From: Kees Cook <keescook@chromium.org>
To: Arnd Bergmann <arnd@arndb.de>
Cc: Andy Lutomirski <luto@kernel.org>,
"x86@kernel.org" <x86@kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
linux-arch <linux-arch@vger.kernel.org>,
Borislav Petkov <bp@alien8.de>, Nadav Amit <nadav.amit@gmail.com>,
Brian Gerst <brgerst@gmail.com>,
"kernel-hardening@lists.openwall.com"
<kernel-hardening@lists.openwall.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Josh Poimboeuf <jpoimboe@redhat.com>, Jann Horn <jann@thejh.net>,
Heiko Carstens <heiko.carstens@de.ibm.com>
Subject: Re: [PATCH v3 00/13] Virtually mapped stacks with guard pages (x86, core)
Date: Tue, 21 Jun 2016 10:16:21 -0700 [thread overview]
Message-ID: <CAGXu5jJaWxcOKLtXG3r1XWE8NpL=GFSZwmV_UYjjv6q0135ETQ@mail.gmail.com> (raw)
In-Reply-To: <13212319.WrhLzgRA6Z@wuerfel>
On Tue, Jun 21, 2016 at 2:24 AM, Arnd Bergmann <arnd@arndb.de> wrote:
> On Monday, June 20, 2016 4:43:30 PM CEST Andy Lutomirski wrote:
>>
>> On my laptop, this adds about 1.5µs of overhead to task creation,
>> which seems to be mainly caused by vmalloc inefficiently allocating
>> individual pages even when a higher-order page is available on the
>> freelist.
>
> Would it help to have a fixed virtual address for the stack instead
> and map the current stack to that during a task switch, similar to
> how we handle fixmap pages?
>
> That would of course trade the allocation overhead for a task switch
> overhead, which may be better or worse. It would also give "current"
> a constant address, which may give a small performance advantage
> but may also introduce a new attack vector unless we randomize it
> again.
Right: we don't want a fixed address. That makes attacks WAY easier.
-Kees
--
Kees Cook
Chrome OS & Brillo Security
WARNING: multiple messages have this Message-ID (diff)
From: Kees Cook <keescook@chromium.org>
To: Arnd Bergmann <arnd@arndb.de>
Cc: Andy Lutomirski <luto@kernel.org>,
"x86@kernel.org" <x86@kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
linux-arch <linux-arch@vger.kernel.org>,
Borislav Petkov <bp@alien8.de>, Nadav Amit <nadav.amit@gmail.com>,
Brian Gerst <brgerst@gmail.com>,
"kernel-hardening@lists.openwall.com"
<kernel-hardening@lists.openwall.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Josh Poimboeuf <jpoimboe@redhat.com>, Jann Horn <jann@thejh.net>,
Heiko Carstens <heiko.carstens@de.ibm.com>
Subject: [kernel-hardening] Re: [PATCH v3 00/13] Virtually mapped stacks with guard pages (x86, core)
Date: Tue, 21 Jun 2016 10:16:21 -0700 [thread overview]
Message-ID: <CAGXu5jJaWxcOKLtXG3r1XWE8NpL=GFSZwmV_UYjjv6q0135ETQ@mail.gmail.com> (raw)
In-Reply-To: <13212319.WrhLzgRA6Z@wuerfel>
On Tue, Jun 21, 2016 at 2:24 AM, Arnd Bergmann <arnd@arndb.de> wrote:
> On Monday, June 20, 2016 4:43:30 PM CEST Andy Lutomirski wrote:
>>
>> On my laptop, this adds about 1.5µs of overhead to task creation,
>> which seems to be mainly caused by vmalloc inefficiently allocating
>> individual pages even when a higher-order page is available on the
>> freelist.
>
> Would it help to have a fixed virtual address for the stack instead
> and map the current stack to that during a task switch, similar to
> how we handle fixmap pages?
>
> That would of course trade the allocation overhead for a task switch
> overhead, which may be better or worse. It would also give "current"
> a constant address, which may give a small performance advantage
> but may also introduce a new attack vector unless we randomize it
> again.
