From: Andy Lutomirski <luto@amacapital.net>
To: "H. Peter Anvin" <hpa@zytor.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>,
aarcange@redhat.com, ak@linux.intel.com,
Pavel Emelyanov <xemul@parallels.com>,
Stefani Seibold <stefani@seibold.net>,
x86@kernel.org, linux-kernel@vger.kernel.org, criu@openvz.org,
mingo@redhat.com, john.stultz@linaro.org, tglx@linutronix.de
Subject: Re: [CRIU] [PATCH] Add VDSO time function support for x86 32-bit kernel
Date: Fri, 14 Dec 2012 13:27:04 -0800 [thread overview]
Message-ID: <CALCETrUS7JDtLd0jYy7cRNoBm1VHhMw3sTPRjhsm3uDwoPQrCA@mail.gmail.com> (raw)
In-Reply-To: <50CB9553.7050808@zytor.com>
On Fri, Dec 14, 2012 at 1:08 PM, H. Peter Anvin <hpa@zytor.com> wrote:
> On 12/14/2012 12:12 PM, Cyrill Gorcunov wrote:
>>>>
>>> The real issue is that happens if the process is checkpointed while
>>> inside the vdso and now eip/rip or a stack frame points into the vdso.
>>> This is not impossible or even unlikely, especially on 32 bits it is
>>> downright likely.
>>
>> I fear if there are stacked ip which point to vdso -- we simply won't
>> be able to restore properly if vdso internal format changed significantly
>> between kernel versions. (At moment we restore vdso exactly at same position
>> it was on checkpoint stage with same content, iirc).
>>
>
> I don't think there is a way around that. It is completely unreasonable
> to say that the vdso cannot change between kernel versions, for obvious
> reasons. It's worse than "significantly"... changing even one
> instruction makes it plausible your eip/rip will point into the middle
> of an instruction.
It's not just kernel versions -- different toolchains may generate
different code. Heck, building from a different directory can
sometimes generate different output.
The ABI of each vdso function is stable, though -- a sufficiently
clever tool could (maybe) use that knowledge along with unwind data in
the vdso to fix everything up. This would be interesting, perhaps,
but certainly not easy.
I say we declare "if you want a working vdso in a weird location,
mremap it". But how does userspace figure out what size to pass to
mremap? If it's one vma, it's easy.
I don't know all that much about the linux vm. Can we create a
special vdso address_space or struct inode or something so that a
single vma can contain pages with different flags?
--Andy
next prev parent reply other threads:[~2012-12-14 21:27 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-12 20:19 [PATCH] Add VDSO time function support for x86 32-bit kernel stefani
2012-12-12 23:34 ` H. Peter Anvin
2012-12-13 5:53 ` Stefani Seibold
2012-12-13 6:10 ` H. Peter Anvin
2012-12-13 6:14 ` H. Peter Anvin
2012-12-13 6:17 ` Stefani Seibold
2012-12-13 6:47 ` H. Peter Anvin
2012-12-13 7:17 ` Stefani Seibold
2012-12-13 19:32 ` Andy Lutomirski
2012-12-14 0:09 ` H. Peter Anvin
2012-12-14 0:20 ` Andy Lutomirski
2012-12-14 0:36 ` H. Peter Anvin
2012-12-14 1:32 ` H. Peter Anvin
2012-12-14 1:42 ` Andy Lutomirski
2012-12-14 1:49 ` H. Peter Anvin
2012-12-14 2:11 ` Andy Lutomirski
2012-12-14 2:18 ` H. Peter Anvin
2012-12-14 2:20 ` Andy Lutomirski
2012-12-14 8:34 ` [CRIU] " Pavel Emelyanov
2012-12-14 18:35 ` H. Peter Anvin
2012-12-14 18:44 ` Andy Lutomirski
2012-12-14 18:47 ` H. Peter Anvin
2012-12-14 20:12 ` Cyrill Gorcunov
2012-12-14 21:08 ` H. Peter Anvin
2012-12-14 21:20 ` Cyrill Gorcunov
2012-12-14 21:21 ` H. Peter Anvin
2012-12-14 21:27 ` Andy Lutomirski [this message]
2012-12-14 22:00 ` H. Peter Anvin
2012-12-14 22:25 ` Cyrill Gorcunov
2012-12-14 22:27 ` H. Peter Anvin
2012-12-14 22:43 ` Cyrill Gorcunov
2012-12-14 22:48 ` H. Peter Anvin
2012-12-14 23:48 ` John Stultz
2012-12-14 23:55 ` H. Peter Anvin
2012-12-17 9:05 ` Pavel Emelyanov
[not found] ` <fb2e871b-3e2a-4e96-9eb9-cb2dd4f66eaa@email.android! .com>
2012-12-17 15:21 ` H. Peter Anvin
2012-12-17 18:56 ` Pavel Emelyanov
2012-12-17 18:57 ` H. Peter Anvin
2012-12-14 22:46 ` H. Peter Anvin
2012-12-14 23:09 ` Stefani Seibold
2012-12-14 23:29 ` 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=CALCETrUS7JDtLd0jYy7cRNoBm1VHhMw3sTPRjhsm3uDwoPQrCA@mail.gmail.com \
--to=luto@amacapital.net \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=criu@openvz.org \
--cc=gorcunov@openvz.org \
--cc=hpa@zytor.com \
--cc=john.stultz@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=stefani@seibold.net \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
--cc=xemul@parallels.com \
/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).