From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1751470AbdJ2JI2 (ORCPT <rfc822;w@1wt.eu>);
        Sun, 29 Oct 2017 05:08:28 -0400
Received: from Galois.linutronix.de ([146.0.238.70]:38052 "EHLO
        Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1750915AbdJ2JI1 (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Sun, 29 Oct 2017 05:08:27 -0400
Date: Sun, 29 Oct 2017 10:08:17 +0100 (CET)
From: Thomas Gleixner <tglx@linutronix.de>
To: Andy Lutomirski <luto@kernel.org>
cc: Linus Torvalds <torvalds@linux-foundation.org>,
        Peter Zijlstra <peterz@infradead.org>, X86 ML <x86@kernel.org>,
        Borislav Petkov <bp@alien8.de>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        linux-abi@vger.kernel.org
Subject: Re: Can we break RDPID/RDTSCP ABI ASAP and see if it's okay?
In-Reply-To: <CALCETrWZBzjw=sGT0SX29NtR+Ki+-eWEH_Yrphzrmi7dLFaBtg@mail.gmail.com>
Message-ID: <alpine.DEB.2.20.1710290952440.1922@nanos>
References: <CALCETrWZBzjw=sGT0SX29NtR+Ki+-eWEH_Yrphzrmi7dLFaBtg@mail.gmail.com>
User-Agent: Alpine 2.20 (DEB 67 2015-01-07)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
X-Linutronix-Spam-Score: -1.0
X-Linutronix-Spam-Level: -
X-Linutronix-Spam-Status: No , -1.0 points, 5.0 required,  ALL_TRUSTED=-1,SHORTCIRCUIT=-0.0001
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Sat, 28 Oct 2017, Andy Lutomirski wrote:

> We currently do this on boot:
> 
> write_rdtscp_aux((node << 12) | cpu);
> 
> This *sucks*.  It means that, to very quickly obtain the CPU number
> using RDPID, an ALU op is needed.  It also doesn't bloody work on
> systems with more than 4096 CPUs.
> 
> IMO it should be ((u64)node << 32) | cpu.  Then getting the CPU number is just:

That breaks 32bit

> RDPID %rax
> MOVL %eax, %eax
> 
> I'm thinking about this because rseq users could avoid ever *loading*
> the rseq cacheline if they used RDPID to get the CPU number, and it
> would be nice to give them a sane way to do it.
> 
> This won't break any existing RDPID users if we do it quickly because
> there aren't any (the CPUs aren't available).  I would be a bit
> surprised if anyone uses RDTSCP for this because it's absurdly slow.

What we can do on 64bit is:

     ((u64) cpu << 32) | (node << 12) | (cpu & 0xfff)

That does not solve the ALU op problem but works on both 32 and 64 bit and
on systems with more than 4096 CPUs.

Thanks,

	tglx