public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Oleg Nesterov <oleg@redhat.com>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Rik van Riel <riel@redhat.com>,
	x86@kernel.org, linux-kernel@vger.kernel.org,
	Borislav Petkov <bp@alien8.de>
Subject: Re: [RFC PATCH] x86, fpu: Use eagerfpu by default on all CPUs
Date: Mon, 23 Feb 2015 15:59:29 +0100	[thread overview]
Message-ID: <20150223145929.GA10342@redhat.com> (raw)
In-Reply-To: <b0ba174ea882ed36cf7011e872baf427c23b7e09.1424458621.git.luto@amacapital.net>

On 02/20, Andy Lutomirski wrote:
>
> We have eager and lazy fpu modes, introduced in:
> 
> 304bceda6a18 x86, fpu: use non-lazy fpu restore for processors supporting xsave
> 
> The result is rather messy.  There are two code paths in almost all of the
> FPU code, and only one of them (the eager case) is tested frequently, since
> most kernel developers have new enough hardware that we use eagerfpu.
> 
> It seems that, on any remotely recent hardware, eagerfpu is a win:
> glibc uses SSE2, so laziness is probably overoptimistic, and, in any
> case, manipulating TS is far slower that saving and restoring the full
> state.
> 
> To try to shake out any latent issues on old hardware, this changes
> the default to eager on all CPUs.  If no performance or functionality
> problems show up, a subsequent patch could remove lazy mode entirely.
> 
> Signed-off-by: Andy Lutomirski <luto@amacapital.net>
> ---
>  arch/x86/kernel/xsave.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
> index 0de1fae2bdf0..1928c8f34ce5 100644
> --- a/arch/x86/kernel/xsave.c
> +++ b/arch/x86/kernel/xsave.c
> @@ -637,8 +637,8 @@ static void __init xstate_enable_boot_cpu(void)
>  	prepare_fx_sw_frame();
>  	setup_init_fpu_buf();
>  
> -	/* Auto enable eagerfpu for xsaveopt */
> -	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
> +	/* Auto enable eagerfpu for everyone */
> +	if (eagerfpu != DISABLE)
>  		eagerfpu = ENABLE;

Well, but if we want this change then perhaps we should simply change
the default value? This way "AUTO" still can work.

Oleg.

--- x/arch/x86/kernel/xsave.c
+++ x/arch/x86/kernel/xsave.c
@@ -563,7 +563,7 @@ static void __init setup_init_fpu_buf(vo
 	xsave_state_booting(init_xstate_buf, -1);
 }
 
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = ENABLE;
 static int __init eager_fpu_setup(char *s)
 {
 	if (!strcmp(s, "on"))


  parent reply	other threads:[~2015-02-23 15:01 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-02-20 18:58 [RFC PATCH] x86, fpu: Use eagerfpu by default on all CPUs Andy Lutomirski
2015-02-20 19:05 ` Borislav Petkov
2015-02-21  9:31 ` Ingo Molnar
2015-02-21 16:38   ` Borislav Petkov
2015-02-21 17:29     ` Borislav Petkov
2015-02-21 18:39       ` Ingo Molnar
2015-02-21 19:15         ` Borislav Petkov
2015-02-21 19:23           ` Ingo Molnar
2015-02-21 21:36             ` Borislav Petkov
2015-02-22  8:18               ` Ingo Molnar
2015-02-22  8:22                 ` Ingo Molnar
2015-02-22 10:48                 ` Borislav Petkov
2015-02-22 12:50                 ` Borislav Petkov
2015-02-22 12:57                   ` Ingo Molnar
2015-02-22 13:21                     ` Borislav Petkov
2015-02-22  0:34       ` Maciej W. Rozycki
2015-02-22  2:18         ` Andy Lutomirski
2015-02-22 11:06           ` Borislav Petkov
2015-02-23  1:45             ` Rik van Riel
2015-02-23  5:22               ` Andy Lutomirski
2015-02-23 12:51                 ` Rik van Riel
2015-02-23 15:03                   ` Borislav Petkov
2015-02-23 15:51                     ` Rik van Riel
2015-02-23 18:06                       ` Borislav Petkov
2015-02-23 21:17           ` Maciej W. Rozycki
2015-02-23 21:21             ` Rik van Riel
2015-02-23 22:14               ` Linus Torvalds
2015-02-24  0:56                 ` Maciej W. Rozycki
2015-02-24  0:59                   ` Andy Lutomirski
2015-02-23 22:27               ` Maciej W. Rozycki
2015-02-23 23:44                 ` Andy Lutomirski
2015-02-24  2:14                   ` Maciej W. Rozycki
2015-02-24  2:31                     ` Andy Lutomirski
2015-02-24 14:43                       ` Rik van Riel
2015-02-21 18:34     ` Ingo Molnar
2015-02-23 14:59 ` Oleg Nesterov [this message]
2015-02-23 15:11   ` Borislav Petkov
2015-02-23 15:53     ` Rik van Riel
2015-02-23 18:40       ` Oleg Nesterov
2015-02-24 19:15 ` Denys Vlasenko
2015-02-25  0:07   ` Andy Lutomirski
2015-02-25 10:37     ` Borislav Petkov
2015-02-25 10:50       ` Ingo Molnar
2015-02-25 10:45     ` Ingo Molnar
2015-02-25 17:12 ` Some results (was: Re: [RFC PATCH] x86, fpu: Use eagerfpu by default on all CPUs) Borislav Petkov

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=20150223145929.GA10342@redhat.com \
    --to=oleg@redhat.com \
    --cc=bp@alien8.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=riel@redhat.com \
    --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