Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20211020104442.021802560@infradead.org> <20211020105843.345016338@infradead.org>
 <YW/4/7MjUf3hWfjz@hirez.programming.kicks-ass.net> <20211021000502.ltn5o6ji6offwzeg@ast-mbp.dhcp.thefacebook.com>
 <YXEpBKxUICIPVj14@hirez.programming.kicks-ass.net> <CAADnVQKD6=HwmnTw=Shup7Rav-+OTWJERRYSAn-as6iikqoHEA@mail.gmail.com>
 <20211021223719.GY174703@worktop.programming.kicks-ass.net>
 <CAADnVQ+cJLYL-r6S8TixJxH1JEXXaNojVoewB3aKcsi7Y8XPdQ@mail.gmail.com>
 <20211021233852.gbkyl7wpunyyq4y5@treble> <CAADnVQ+iMysKSKBGzx7Wa+ygpr9nTJbRo4eGYADLFDE4PmtjOQ@mail.gmail.com>
 <YXKhLzd/DtkjURpc@hirez.programming.kicks-ass.net>
In-Reply-To: <YXKhLzd/DtkjURpc@hirez.programming.kicks-ass.net>
From:   Alexei Starovoitov <alexei.starovoitov@gmail.com>
Date:   Fri, 22 Oct 2021 08:22:35 -0700
Message-ID: <CAADnVQKJojWGaTCpUhkmU+vUxXORPacX_ByjyHWY0V03hGH7KA@mail.gmail.com>
Subject: Re: [PATCH v2 14/14] bpf,x86: Respect X86_FEATURE_RETPOLINE*
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     Josh Poimboeuf <jpoimboe@redhat.com>, X86 ML <x86@kernel.org>,
        Andrew Cooper <andrew.cooper3@citrix.com>,
        LKML <linux-kernel@vger.kernel.org>,
        Nick Desaulniers <ndesaulniers@google.com>,
        Daniel Borkmann <daniel@iogearbox.net>,
        bpf <bpf@vger.kernel.org>, Andrii Nakryiko <andrii@kernel.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Fri, Oct 22, 2021 at 4:33 AM Peter Zijlstra <peterz@infradead.org> wrote:
>
> On Thu, Oct 21, 2021 at 04:42:12PM -0700, Alexei Starovoitov wrote:
>
> > Ahh. Right. It's potentially a different offset for every prog.
> > Let's put it into struct jit_context then.
>
> Something like this...

Yep. Looks nice and clean to me.

> -       poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
> +       poke->tailcall_bypass = ip + (prog - start);
>         poke->adj_off = X86_TAIL_CALL_OFFSET;
> -       poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
> +       poke->tailcall_target = ip + ctx->tail_call_direct_label - X86_PATCH_SIZE;

This part looks correct too, but this is Daniel's magic.
He'll probably take a look next week when he comes back from PTO.
I don't recall which test exercises this tailcall poking logic.
It's only used with dynamic updates to prog_array.
insmod test_bpf.ko and test_verifier won't go down this path.