From: Heiko Carstens <heiko.carstens@de.ibm.com>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Nadav Amit <nadav.amit@gmail.com>,
Kees Cook <keescook@chromium.org>,
Josh Poimboeuf <jpoimboe@redhat.com>,
Borislav Petkov <bp@alien8.de>, X86 ML <x86@kernel.org>,
"kernel-hardening@lists.openwall.com"
<kernel-hardening@lists.openwall.com>,
Brian Gerst <brgerst@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH 00/13] Virtually mapped stacks with guard pages (x86, core)
Date: Mon, 20 Jun 2016 07:58:36 +0200 [thread overview]
Message-ID: <20160620055836.GA3266@osiris> (raw)
In-Reply-To: <CALCETrVh+w1Bj2K5QGvJwsbrGrrD_=zz1vWPC2zXUai6YB9dBA@mail.gmail.com>
On Fri, Jun 17, 2016 at 10:38:24AM -0700, Andy Lutomirski wrote:
> > A disassembly looks like this (r15 is the stackpointer):
> >
> > 0000000000000670 <setup_arch>:
> > 670: eb 6f f0 48 00 24 stmg %r6,%r15,72(%r15)
> > 676: c0 d0 00 00 00 00 larl %r13,676 <setup_arch+0x6>
> > 67c: a7 f1 3f 80 tmll %r15,16256 <--- test if enough space left
> > 680: b9 04 00 ef lgr %r14,%r15
> > 684: a7 84 00 01 je 686 <setup_arch+0x16> <--- branch to illegal op
> > 688: e3 f0 ff 90 ff 71 lay %r15,-112(%r15)
> >
> > The branch jumps actually into the branch instruction itself since the 0001
> > part of the "je" instruction is an illegal instruction.
> >
> > This catches at least wild stack overflows because of two many functions
> > being called.
> >
> > Of course it doesn't catch wild accesses outside the stack because e.g. the
> > index into an array on the stack is wrong.
> >
> > The runtime overhead is within noise ratio, therefore we have this always
> > enabled.
> >
>
> Neat! What exactly does tmll do? I assume this works by checking the
> low bits of the stack pointer.
>
> x86_64 would have to do:
>
> movl %esp, %r11d
> shll %r11d, $18
> cmpl %r11d, <threshold>
> jg error
>
> Or similar. I think the cmpl could be eliminated if the threshold
> were a power of two by simply testing the low bits of the stack
> pointer.
The tmll instruction tests if any of the higher bits within the 16k
stackframe address are set. In this specific case that would be bits 7-15
(mask 0x3f80). If no bit would be set we know that only up to 128 bytes
would be left on the stack, and thus trigger an exception.
This check does of course only work if a 16k stack is also 16k aligned,
which is always the case.
WARNING: multiple messages have this Message-ID (diff)
From: Heiko Carstens <heiko.carstens@de.ibm.com>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Nadav Amit <nadav.amit@gmail.com>,
Kees Cook <keescook@chromium.org>,
Josh Poimboeuf <jpoimboe@redhat.com>,
Borislav Petkov <bp@alien8.de>, X86 ML <x86@kernel.org>,
"kernel-hardening@lists.openwall.com"
<kernel-hardening@lists.openwall.com>,
Brian Gerst <brgerst@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: [kernel-hardening] Re: [PATCH 00/13] Virtually mapped stacks with guard pages (x86, core)
Date: Mon, 20 Jun 2016 07:58:36 +0200 [thread overview]
Message-ID: <20160620055836.GA3266@osiris> (raw)
In-Reply-To: <CALCETrVh+w1Bj2K5QGvJwsbrGrrD_=zz1vWPC2zXUai6YB9dBA@mail.gmail.com>
On Fri, Jun 17, 2016 at 10:38:24AM -0700, Andy Lutomirski wrote:
> > A disassembly looks like this (r15 is the stackpointer):
> >
> > 0000000000000670 <setup_arch>:
> > 670: eb 6f f0 48 00 24 stmg %r6,%r15,72(%r15)
> > 676: c0 d0 00 00 00 00 larl %r13,676 <setup_arch+0x6>
> > 67c: a7 f1 3f 80 tmll %r15,16256 <--- test if enough space left
> > 680: b9 04 00 ef lgr %r14,%r15
> > 684: a7 84 00 01 je 686 <setup_arch+0x16> <--- branch to illegal op
> > 688: e3 f0 ff 90 ff 71 lay %r15,-112(%r15)
> >
> > The branch jumps actually into the branch instruction itself since the 0001
> > part of the "je" instruction is an illegal instruction.
