From: "Chang S. Bae" <chang.seok.bae@intel.com>
To: Ingo Molnar <mingo@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Andy Lutomirski <luto@kernel.org>,
"H . Peter Anvin" <hpa@zytor.com>
Cc: Andi Kleen <ak@linux.intel.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
Markus T Metzger <markus.t.metzger@intel.com>,
Ravi Shankar <ravi.v.shankar@intel.com>,
"Chang S . Bae" <chang.seok.bae@intel.com>,
LKML <linux-kernel@vger.kernel.org>
Subject: [v3 00/12] x86: Enable FSGSBASE instructions
Date: Tue, 23 Oct 2018 11:42:22 -0700 [thread overview]
Message-ID: <20181023184234.14025-1-chang.seok.bae@intel.com> (raw)
FSGSBASE is a 64-bit instruction set to allow read/write FS/GSBASE from
any privileges. Since introduced in Ivybridge, enabling efforts has been
revolving in a quite long period of time, for various reasons [2,3,4].
After the extended discussions [1], the new ABIs are finally introduced to
customize FS/GSBASE separately from the selector.
Benefits:
Some performance benefit in context switch is expected by skipping MSR
write for GSBASE. User-level programs (such as JAVA-based) may benefit
from avoiding system calls to edit FS/GSBASE.
Major changes in the kernel:
* In a context switch, a thread's FS/GSBASE will be secured regardless of
its selector, base on the discussion [1].
* (Subsequently) ptracer should expect a divergence of FS/GS index and
base values. There was a controversial debate on the concerns for a
backward compatibility (mostly for GDB. [7,8]). We finally concluded it is
insignificant in real usages.
* On the paranoid_entry, GSBASE is updated to point the per_CPU base and
the original GSBASE is restored at the exit.
Virtualization:
A FSGSBASE-enabled VM can be located on a host either with HW
virtualization or with SW emulation. KVM advertises FSGSBASE when
physical CPU has. The emulation is supported in QEMU/TCG [5]. In a pool of
the mixed systems, VMM may disable FSGSBASE for seamless VM migrations [6].
Update from v2 [10]:
* Separate out the preparatory patches [11] (now merged to the tip)
* Bisect the paranoid_entry update patch
* Edit minor nits
Updates from v1 [9]:
* Update the GSBASE update mechanism on the paranoid entry/exit.
* Exclude ptracer backward compatibility patches.
* Include FSGSBASE documentation and enumerating capability
for user space
* Add the TAINT_INSECURE flag.
[1] Recent discussion on LKML:
https://marc.info/?t=150147053700001&r=1&w=2
[2] Andy Lutomirski’s patchwork work :
https://git.kernel.org/pub/scm/linux/kernel/git/luto/linux.git/log/?h=x86/fsgsbase
[3] Patchset shown in 2016:
https://lore.kernel.org/patchwork/patch/660520
[4] Patchset shown in 2014:
https://lore.kernel.org/patchwork/patch/460288
[5] QEMU with FSGSBASE emulation:
https://github.com/qemu/qemu/blob/026aaf47c02b79036feb830206cfebb2a726510d/target/i386/translate.c#L8186
[6] 5-level EPT:
http://lkml.kernel.org/r/9ddf602b-6c8b-8c1e-ab46-07ed12366593@redhat.com
[7] RR/FSGSBASE:
https://mail.mozilla.org/pipermail/rr-dev/2018-March/000616.html
[8] CRIU/FSGSBASE:
https://lists.openvz.org/pipermail/criu/2018-March/040654.html
[9] Version 1:
https://lore.kernel.org/patchwork/cover/934843
[10] Version 2:
https://lore.kernel.org/patchwork/cover/912063
[11] x86: infra to enable FSGSBASE
https://lore.kernel.org/patchwork/cover/988180
Andi Kleen (3):
x86/fsgsbase/64: Add intrinsics/macros for FSGSBASE instructions
x86/elf: Enumerate kernel FSGSBASE capability in AT_HWCAP2
x86/fsgsbase/64: Add documentation for FSGSBASE
Andy Lutomirski (4):
x86/fsgsbase/64: Add 'unsafe_fsgsbase' to enable CR4.FSGSBASE
