From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ozlabs.org (ozlabs.org [103.22.144.67]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3F74F1A0050 for ; Fri, 15 Jan 2016 16:42:23 +1100 (AEDT) Message-ID: <1452836542.25634.33.camel@neuling.org> Subject: Re: [PATCH V2 4/8] powerpc: Explicitly disable math features when copying thread From: Michael Neuling To: Cyril Bur , linuxppc-dev@ozlabs.org Date: Fri, 15 Jan 2016 16:42:22 +1100 In-Reply-To: <1452834254-22078-5-git-send-email-cyrilbur@gmail.com> References: <1452834254-22078-1-git-send-email-cyrilbur@gmail.com> <1452834254-22078-5-git-send-email-cyrilbur@gmail.com> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Fri, 2016-01-15 at 16:04 +1100, Cyril Bur wrote: > With threads leaving the math bits enabled in their saved MSR to indicate > that the hardware is hot and a restore is not needed, children need to tu= rn > it off as when they do get scheduled, there's no way their registers coul= d > have been hot. Is this a bug in the current code? Mikey > Signed-off-by: Cyril Bur > --- > arch/powerpc/kernel/process.c | 1 + > 1 file changed, 1 insertion(+) >=20 > diff --git a/arch/powerpc/kernel/process.c > b/arch/powerpc/kernel/process.c > index dccc87e..e0c3d2d 100644 > --- a/arch/powerpc/kernel/process.c > +++ b/arch/powerpc/kernel/process.c > @@ -1307,6 +1307,7 @@ int copy_thread(unsigned long clone_flags, > unsigned long usp, > =20 > f =3D ret_from_fork; > } > + childregs->msr &=3D ~(MSR_FP|MSR_VEC|MSR_VSX); > sp -=3D STACK_FRAME_OVERHEAD; > =20 > /*