> >
> > This catches at least wild stack overflows because of two many functions
> > being called.
> >
> > Of course it doesn't catch wild accesses outside the stack because e.g. the
> > index into an array on the stack is wrong.
> >
> > The runtime overhead is within noise ratio, therefore we have this always
> > enabled.
> >
>
> Neat! What exactly does tmll do? I assume this works by checking the
> low bits of the stack pointer.
>
> x86_64 would have to do:
>
> movl %esp, %r11d
> shll %r11d, $18
> cmpl %r11d, <threshold>
> jg error
>
> Or similar. I think the cmpl could be eliminated if the threshold
> were a power of two by simply testing the low bits of the stack
> pointer.
The tmll instruction tests if any of the higher bits within the 16k
stackframe address are set. In this specific case that would be bits 7-15
(mask 0x3f80). If no bit would be set we know that only up to 128 bytes
would be left on the stack, and thus trigger an exception.
This check does of course only work if a 16k stack is also 16k aligned,
which is always the case.
next prev parent reply other threads:[~2016-06-20 5:58 UTC|newest]
Thread overview: 112+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-16 0:28 [PATCH 00/13] Virtually mapped stacks with guard pages (x86, core) Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` [PATCH 01/13] x86/mm/hotplug: Don't remove PGD entries in remove_pagetable() Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` Andy Lutomirski
2016-06-16 0:28 ` [PATCH 02/13] x86/cpa: In populate_pgd, don't set the pgd entry until it's populated Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` [PATCH 03/13] x86/cpa: Warn if kernel_unmap_pages_in_pgd is used inappropriately Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` [PATCH 04/13] mm: Track NR_KERNEL_STACK in pages instead of number of stacks Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` Andy Lutomirski
2016-06-16 11:10 ` Vladimir Davydov
2016-06-16 11:10 ` [kernel-hardening] " Vladimir Davydov
2016-06-16 11:10 ` Vladimir Davydov
2016-06-16 17:21 ` Andy Lutomirski
2016-06-16 17:21 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 17:21 ` Andy Lutomirski
2016-06-16 19:20 ` Andy Lutomirski
2016-06-16 19:20 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 19:20 ` Andy Lutomirski
2016-06-16 15:33 ` Josh Poimboeuf
2016-06-16 15:33 ` [kernel-hardening] " Josh Poimboeuf
2016-06-16 15:33 ` Josh Poimboeuf
2016-06-16 17:39 ` Andy Lutomirski
2016-06-16 17:39 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 17:39 ` Andy Lutomirski
2016-06-16 19:39 ` Josh Poimboeuf
2016-06-16 19:39 ` [kernel-hardening] " Josh Poimboeuf
2016-06-16 19:39 ` Josh Poimboeuf
2016-06-16 0:28 ` [PATCH 05/13] mm: Move memcg stack accounting to account_kernel_stack Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` Andy Lutomirski
2016-06-16 0:28 ` [PATCH 06/13] fork: Add generic vmalloced stack support Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 17:25 ` Kees Cook
2016-06-16 17:25 ` [kernel-hardening] " Kees Cook
2016-06-16 17:37 ` Andy Lutomirski
2016-06-16 17:37 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` [PATCH 07/13] x86/die: Don't try to recover from an OOPS on a non-default stack Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` [PATCH 08/13] x86/dumpstack: When OOPSing, rewind the stack before do_exit Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 17:50 ` Josh Poimboeuf
2016-06-16 17:50 ` [kernel-hardening] " Josh Poimboeuf
2016-06-16 17:57 ` Andy Lutomirski
2016-06-16 17:57 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` [PATCH 09/13] x86/dumpstack: When dumping stack bytes due to OOPS, start with regs->sp Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 11:56 ` Borislav Petkov
