[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date: Thu, 7 Jul 2022 10:58:14 +0100
From: Jiaxun Yang <jiaxun.yang@...goat.com>
To: WANG Xuerui <kernel@...0n.name>, Qi Hu <huqi@...ngson.cn>,
Huacai Chen <chenhuacai@...nel.org>
Cc: loongarch@...ts.linux.dev, LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v3] LoongArch: Remove vcsr in loongarch_fpu
在 2022/7/7 9:56, WANG Xuerui 写道:
>
> However, the experiment result is counter-intuitive to me after all;
> are you aware that perhaps *some* 3A5000's in the wild actually have
> functional VCSR? If so, the state obviously needs isolation
> (saving/restoring simply becoming no-ops on later steppings), but
> otherwise this cleanup should be correct.
^ Yep, my concern was 3A5000 with VCSR enabled can be vulnerable.
Thanks
- Jiaxun
Powered by blists - more mailing lists