mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: Andi Kleen <andi@firstfloor.org>
Cc: Andy Lutomirski <luto@amacapital.net>,
	Brian Gerst <brgerst@gmail.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	the arch/x86 maintainers <x86@kernel.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	David Woodhouse <dwmw@amazon.co.uk>, Paul Turner <pjt@google.com>,
	Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Tom Lendacky <thomas.lendacky@amd.com>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	Greg Kroah-Hartman <gregkh@linux-foundation.org>,
	Dave Hansen <dave.hansen@intel.com>,
	Jiri Kosina <jikos@kernel.org>, Andi Kleen <ak@linux.intel.com>
Subject: Re: [PATCH v1 1/8] x86/entry/clearregs: Remove partial stack frame in fast system call
Date: Thu, 11 Jan 2018 10:44:40 -0800	[thread overview]
Message-ID: <20180111184440.w3rmykkswnthvo2f@two.firstfloor.org> (raw)
In-Reply-To: <20180111014747.d5k4bpggmqxmczu5@two.firstfloor.org>

> Well it's kernel hardening to guard against possible future speculation
> attacks. Linus discussed it here for example:
> 
> https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1580667.html
> 
> For the on/off switch I can add a CONFIG to enable it, even though
> it seems somewhat silly.

I did some micro benchmarking now, sampling different real system
calls.

For the entry code (entry to call) I get on average 62 cycles 
for the old code, vs 78 cycles with clear regs and full
stack frame saving on Skylake.

So it's roughly ~20 cycles difference, if we include the restore.

I would conclude 20 cycles are not significant for a syscall,
so there's not a lot of motivation to add a switch
for less security.

-Andi

  reply	other threads:[~2018-01-11 18:44 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-10  1:03 x86/clearregs: Register sanitizing at kernel entry for speculation hygiene Andi Kleen
2018-01-10  1:03 ` [PATCH v1 1/8] x86/entry/clearregs: Remove partial stack frame in fast system call Andi Kleen
2018-01-10  2:46   ` Brian Gerst
2018-01-11  0:16     ` Andi Kleen
2018-01-11  0:54       ` Brian Gerst
2018-01-11  1:02         ` Andi Kleen
2018-01-11  0:55       ` Andy Lutomirski
2018-01-11  1:01         ` Andi Kleen
2018-01-11  1:01         ` Brian Gerst
2018-01-11  1:22           ` Andy Lutomirski
2018-01-11  1:47             ` Andi Kleen
2018-01-11 18:44               ` Andi Kleen [this message]
2018-01-11  2:09   ` Josh Poimboeuf
2018-01-12  3:22   ` Josh Poimboeuf
2018-01-10  1:03 ` [PATCH v1 2/8] x86/entry/clearregs: Add infrastructure to clear registers Andi Kleen
2018-01-11 19:58   ` Konrad Rzeszutek Wilk
2018-01-11 20:10     ` Andi Kleen
2018-01-10  1:03 ` [PATCH v1 3/8] x86/entry/clearregs: Clear registers for 64bit SYSCALL Andi Kleen
2018-01-11  3:35   ` Brian Gerst
2018-01-11 18:47     ` Andi Kleen
2018-01-12  3:45   ` Josh Poimboeuf
2018-01-10  1:03 ` [PATCH v1 4/8] x86/entry/retpoline: Clear extra registers for compat syscalls Andi Kleen
2018-01-10  1:03 ` [PATCH v1 5/8] x86/entry/clearregs: Clear registers for 64bit exceptions/interrupts Andi Kleen
2018-01-10  1:23   ` Andy Lutomirski
2018-01-10  1:03 ` [PATCH v1 6/8] x86/entry/clearregs: Add number of arguments to syscall tables Andi Kleen
2018-01-10  1:26   ` Andy Lutomirski
2018-01-10  4:37     ` Andi Kleen
2018-01-10 20:05       ` Andy Lutomirski
2018-01-10  1:03 ` [PATCH v1 7/8] x86/entry/clearregs: Add 64bit stubs to clear unused arguments regs Andi Kleen
2018-01-10  1:03 ` [PATCH v1 8/8] x86/entry/clearregs: Clear registers for 32bit kernel Andi Kleen
2018-01-10  1:24   ` Andy Lutomirski
2018-01-10  1:16 ` x86/clearregs: Register sanitizing at kernel entry for speculation hygiene Andy Lutomirski
2018-01-10  1:34   ` Andi Kleen
2018-01-10  1:39     ` Andy Lutomirski

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=20180111184440.w3rmykkswnthvo2f@two.firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=ak@linux.intel.com \
    --cc=brgerst@gmail.com \
    --cc=dave.hansen@intel.com \
    --cc=dwmw@amazon.co.uk \
    --cc=gregkh@linux-foundation.org \
    --cc=jikos@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=luto@kernel.org \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=tim.c.chen@linux.intel.com \
    --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
Powered by JetHome