x86/fsgsbase/64: Preserve FS/GS state in __switch_to() if FSGSBASE is
on
selftests/x86/fsgsbase: Test WRGSBASE
x86/fsgsbase/64: Enable FSGSBASE by default and add a chicken bit
Chang S. Bae (5):
taint: Introduce a new taint flag (insecure)
x86/fsgsbase/64: Enable FSGSBASE instructions in the helper functions
x86/fsgsbase/64: When copying a thread, use the FSGSBASE instructions
if available
x86/fsgsbase/64: Introduce the new FIND_PERCPU_BASE macro
x86/fsgsbase/64: Use the per-CPU base as GSBASE at the paranoid_entry
.../admin-guide/kernel-parameters.txt | 2 +
Documentation/sysctl/kernel.txt | 1 +
Documentation/x86/fsgs.txt | 104 +++++++++++++
arch/x86/entry/entry_64.S | 73 +++++++--
arch/x86/include/asm/fsgsbase.h | 140 +++++++++++++++++-
arch/x86/include/asm/inst.h | 15 ++
arch/x86/include/uapi/asm/hwcap2.h | 3 +
arch/x86/kernel/cpu/common.c | 22 +++
arch/x86/kernel/process_64.c | 128 +++++++++++++---
include/linux/kernel.h | 3 +-
kernel/panic.c | 1 +
tools/testing/selftests/x86/fsgsbase.c | 110 +++++++++++++-
12 files changed, 556 insertions(+), 46 deletions(-)
create mode 100644 Documentation/x86/fsgs.txt
--
2.19.1
next reply other threads:[~2018-10-23 18:43 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-23 18:42 Chang S. Bae [this message]
2018-10-23 18:42 ` [v3 01/12] taint: Introduce a new taint flag (insecure) Chang S. Bae
2018-10-24 18:50 ` Andy Lutomirski
2018-10-23 18:42 ` [v3 02/12] x86/fsgsbase/64: Add 'unsafe_fsgsbase' to enable CR4.FSGSBASE Chang S. Bae
2018-10-24 18:51 ` Andy Lutomirski
2018-10-23 18:42 ` [v3 03/12] x86/fsgsbase/64: Add intrinsics/macros for FSGSBASE instructions Chang S. Bae
2018-10-24 18:53 ` Andy Lutomirski
2018-10-24 19:21 ` Andi Kleen
2018-10-25 23:14 ` Andy Lutomirski
2018-10-25 23:31 ` Linus Torvalds
2018-10-26 0:09 ` Andy Lutomirski
2018-10-23 18:42 ` [v3 04/12] x86/fsgsbase/64: Enable FSGSBASE instructions in the helper functions Chang S. Bae
2018-10-24 19:16 ` Andy Lutomirski
2018-10-24 19:41 ` [Xen-devel] " Andrew Cooper
2018-10-25 6:09 ` Juergen Gross
2018-10-25 23:08 ` Andrew Cooper
2018-10-25 23:11 ` Andy Lutomirski
2018-10-25 23:14 ` Andrew Cooper
2018-10-25 7:32 ` Bae, Chang Seok
2018-10-25 23:00 ` Andy Lutomirski
2018-10-25 23:03 ` Bae, Chang Seok
2018-10-25 23:16 ` Andy Lutomirski
2018-10-23 18:42 ` [v3 05/12] x86/fsgsbase/64: Preserve FS/GS state in __switch_to() if FSGSBASE is on Chang S. Bae
2018-10-24 19:21 ` Andy Lutomirski
2018-10-24 19:36 ` Bae, Chang Seok
2018-10-23 18:42 ` [v3 06/12] x86/fsgsbase/64: When copying a thread, use the FSGSBASE instructions if available Chang S. Bae
2018-10-23 18:42 ` [v3 07/12] x86/fsgsbase/64: Introduce the new FIND_PERCPU_BASE macro Chang S. Bae
2018-10-26 0:25 ` Andy Lutomirski
2018-10-26 0:59 ` Nadav Amit
2018-10-23 18:42 ` [v3 08/12] x86/fsgsbase/64: Use the per-CPU base as GSBASE at the paranoid_entry Chang S. Bae
2018-10-23 18:42 ` [v3 09/12] selftests/x86/fsgsbase: Test WRGSBASE Chang S. Bae
2018-10-23 18:42 ` [v3 10/12] x86/fsgsbase/64: Enable FSGSBASE by default and add a chicken bit Chang S. Bae
2018-10-23 18:42 ` [v3 11/12] x86/elf: Enumerate kernel FSGSBASE capability in AT_HWCAP2 Chang S. Bae
2018-10-23 18:42 ` [v3 12/12] x86/fsgsbase/64: Add documentation for FSGSBASE Chang S. Bae
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=20181023184234.14025-1-chang.seok.bae@intel.com \
--to=chang.seok.bae@intel.com \
--cc=ak@linux.intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=markus.t.metzger@intel.com \
--cc=mingo@kernel.org \
--cc=ravi.v.shankar@intel.com \
--cc=tglx@linutronix.de \
/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).