Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 13 Sep 2016 11:20:37 +0100
From:      Andrew Turner <andrew@fubar.geek.nz>
To:        John-Mark Gurney <jmg@funkthat.com>
Cc:        freebsd-arm@FreeBSD.org
Subject:   Re: interesting arm issue/bug
Message-ID:  <20160913112037.0e06cb4d@zapp>
In-Reply-To: <20160912213643.GE1691@funkthat.com>
References:  <20160912213643.GE1691@funkthat.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 12 Sep 2016 14:36:43 -0700
John-Mark Gurney <jmg@funkthat.com> wrote:

> I'm not sure if we run on this hardware or not, but I thought it'd be
> good to bring this to the attention of the list:
> http://www.mono-project.com/news/2016/09/12/arm64-icache/
> 

We don't boot on this hardware. It is also my understanding having a
mismatch in the CTR_EL0 register is a violation of the architecture,
and therefore a hardware bug.

If someone was to port FreeBSD to this SoC they would need to do
something similar to the proposed Linux fix and trap access to the
CTR_EL0 register to return a stable minimum value.

I note there is a similar issue with an earlier Samsung ARMv7 SoC,
however we don't support multi-cluster on 32-bit ARM so this isn't a
problem for us.

Andrew



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20160913112037.0e06cb4d>