From: Thomas Gleixner <tglx@linutronix.de>
To: speck@linutronix.de
Subject: L!TF Bulletin #6: The vacation brain edition
Date: Fri, 20 Jul 2018 22:47:14 +0200 (CEST) [thread overview]
Message-ID: <alpine.DEB.2.21.1807202158270.1694@nanos.tec.linutronix.de> (raw)
[-- Attachment #1: Type: text/plain, Size: 2242 bytes --]
Hi!
I'm going to take a one week break to regain some mental sanity as I'm
running on emergency fuel way too long already.
The current state of affairs is attached as git bundle, which would be the
pile to pull from in case the embargo breaks unexpectedly next week. The
stable branches (4.17,16,14) in the sekrit repository contain the same pile
of changes.
The bundle contains:
- Host side L1TF mitigation: Page Table Inversion for non present PTEs on
all levels. This makes sure that non-present PTEs point to non-existing
or non-cachable areas.
- A sysfs interface for exposing the L1TF mitigation state of the kernel
including VMX.
- A sysfs interface to control and query SMT state. Allows to offline all
"secondary" hyperthreads so that only one thread per physical core
stays online. Turning it back on, re-onlines the offline hyper threads
again.
- Command line interface for controlling SMT state at boot time.
- VMX support for fluhsing L1D before VMENTER either via a software
algorithm or via the new MSR if updated microcode provides it.
- Command line/module parameter to control L1D flush before VMENTER at
module init and at run time.
- Command line option to select the mitigation state for VMX via
combinations of L1D flush methods and SMT control.
- Comprehensive documentation of the issue, affected processors,
mitigation methods, their limitations and the control interfaces.
What's outstanding at moment are the optimizations for nested VMs, but as
these are optimizations they are not super urgent right now. Let's hope
everything works out according to embargo plan, so we have enough time to
hash out the extra bells and whistles.
Aside of that the promised 4.9 backport has not materialized yet, but
that's the least of _my_ worries as I'm not a member of the kernel
necrophilia cult.
If urgent fixes need to be applied, Peter Zijlstra and Ingo Molnar have
write access to the repository.
If there are any issues with the mailing list(s), please contact:
Anna-Maria Gleixner <anna-maria@linutronix.de>
and
Sebastian Siewior <bigeasy@linutronix.de>
They can add/change subscribers as well.
Talk to you soon again!
Thanks,
Thomas
[-- Attachment #2: Type: application/octet-stream, Size: 84880 bytes --]
next reply other threads:[~2018-07-20 20:47 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-20 20:47 Thomas Gleixner [this message]
2018-07-20 21:21 ` [MODERATED] Re: L!TF Bulletin #6: The vacation brain edition Konrad Rzeszutek Wilk
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=alpine.DEB.2.21.1807202158270.1694@nanos.tec.linutronix.de \
--to=tglx@linutronix.de \
--cc=speck@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 read-only IMAP folder(s) and NNTP newsgroup(s).