[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20170123211640.GA3976@test-lenovo>
Date: Mon, 23 Jan 2017 13:16:40 -0800
From: Yu-cheng Yu <yu-cheng.yu@...el.com>
To: Dave Hansen <dave.hansen@...ux.intel.com>
Cc: fenghua.yu@...el.com, dvlasenk@...hat.com, peterz@...radead.org,
oleg@...hat.com, mingo@...nel.org, linux-kernel@...r.kernel.org,
brgerst@...il.com, luto@...nel.org, bp@...en8.de,
jpoimboe@...hat.com, haokexin@...il.com, hpa@...or.com,
quentin.casasnovas@...cle.com, tglx@...utronix.de,
torvalds@...ux-foundation.org, riel@...hat.com,
linux-tip-commits@...r.kernel.org
Subject: Re: [tip:x86/urgent] x86/fpu: Set the xcomp_bv when we fake up a
XSAVES area
On Mon, Jan 23, 2017 at 01:10:20PM -0800, Dave Hansen wrote:
> The code is:
>
> > void fpstate_init(union fpregs_state *state)
> > {
> > if (!static_cpu_has(X86_FEATURE_FPU)) {
> > fpstate_init_soft(&state->soft);
> > return;
> > }
> >
> > memset(state, 0, fpu_kernel_xstate_size);
> >
> > /*
> > * XRSTORS requires that this bit is set in xcomp_bv, or
> > * it will #GP. Make sure it is replaced after the memset().
> > */
> > if (static_cpu_has(X86_FEATURE_XSAVES))
> > state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT;
>
> That seems to set it unconditionally. What am I missing?
The fix I am proposing is...
state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
xfeatures_mask;
Powered by blists - more mailing lists