Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sun, 22 Oct 2017 15:11:57 +0200
From: Peter Zijlstra <>
To: Alexander Popov <>
	Ingo Molnar <>, Andy Lutomirski <>,, Laura Abbott <>,
	Mark Rutland <>,
	Ard Biesheuvel <>,
	Borislav Petkov <>,
	Thomas Gleixner <>,
	"H . Peter Anvin" <>,
Subject: Re: [PATCH RFC v5 0/5] Introduce the STACKLEAK feature and a test
 for it

On Sun, Oct 22, 2017 at 03:22:48AM +0300, Alexander Popov wrote:
> These numbers were obtained for the 4th version of the patch series.
> Size of vmlinux (x86_64_defconfig):
>  file size:
>   - STACKLEAK disabled: 35014784 bytes
>   - STACKLEAK enabled: 35044952 bytes (+0.086%)
>  .text section size (calculated by size utility):
>   - STACKLEAK disabled: 10752983
>   - STACKLEAK enabled: 11062221 (+2.876%)

Why no runtime costs? This should not be hard to measure.

> Further work
> =============
>  - Rewrite erase_kstack() in C (if Ingo Molnar insists).

Aside from legacy, is there any sane reason that stuff is in ASM? That
is, I too will insist it being in C unless you can provide good
arguments on why it needs be asm. All it does is memzero() right? And I
would think architectures already have fairly optimized implementations
of that around.

Powered by blists - more mailing lists

Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.