linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "H. Peter Anvin" <hpa@zytor.com>
To: Borislav Petkov <bp@alien8.de>
Cc: X86 ML <x86@kernel.org>, LKML <linux-kernel@vger.kernel.org>,
	Borislav Petkov <bp@suse.de>
Subject: Re: [PATCH 3/3] x86, FPU: Do not use static_cpu_has before alternatives
Date: Mon, 29 Apr 2013 08:42:30 -0700	[thread overview]
Message-ID: <517E94E6.6040201@zytor.com> (raw)
In-Reply-To: <1367244262-29511-4-git-send-email-bp@alien8.de>

On 04/29/2013 07:04 AM, Borislav Petkov wrote:
> From: Borislav Petkov <bp@suse.de>
> 
> The call stack below shows how this happens: basically eager_fpu_init()
> calls __thread_fpu_begin(current) which then does if (!use_eager_fpu()),
> which, in turn, uses static_cpu_has.
> 
> And we're executing before alternatives so static_cpu_has doesn't work
> there yet.
> 
> However, I don't want to cause the penalty of not using static_cpu_has
> to all callers of use_eager_fpu() which are a bunch spread around the
> tree so let's add the change only to __thread_fpu_begin() - it is still
> on the context switch path but we can at least keep the static_cpu_has
> call in the rest of the use_eager_fpu() callsites.
> 

I *was* considering adding static_cpu_has_safe() at some point which
would have a three-state jump, with the default (pre-alternatives) jump
pointing to dynamic detection code.

This might be useful here, on the other hand, perhaps it is acceptable
for use_eager_fpu() to be initially false?

	-hpa



  reply	other threads:[~2013-04-29 15:42 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-04-29 14:04 [PATCH 0/3] FPU detection in C, second try Borislav Petkov
2013-04-29 14:04 ` [PATCH 1/3] x86: Get rid of ->hard_math and all the FPU asm fu Borislav Petkov
2013-04-29 14:04 ` [PATCH 2/3] x86: Sanity-check static_cpu_has usage Borislav Petkov
2013-04-29 15:38   ` H. Peter Anvin
2013-04-29 14:04 ` [PATCH 3/3] x86, FPU: Do not use static_cpu_has before alternatives Borislav Petkov
2013-04-29 15:42   ` H. Peter Anvin [this message]
2013-04-29 18:51     ` Borislav Petkov
2013-04-29 18:58       ` H. Peter Anvin
  -- strict thread matches above, loose matches on Subject: below --
2013-04-08 15:57 [PATCH 0/4] x86: FPU detection in C Borislav Petkov
2013-04-08 15:57 ` [PATCH 1/4] x86: Get rid of ->hard_math and all the FPU asm fu Borislav Petkov
2013-04-08 16:26   ` [tip:x86/cpu] " tip-bot for H. Peter Anvin
2013-06-12 20:48   ` [tip:x86/fpu] " tip-bot for H. Peter Anvin
2013-04-08 15:57 ` [PATCH 2/4] x86: Fold-in trivial check_config function Borislav Petkov
2013-04-08 16:27   ` [tip:x86/cpu] " tip-bot for Borislav Petkov
2013-04-16 13:51   ` tip-bot for Borislav Petkov
2013-04-08 15:57 ` [PATCH 3/4] x86, AMD: Correct {rd,wr}msr_amd_safe warnings Borislav Petkov
2013-04-08 16:28   ` [tip:x86/cpu] " tip-bot for Borislav Petkov
2013-04-16 13:53   ` tip-bot for Borislav Petkov
2013-04-08 15:57 ` [PATCH 4/4] x86, CPU, AMD: Drop useless label Borislav Petkov
2013-04-08 16:29   ` [tip:x86/cpu] " tip-bot for Borislav Petkov
2013-04-16 13:54   ` tip-bot for Borislav Petkov
2013-04-10 11:08 ` [PATCH 0/4] x86: FPU detection in C Ingo Molnar
2013-04-10 12:24   ` Borislav Petkov
2013-04-10 12:25     ` Ingo Molnar
2013-04-10 13:32       ` Borislav Petkov
2013-04-10 15:35         ` H. Peter Anvin
2013-04-10 16:11           ` Borislav Petkov
2013-04-10 21:29             ` [PATCH] x86, FPU: Fix FPU initialization Borislav Petkov
2013-04-11 12:09               ` Ingo Molnar
2013-04-11 14:23                 ` Borislav Petkov
2013-04-11 19:26                 ` H. Peter Anvin
2013-04-11 20:23                   ` Borislav Petkov
2013-04-12  5:32                     ` Ingo Molnar
2013-04-12  5:34                       ` H. Peter Anvin
2013-04-12  9:47                         ` Borislav Petkov
2013-04-12 11:26                           ` Borislav Petkov
2013-04-15 10:08                             ` Ingo Molnar
2013-04-15 10:17                               ` Borislav Petkov
2013-04-15 10:18                                 ` Ingo Molnar
2013-04-15 15:54                                   ` Borislav Petkov
2013-04-15 22:04                                     ` Borislav Petkov
2013-04-16  9:25                                       ` Ingo Molnar
2013-04-16  9:48                                         ` Borislav Petkov
2013-04-16 10:08                                           ` [GIT PULL] Rebase tip:x86/cpu Borislav Petkov
2013-04-16 11:35                                             ` Ingo Molnar
2013-04-16 11:33                                           ` [PATCH] x86, FPU: Fix FPU initialization Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=517E94E6.6040201@zytor.com \
    --to=hpa@zytor.com \
    --cc=bp@alien8.de \
    --cc=bp@suse.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).