From: Andi Kleen <andi@firstfloor.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Andi Kleen <andi@firstfloor.org>,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@elte.hu>,
Andrew Morton <akpm@linux-foundation.org>,
Thomas Gleixner <tglx@linutronix.de>,
Peter Zijlstra <peterz@infradead.org>,
Frederic Weisbecker <fweisbec@gmail.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Arjan van de Ven <arjan@infradead.org>,
Rusty Russell <rusty@rustcorp.com.au>,
Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>,
"H. Peter Anvin" <hpa@zytor.com>,
Steven Rostedt <srostedt@redhat.com>
Subject: Re: [PATCH 4/6] ftrace, x86: make kernel text writable only for conversions
Date: Mon, 23 Feb 2009 01:29:18 +0100 [thread overview]
Message-ID: <20090223002918.GQ26292@one.firstfloor.org> (raw)
In-Reply-To: <alpine.DEB.2.00.0902221741040.18221@gandalf.stny.rr.com>
> We are changing over 19000 locations in the kernel. This touches almost
> all kernel text pages anyway. You want to map a page in and out for over
> 19000 locations?
Well kernel size / PAGE_SIZE times if you sort locations first and
take a last-hit cache. Or if you want to overoptimize you can
also use 2MB pages when available. Also it can be done much cheaper
than a full flush because it doesn't need to be global over all CPUs
(assuming you disable preempt, which you probably do anyways)
And it can use INVLPG on x86 (or similar directed flushed)
which is much much cheaper than blowing everything away.
I'm not sure which one would be faster, but I suspect the difference
will not be very large. And not changing the kernel has the
advantage that there is no window where it is unprotected.
-Andi
--
ak@linux.intel.com -- Speaking for myself only.
next prev parent reply other threads:[~2009-02-23 0:11 UTC|newest]
Thread overview: 89+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-02-20 1:13 [git pull] changes for tip, and a nasty x86 page table bug Steven Rostedt
2009-02-20 1:13 ` [PATCH 1/6] x86: check PMD in spurious_fault handler Steven Rostedt
2009-02-20 1:13 ` [PATCH 2/6] x86: keep pmd rw bit set when creating 4K level pages Steven Rostedt
2009-02-20 1:13 ` [PATCH 3/6] ftrace: allow archs to preform pre and post process for code modification Steven Rostedt
2009-02-20 1:13 ` [PATCH 4/6] ftrace, x86: make kernel text writable only for conversions Steven Rostedt
2009-02-20 1:32 ` Andrew Morton
2009-02-20 1:44 ` Steven Rostedt
2009-02-20 2:05 ` [PATCH][git pull] update to tip/tracing/ftrace Steven Rostedt
2009-02-22 17:50 ` [PATCH 4/6] ftrace, x86: make kernel text writable only for conversions Andi Kleen
2009-02-22 22:53 ` Steven Rostedt
2009-02-23 0:29 ` Andi Kleen [this message]
2009-02-23 2:33 ` Mathieu Desnoyers
2009-02-23 4:29 ` Steven Rostedt
2009-02-23 4:53 ` Mathieu Desnoyers
2009-02-23 14:48 ` Steven Rostedt
2009-02-23 15:42 ` Mathieu Desnoyers
2009-02-23 15:51 ` Steven Rostedt
2009-02-23 15:55 ` Steven Rostedt
2009-02-23 16:13 ` Mathieu Desnoyers
2009-02-23 16:48 ` Steven Rostedt
2009-02-23 17:31 ` Mathieu Desnoyers
2009-02-23 18:17 ` Steven Rostedt
2009-02-23 18:34 ` Mathieu Desnoyers
2009-02-27 17:52 ` Masami Hiramatsu
2009-02-27 18:07 ` Mathieu Desnoyers
2009-02-27 18:34 ` Masami Hiramatsu
2009-02-27 18:53 ` Mathieu Desnoyers
2009-02-27 20:57 ` Masami Hiramatsu
2009-03-02 17:01 ` [RFC][PATCH] x86: make text_poke() atomic Masami Hiramatsu
2009-03-02 17:19 ` Mathieu Desnoyers
