From: Andi Kleen <andi@firstfloor.org>
To: luto@mit.edu, x86@kernel.org, linux-kernel@vger.kernel.org,
torvalds@linux-foundation.org
Cc: lueckintel@yahoo.com, kimwooyoung@gmail.com
Subject: New vsyscall emulation breaks JITs
Date: Fri, 5 Aug 2011 13:09:45 -0700 [thread overview]
Message-ID: <20110805200945.GA14014@tassilo.jf.intel.com> (raw)
Andy,
We found that your new vsyscall emulation in
commit 5cec93c216db77c45f7ce970d46283bcb1933884
Author: Andy Lutomirski <luto@MIT.EDU>
Date: Sun Jun 5 13:50:24 2011 -0400
x86-64: Emulate legacy vsyscalls
breaks JITs that execute x86 code and use the legacy vsyscalls.
The problem is that the JIT translates the vsyscall page into
its code buffer and executes the "int 0xcc" there. Then
when the kernel gets the interrupt it doesn't see the vsyscall
page as the source and crashes the program.
For some reason several modern executables also seem
to still use the old vsyscall page, so this problem can be hit
quickly.
This happened with pin (http://www.pintool.org/), however
I expect it will affect all user space x86 JITs (valgrind,
dynamo, qemu-user, etc.)
What to do? Right now this broke existing setups.
-Andi
--
ak@linux.intel.com -- Speaking for myself only
next reply other threads:[~2011-08-05 20:09 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-08-05 20:09 Andi Kleen [this message]
2011-08-05 20:23 ` New vsyscall emulation breaks JITs H. Peter Anvin
2011-08-05 20:26 ` Andi Kleen
2011-08-05 20:36 ` H. Peter Anvin
2011-08-05 20:47 ` Andi Kleen
2011-08-05 20:45 ` Andrew Lutomirski
2011-08-05 20:48 ` H. Peter Anvin
2011-08-05 20:52 ` Andi Kleen
2011-08-05 21:00 ` Andrew Lutomirski
2011-08-05 21:21 ` Andi Kleen
2011-08-05 21:26 ` Andrew Lutomirski
2011-08-05 22:06 ` H. Peter Anvin
2011-08-05 22:11 ` Andrew Lutomirski
2011-08-06 0:20 ` Andrew Lutomirski
2011-08-06 0:32 ` H. Peter Anvin
2011-08-06 3:01 ` [RFC] x86-64: Allow emulated vsyscalls from user addresses Andy Lutomirski
2011-08-06 3:04 ` [RFC v2] " Andy Lutomirski
2011-08-06 6:45 ` Ingo Molnar
2011-08-07 12:19 ` Borislav Petkov
2011-08-07 12:58 ` Andrew Lutomirski
2011-08-07 15:44 ` Borislav Petkov
2011-08-07 16:14 ` Andrew Lutomirski
2011-08-11 13:16 ` Pavel Machek
2011-08-11 13:27 ` Andrew Lutomirski
2011-08-09 22:27 ` New vsyscall emulation breaks JITs Suresh Siddha
2011-08-09 13:26 ` Andrew Lutomirski
2011-08-09 15:04 ` Andi Kleen
2011-08-09 15:22 ` Andrew Lutomirski
2011-08-09 16:47 ` [RFC] x86-64: Add vsyscall=emulate|native|none option Andy Lutomirski
2011-08-09 19:54 ` Linus Torvalds
2011-08-09 16:57 ` New vsyscall emulation breaks JITs H. Peter Anvin
2011-08-09 17:05 ` Andrew Lutomirski
[not found] ` <1312919938.17118.YahooMailNeo@web120010.mail.ne1.yahoo.com>
2011-08-09 20:59 ` H. Peter Anvin
2011-08-09 21:04 ` Andrew Lutomirski
2011-08-09 22:36 ` Linus Torvalds
2011-08-10 0:56 ` H. Peter Anvin
[not found] ` <1312934493.45753.YahooMailNeo@web120015.mail.ne1.yahoo.com>
2011-08-10 1:49 ` H. Peter Anvin
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=20110805200945.GA14014@tassilo.jf.intel.com \
--to=andi@firstfloor.org \
--cc=kimwooyoung@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lueckintel@yahoo.com \
--cc=luto@mit.edu \
--cc=torvalds@linux-foundation.org \
--cc=x86@kernel.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