From: "H. Peter Anvin" <hpa@zytor.com>
To: Ren Qiaowei <qiaowei.ren@intel.com>, Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
x86@kernel.org, linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: Re: [PATCH v3 0/4] Intel MPX support
Date: Tue, 28 Jan 2014 10:26:37 -0800 [thread overview]
Message-ID: <52E7F65D.4040503@zytor.com> (raw)
In-Reply-To: <52E755BB.9000201@intel.com>
On 01/27/2014 11:01 PM, Ren Qiaowei wrote:
>
> Yes. Though all non-MPX threads are slowed down, the whole process
> benefit from MPX.
>
> Anyway, HPA suggest these syscalls, which use MMU notifier, should be
> not needed, we can do what they do in userspace runtime. What do you
> think about it? I guess that I should remove the third patch which adds
> new prctl() syscalls in next version of this patchset.
>
The syscalls is one thing, managing the bounds map in kernel space is
another.
We could manage the bounds map entirely in user space in a signal
handler, but that has both ABI issues (#BR currently turns into SIGSEGV
which is commonly hooked by applications; we could switch to a different
signal but there aren't many unclaimed ones) and performance issues.
I would think it would be extremely unusual for an application to have
some MPX and some non-MPX threads, since they would share the same
address space and the non-MPX threads would mess up the bounds.
-hpa
next prev parent reply other threads:[~2014-01-28 18:27 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-26 9:08 [PATCH v3 0/4] Intel MPX support Qiaowei Ren
2014-01-26 8:19 ` Ingo Molnar
2014-01-26 8:20 ` Ren Qiaowei
2014-01-28 6:42 ` Ingo Molnar
2014-01-28 7:01 ` Ren Qiaowei
2014-01-28 18:26 ` H. Peter Anvin [this message]
2014-01-26 9:08 ` [PATCH v3 1/4] x86, mpx: add documentation on Intel MPX Qiaowei Ren
2014-01-26 3:06 ` Randy Dunlap
2014-01-26 3:15 ` Ren Qiaowei
2014-01-27 20:27 ` Andy Lutomirski
2014-01-28 3:40 ` Ren Qiaowei
2014-01-26 9:08 ` [PATCH v3 2/4] x86, mpx: hook #BR exception handler to allocate bound tables Qiaowei Ren
2014-01-27 20:36 ` Andy Lutomirski
2014-01-28 3:35 ` Ren Qiaowei
2014-01-28 5:21 ` Andy Lutomirski
2014-01-28 5:39 ` Ren Qiaowei
2014-01-28 6:42 ` Andy Lutomirski
2014-01-28 6:46 ` Ren Qiaowei
2014-01-26 9:08 ` [PATCH v3 3/4] x86, mpx: add prctl commands PR_MPX_INIT, PR_MPX_RELEASE Qiaowei Ren
2014-01-26 8:22 ` Ingo Molnar
2014-01-26 8:23 ` Ren Qiaowei
2014-01-26 8:39 ` Ingo Molnar
2014-01-26 11:37 ` Ren, Qiaowei
2014-01-27 1:50 ` H. Peter Anvin
2014-01-27 1:55 ` Ren Qiaowei
2014-01-27 2:10 ` H. Peter Anvin
2014-01-27 2:16 ` Ren Qiaowei
2014-01-27 21:54 ` Andy Lutomirski
2014-01-27 22:01 ` H. Peter Anvin
2014-01-26 9:08 ` Ingo Molnar
2014-01-26 12:49 ` Ren, Qiaowei
2014-01-26 15:14 ` Ingo Molnar
2014-01-27 2:01 ` Ren Qiaowei
2014-01-27 20:59 ` Andy Lutomirski
2014-01-26 9:08 ` [PATCH v3 4/4] x86, mpx: extend siginfo structure to include bound violation information Qiaowei Ren
2014-01-26 4:22 ` David Rientjes
2014-01-26 4:39 ` Ren Qiaowei
2014-01-26 21:38 ` David Rientjes
2014-01-27 1:34 ` Ren Qiaowei
2014-01-27 1:53 ` H. Peter Anvin
2014-01-27 1:56 ` Ren Qiaowei
2014-01-27 21:58 ` Andy Lutomirski
2014-01-28 2:43 ` Ren Qiaowei
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=52E7F65D.4040503@zytor.com \
--to=hpa@zytor.com \
--cc=a.p.zijlstra@chello.nl \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=mingo@redhat.com \
--cc=qiaowei.ren@intel.com \
--cc=tglx@linutronix.de \
--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 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.