Right: we don't want a fixed address. That makes attacks WAY easier.
-Kees
--
Kees Cook
Chrome OS & Brillo Security
next prev parent reply other threads:[~2016-06-21 17:24 UTC|newest]
Thread overview: 269+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-20 23:43 [PATCH v3 00/13] Virtually mapped stacks with guard pages (x86, core) Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 01/13] x86/mm/hotplug: Don't remove PGD entries in remove_pagetable() Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 02/13] x86/cpa: In populate_pgd, don't set the pgd entry until it's populated Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 03/13] x86/mm: Remove kernel_unmap_pages_in_pgd() and efi_cleanup_page_tables() Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-21 9:53 ` Matt Fleming
2016-06-21 9:53 ` [kernel-hardening] " Matt Fleming
2016-06-21 9:53 ` Matt Fleming
2016-06-20 23:43 ` [PATCH v3 04/13] mm: Track NR_KERNEL_STACK in KiB instead of number of stacks Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-21 9:46 ` Vladimir Davydov
2016-06-21 9:46 ` [kernel-hardening] " Vladimir Davydov
2016-06-21 9:46 ` Vladimir Davydov
2016-06-21 9:46 ` Vladimir Davydov
2016-06-22 7:35 ` Michal Hocko
2016-06-22 7:35 ` [kernel-hardening] " Michal Hocko
2016-06-22 7:35 ` Michal Hocko
2016-06-22 7:35 ` Michal Hocko
2016-06-20 23:43 ` [PATCH v3 05/13] mm: Fix memcg stack accounting for sub-page stacks Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-21 9:54 ` Vladimir Davydov
2016-06-21 9:54 ` [kernel-hardening] " Vladimir Davydov
2016-06-21 9:54 ` Vladimir Davydov
2016-06-21 9:54 ` Vladimir Davydov
2016-06-22 7:38 ` Michal Hocko
2016-06-22 7:38 ` [kernel-hardening] " Michal Hocko
2016-06-22 7:38 ` Michal Hocko
2016-06-22 7:38 ` Michal Hocko
2016-06-20 23:43 ` [PATCH v3 06/13] fork: Add generic vmalloced stack support Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-21 7:30 ` Jann Horn
2016-06-21 7:30 ` [kernel-hardening] " Jann Horn
2016-06-21 7:30 ` Jann Horn
2016-06-21 16:59 ` Andy Lutomirski
2016-06-21 16:59 ` [kernel-hardening] " Andy Lutomirski
2016-06-21 16:59 ` Andy Lutomirski
2016-06-21 17:13 ` Kees Cook
2016-06-21 17:13 ` [kernel-hardening] " Kees Cook
2016-06-21 17:13 ` Kees Cook
2016-06-21 17:28 ` Andy Lutomirski
2016-06-21 17:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-21 17:28 ` Andy Lutomirski
2016-06-21 18:32 ` [kernel-hardening] " Rik van Riel
2016-06-21 18:32 ` Rik van Riel
2016-06-21 19:44 ` [kernel-hardening] " Arnd Bergmann
2016-06-21 19:44 ` Arnd Bergmann
2016-06-21 19:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-21 19:43 ` Andy Lutomirski
2016-06-21 19:43 ` Andy Lutomirski
2016-07-11 17:00 ` [kernel-hardening] " Andrey Ryabinin
