[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190108185751.GB1900@hirez.programming.kicks-ass.net>
Date: Tue, 8 Jan 2019 19:57:51 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Andi Kleen <ak@...ux.intel.com>
Cc: Adrian Hunter <adrian.hunter@...el.com>,
Nadav Amit <namit@...are.com>, Ingo Molnar <mingo@...hat.com>,
Andy Lutomirski <luto@...nel.org>,
Josh Poimboeuf <jpoimboe@...hat.com>,
Edward Cree <ecree@...arflare.com>,
"H . Peter Anvin" <hpa@...or.com>,
Thomas Gleixner <tglx@...utronix.de>,
LKML <linux-kernel@...r.kernel.org>,
Nadav Amit <nadav.amit@...il.com>, X86 ML <x86@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Borislav Petkov <bp@...en8.de>,
David Woodhouse <dwmw@...zon.co.uk>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
songliubraving@...com
Subject: Re: [RFC v2 0/6] x86: dynamic indirect branch promotion
On Tue, Jan 08, 2019 at 09:27:21AM -0800, Andi Kleen wrote:
> It doesn't work when the code is modified in place, like the
> patch in the $SUBJECT.
For in-place modification a-la jump_label / static_call etc. we can
'trivially' log the new instruction and the decoder can do matching
in-place kcore adjustments.
Powered by blists - more mailing lists