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;
Date:   Fri, 9 Apr 2021 08:03:42 -0500
From:   Segher Boessenkool <segher@kernel.crashing.org>
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     linux-toolchains@vger.kernel.org, linux-kernel@vger.kernel.org,
        jpoimboe@redhat.com, jbaron@akamai.com, rostedt@goodmis.org,
        ardb@kernel.org
Subject: Re: static_branch/jump_label vs branch merging
Message-ID: <20210409130342.GF26583@gate.crashing.org>
References: <YG80wg/2iZjXfCDJ@hirez.programming.kicks-ass.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <YG80wg/2iZjXfCDJ@hirez.programming.kicks-ass.net>
User-Agent: Mutt/1.4.2.3i
Precedence: bulk

On Thu, Apr 08, 2021 at 06:52:18PM +0200, Peter Zijlstra wrote:
> Is there *any* way in which we can have the compiler recognise that the
> asm_goto only depends on its arguments and have it merge the branches
> itself?
> 
> I do realize that asm-goto being volatile this is a fairly huge ask, but
> I figured I should at least raise the issue, if only to raise awareness.

"volatile" should not be an impediment to this at all, volatile means
there is an unspecified side effect, nothing more, nothing less.  But
yes this currently does not work with GCC:

void f(int x)
{       if (x)
                asm volatile("ojee %0" :: "r"(x));
        else
                asm volatile("ojee %0" :: "r"(x));
}

or even

static inline void h(int x)
{
        asm volatile("ojee %0" :: "r"(x));
}

void f1(int x)
{       if (x)
                h(x);
        else
                h(x);
}

which both emit silly machine code.


Segher