codeblog code is freedom — patching my itch

January 4, 2018

SMEP emulation in PTI

Filed under: Chrome OS,Debian,Kernel,Security,Ubuntu,Ubuntu-Server — kees @ 1:43 pm

An nice additional benefit of the recent Kernel Page Table Isolation (CONFIG_PAGE_TABLE_ISOLATION) patches (to defend against CVE-2017-5754, the speculative execution “rogue data cache load” or “Meltdown” flaw) is that the userspace page tables visible while running in kernel mode lack the executable bit. As a result, systems without the SMEP CPU feature (before Ivy-Bridge) get it emulated for “free”.

Here’s a non-SMEP system with PTI disabled (booted with “pti=off“), running the EXEC_USERSPACE LKDTM test:

# grep smep /proc/cpuinfo
# dmesg -c | grep isolation
[    0.000000] Kernel/User page tables isolation: disabled on command line.
# cat <(echo EXEC_USERSPACE) > /sys/kernel/debug/provoke-crash/DIRECT
# dmesg
[   17.883754] lkdtm: Performing direct entry EXEC_USERSPACE
[   17.885149] lkdtm: attempting ok execution at ffffffff9f6293a0
[   17.886350] lkdtm: attempting bad execution at 00007f6a2f84d000

No crash! The kernel was happily executing userspace memory.

But with PTI enabled:

# grep smep /proc/cpuinfo
# dmesg -c | grep isolation
[    0.000000] Kernel/User page tables isolation: enabled
# cat <(echo EXEC_USERSPACE) > /sys/kernel/debug/provoke-crash/DIRECT
Killed
# dmesg
[   33.657695] lkdtm: Performing direct entry EXEC_USERSPACE
[   33.658800] lkdtm: attempting ok execution at ffffffff926293a0
[   33.660110] lkdtm: attempting bad execution at 00007f7c64546000
[   33.661301] BUG: unable to handle kernel paging request at 00007f7c64546000
[   33.662554] IP: 0x7f7c64546000
...

It should only take a little more work to leave the userspace page tables entirely unmapped while in kernel mode, and only map them in during copy_to_user()/copy_from_user() as ARM already does with ARM64_SW_TTBR0_PAN (or CONFIG_CPU_SW_DOMAIN_PAN on arm32).

© 2018, Kees Cook. This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License.
Creative Commons License

3 Comments »

  1. Is KPTI something that you still see being used once Meltdown gets a hardware/microcode fix on future CPUs?
    In other words, was KPTI/KAISER something you felt was necessary even before you guys discovered Meltdown?

    Comment by ZZ — January 6, 2018 @ 4:21 pm

  2. I’m more interested in unmapping userspace while in kernel (PTI is the reverse of this), but yeah, unmapping the kernel while in userspace kills a bunch of other side-channel attacks, so I would personally continue to use it even on “fixed hardware”.

    Comment by kees — January 27, 2018 @ 2:48 am

  3. Hello. Mr Cook I would like to ask a questions about PTI for ix86/x86_32 architecture: are there any plans to backport this feature? I know, that Developers (OpenSUSE and so on) are working on this etc. (see 1.) So, if everything will be okay, ‘Kernel Page Table Isolation’ should be available on 32. bit systems also, right?

    Thanks, best regards.
    _____________________
    1. http://lkml.iu.edu/hypermail/linux/kernel/1802.1/00925.html

    Comment by kurdt — March 4, 2018 @ 11:08 am

Leave a Reply

Your email address will not be published. Required fields are marked *

Powered by WordPress