Date: Thu, 23 Jul 2015 13:18:40 -0400
From: Steven Rostedt <rostedt@goodmis.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Jason Baron <jasonbaron0@gmail.com>, Borislav Petkov <bp@alien8.de>,
        Andy Lutomirski <luto@amacapital.net>,
        Thomas Gleixner <tglx@linutronix.de>,
        Mikulas Patocka <mpatocka@redhat.com>,
        Paul Mackerras <paulus@samba.org>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Kees Cook <keescook@chromium.org>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Vince Weaver <vince@deater.net>, "hillf.zj" <hillf.zj@alibaba-inc.com>,
        Valdis Kletnieks <Valdis.Kletnieks@vt.edu>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: Kernel broken on processors without performance counters
Message-ID: <20150723131840.2a6691f4@gandalf.local.home>
In-Reply-To: <20150723170811.GJ25159@twins.programming.kicks-ass.net>
References: <alpine.DEB.2.11.1507211726040.18576@nanos>
	<20150721154959.GS19282@twins.programming.kicks-ass.net>
	<CALCETrWwy777nYTVpOn8Hs1JRG5nDyvky9B11otDRAid1L19vg@mail.gmail.com>
	<20150721161215.GU19282@twins.programming.kicks-ass.net>
	<20150721181553.GA3378@nazgul.tnic>
	<55AE9471.1000601@gmail.com>
	<20150722042403.GA6345@nazgul.tnic>
	<55AFCDA4.5010406@gmail.com>
	<20150723104215.GH25159@twins.programming.kicks-ass.net>
	<20150723113450.67db0152@gandalf.local.home>
	<20150723170811.GJ25159@twins.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1701
Lines: 42

On Thu, 23 Jul 2015 19:08:11 +0200
Peter Zijlstra <peterz@infradead.org> wrote:

> On Thu, Jul 23, 2015 at 11:34:50AM -0400, Steven Rostedt wrote:
> > On Thu, 23 Jul 2015 12:42:15 +0200
> > Peter Zijlstra <peterz@infradead.org> wrote:
> > 
> > > static __always_inline bool arch_static_branch_jump(struct static_key *key, bool inv)
> > > {
> > > 	if (!inv) {
> > > 		asm_volatile_goto("1:"
> > > 			"jmp %l[l_yes]\n\t"
> > 
> > And what happens when this gets converted to a two byte jump?
> > 
> 
> That would be bad, how can we force it to emit 5 bytes?

No idea, but I could pull out that old code that converted them :-)

The complexity was in the elf parser that was run at kernel compile
time. It was based on the same code that does the work with
record-mcount.c to find all the mcount callers and made the sections
for them. In fact, it wasn't much different, as record-mcount.c will
convert the black listed sections into nops, so they do not bother
calling mcount at all. But those sections were not recorded, as they
were blacklisted anyway (not whitelisted really, as to be a blacklisted
section, it just had to not be in the whitelisted list).

If we got the jmp conversion in, I was going to clean up the code such
that both record-mcount.c and the jmp conversions used the same code
where applicable.

I would probably still convert every jmp to a nop (2 or 5 byte), and
then at boot up convert those back to jmps that are needed.

-- Steve
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/