2016-06-16 11:56 ` [kernel-hardening] " Borislav Petkov
2016-07-08 12:07 ` [tip:x86/debug] x86/dumpstack: Honor supplied @regs arg tip-bot for Andy Lutomirski
2016-06-16 0:28 ` [PATCH 10/13] x86/dumpstack: Try harder to get a call trace on stack overflow Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 18:16 ` Josh Poimboeuf
2016-06-16 18:16 ` [kernel-hardening] " Josh Poimboeuf
2016-06-16 18:22 ` Andy Lutomirski
2016-06-16 18:22 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 18:33 ` Josh Poimboeuf
2016-06-16 18:33 ` [kernel-hardening] " Josh Poimboeuf
2016-06-16 18:37 ` Andy Lutomirski
2016-06-16 18:37 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 18:54 ` Josh Poimboeuf
2016-06-16 18:54 ` [kernel-hardening] " Josh Poimboeuf
2016-06-16 0:28 ` [PATCH 11/13] x86/dumpstack/64: Handle faults when printing the "Stack:" part of an OOPS Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 0:28 ` [PATCH 12/13] x86/mm/64: Enable vmapped stacks Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 4:17 ` Mika Penttilä
2016-06-16 4:17 ` [kernel-hardening] " Mika Penttilä
2016-06-16 5:33 ` Andy Lutomirski
2016-06-16 5:33 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 13:11 ` Rik van Riel
2016-06-16 0:28 ` [PATCH 13/13] x86/mm: Improve stack-overflow #PF handling Andy Lutomirski
2016-06-16 0:28 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 6:05 ` [PATCH 00/13] Virtually mapped stacks with guard pages (x86, core) Heiko Carstens
2016-06-16 6:05 ` [kernel-hardening] " Heiko Carstens
2016-06-16 17:50 ` Andy Lutomirski
2016-06-16 17:50 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 18:14 ` Andy Lutomirski
2016-06-16 18:14 ` [kernel-hardening] " Andy Lutomirski
2016-06-16 21:27 ` Andy Lutomirski
2016-06-16 21:27 ` [kernel-hardening] " Andy Lutomirski
2016-06-17 3:58 ` Andy Lutomirski
2016-06-17 3:58 ` [kernel-hardening] " Andy Lutomirski
2016-06-17 7:27 ` Heiko Carstens
2016-06-17 7:27 ` [kernel-hardening] " Heiko Carstens
2016-06-17 17:38 ` Andy Lutomirski
2016-06-17 17:38 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 5:58 ` Heiko Carstens [this message]
2016-06-20 5:58 ` Heiko Carstens
2016-06-20 6:01 ` Andy Lutomirski
2016-06-20 6:01 ` [kernel-hardening] " Andy Lutomirski
2016-06-20 7:07 ` Heiko Carstens
2016-06-20 7:07 ` [kernel-hardening] " Heiko Carstens
2016-06-16 17:24 ` Kees Cook
2016-06-16 17:24 ` [kernel-hardening] " Kees Cook
2016-07-04 22:31 [PATCH -v2 0/3] x86/MSR: Improve unhandled MSR access error message Borislav Petkov
2016-07-04 22:31 ` [PATCH -v2 1/3] x86/dumpstack: Honor supplied @regs arg Borislav Petkov
2016-07-04 22:31 ` [PATCH -v2 2/3] printk: Make the printk*once() variants return a value Borislav Petkov
2016-07-08 12:08 ` [tip:x86/debug] " tip-bot for Borislav Petkov
2016-07-09 2:40 ` Joe Perches
2016-07-09 7:50 ` Borislav Petkov
2016-07-09 17:56 ` Joe Perches
2016-07-10 6:49 ` Borislav Petkov
2016-07-10 8:23 ` Joe Perches
2016-07-10 12:06 ` Borislav Petkov
2016-07-10 12:33 ` Joe Perches
2016-07-04 22:31 ` [PATCH -v2 3/3] x86/dumpstack: Add show_stack_regs() and use it Borislav Petkov
2016-07-08 12:08 ` [tip:x86/debug] " tip-bot for Borislav Petkov
2016-07-06 12:58 ` [PATCH -v2 0/3] x86/MSR: Improve unhandled MSR access error message Andy Lutomirski
2016-07-06 13:11 ` Borislav Petkov
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=20160620055836.GA3266@osiris \
--to=heiko.carstens@de.ibm.com \
--cc=bp@alien8.de \
--cc=brgerst@gmail.com \
--cc=jpoimboe@redhat.com \
--cc=keescook@chromium.org \
--cc=kernel-hardening@lists.openwall.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--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.