From: "H. Peter Anvin" <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org>
To: Filipe Brandenburger
<filbranden-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org>
Cc: Richard Larocque
<rlarocque-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>,
Michael Davidson <md-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
Greg Thelen <gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
X86 ML <x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Linux API <linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
"linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
<linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: Re: [PATCH] x86/vdso: Add prctl to set per-process VDSO load
Date: Wed, 17 Sep 2014 01:46:02 -0700 [thread overview]
Message-ID: <54194A4A.7030104@zytor.com> (raw)
In-Reply-To: <CADU+-uCguxhkw259MefABuzOxvyK_F6bhwza0YhveCCJxEV8wQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On 09/16/2014 11:21 PM, Filipe Brandenburger wrote:
> Hi Andy,
>
> On Tue, Sep 16, 2014 at 10:00 PM, Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org> wrote:
>> I think that the patch should instead tweak the vvar mapping to tell
>> the vdso not to use rdtsc. It should be based on this:
>
> I've been working on this approach which extends the vvar from 2 to 3
> pages. The third page would initially be mapped to a zero page but
> then through a prctl a task could replace it with a real page that
> could then be inherited through fork and exec.
>
> That would make it possible to have per-task vvar contents.
>
> We could use some of those values as flags to indicate whether vdso
> routines may use RDTSC or not.
>
> In the future, we're planning to also use that to store clock offsets
> so that we can ensure CLOCK_MONOTONIC works after CRIU migration
> without having to turn off the VDSO or have to always fallback to full
> syscalls on every case.
>
> Do you think that would be a reasonable way to accomplish that?
>
Why would we need/want per process vvar contents? It seems better to
have the code swapped out.
-hpa
WARNING: multiple messages have this Message-ID (diff)
From: "H. Peter Anvin" <hpa@zytor.com>
To: Filipe Brandenburger <filbranden@google.com>,
Andy Lutomirski <luto@amacapital.net>
Cc: Richard Larocque <rlarocque@google.com>,
Ingo Molnar <mingo@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Michael Davidson <md@google.com>,
Greg Thelen <gthelen@google.com>, X86 ML <x86@kernel.org>,
Linux API <linux-api@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] x86/vdso: Add prctl to set per-process VDSO load
Date: Wed, 17 Sep 2014 01:46:02 -0700 [thread overview]
Message-ID: <54194A4A.7030104@zytor.com> (raw)
In-Reply-To: <CADU+-uCguxhkw259MefABuzOxvyK_F6bhwza0YhveCCJxEV8wQ@mail.gmail.com>
On 09/16/2014 11:21 PM, Filipe Brandenburger wrote:
> Hi Andy,
>
> On Tue, Sep 16, 2014 at 10:00 PM, Andy Lutomirski <luto@amacapital.net> wrote:
>> I think that the patch should instead tweak the vvar mapping to tell
>> the vdso not to use rdtsc. It should be based on this:
>
> I've been working on this approach which extends the vvar from 2 to 3
> pages. The third page would initially be mapped to a zero page but
> then through a prctl a task could replace it with a real page that
> could then be inherited through fork and exec.
>
> That would make it possible to have per-task vvar contents.
>
> We could use some of those values as flags to indicate whether vdso
> routines may use RDTSC or not.
>
> In the future, we're planning to also use that to store clock offsets
> so that we can ensure CLOCK_MONOTONIC works after CRIU migration
> without having to turn off the VDSO or have to always fallback to full
> syscalls on every case.
>
> Do you think that would be a reasonable way to accomplish that?
>
Why would we need/want per process vvar contents? It seems better to
have the code swapped out.
-hpa
next prev parent reply other threads:[~2014-09-17 8:46 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-17 0:05 [PATCH] x86/vdso: Add prctl to set per-process VDSO load Richard Larocque
2014-09-17 0:13 ` Andi Kleen
[not found] ` <8738brhzoc.fsf-KWJ+5VKanrL29G5dvP0v1laTQe2KTcn/@public.gmane.org>
2014-09-17 0:21 ` Richard Larocque
2014-09-17 0:21 ` Richard Larocque
[not found] ` <1410912351-31273-1-git-send-email-rlarocque-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2014-09-17 0:27 ` Andy Lutomirski
2014-09-17 0:27 ` Andy Lutomirski
[not found] ` <CALCETrXtYV5xKkTxothuqNb7ra80Be7ZXJ-hDnC6p-bfEPZ=Lw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-17 1:18 ` Richard Larocque
2014-09-17 1:18 ` Richard Larocque
[not found] ` <CABgu+=NC1ZMQkV0J2c9-MD1+TAmTjDm4ACZASPnfX2Fwiu5rMQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-17 5:00 ` Andy Lutomirski
2014-09-17 5:00 ` Andy Lutomirski
[not found] ` <CALCETrWj8Pj8d8YjybvOKG-=xmy-XGFo9cGQ9qn0V4t9Oj+dOw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-17 5:34 ` Andy Lutomirski
2014-09-17 5:34 ` Andy Lutomirski
2014-09-17 6:21 ` Filipe Brandenburger
2014-09-17 6:21 ` Filipe Brandenburger
[not found] ` <CADU+-uCguxhkw259MefABuzOxvyK_F6bhwza0YhveCCJxEV8wQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-17 8:46 ` H. Peter Anvin [this message]
2014-09-17 8:46 ` H. Peter Anvin
2014-09-17 13:48 ` Filipe Brandenburger
2014-09-17 14:28 ` Andy Lutomirski
2014-09-19 19:27 ` Andy Lutomirski
2014-09-19 21:26 ` Richard Larocque
[not found] ` <CALCETrXpB4qOS+JUBqJnTY8JUfQ=A6DaebU6e=32sSv=0c0QCg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-19 22:02 ` Filipe Brandenburger
2014-09-19 22:02 ` Filipe Brandenburger
2014-09-19 22:09 ` Andy Lutomirski
[not found] ` <CALCETrXOeD=zBPvYV+-j0Ok6MXNZwdjRaz73rjuLGShx+o6Y0w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-19 22:19 ` Filipe Brandenburger
2014-09-19 22:19 ` Filipe Brandenburger
[not found] ` <CADU+-uBmQdKSX==5NrYfSEWLg-X4cvJYXj=N8UdMdN_rHnWk4w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-19 22:31 ` Andy Lutomirski
2014-09-19 22:31 ` Andy Lutomirski
[not found] ` <CALCETrV7thL-0mST4O6YZgDNm1LyLqB=_bQ3vwwrAPYZCB=W+A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-20 3:10 ` Filipe Brandenburger
2014-09-20 3:10 ` Filipe Brandenburger
[not found] ` <CADU+-uBoMrF=vbOM4TW7YzD5cdHSn8BJdfs5nnPM6uS9-6n_Ag-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-20 3:27 ` Andy Lutomirski
2014-09-20 3:27 ` Andy Lutomirski
[not found] ` <CALCETrUgtveB-ddeL2t0cK18r_VeP5T7LrWCzszfFo+8GcdmEg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-20 3:46 ` Filipe Brandenburger
2014-09-20 3:46 ` Filipe Brandenburger
[not found] ` <CADU+-uAw8wLbY6E0msuwZFgW9hDXz8a6oeDJBTSURUfS3aO1gw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-09-20 5:30 ` Andy Lutomirski
2014-09-20 5:30 ` Andy Lutomirski
2014-09-17 11:36 ` Kevin Easton
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=54194A4A.7030104@zytor.com \
--to=hpa-ymnouzjc4hwavxtiumwx3w@public.gmane.org \
--cc=filbranden-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org \
--cc=md-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=rlarocque-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org \
--cc=x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.