2016-06-20 23:43 ` [PATCH v3 07/13] x86/die: Don't try to recover from an OOPS on a non-default stack Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 08/13] x86/dumpstack: When OOPSing, rewind the stack before do_exit Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 09/13] x86/dumpstack: When dumping stack bytes due to OOPS, start with regs->sp Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 10/13] x86/dumpstack: Try harder to get a call trace on stack overflow Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 11/13] x86/dumpstack/64: Handle faults when printing the "Stack:" part of an OOPS Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 12/13] x86/mm/64: Enable vmapped stacks Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-20 23:43 ` [PATCH v3 13/13] x86/mm: Improve stack-overflow #PF handling Andy Lutomirski
2016-06-20 23:43 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 23:43 ` Andy Lutomirski
2016-06-21 4:01 ` [PATCH v3 00/13] Virtually mapped stacks with guard pages (x86, core) Linus Torvalds
2016-06-21 4:01 ` [kernel-hardening] " Linus Torvalds
2016-06-21 4:01 ` Linus Torvalds
2016-06-21 16:45 ` Andy Lutomirski
2016-06-21 16:45 ` [kernel-hardening] " Andy Lutomirski
2016-06-21 16:45 ` Andy Lutomirski
2016-06-21 17:16 ` Linus Torvalds
2016-06-21 17:16 ` [kernel-hardening] " Linus Torvalds
2016-06-21 17:16 ` Linus Torvalds
2016-06-21 17:27 ` Andy Lutomirski
2016-06-21 17:27 ` [kernel-hardening] " Andy Lutomirski
2016-06-21 17:27 ` Andy Lutomirski
2016-06-21 18:12 ` Kees Cook
2016-06-21 18:12 ` [kernel-hardening] " Kees Cook
2016-06-21 18:12 ` Kees Cook
2016-06-21 18:19 ` [kernel-hardening] " Rik van Riel
2016-06-21 18:19 ` Rik van Riel
2016-06-23 1:22 ` Andy Lutomirski
2016-06-23 1:22 ` [kernel-hardening] " Andy Lutomirski
2016-06-23 1:22 ` Andy Lutomirski
2016-06-23 6:02 ` Linus Torvalds
2016-06-23 6:02 ` [kernel-hardening] " Linus Torvalds
2016-06-23 6:02 ` Linus Torvalds
2016-06-23 14:31 ` Oleg Nesterov
2016-06-23 14:31 ` [kernel-hardening] " Oleg Nesterov
2016-06-23 14:31 ` Oleg Nesterov
2016-06-23 16:30 ` Linus Torvalds
2016-06-23 16:30 ` [kernel-hardening] " Linus Torvalds
2016-06-23 16:30 ` Linus Torvalds
2016-06-23 16:41 ` Andy Lutomirski
2016-06-23 16:41 ` [kernel-hardening] " Andy Lutomirski
2016-06-23 16:41 ` Andy Lutomirski
2016-06-23 17:10 ` Oleg Nesterov
2016-06-23 17:10 ` [kernel-hardening] " Oleg Nesterov
2016-06-23 17:10 ` Oleg Nesterov
2016-09-06 16:19 ` Jann Horn
2016-09-06 16:19 ` [kernel-hardening] " Jann Horn
2016-09-06 16:19 ` Jann Horn
2016-09-06 16:40 ` Andy Lutomirski
2016-09-06 16:40 ` [kernel-hardening] " Andy Lutomirski
2016-09-06 16:40 ` Andy Lutomirski
2016-06-23 17:03 ` Oleg Nesterov
2016-06-23 17:03 ` [kernel-hardening] " Oleg Nesterov
2016-06-23 17:03 ` Oleg Nesterov
2016-06-23 17:44 ` Linus Torvalds
2016-06-23 17:44 ` [kernel-hardening] " Linus Torvalds
2016-06-23 17:44 ` Linus Torvalds
2016-06-23 17:52 ` Linus Torvalds
2016-06-23 17:52 ` [kernel-hardening] " Linus Torvalds
2016-06-23 17:52 ` Linus Torvalds
2016-06-23 18:00 ` Kees Cook
2016-06-23 18:00 ` [kernel-hardening] " Kees Cook
2016-06-23 18:00 ` Kees Cook
2016-06-23 18:54 ` Peter Zijlstra
