mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Nadav Amit <nadav.amit@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>,
	Ingo Molnar <mingo@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>, Willy Tarreau <w@1wt.eu>,
	X86 ML <x86@kernel.org>,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH RFC v2 0/6] x86: Disabling PTI in compatibility mode
Date: Fri, 16 Feb 2018 01:04:07 +0000	[thread overview]
Message-ID: <ae54d08f-d79b-c89d-d14f-a8211d2782a8@citrix.com> (raw)
In-Reply-To: <D9B68521-7BDA-4088-BF66-8B1B6BF85E78@gmail.com>

On 16/02/2018 00:51, Nadav Amit wrote:
> Andrew Cooper <andrew.cooper3@citrix.com> wrote:
>
>> On 16/02/2018 00:25, Nadav Amit wrote:
>>> Dave Hansen <dave.hansen@linux.intel.com> wrote:
>>>
>>>> On 02/15/2018 08:35 AM, Nadav Amit wrote:
>>>>> I removed the PTI disabling while SMEP is unsupported, although I
>>>>> must admit I did not fully understand why it is required.
>>>> Do you mean you don't fully understand how PTI gives SMEP-like behavior
>>>> on non-SMEP hardware?
>>> No. I understand how it provide SMEP-like behavior, and I understand the value
>>> of SMEP by itself.
>>>
>>> However, I do not understand why SMEP-like protection is required to protect
>>> processes that run in compatibility-mode from Meltdown/Spectre attacks. As
>>> far as I understand, the process should not be able to manipulate the kernel
>>> to execute code in the low 4GB.
>> Being 32bit is itself sufficient protection against Meltdown (as long as
>> there nothing interesting of the kernels mapped below the 4G boundary).
>>
>> However, a 32bit compatibility process try to attack with Spectre/SP2 to
>> redirect speculation back into userspace, at which point (if successful)
>> the pipeline will be speculating in 64bit mode, and Meltdown is back on
>> the table.  SMEP will block this attack vector, irrespective of other
>> SP2 defences the kernel may employ, but a fully SP2-defended kernel
>> doesn't require SMEP to be safe in this case.
> Based on Jann Horn’s description of the branch predictor, it basically only
> holds the lowest 31-bits of the target address. There might be a subtle
> problem if the prediction wrapsaround, but excluding this case, I do not see
> how Spectre v2 can be used to jump into running user code.

RSB poisoning is also part of SP2, and does have full width addresses.

~Andrew

P.S. Consider yourself lucky that the 32bit code isn't running in
Ring1.  Xen has a substantially more interesting time in this regard.

  reply	other threads:[~2018-02-16  1:04 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-15 16:35 Nadav Amit
2018-02-15 16:35 ` [PATCH RFC v2 1/6] x86: Skip PTI when disable indication is set Nadav Amit
2018-02-15 18:10   ` Dave Hansen
2018-02-15 19:51   ` Andy Lutomirski
2018-02-15 20:51     ` Nadav Amit
2018-02-15 23:35       ` Andy Lutomirski
2018-02-15 16:35 ` [PATCH RFC v2 2/6] x86: Save pti_disable for each mm_context Nadav Amit
2018-02-15 16:35 ` [PATCH RFC v2 3/6] x86: Switching page-table isolation Nadav Amit
2018-02-15 16:36 ` [PATCH RFC v2 4/6] x86: Disable PTI on compatibility mode Nadav Amit
2018-02-15 20:02   ` Andy Lutomirski
2018-02-15 20:58     ` Nadav Amit
2018-02-15 23:29       ` Andy Lutomirski
2018-02-16  0:08         ` Linus Torvalds
2018-02-16  0:22           ` Nadav Amit
2018-02-16  0:42             ` Linus Torvalds
2018-02-16  3:03               ` Andy Lutomirski
2018-02-16  4:55                 ` Nadav Amit
2018-02-16  0:35           ` Andrew Cooper
2018-02-16 15:20           ` Andy Lutomirski
2018-02-16  7:11         ` Cyrill Gorcunov
2018-02-16 22:07           ` Dmitry Safonov
2018-02-16 22:11             ` Nadav Amit
2018-02-16 16:25     ` Dmitry Safonov
2018-02-15 16:36 ` [PATCH RFC v2 5/6] x86: Use global pages when PTI is disabled Nadav Amit
2018-02-15 16:54   ` Dave Hansen
2018-02-15 17:36     ` Nadav Amit
2018-02-15 17:47     ` Nadav Amit
2018-02-15 18:08       ` Dave Hansen
2018-02-15 19:53   ` Andy Lutomirski
2018-02-15 20:32     ` Dave Hansen
2018-02-15 20:45       ` Nadav Amit
2018-02-15 16:36 ` [PATCH RFC v2 6/6] selftest: x86: test using CS64 on compatibility-mode Nadav Amit
2018-02-16  0:21 ` [PATCH RFC v2 0/6] x86: Disabling PTI in compatibility mode Dave Hansen
2018-02-16  0:25   ` Nadav Amit
2018-02-16  0:42     ` Dave Hansen
2018-02-16  0:48       ` Nadav Amit
2018-02-16  0:45     ` Andrew Cooper
2018-02-16  0:51       ` Nadav Amit
2018-02-16  1:04         ` Andrew Cooper [this message]
2018-02-16  3:05         ` 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=ae54d08f-d79b-c89d-d14f-a8211d2782a8@citrix.com \
    --to=andrew.cooper3@citrix.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=nadav.amit@gmail.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=w@1wt.eu \
    --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

all inboxes | Powered by JetHome®