+#define SWP_SWAPIN_ERROR     (MAX_SWAPFILES + SWP_HWPOISON_NUM + \
+			     SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \
+			     SWP_PTE_MARKER_NUM)
 /*
  * PTE markers are used to persist information onto PTEs that are mapped with
  * file-backed memories.  As its name "PTE" hints, it should only be applied to
@@ -120,7 +124,8 @@ static inline int current_is_kswapd(void)
 
 #define MAX_SWAPFILES \
 	((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \
-	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM)
+	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \
+	SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM)
 
 /*
  * Magic header for a swap area. The first part of the union is
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index a291f210e7f8..9d989ed049a6 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -108,6 +108,16 @@ static inline void *swp_to_radix_entry(swp_entry_t entry)
 	return xa_mk_value(entry.val);
 }
 
+static inline swp_entry_t make_swapin_error_entry(struct page *page)
+{
+	return swp_entry(SWP_SWAPIN_ERROR, page_to_pfn(page));
+}
+
+static inline int is_swapin_error_entry(swp_entry_t entry)
+{
+	return swp_type(entry) == SWP_SWAPIN_ERROR;
+}
+
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
 static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
 {
diff --git a/mm/memory.c b/mm/memory.c
index f4161fb07ffa..626f63858e0c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1488,7 +1488,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			/* Only drop the uffd-wp marker if explicitly requested */
 			if (!zap_drop_file_uffd_wp(details))
 				continue;
-		} else if (is_hwpoison_entry(entry)) {
+		} else if (is_hwpoison_entry(entry) ||
+			   is_swapin_error_entry(entry)) {
 			if (!should_zap_cows(details))
 				continue;
 		} else {
@@ -3728,6 +3729,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
+		} else if (is_swapin_error_entry(entry)) {
+			ret = VM_FAULT_SIGBUS;
 		} else if (is_pte_marker_entry(entry)) {
 			ret = handle_pte_marker(vmf);
 		} else {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 9398e915b36b..95b63f69f388 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1797,6 +1797,17 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		goto out;
 	}
 
+	if (unlikely(!PageUptodate(page))) {
+		pte_t pteval;
+
+		dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
+		pteval = swp_entry_to_pte(make_swapin_error_entry(page));
+		set_pte_at(vma->vm_mm, addr, pte, pteval);
+		swap_free(entry);
+		ret = 0;
+		goto out;
+	}
+
 	/* See do_swap_page() */
 	BUG_ON(!PageAnon(page) && PageMappedToDisk(page));
 	BUG_ON(PageAnon(page) && PageAnonExclusive(page));
-- 
2.23.0