From mboxrd@z Thu Jan  1 00:00:00 1970
X-Msuck: nntp://news.gmane.org/gmane.linux.lib.musl.general/7697
Path: news.gmane.org!not-for-mail
From: Rich Felker <dalias@libc.org>
Newsgroups: gmane.linux.lib.musl.general
Subject: Re: [PATCH] inline llsc atomics when compiling for sh4a
Date: Mon, 18 May 2015 22:12:38 -0400
Message-ID: <20150519021238.GE17573@brightrain.aerifal.cx>
References: <20150517185516.GA32020@duality.lan>
 <20150518023402.GS17573@brightrain.aerifal.cx>
 <20150518225617.GA1905@duality.lan>
 <20150519003045.GC17573@brightrain.aerifal.cx>
Reply-To: musl@lists.openwall.com
NNTP-Posting-Host: plane.gmane.org
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Trace: ger.gmane.org 1432001579 9539 80.91.229.3 (19 May 2015 02:12:59 GMT)
X-Complaints-To: usenet@ger.gmane.org
NNTP-Posting-Date: Tue, 19 May 2015 02:12:59 +0000 (UTC)
To: musl@lists.openwall.com
Original-X-From: musl-return-7709-gllmg-musl=m.gmane.org@lists.openwall.com Tue May 19 04:12:53 2015
Return-path: <musl-return-7709-gllmg-musl=m.gmane.org@lists.openwall.com>
Envelope-to: gllmg-musl@m.gmane.org
Original-Received: from mother.openwall.net ([195.42.179.200])
	by plane.gmane.org with smtp (Exim 4.69)
	(envelope-from <musl-return-7709-gllmg-musl=m.gmane.org@lists.openwall.com>)
	id 1YuX1Z-0004Z2-Hi
	for gllmg-musl@m.gmane.org; Tue, 19 May 2015 04:12:53 +0200
Original-Received: (qmail 6011 invoked by uid 550); 19 May 2015 02:12:52 -0000
Mailing-List: contact musl-help@lists.openwall.com; run by ezmlm
Precedence: bulk
List-Post: <mailto:musl@lists.openwall.com>
List-Help: <mailto:musl-help@lists.openwall.com>
List-Unsubscribe: <mailto:musl-unsubscribe@lists.openwall.com>
List-Subscribe: <mailto:musl-subscribe@lists.openwall.com>
Original-Received: (qmail 5992 invoked from network); 19 May 2015 02:12:51 -0000
Content-Disposition: inline
In-Reply-To: <20150519003045.GC17573@brightrain.aerifal.cx>
User-Agent: Mutt/1.5.21 (2010-09-15)
Original-Sender: Rich Felker <dalias@aerifal.cx>
Xref: news.gmane.org gmane.linux.lib.musl.general:7697
Archived-At: <http://permalink.gmane.org/gmane.linux.lib.musl.general/7697>

On Mon, May 18, 2015 at 08:30:45PM -0400, Rich Felker wrote:
> [...]
> static inline int __sh_cas_llsc(volatile int *p, int t, int s)
> {
> 	do old = llsc_start(p);
> 	while (!llsc_end(p, old==t ? s : old));
> 	return old;
> }
> 
> This version is structurally analogous to the non-CAS atomics, but
> perhaps more costly in the old!=t case.
> 
> Anyway at this point I don't see an efficient way do to the
> conditional, so it's mostly a theoretical topic at this point.

I have a partial solution but it's utterly hideous:

static inline int llsc_end(volatile int *p, int v)
{
	__asm__ __volatile__ goto ( "mov.co %1, @%0 ; bf %l[fail]" : :
	"r"(p), "z"(v) : "memory" : fail );
	return 1;
fail:
	return 0;
}

This doesn't eliminate the branch in the asm, but it does allow gcc to
eliminate the branch outside the asm. The resulting code is:

a_cas:
        .align 2
.L2:
#APP
        synco ; mov.li @r4, r0
#NO_APP
        cmp/eq  r0,r5
        bf      .L4
        mov     r6,r0
#APP
        mov.co r0, @r4 ; bf .L2
#NO_APP
.L6:
        rts
        mov     r5,r0
        .align 1
.L4:
        bra     .L6
        mov     r0,r5

Of course asm goto is utterly hideous, so I don't propose actually
using this. I doubt any of the non-GCC compilers we support would
accept it.

Rich