From: "H. Peter Anvin" <hpa@zytor.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
Ingo Molnar <mingo@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Al Viro <viro@zeniv.linux.org.uk>
Cc: the arch/x86 maintainers <x86@kernel.org>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [RFC] speeding up the stat() family of system calls...
Date: Mon, 23 Dec 2013 16:00:25 -0800 [thread overview]
Message-ID: <52B8CE99.2050608@zytor.com> (raw)
In-Reply-To: <CA+55aFxZ2u+M72u3HSD7TVY2+WRRi27pYC=_4Wawr5y1m8DfnQ@mail.gmail.com>
On 12/21/2013 12:27 PM, Linus Torvalds wrote:
>
> HOWEVER. On x86, doing an efficient field-at-a-time copy also requires
> us to use put_user_try() and put_user_catch() in order to not have
> tons of clac/stac instructions for the extended permission testing.
> And the implementation of that was actually fairly non-optimal, so to
> actually get the code I wanted, I had to change how that all worked
> too, using "asm_volatile_goto()".
>
I guess I'm a bit puzzled... the current code should be just fine if
everything is present, and do we really care about the performance if we
actually have an error condition?
I'm a bit concerned about the put_user_fail: label having uniqueness
problem, which I know some versions of gcc at least get very noisy over.
I like the overall approach, however.
-hpa
next prev parent reply other threads:[~2013-12-24 0:00 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-12-21 20:27 [RFC] speeding up the stat() family of system calls Linus Torvalds
2013-12-21 22:54 ` John Stoffel
2013-12-22 0:11 ` Linus Torvalds
2013-12-24 0:00 ` H. Peter Anvin [this message]
2013-12-24 0:12 ` Linus Torvalds
2013-12-24 6:00 ` H. Peter Anvin
2013-12-24 20:46 ` Ingo Molnar
2013-12-26 19:00 ` Linus Torvalds
2013-12-27 0:45 ` H. Peter Anvin
2013-12-27 3:18 ` H. Peter Anvin
2013-12-27 6:09 ` H. Peter Anvin
2013-12-27 23:30 ` H. Peter Anvin
2014-01-12 17:46 ` Ingo Molnar
2013-12-28 1:00 ` [tip:x86/asm] x86: Replace assembly access_ok() with a C variant tip-bot for Linus Torvalds
2013-12-28 1:00 ` [tip:x86/asm] x86: Slightly tweak the access_ok() C variant for better code tip-bot for H. Peter Anvin
2013-12-28 1:06 ` tip-bot for H. Peter Anvin
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=52B8CE99.2050608@zytor.com \
--to=hpa@zytor.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.