2016-06-23 18:54 ` [kernel-hardening] " Peter Zijlstra
2016-06-23 18:54 ` Peter Zijlstra
2016-06-23 18:12 ` Oleg Nesterov
2016-06-23 18:12 ` [kernel-hardening] " Oleg Nesterov
2016-06-23 18:12 ` Oleg Nesterov
2016-06-23 18:55 ` Peter Zijlstra
2016-06-23 18:55 ` [kernel-hardening] " Peter Zijlstra
2016-06-23 18:55 ` Peter Zijlstra
2016-06-23 18:46 ` Linus Torvalds
2016-06-23 18:46 ` [kernel-hardening] " Linus Torvalds
2016-06-23 18:46 ` Linus Torvalds
2016-06-23 19:08 ` Andy Lutomirski
2016-06-23 19:08 ` [kernel-hardening] " Andy Lutomirski
2016-06-23 19:08 ` Andy Lutomirski
2016-06-23 18:53 ` Peter Zijlstra
2016-06-23 18:53 ` [kernel-hardening] " Peter Zijlstra
2016-06-23 18:53 ` Peter Zijlstra
2016-06-23 19:09 ` Andy Lutomirski
2016-06-23 19:09 ` [kernel-hardening] " Andy Lutomirski
2016-06-23 19:09 ` Andy Lutomirski
2016-06-23 19:13 ` Peter Zijlstra
2016-06-23 19:13 ` [kernel-hardening] " Peter Zijlstra
2016-06-23 19:13 ` Peter Zijlstra
2016-06-23 19:17 ` Linus Torvalds
2016-06-23 19:17 ` [kernel-hardening] " Linus Torvalds
2016-06-23 19:17 ` Linus Torvalds
2016-06-24 6:17 ` Linus Torvalds
2016-06-24 6:17 ` [kernel-hardening] " Linus Torvalds
2016-06-24 6:17 ` Linus Torvalds
2016-06-24 12:25 ` Brian Gerst
2016-06-24 12:25 ` [kernel-hardening] " Brian Gerst
2016-06-24 12:25 ` Brian Gerst
2016-06-24 17:21 ` Linus Torvalds
2016-06-24 17:21 ` [kernel-hardening] " Linus Torvalds
2016-06-24 17:21 ` Linus Torvalds
2016-06-24 17:40 ` Linus Torvalds
2016-06-24 17:40 ` [kernel-hardening] " Linus Torvalds
2016-06-24 17:40 ` Linus Torvalds
2016-06-24 17:47 ` Andy Lutomirski
2016-06-24 17:47 ` [kernel-hardening] " Andy Lutomirski
2016-06-24 17:47 ` Andy Lutomirski
2016-06-24 17:56 ` Linus Torvalds
2016-06-24 17:56 ` [kernel-hardening] " Linus Torvalds
2016-06-24 17:56 ` Linus Torvalds
2016-06-24 18:36 ` Andy Lutomirski
2016-06-24 18:36 ` [kernel-hardening] " Andy Lutomirski
2016-06-24 18:36 ` Andy Lutomirski
2016-06-24 17:51 ` Linus Torvalds
2016-06-24 17:51 ` [kernel-hardening] " Linus Torvalds
2016-06-24 17:51 ` Linus Torvalds
2016-06-24 18:11 ` Linus Torvalds
2016-06-24 18:11 ` [kernel-hardening] " Linus Torvalds
2016-06-24 18:11 ` Linus Torvalds
2016-06-24 20:25 ` Josh Poimboeuf
2016-06-24 20:25 ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 20:25 ` Josh Poimboeuf
2016-06-24 20:51 ` Josh Poimboeuf
2016-06-24 20:51 ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 20:51 ` Josh Poimboeuf
2016-06-24 20:53 ` Andy Lutomirski
2016-06-24 20:53 ` [kernel-hardening] " Andy Lutomirski
2016-06-24 20:53 ` Andy Lutomirski
2016-06-24 21:06 ` Linus Torvalds
2016-06-24 21:06 ` [kernel-hardening] " Linus Torvalds
2016-06-24 21:06 ` Linus Torvalds
2016-06-24 21:25 ` Andy Lutomirski
2016-06-24 21:25 ` [kernel-hardening] " Andy Lutomirski
2016-06-24 21:25 ` Andy Lutomirski
2016-06-24 21:32 ` Linus Torvalds
2016-06-24 21:32 ` [kernel-hardening] " Linus Torvalds
2016-06-24 21:32 ` Linus Torvalds
