linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Dave Hansen <dave.hansen@linux.intel.com>
To: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org, Dave Hansen <dave.hansen@linux.intel.com>,
	aarcange@redhat.com, luto@kernel.org,
	torvalds@linux-foundation.org, keescook@google.com,
	hughd@google.com, jgross@suse.com, x86@kernel.org,
	namit@vmware.com
Subject: [PATCH 11/11] x86/pti: leave kernel text global for !PCID
Date: Fri, 23 Mar 2018 10:45:04 -0700	[thread overview]
Message-ID: <20180323174504.60B178AB@viggo.jf.intel.com> (raw)
In-Reply-To: <20180323174447.55F35636@viggo.jf.intel.com>


I'm sticking this at the end of the series because it's a bit weird.
It can be dropped and the rest of the series is still useful without
it.

Global pages are bad for hardening because they potentially let an
exploit read the kernel image via a Meltdown-style attack which
makes it easier to find gadgets.

But, global pages are good for performance because they reduce TLB
misses when making user/kernel transitions, especially when PCIDs
are not available, such as on older hardware, or where a hypervisor
has disabled them for some reason.

This patch implements a basic, sane policy: If you have PCIDs, you
only map a minimal amount of kernel text global.  If you do not have
PCIDs, you map all kernel text global.

This policy effectively makes PCIDs something that not only adds
performance but a little bit of hardening as well.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Kees Cook <keescook@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: x86@kernel.org
Cc: Nadav Amit <namit@vmware.com>
---

 b/arch/x86/mm/pti.c |   34 +++++++++++++++++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff -puN arch/x86/mm/pti.c~kpti-global-text-option arch/x86/mm/pti.c
--- a/arch/x86/mm/pti.c~kpti-global-text-option	2018-03-21 16:32:14.312192277 -0700
+++ b/arch/x86/mm/pti.c	2018-03-21 16:32:14.316192277 -0700
@@ -66,12 +66,22 @@ static void __init pti_print_if_secure(c
 		pr_info("%s\n", reason);
 }
 
+enum pti_mode {
+	PTI_AUTO = 0,
+	PTI_FORCE_OFF,
+	PTI_FORCE_ON
+} pti_mode;
+
 void __init pti_check_boottime_disable(void)
 {
 	char arg[5];
 	int ret;
 
+	/* Assume mode is auto unless overridden. */
+	pti_mode = PTI_AUTO;
+
 	if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
+		pti_mode = PTI_FORCE_OFF;
 		pti_print_if_insecure("disabled on XEN PV.");
 		return;
 	}
@@ -79,18 +89,23 @@ void __init pti_check_boottime_disable(v
 	ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
 	if (ret > 0)  {
 		if (ret == 3 && !strncmp(arg, "off", 3)) {
+			pti_mode = PTI_FORCE_OFF;
 			pti_print_if_insecure("disabled on command line.");
 			return;
 		}
 		if (ret == 2 && !strncmp(arg, "on", 2)) {
+			pti_mode = PTI_FORCE_ON;
 			pti_print_if_secure("force enabled on command line.");
 			goto enable;
 		}
-		if (ret == 4 && !strncmp(arg, "auto", 4))
+		if (ret == 4 && !strncmp(arg, "auto", 4)) {
+			pti_mode = PTI_AUTO;
 			goto autosel;
+		}
 	}
 
 	if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+		pti_mode = PTI_FORCE_OFF;
 		pti_print_if_insecure("disabled on command line.");
 		return;
 	}
@@ -374,6 +389,23 @@ void pti_set_kernel_image_nonglobal(void
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
 
+	/*
+	 * Global pages and PCIDs are both ways to make kernel TLB
+	 * entries live longer, reduce TLB misses and improve kernel
+	 * performance.  But, leaving all kernel text Global makes
+	 * it potentially accessible to meltdown-style attacks which
+	 * make it trivial to find gadgets or defeat KASLR.
+	 *
+	 * Leave kernel text global, but only on systems that do not
+	 * have PCIDs and which have not explicitly enabled pti=on.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_PCID) &&
+	    (pti_mode == PTI_AUTO)) {
+		pr_debug("processor does not support PCIDs, leaving "
+			 "kernel image global\n");
+		return;
+	}
+
 	pr_debug("set kernel image non-global\n");
 
