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;
Content-Type: text/plain;
        charset=utf-8
Mime-Version: 1.0 (1.0)
Subject: Re: [POC][RFC][PATCH 1/2] jump_function: Addition of new feature "jump_function"
From:   Andy Lutomirski <luto@amacapital.net>
In-Reply-To: <20181008155757.GC5663@hirez.programming.kicks-ass.net>
Date:   Mon, 8 Oct 2018 09:29:56 -0700
Cc:     Steven Rostedt <rostedt@goodmis.org>, linux-kernel@vger.kernel.org,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Ingo Molnar <mingo@kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
        Matthew Helsley <mhelsley@vmware.com>,
        "Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
        David Woodhouse <dwmw2@infradead.org>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        Jason Baron <jbaron@akamai.com>, Jiri Kosina <jkosina@suse.cz>,
        ard.biesheuvel@linaro.org, Andy Lutomirski <luto@kernel.org>
Content-Transfer-Encoding: quoted-printable
Message-Id: <F36C6419-7D92-4357-BDB1-D8B90DE09889@amacapital.net>
References: <20181006015110.653946300@goodmis.org> <20181006015720.634688468@goodmis.org> <20181006121211.GA5663@hirez.programming.kicks-ass.net> <20181006093905.46276505@vmware.local.home> <20181008072134.GB5663@hirez.programming.kicks-ass.net> <A9379DDB-3210-407C-8157-8DA980944F8C@amacapital.net> <20181008155757.GC5663@hirez.programming.kicks-ass.net>
To:     Peter Zijlstra <peterz@infradead.org>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


> On Oct 8, 2018, at 8:57 AM, Peter Zijlstra <peterz@infradead.org> wrote:
>=20
> On Mon, Oct 08, 2018 at 01:33:14AM -0700, Andy Lutomirski wrote:
>>> Can't we hijack the relocation records for these functions before they
>>> get thrown out in the (final) link pass or something?
>>=20
>> I could be talking out my arse here, but I thought we could do this,
>> too, then changed my mind.  The relocation records give us the
>> location of the call or jump operand, but they don=E2=80=99t give the add=
ress
>> of the beginning of the instruction.
>=20
> But that's like 1 byte before the operand, right? We could even double che=
ck
> this by reading back that byte and ensuring it is in fact 0xE8 (CALL).
>=20
> AFAICT there is only the _1_ CALL encoding, and that is the 5 byte: E8 <PL=
T32>,
> so if we have the PLT32 location, we also have the instruction location. O=
r am
> I missing something?

There=E2=80=99s also JMP and Jcc, any of which can be used for rail calls, b=
ut those are also one byte. I suppose GCC is unlikely to emit a prefixed for=
m of any of these. So maybe we really can assume they=E2=80=99re all one byt=
e.

But there is a nasty potential special case: anything that takes the functio=
n=E2=80=99s address. This includes jump tables, computed gotos, and plain ol=
d function pointers. And I suspect that any of these could have one of the r=
ather large number of CALL/JMP/Jcc bytes before the relocation by coincidenc=
e.