linux-kernel - Re: [PATCH] x86: static_cpu_has_safe: discard dynamic check after init

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAMzpN2hHVhjJD57wYnRLPZ_58FQGvSEn511ywGhgXzuSAZXD_A@mail.gmail.com>
Date:	Sat, 16 Jan 2016 14:58:21 -0500
From:	Brian Gerst <brgerst@...il.com>
To:	Borislav Petkov <bp@...e.de>
Cc:	"the arch/x86 maintainers" <x86@...nel.org>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Ingo Molnar <mingo@...nel.org>,
	"H. Peter Anvin" <hpa@...or.com>,
	Denys Vlasenko <dvlasenk@...hat.com>,
	Andy Lutomirski <luto@...capital.net>,
	Linus Torvalds <torvalds@...ux-foundation.org>
Subject: Re: [PATCH] x86: static_cpu_has_safe: discard dynamic check after init

On Sat, Jan 16, 2016 at 2:36 PM, Borislav Petkov <bp@...e.de> wrote:
> On Sat, Jan 16, 2016 at 02:22:04PM -0500, Brian Gerst wrote:
>> Move the code to do the dynamic check to the init text section so that it
>> is discarded after alternatives have run and a static branch has been
>> chosen.
>>
>> A new section is defined to avoid warnings with modpost due to references
>> to init text from main text, which in this case is legitimate.  All such
>> references are patched out before init mem is discarded.
>
> And we're doing this because...? Space savings? How much are we talkin'?

It saves space.  The only thing left in main text is one jump
instruction (5 bytes).

The old t_dynamic branch looked something like this (26 bytes in
.text, not discarded):
     553:       bf 7d 00 00 00          mov    $0x7d,%edi
     558:       48 89 4d c8             mov    %rcx,-0x38(%rbp)
     55c:       e8 00 00 00 00          callq  561 <__switch_to+0xf1>
                        55d: R_X86_64_PC32      __static_cpu_has_safe-0x4
     561:       84 c0                   test   %al,%al
     563:       48 8b 4d c8             mov    -0x38(%rbp),%rcx
     567:       0f 85 77 01 00 00       jne    6e4 <__switch_to+0x274>

New (21 bytes, discarded after init):
   0:   f7 05 00 00 00 00 00    testl  $0x20000000,0x0(%rip)        #
a <.static_cpu_has+0xa>
   7:   00 00 20
                        2: R_X86_64_PC32        boot_cpu_data+0x18
   a:   0f 85 00 00 00 00       jne    10 <.static_cpu_has+0x10>
                        c: R_X86_64_PC32        .text+0x4b9
  10:   e9 00 00 00 00          jmpq   15 <.static_cpu_has+0x15>
                        11: R_X86_64_PC32       .text+0x529

--
Brian Gerst