2016-06-24 21:34 ` Andy Lutomirski
2016-06-24 21:34 ` [kernel-hardening] " Andy Lutomirski
2016-06-24 21:34 ` Andy Lutomirski
2016-06-25 2:41 ` Linus Torvalds
2016-06-25 2:41 ` [kernel-hardening] " Linus Torvalds
2016-06-25 2:41 ` Linus Torvalds
2016-06-25 23:19 ` Andy Lutomirski
2016-06-25 23:19 ` [kernel-hardening] " Andy Lutomirski
2016-06-25 23:19 ` Andy Lutomirski
2016-06-25 23:30 ` Andy Lutomirski
2016-06-25 23:30 ` [kernel-hardening] " Andy Lutomirski
2016-06-25 23:30 ` Andy Lutomirski
2016-06-26 1:23 ` Linus Torvalds
2016-06-26 1:23 ` [kernel-hardening] " Linus Torvalds
2016-06-26 1:23 ` Linus Torvalds
2016-06-23 18:52 ` Oleg Nesterov
2016-06-23 18:52 ` [kernel-hardening] " Oleg Nesterov
2016-06-23 18:52 ` Oleg Nesterov
2016-06-24 14:05 ` Michal Hocko
2016-06-24 14:05 ` [kernel-hardening] " Michal Hocko
2016-06-24 14:05 ` Michal Hocko
2016-06-24 15:06 ` Michal Hocko
2016-06-24 15:06 ` [kernel-hardening] " Michal Hocko
2016-06-24 15:06 ` Michal Hocko
2016-06-24 15:06 ` Michal Hocko
2016-06-24 20:22 ` Oleg Nesterov
2016-06-24 20:22 ` [kernel-hardening] " Oleg Nesterov
2016-06-24 20:22 ` Oleg Nesterov
2016-06-27 10:36 ` Michal Hocko
2016-06-27 10:36 ` [kernel-hardening] " Michal Hocko
2016-06-27 10:36 ` Michal Hocko
2016-06-23 19:11 ` Peter Zijlstra
2016-06-23 19:11 ` [kernel-hardening] " Peter Zijlstra
2016-06-23 19:11 ` Peter Zijlstra
2016-06-23 19:34 ` Linus Torvalds
2016-06-23 19:34 ` [kernel-hardening] " Linus Torvalds
2016-06-23 19:34 ` Linus Torvalds
2016-06-23 19:46 ` Peter Zijlstra
2016-06-23 19:46 ` [kernel-hardening] " Peter Zijlstra
2016-06-23 19:46 ` Peter Zijlstra
2016-06-21 9:24 ` Arnd Bergmann
2016-06-21 9:24 ` [kernel-hardening] " Arnd Bergmann
2016-06-21 9:24 ` Arnd Bergmann
2016-06-21 17:16 ` Kees Cook [this message]
2016-06-21 17:16 ` [kernel-hardening] " Kees Cook
2016-06-21 17:16 ` Kees Cook
2016-06-21 18:02 ` [kernel-hardening] " Rik van Riel
2016-06-21 18:02 ` Rik van Riel
2016-06-21 18:05 ` [kernel-hardening] " Andy Lutomirski
2016-06-21 18:05 ` Andy Lutomirski
2016-06-21 18:05 ` Andy Lutomirski
2016-06-21 19:47 ` Arnd Bergmann
2016-06-21 19:47 ` [kernel-hardening] " Arnd Bergmann
2016-06-21 19:47 ` Arnd Bergmann
2016-06-21 19:47 ` Andy Lutomirski
2016-06-21 19:47 ` [kernel-hardening] " Andy Lutomirski
2016-06-21 19:47 ` Andy Lutomirski
2016-06-21 20:18 ` Kees Cook
2016-06-21 20:18 ` [kernel-hardening] " Kees Cook
2016-06-21 20:18 ` Kees Cook
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='CAGXu5jJaWxcOKLtXG3r1XWE8NpL=GFSZwmV_UYjjv6q0135ETQ@mail.gmail.com' \
--to=keescook@chromium.org \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=brgerst@gmail.com \
--cc=heiko.carstens@de.ibm.com \
--cc=jann@thejh.net \
--cc=jpoimboe@redhat.com \
--cc=kernel-hardening@lists.openwall.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=nadav.amit@gmail.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 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.