2009-03-02 22:15 ` Masami Hiramatsu
2009-03-02 22:22 ` Ingo Molnar
2009-03-02 22:55 ` Masami Hiramatsu
2009-03-02 23:09 ` Ingo Molnar
2009-03-02 23:38 ` Masami Hiramatsu
2009-03-02 23:49 ` Ingo Molnar
2009-03-03 0:00 ` Mathieu Desnoyers
2009-03-03 0:00 ` [PATCH] Text Edit Lock - Architecture Independent Code Mathieu Desnoyers
2009-03-03 0:32 ` Ingo Molnar
2009-03-03 0:39 ` Mathieu Desnoyers
2009-03-03 1:30 ` [PATCH] Text Edit Lock - Architecture Independent Code (v2) Mathieu Desnoyers
2009-03-03 1:31 ` [PATCH] Text Edit Lock - kprobes architecture independent support (v2) Mathieu Desnoyers
2009-03-03 9:27 ` Ingo Molnar
2009-03-03 12:06 ` Ananth N Mavinakayanahalli
2009-03-03 14:28 ` Mathieu Desnoyers
2009-03-03 14:33 ` [PATCH] Text Edit Lock - kprobes architecture independent support (v3) Mathieu Desnoyers
2009-03-03 14:53 ` [PATCH] Text Edit Lock - kprobes architecture independent support (v2) Ingo Molnar
2009-03-03 0:01 ` [PATCH] Text Edit Lock - kprobes architecture independent support Mathieu Desnoyers
2009-03-03 0:10 ` Masami Hiramatsu
2009-03-03 0:05 ` [RFC][PATCH] x86: make text_poke() atomic Masami Hiramatsu
2009-03-03 0:22 ` Ingo Molnar
2009-03-03 0:31 ` Masami Hiramatsu
2009-03-03 16:31 ` [PATCH] x86: make text_poke() atomic using fixmap Masami Hiramatsu
2009-03-03 17:08 ` Mathieu Desnoyers
2009-03-05 10:38 ` Ingo Molnar
2009-03-06 14:06 ` Ingo Molnar
2009-03-06 14:49 ` Masami Hiramatsu
2009-03-02 18:28 ` [RFC][PATCH] x86: make text_poke() atomic Arjan van de Ven
2009-03-02 18:36 ` Mathieu Desnoyers
2009-03-02 18:55 ` Arjan van de Ven
2009-03-02 19:13 ` Masami Hiramatsu
2009-03-02 19:23 ` H. Peter Anvin
2009-03-02 19:47 ` Mathieu Desnoyers
2009-03-02 18:42 ` Linus Torvalds
2009-03-03 4:54 ` Nick Piggin
2009-02-23 18:23 ` [PATCH 4/6] ftrace, x86: make kernel text writable only for conversions Steven Rostedt
2009-02-23 9:02 ` Ingo Molnar
2009-02-27 21:08 ` Pavel Machek
2009-02-28 16:56 ` Andi Kleen
2009-02-28 22:08 ` Pavel Machek
[not found] ` <87wsba1a9f.fsf@basil.nowhere.org>
2009-02-28 22:19 ` Pavel Machek
2009-02-28 23:52 ` Andi Kleen
2009-02-20 1:13 ` [PATCH 5/6] ftrace: immediately stop code modification if failure is detected Steven Rostedt
2009-02-20 1:13 ` [PATCH 6/6] ftrace: break out modify loop immediately on detection of error Steven Rostedt
2009-02-20 2:00 ` [git pull] changes for tip, and a nasty x86 page table bug Linus Torvalds
2009-02-20 2:08 ` Steven Rostedt
2009-02-20 3:44 ` Linus Torvalds
2009-02-20 4:00 ` Steven Rostedt
2009-02-20 4:17 ` Linus Torvalds
2009-02-20 4:34 ` Steven Rostedt
2009-02-20 5:02 ` Huang Ying
2009-02-20 7:29 ` [PATCH] x86: use the right protections for split-up pagetables Ingo Molnar
2009-02-20 7:39 ` [PATCH, v2] " Ingo Molnar
2009-02-20 8:02 ` Ingo Molnar
2009-02-20 10:24 ` Ingo Molnar
2009-02-20 13:57 ` [PATCH] " Steven Rostedt
2009-02-20 15:40 ` Linus Torvalds
2009-02-20 16:59 ` Ingo Molnar
2009-02-20 18:33 ` H. Peter Anvin
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=20090223002918.GQ26292@one.firstfloor.org \
--to=andi@firstfloor.org \
--cc=akpm@linux-foundation.org \
--cc=arjan@infradead.org \
--cc=fweisbec@gmail.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@polymtl.ca \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=rusty@rustcorp.com.au \
--cc=srostedt@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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).