 	set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
_

  parent reply	other threads:[~2018-03-23 17:47 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-23 17:44 [PATCH 00/11] Use global pages with PTI Dave Hansen
2018-03-23 17:44 ` [PATCH 01/11] x86/mm: factor out pageattr _PAGE_GLOBAL setting Dave Hansen
2018-03-23 17:44 ` [PATCH 02/11] x86/mm: undo double _PAGE_PSE clearing Dave Hansen
2018-03-23 17:44 ` [PATCH 03/11] x86/mm: introduce "default" kernel PTE mask Dave Hansen
2018-03-23 17:44 ` [PATCH 04/11] x86/espfix: document use of _PAGE_GLOBAL Dave Hansen
2018-03-23 17:44 ` [PATCH 05/11] x86/mm: do not auto-massage page protections Dave Hansen
2018-03-23 19:15   ` Nadav Amit
2018-03-23 19:26     ` Dave Hansen
2018-03-23 19:34       ` Nadav Amit
2018-03-23 19:38         ` Dave Hansen
2018-03-24 15:10   ` kbuild test robot
2018-03-24 15:21   ` kbuild test robot
2018-03-23 17:44 ` [PATCH 06/11] x86/mm: remove extra filtering in pageattr code Dave Hansen
2018-03-23 17:44 ` [PATCH 07/11] x86/mm: comment _PAGE_GLOBAL mystery Dave Hansen
2018-03-23 17:44 ` [PATCH 08/11] x86/mm: do not forbid _PAGE_RW before init for __ro_after_init Dave Hansen
2018-03-23 17:45 ` [PATCH 09/11] x86/pti: enable global pages for shared areas Dave Hansen
2018-03-23 19:12   ` Nadav Amit
2018-03-23 19:36     ` Dave Hansen
2018-03-23 17:45 ` [PATCH 10/11] x86/pti: clear _PAGE_GLOBAL for kernel image Dave Hansen
2018-03-23 17:45 ` Dave Hansen [this message]
2018-03-23 18:26 ` [PATCH 00/11] Use global pages with PTI Linus Torvalds
2018-03-24  0:40   ` Dave Hansen
2018-03-24  0:46     ` Linus Torvalds
2018-03-24  0:54       ` Linus Torvalds
2018-03-24 11:05     ` Ingo Molnar
2018-03-27 13:36     ` Thomas Gleixner
2018-03-27 16:32       ` Dave Hansen
2018-03-27 17:51         ` Thomas Gleixner
2018-03-27 20:07           ` Ingo Molnar
2018-03-27 20:19             ` Dave Hansen
2018-03-29  0:17             ` Dave Hansen
2018-03-30 12:09               ` Ingo Molnar
2018-03-30 12:17                 ` Ingo Molnar
2018-03-30 20:26                   ` Dave Hansen
2018-03-30 20:32                     ` Thomas Gleixner
2018-03-30 21:40                       ` Dave Hansen
2018-03-31  5:39                         ` Ingo Molnar
2018-03-31 18:19                           ` Dave Hansen
2018-04-02 17:27 [PATCH 00/11] [v3] " Dave Hansen
2018-04-02 17:27 ` [PATCH 11/11] x86/pti: leave kernel text global for !PCID Dave Hansen
2018-04-04  1:09 [PATCH 00/11] [v4] Use global pages with PTI Dave Hansen
2018-04-04  1:10 ` [PATCH 11/11] x86/pti: leave kernel text global for !PCID Dave Hansen
2018-04-04  7:42   ` kbuild test robot
2018-04-06 20:55 [PATCH 00/11] [v5] Use global pages with PTI Dave Hansen
2018-04-06 20:55 ` [PATCH 11/11] x86/pti: leave kernel text global for !PCID Dave Hansen
2018-04-19  0:11   ` Kees Cook
2018-04-19 16:02     ` Dave Hansen
2018-04-19 16:55       ` 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=20180323174504.60B178AB@viggo.jf.intel.com \
    --to=dave.hansen@linux.intel.com \
    --cc=aarcange@redhat.com \
    --cc=hughd@google.com \
    --cc=jgross@suse.com \
    --cc=keescook@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=namit@vmware.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox