Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1394762 > unrolled thread

Re: [PATCH v4 10/10] x86/xsaves: Re-enable XSAVES

Started byDave Hansen <dave.hansen@intel.com>
First post2016-05-05 00:50 +0200
Last post2016-05-05 00:50 +0200
Articles 1 — 1 participant

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: [PATCH v4 10/10] x86/xsaves: Re-enable XSAVES Dave Hansen <dave.hansen@intel.com> - 2016-05-05 00:50 +0200

#1394762 — Re: [PATCH v4 10/10] x86/xsaves: Re-enable XSAVES

FromDave Hansen <dave.hansen@intel.com>
Date2016-05-05 00:50 +0200
SubjectRe: [PATCH v4 10/10] x86/xsaves: Re-enable XSAVES
Message-ID<rvdMe-4aR-3@gated-at.bofh.it>
On 05/04/2016 03:41 PM, Dave Hansen wrote:
> But, since we *always* call XSAVES with an instruction mask of -1 and
> end up with a requested feature bitmap (RFBM) equal to XCR0, I think we
> can do a shortcut because we'll practically *always* have an
> xcomp_bv==RFBM==XCR0, which means that all (present) components will
> always have an address.

Actually, we depend on that anyway.  xstate_comp_offsets[] is completely
bogus if we don't have xcomp_bv==RFBM==XCR0.

Perhaps we need to add those checks anyway.

[toc] | [standalone]


Back to top | Article view | linux.kernel


csiph-web