From: Andy Lutomirski <luto@amacapital.net>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Paul Mackerras <paulus@samba.org>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Ingo Molnar <mingo@redhat.com>, Kees Cook <keescook@chromium.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Erik Bosman <ebn310@few.vu.nl>,
Andy Lutomirski <luto@amacapital.net>
Subject: [RFC 0/5] CR4 handling improvements
Date: Tue, 14 Oct 2014 15:57:34 -0700 [thread overview]
Message-ID: <cover.1413323611.git.luto@amacapital.net> (raw)
Hi Peter, etc,
This little series tightens up rdpmc permissions. With it applied,
rdpmc can only be used if a perf_event is actually mmapped. For now,
this is only really useful for seccomp.
At some point this could be further tightened up to only allow rdpmc
if an actual self-monitoring perf event that is compatible with
rdpmc is mapped. (Is the current code there even correct? What
happens if you set up a perf counter targetting a different pid and
then try to rdpmc it? Do you end up reading the right value or does
perf event context switching mess you up?)
This should add <50ns to context switches between rdpmc-capable and
rdpmc-non-capable mms. I suspect that this is well under 10%
overhead, given that perf already adds some context switch latency.
If needed, we could add a global switch that turns this behavior
off. We could also rehink the logic.
I think that patches 1-3 are a good idea regardless of any rdpmc changes.
(Please don't apply quite yet, because there'll be a merge conflict
with some changes that haven't landed yet. This is against 3.17.)
Andy Lutomirski (5):
x86: Clean up cr4 manipulation
x86: Store a per-cpu shadow copy of CR4
x86: Add a comment clarifying LDT context switching
perf: Add pmu callbacks to track event mapping and unmapping
x86,perf: Only allow rdpmc if a perf_event is mapped
arch/x86/include/asm/mmu.h | 2 +
arch/x86/include/asm/mmu_context.h | 30 +++++++++++++-
arch/x86/include/asm/processor.h | 33 ----------------
arch/x86/include/asm/tlbflush.h | 77 ++++++++++++++++++++++++++++++++----
arch/x86/include/asm/virtext.h | 3 +-
arch/x86/kernel/cpu/common.c | 17 +++++---
arch/x86/kernel/cpu/mcheck/mce.c | 3 +-
arch/x86/kernel/cpu/mcheck/p5.c | 3 +-
arch/x86/kernel/cpu/mcheck/winchip.c | 3 +-
arch/x86/kernel/cpu/perf_event.c | 61 +++++++++++++++++++++-------
arch/x86/kernel/head32.c | 1 +
arch/x86/kernel/head64.c | 2 +
arch/x86/kernel/i387.c | 3 +-
arch/x86/kernel/process.c | 5 ++-
arch/x86/kernel/xsave.c | 3 +-
arch/x86/kvm/vmx.c | 8 ++--
arch/x86/mm/init.c | 12 +++++-
arch/x86/mm/tlb.c | 3 --
arch/x86/xen/enlighten.c | 4 +-
include/linux/perf_event.h | 7 ++++
kernel/events/core.c | 9 +++++
21 files changed, 210 insertions(+), 79 deletions(-)
--
1.9.3
next reply other threads:[~2014-10-14 22:57 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-14 22:57 Andy Lutomirski [this message]
2014-10-14 22:57 ` [RFC 1/5] x86: Clean up cr4 manipulation Andy Lutomirski
2014-10-16 8:16 ` Peter Zijlstra
2014-10-16 11:18 ` Borislav Petkov
2014-10-16 11:29 ` Borislav Petkov
2014-10-16 15:32 ` Andy Lutomirski
2014-10-16 15:47 ` Borislav Petkov
2014-10-14 22:57 ` [RFC 2/5] x86: Store a per-cpu shadow copy of CR4 Andy Lutomirski
2014-10-16 8:26 ` Peter Zijlstra
2014-10-16 11:49 ` Borislav Petkov
2014-10-16 15:30 ` Andy Lutomirski
2014-10-14 22:57 ` [RFC 3/5] x86: Add a comment clarifying LDT context switching Andy Lutomirski
2014-10-16 15:49 ` Borislav Petkov
2014-10-16 16:21 ` Andy Lutomirski
2014-10-21 5:41 ` Borislav Petkov
2014-10-21 5:44 ` Andy Lutomirski
2014-10-21 6:05 ` Borislav Petkov
2014-10-14 22:57 ` [RFC 4/5] perf: Add pmu callbacks to track event mapping and unmapping Andy Lutomirski
2014-10-14 22:57 ` [RFC 5/5] x86,perf: Only allow rdpmc if a perf_event is mapped Andy Lutomirski
2014-10-16 8:42 ` Peter Zijlstra
2014-10-16 15:37 ` Andy Lutomirski
2014-10-16 15:57 ` Borislav Petkov
2014-10-17 0:00 ` Andy Lutomirski
2014-10-19 20:23 ` Andy Lutomirski
2014-10-19 21:33 ` Peter Zijlstra
2014-10-19 22:05 ` Andy Lutomirski
2014-10-19 22:20 ` Peter Zijlstra
2014-10-19 22:57 ` Andy Lutomirski
2014-10-20 8:33 ` Peter Zijlstra
2014-10-20 16:49 ` Andy Lutomirski
2014-10-20 17:39 ` Andy Lutomirski
2014-10-21 8:59 ` Peter Zijlstra
2014-10-19 21:35 ` Peter Zijlstra
2014-10-20 0:08 ` Andy Lutomirski
2014-10-20 8:48 ` Peter Zijlstra
2014-10-20 9:24 ` Martin Schwidefsky
2014-10-20 10:51 ` Hendrik Brueckner
2014-10-21 9:14 ` Peter Zijlstra
2014-10-21 15:52 ` Andy Lutomirski
2014-10-21 4:06 ` [RFC 0/5] CR4 handling improvements Vince Weaver
2014-10-21 4:28 ` Andy Lutomirski
2014-10-21 15:00 ` Vince Weaver
2014-10-21 16:04 ` Peter Zijlstra
2014-10-21 17:05 ` Vince Weaver
2014-10-23 11:42 ` Peter Zijlstra
2014-10-24 12:41 ` Vince Weaver
2014-10-24 22:14 ` Andy Lutomirski
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=cover.1413323611.git.luto@amacapital.net \
--to=luto@amacapital.net \
--cc=Valdis.Kletnieks@vt.edu \
--cc=aarcange@redhat.com \
--cc=acme@kernel.org \
--cc=ebn310@few.vu.nl \
--cc=keescook@chromium.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=paulus@samba.org \
--cc=peterz@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
Powered by JetHome