Re: [cryptodev:master 130/134] aes_generic.c:undefined reference to `_restgpr_31_x'

From: Segher Boessenkool <segher@kernel.crashing.org>
To: Arnd Bergmann <arnd@arndb.de>
Cc: "open list:HARDWARE RANDOM NUMBER GENERATOR CORE"
	<linux-crypto@vger.kernel.org>,
	kbuild test robot <fengguang.wu@intel.com>,
	linuxppc-dev <linuxppc-dev@lists.ozlabs.org>,
	Herbert Xu <herbert@gondor.apana.org.au>
Subject: Re: [cryptodev:master 130/134] aes_generic.c:undefined reference to `_restgpr_31_x'
Date: Sun, 14 Jan 2018 18:21:09 -0600	[thread overview]
Message-ID: <20180115002109.GX21977@gate.crashing.org> (raw)
In-Reply-To: <CAK8P3a30k-JjMJ0M9KWXqUMT3eHmuuFvAe1KuKdqNoAiSZrgog@mail.gmail.com>

On Sun, Jan 14, 2018 at 10:40:36PM +0100, Arnd Bergmann wrote:
> Right. I've done some more investigation anyway, starting over with the
> analysis of the gcc options that change it. I've found now that turning
> off '-fcode-hoisting' but leaving on the other options I had suspected
> earlier (-O2 instead of -Os, -ftree-sra, -ftree-pre) also fixes the
> stack problem, and appears to result in the best performance so
> far.

Oh nice!

> I need to rerun the whole test matrix, but that seems rather
> promising, and the result may also help debug what's really happening.

-fcode-hoisting moves all expression evaluation to as early as possible;
for this AES code that means it will increase register pressure a lot,
causing a lot of spilling (well, that is my guess).  If that is so, then
we need to dial down -fcode-hoisting a bit, maybe make it aware of
register pressure.

Glad you found a smoking gun,

Segher