From: Andrea Arcangeli <aarcange@redhat.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Jon Masters <jcm@redhat.com>,
"Woodhouse, David" <dwmw@amazon.co.uk>,
Paolo Bonzini <pbonzini@redhat.com>,
Alan Cox <gnomes@lxorguk.ukuu.org.uk>,
Linus Torvalds <torvalds@linux-foundation.org>,
Andi Kleen <andi@firstfloor.org>,
Greg Kroah-Hartman <gregkh@linux-foundation.org>,
Tim Chen <tim.c.chen@linux.intel.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Dave Hansen <dave.hansen@intel.com>, Jeff Law <law@redhat.com>,
Nick Clifton <nickc@redhat.com>
Subject: Re: Avoid speculative indirect calls in kernel
Date: Mon, 8 Jan 2018 22:32:23 +0100 [thread overview]
Message-ID: <20180108213223.GF4703@redhat.com> (raw)
In-Reply-To: <alpine.DEB.2.20.1801082152200.2253@nanos>
On Mon, Jan 08, 2018 at 09:53:02PM +0100, Thomas Gleixner wrote:
> Thanks for resending it.
Thanks to you for the PTI improvements!
Did my best to do the cleanest patch for tip, but I now figured Dave's
original comment was spot on: a _PAGE_NX clear then becomes necessary
also after pud_alloc not only after p4d_alloc.
pmd_alloc would run into the same with x86 32bit non-PAE too.
So there are two choices, either going back to one single _PAGE_NX
clear from the original Dave's original patch as below, or to add
multiple clear after each level which was my objective and is more
robust, but it may be overkill in this case. As long as it was one
line it looked a clear improvement.
Considering the caller in both cases is going to abort I guess we can
use the one liner approach as Dave and Jiri did originally.
It's up to you, doing it at each level would be more resilent in case
the caller is changed.
For the efi_64 same issue, the current tip patch will work better, but
it can still be cleaned up with pgd_efi instead of pgd_offset_k().
I got partly fooled because it worked great with 4levels, but it
wasn't ok anyway for 32bit non-PAE. Sometime it's the simpler stuff
that gets more subtle.
Andrea
>From 391517951e904cdd231dda9943c36a25a7bf01b9 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Sat, 6 Jan 2018 18:41:14 +0100
Subject: [PATCH 1/1] x86/kaiser/efi: unbreak tboot
This is another case similar to what EFI does: create a new set of
page tables, map some code at a low address, and jump to it. PTI
mistakes this low address for userspace and mistakenly marks it
non-executable in an effort to make it unusable for userspace. Undo
the poison to allow execution.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ning Sun <ning.sun@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: tboot-devel@lists.sourceforge.net
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
---
arch/x86/kernel/tboot.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index a4eb27918ceb..a2486f444073 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -138,6 +138,17 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
return -1;
set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
pte_unmap(pte);
+
+ /*
+ * PTI poisons low addresses in the kernel page tables in the
+ * name of making them unusable for userspace. To execute
+ * code at such a low address, the poison must be cleared.
+ *
+ * Note: 'pgd' actually gets set in p4d_alloc() _or_
+ * pud_alloc() depending on 4/5-level paging.
+ */
+ pgd->pgd &= ~_PAGE_NX;
+
return 0;
}
next prev parent reply other threads:[~2018-01-08 21:32 UTC|newest]
Thread overview: 107+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-03 23:09 Avoid speculative indirect calls in kernel Andi Kleen
2018-01-03 23:09 ` [PATCH 01/11] x86/retpoline: Define retpoline indirect thunk and macros Andi Kleen
2018-01-03 23:09 ` [PATCH 02/11] x86/retpoline/crypto: Convert crypto assembler indirect jumps Andi Kleen
2018-01-03 23:09 ` [PATCH 03/11] x86/retpoline/entry: Convert entry " Andi Kleen
2018-01-03 23:09 ` [PATCH 04/11] x86/retpoline/ftrace: Convert ftrace " Andi Kleen
2018-01-03 23:09 ` [PATCH 05/11] x86/retpoline/hyperv: Convert " Andi Kleen
2018-01-03 23:09 ` [PATCH 06/11] x86/retpoline/crypto: Convert xen " Andi Kleen
2018-01-03 23:09 ` [PATCH 07/11] x86/retpoline/checksum32: Convert " Andi Kleen
2018-01-03 23:09 ` [PATCH 08/11] x86/retpoline/irq32: " Andi Kleen
