linux-kernel - [PATCH 3.12 039/100] mm: thp: fix SMP race condition between THP page fault and MADV

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 for Android: free password hash cracker in your pocket

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

Message-Id: <86a14559c6f0a91888957f8381664cfb10ce48ac.1471589700.git.jslaby@suse.cz>
Date:   Fri, 19 Aug 2016 09:10:38 +0200
From:   Jiri Slaby <jslaby@...e.cz>
To:     stable@...r.kernel.org
Cc:     linux-kernel@...r.kernel.org,
        Andrea Arcangeli <aarcange@...hat.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Vlastimil Babka <vbabka@...e.cz>, Jiri Slaby <jslaby@...e.cz>
Subject: [PATCH 3.12 039/100] mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED

From: Andrea Arcangeli <aarcange@...hat.com>

3.12-stable review patch.  If anyone has any objections, please let me know.

===============

commit ad33bb04b2a6cee6c1f99fabb15cddbf93ff0433 upstream.

pmd_trans_unstable()/pmd_none_or_trans_huge_or_clear_bad() were
introduced to locklessy (but atomically) detect when a pmd is a regular
(stable) pmd or when the pmd is unstable and can infinitely transition
from pmd_none() and pmd_trans_huge() from under us, while only holding
the mmap_sem for reading (for writing not).

While holding the mmap_sem only for reading, MADV_DONTNEED can run from
under us and so before we can assume the pmd to be a regular stable pmd
we need to compare it against pmd_none() and pmd_trans_huge() in an
atomic way, with pmd_trans_unstable().  The old pmd_trans_huge() left a
tiny window for a race.

Useful applications are unlikely to notice the difference as doing
MADV_DONTNEED concurrently with a page fault would lead to undefined
behavior.

[js] 3.12 backport: no pmd_devmap in 3.12 yet.

[akpm@...ux-foundation.org: tidy up comment grammar/layout]
Signed-off-by: Andrea Arcangeli <aarcange@...hat.com>
Reported-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Signed-off-by: Andrew Morton <akpm@...ux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Vlastimil Babka <vbabka@...e.cz>
Signed-off-by: Jiri Slaby <jslaby@...e.cz>
---
 mm/memory.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index d0d84c36cd5c..61926356c09a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3814,8 +3814,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(pmd_none(*pmd)) &&
 	    unlikely(__pte_alloc(mm, vma, pmd, address)))
 		return VM_FAULT_OOM;
-	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd)))
+	/*
+	 * If a huge pmd materialized under us just retry later.  Use
+	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
+	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
+	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
+	 * in a different thread of this mm, in turn leading to a misleading
+	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
+	 * regular pmd that we can walk with pte_offset_map() and we can do that
+	 * through an atomic read in C, which is what pmd_trans_unstable()
+	 * provides.
+	 */
+	if (unlikely(pmd_trans_unstable(pmd)))
 		return 0;
 	/*
 	 * A regular pmd is established and it can't morph into a huge pmd
-- 
2.9.3