linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Andrea Arcangeli <aarcange@redhat.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	"\\\"Kirill A. Shutemov\\\"" <kirill@shutemov.name>
Cc: linux-mm@kvack.org
Subject: [PATCH 1/1] mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED
Date: Tue, 23 Feb 2016 19:49:10 +0100	[thread overview]
Message-ID: <1456253350-3959-2-git-send-email-aarcange@redhat.com> (raw)
In-Reply-To: <1456253350-3959-1-git-send-email-aarcange@redhat.com>

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.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 mm/memory.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 635451a..50347ed 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3404,8 +3404,19 @@ 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) || pmd_devmap(*pmd)))
+	/*
+	 * If an huge pmd materialized from under us just retry later.
+	 * Use pmd_trans_unstable() instead of pmd_trans_huge() to
+	 * ensure the pmd didn't become pmd_trans_huge from under us
+	 * and then back to pmd_none, as result of MADV_DONTNEED
+	 * running immediately after a huge pmd fault of 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() is provided for.
+	 */
+	if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd)))
 		return 0;
 	/*
 	 * A regular pmd is established and it can't morph into a huge pmd

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2016-02-23 18:49 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-23 15:49 THP race? Kirill A. Shutemov
2016-02-23 18:06 ` Andrea Arcangeli
2016-02-23 18:18   ` [PATCH 1/1] mm: thp: fix SMP race condition between THP page fault kbuild test robot
2016-02-23 18:21   ` kbuild test robot
2016-02-23 18:27   ` kbuild test robot
2016-02-23 18:38   ` THP race? Kirill A. Shutemov
2016-02-23 19:28     ` Andrea Arcangeli
2016-02-25 18:45       ` Dan Williams
2016-02-26 10:37         ` Kirill A. Shutemov
2016-02-26 14:46           ` Dan Williams
2016-02-23 18:49 ` [PATCH 0/1] " Andrea Arcangeli
2016-02-23 18:49   ` Andrea Arcangeli [this message]
2016-02-23 21:18     ` [PATCH 1/1] mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED Andrew Morton

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1456253350-3959-2-git-send-email-aarcange@redhat.com \
    --to=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=kirill@shutemov.name \
    --cc=linux-mm@kvack.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).