2018-01-03 23:09 ` [PATCH 09/11] x86/retpoline: Finally enable retpoline for C code Andi Kleen
2018-01-04 8:28 ` Greg KH
2018-01-04 8:30 ` Dave Hansen
2018-01-03 23:09 ` [PATCH 10/11] retpoline/taint: Taint kernel for missing retpoline in compiler Andi Kleen
2018-01-04 0:29 ` Thomas Gleixner
2018-01-04 0:35 ` Randy Dunlap
2018-01-03 23:09 ` [PATCH 11/11] retpoline/objtool: Disable some objtool warnings Andi Kleen
2018-01-03 23:51 ` Avoid speculative indirect calls in kernel Linus Torvalds
2018-01-04 0:00 ` Alan Cox
2018-01-04 0:09 ` Andi Kleen
2018-01-04 0:12 ` Thomas Gleixner
2018-01-04 0:15 ` Andi Kleen
2018-01-04 0:19 ` Jiri Kosina
2018-01-05 2:01 ` james harvey
2018-01-05 10:40 ` Woodhouse, David
2018-01-05 12:29 ` james harvey
2018-01-05 12:06 ` Alan Cox
2018-01-04 0:29 ` Alan Cox
2018-01-04 0:31 ` Thomas Gleixner
2018-01-04 0:38 ` Alan Cox
2018-01-04 0:40 ` Andi Kleen
2018-01-04 8:15 ` Woodhouse, David
2018-01-04 15:53 ` Andi Kleen
2018-01-04 15:55 ` Woodhouse, David
2018-01-04 0:20 ` Linus Torvalds
2018-01-04 0:26 ` Thomas Gleixner
2018-01-04 0:18 ` David Lang
2018-01-04 1:00 ` Paul Turner
2018-01-04 1:41 ` Paolo Bonzini
2018-01-04 1:59 ` Alan Cox
2018-01-04 2:11 ` Paolo Bonzini
2018-01-04 8:20 ` Woodhouse, David
2018-01-04 11:42 ` Pavel Machek
2018-01-04 11:47 ` Woodhouse, David
2018-01-04 14:20 ` Paolo Bonzini
2018-01-04 14:51 ` Andrew Cooper
2018-01-04 15:29 ` Woodhouse, David
2018-01-04 15:32 ` Paolo Bonzini
2018-01-04 15:37 ` Andrew Cooper
2018-01-04 16:15 ` David Woodhouse
2018-01-04 20:00 ` Tom Lendacky
2018-01-04 20:05 ` David Woodhouse
2018-01-04 23:47 ` Tom Lendacky
2018-01-05 0:06 ` Andrew Cooper
2018-01-05 0:26 ` Tom Lendacky
2018-01-04 16:52 ` Andrea Arcangeli
2018-01-04 15:32 ` Paolo Bonzini
2018-01-04 16:25 ` Andrea Arcangeli
2018-01-04 17:04 ` Alan Cox
2018-01-04 17:40 ` Andrea Arcangeli
2018-01-04 17:13 ` Dave Hansen
2018-01-04 17:15 ` Paolo Bonzini
2018-01-04 18:05 ` Andrea Arcangeli
2018-01-04 14:55 ` Woodhouse, David
2018-01-04 18:24 ` Pavel Machek
2018-01-04 19:57 ` Jon Masters
2018-01-05 0:41 ` Jon Masters
2018-01-05 0:54 ` Thomas Gleixner
2018-01-05 4:11 ` Jon Masters
2018-01-05 9:59 ` Thomas Gleixner
2018-01-08 10:28 ` Andrea Arcangeli
2018-01-08 20:42 ` [tip:x86/pti] x86/tboot: Unbreak tboot with PTI enabled tip-bot for Dave Hansen
2018-01-08 20:53 ` Avoid speculative indirect calls in kernel Thomas Gleixner
2018-01-08 21:32 ` Andrea Arcangeli [this message]
2018-01-10 0:45 ` Thomas Gleixner
2018-01-10 1:11 ` Dave Hansen
2018-01-10 16:02 ` Thomas Gleixner
2018-01-05 6:49 ` Willy Tarreau
2018-01-05 6:57 ` Dave Hansen
2018-01-05 7:13 ` Willy Tarreau
2018-01-07 14:14 ` Borislav Petkov
2018-01-07 17:21 ` David Lang
2018-01-07 18:49 ` Borislav Petkov
2018-01-07 17:44 ` Willy Tarreau
2018-01-07 18:55 ` Borislav Petkov
2018-01-07 22:10 ` Willy Tarreau
2018-01-08 9:18 ` Thomas Gleixner
2018-01-08 9:29 ` Willy Tarreau
2018-01-08 16:22 ` Borislav Petkov
2018-01-08 16:53 ` Willy Tarreau
2018-01-05 12:12 ` Alan Cox
2018-01-09 1:44 ` Samir Bellabes
[not found] ` <CAL9bgJ8XNJgCtxR6+M+Vm9eDBVZ4Dyi_-Lt-Q1ei9N=TE2c6cg@mail.gmail.com>
2018-01-07 5:04 ` Fwd: " Kiernan Hager
2018-01-07 6:39 ` Willy Tarreau
2018-01-07 14:01 ` Alan Cox
2018-01-07 17:47 ` Willy Tarreau
2018-01-07 18:01 ` Ivan Ivanov
2018-01-07 18:16 ` Woodhouse, David
2018-01-04 11:26 ` Pavel Machek
2018-01-04 11:54 ` Alan Cox
2018-01-04 18:33 ` Linus Torvalds
2018-01-04 20:08 ` Jon Masters
-- strict thread matches above, loose matches on Subject: below --
2018-01-04 2:00 Andi Kleen
2018-01-04 11:49 ` Pavel Machek
2018-01-04 12:09 ` Alan Cox
2018-01-04 13:32 ` Pavel Machek
2018-01-12 8:20 Dr. Greg Wettstein
2018-02-23 21:10 Ywe Cærlyn
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=20180108213223.GF4703@redhat.com \
--to=aarcange@redhat.com \
--cc=andi@firstfloor.org \
--cc=dave.hansen@intel.com \
--cc=dwmw@amazon.co.uk \
--cc=gnomes@lxorguk.ukuu.org.uk \
--cc=gregkh@linux-foundation.org \
--cc=jcm@redhat.com \
--cc=law@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nickc@redhat.com \
--cc=pbonzini@redhat.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.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;
as well as URLs for NNTP newsgroup(s).