From: will.deacon@arm.com (Will Deacon)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 00/11] arm64 kpti hardening and variant 2 workarounds
Date: Thu, 4 Jan 2018 15:08:24 +0000 [thread overview]
Message-ID: <1515078515-13723-1-git-send-email-will.deacon@arm.com> (raw)
Hi all,
This set of patches builds on top of the arm64 kpti patches[1] queued for
4.16 and further hardens the arm64 Linux kernel against the side-channel
attacks recently published by Google Project Zero.
In particular, the series does the following:
* Enable kpti by default on arm64, based on the value of ID_AA64PFR0_EL1.CSV3
* Prevent speculative resteering of the indirect branch in the exception
trampoline page, which resides at a fixed virtual address to avoid a
KASLR leak
* Add hooks to changes of context where the branch predictor could
theoretically resteer the speculative instruction stream having been trained
by userspace or a guest OS. These hooks are signal delivery (to prevent
training the branch predictor on kernel addresses from userspace),
switch_mm (return to user if SW PAN is enabled) and exit from a guest VM.
* Implement a dummy PSCI "VERSION" call as the hook for affected Cortex-A
CPUs. This will invalidate the predictor state with the latest Arm Trusted
Firmware patches which will appear at [2] and SoC vendors with affected
CPUs are strongly encouraged to update. We plan to switch to a more
efficient, special-purpose call when it is available and the PSCI spec
has been updated accordingly.
I'd like to get this in for 4.16, but that doesn't mean we can't improve
it further once it's merged.
For more information about the impact of this issue and the software migitations
for Arm processors, please see http://www.arm.com/security-update.
Thanks,
Will
[1] https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git/tag/?h=kpti-base
[2] https://github.com/ARM-software/arm-trusted-firmware/wiki/ARM-Trusted-Firmware-Security-Advisory-TFV-6
--->8
Marc Zyngier (3):
arm64: Move post_ttbr_update_workaround to C code
arm64: KVM: Use per-CPU vector when BP hardening is enabled
arm64: KVM: Make PSCI_VERSION a fast path
Will Deacon (8):
arm64: use RET instruction for exiting the trampoline
arm64: Kconfig: Reword UNMAP_KERNEL_AT_EL0 kconfig entry
arm64: Take into account ID_AA64PFR0_EL1.CSV3
arm64: cpufeature: Pass capability structure to ->enable callback
drivers/firmware: Expose psci_get_version through psci_ops structure
arm64: Add skeleton to harden the branch predictor against aliasing
attacks
arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75
arm64: Implement branch predictor hardening for affected Cortex-A CPUs
arch/arm/include/asm/kvm_mmu.h | 10 ++++
arch/arm64/Kconfig | 30 +++++++---
arch/arm64/include/asm/assembler.h | 13 -----
arch/arm64/include/asm/cpucaps.h | 3 +-
arch/arm64/include/asm/cputype.h | 4 ++
arch/arm64/include/asm/kvm_mmu.h | 38 ++++++++++++
arch/arm64/include/asm/mmu.h | 37 ++++++++++++
arch/arm64/include/asm/sysreg.h | 2 +
arch/arm64/kernel/Makefile | 4 ++
arch/arm64/kernel/bpi.S | 79 +++++++++++++++++++++++++
arch/arm64/kernel/cpu_errata.c | 116 +++++++++++++++++++++++++++++++++++++
arch/arm64/kernel/cpufeature.c | 12 +++-
arch/arm64/kernel/entry.S | 7 ++-
arch/arm64/kvm/hyp/switch.c | 15 ++++-
arch/arm64/mm/context.c | 11 ++++
arch/arm64/mm/fault.c | 1 +
arch/arm64/mm/proc.S | 3 +-
drivers/firmware/psci.c | 2 +
include/linux/psci.h | 1 +
virt/kvm/arm/arm.c | 8 ++-
20 files changed, 366 insertions(+), 30 deletions(-)
create mode 100644 arch/arm64/kernel/bpi.S
--
2.1.4
next reply other threads:[~2018-01-04 15:08 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-04 15:08 Will Deacon [this message]
2018-01-04 15:08 ` [PATCH 01/11] arm64: use RET instruction for exiting the trampoline Will Deacon
2018-01-04 16:24 ` Ard Biesheuvel
2018-01-04 18:31 ` Will Deacon
2018-01-04 18:35 ` Ard Biesheuvel
2018-01-04 15:08 ` [PATCH 02/11] arm64: Kconfig: Reword UNMAP_KERNEL_AT_EL0 kconfig entry Will Deacon
2018-01-04 15:39 ` Christoph Hellwig
2018-01-04 15:08 ` [PATCH 03/11] arm64: Take into account ID_AA64PFR0_EL1.CSV3 Will Deacon
2018-01-04 23:15 ` Laura Abbott
2018-01-05 10:24 ` Suzuki K Poulose
2018-01-04 15:08 ` [PATCH 04/11] arm64: cpufeature: Pass capability structure to ->enable callback Will Deacon
2018-01-05 10:29 ` Suzuki K Poulose
2018-01-04 15:08 ` [PATCH 05/11] drivers/firmware: Expose psci_get_version through psci_ops structure Will Deacon
2018-01-04 16:10 ` Lorenzo Pieralisi
2018-01-04 15:08 ` [PATCH 06/11] arm64: Move post_ttbr_update_workaround to C code Will Deacon
2018-01-04 16:25 ` Ard Biesheuvel
2018-01-04 15:08 ` [PATCH 07/11] arm64: Add skeleton to harden the branch predictor against aliasing attacks Will Deacon
2018-01-04 15:08 ` [PATCH 08/11] arm64: KVM: Use per-CPU vector when BP hardening is enabled Will Deacon
2018-01-04 16:28 ` Ard Biesheuvel
2018-01-04 17:04 ` Marc Zyngier
2018-01-04 17:05 ` Ard Biesheuvel
2018-01-04 15:08 ` [PATCH 09/11] arm64: KVM: Make PSCI_VERSION a fast path Will Deacon
2018-01-04 15:08 ` [PATCH 10/11] arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75 Will Deacon
2018-01-04 15:08 ` [PATCH 11/11] arm64: Implement branch predictor hardening for affected Cortex-A CPUs Will Deacon
2018-01-04 16:31 ` Ard Biesheuvel
2018-01-04 17:14 ` Marc Zyngier
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=1515078515-13723-1-git-send-email-will.deacon@arm.com \
--to=will.deacon@arm.com \
--cc=linux-arm-kernel@lists.infradead.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).