Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 7 Jan 2019 17:32:27 +0100
From:   Peter Zijlstra <peterz@infradead.org>
To:     Andi Kleen <ak@linux.intel.com>
Cc:     Nadav Amit <namit@vmware.com>, Ingo Molnar <mingo@redhat.com>,
        Andy Lutomirski <luto@kernel.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        Edward Cree <ecree@solarflare.com>,
        "H . Peter Anvin" <hpa@zytor.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        LKML <linux-kernel@vger.kernel.org>,
        Nadav Amit <nadav.amit@gmail.com>, X86 ML <x86@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Borislav Petkov <bp@alien8.de>,
        David Woodhouse <dwmw@amazon.co.uk>, adrian.hunter@intel.com,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>
Subject: Re: [RFC v2 0/6] x86: dynamic indirect branch promotion
Message-ID: <20190107163227.GH14122@hirez.programming.kicks-ass.net>
References: <20181231072112.21051-1-namit@vmware.com>
 <87zhshe66w.fsf@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <87zhshe66w.fsf@linux.intel.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, Jan 03, 2019 at 02:18:15PM -0800, Andi Kleen wrote:
> Nadav Amit <namit@vmware.com> writes:
> >
> > - Do we use periodic learning or not? Josh suggested to reconfigure the
> >   branches whenever a new target is found. However, I do not know at
> >   this time how to do learning efficiently, without making learning much
> >   more expensive.
> 
> FWIW frequent patching will likely completely break perf Processor Trace
> decoding, which needs a somewhat stable kernel text image to decode the
> traces generated by the CPU. Right now it relies on kcore dumped after
> the trace usually being stable because jumplabel changes happen only
> infrequently. But if you start patching frequently this assumption will
> break.
> 
> You would either need a way to turn this off, or provide
> updates for every change to the trace, so that the decoder can
> keep track.

I'm thining it would be entirely possible to create and feed text_poke
events into the regular (!aux) buffer which can be timestamp correlated
to the PT data.