From: Robert Love <rml@ximian.com>
To: Linus Torvalds <torvalds@osdl.org>
Cc: Arjan van de Ven <arjanv@redhat.com>,
Ulrich Drepper <drepper@redhat.com>,
Russell Leighton <russ@elegant-software.com>,
Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: clone() <-> getpid() bug in 2.6?
Date: Sat, 05 Jun 2004 17:48:02 -0400 [thread overview]
Message-ID: <1086472082.7940.48.camel@localhost> (raw)
In-Reply-To: <Pine.LNX.4.58.0406051405110.7010@ppc970.osdl.org>
On Sat, 2004-06-05 at 14:13 -0700, Linus Torvalds wrote:
> Uli, if Arjan is right, then please fix this. It's a buggy and pointless
> optimization. Anybody who optimizes purely for benchmarks should be
> ashamed of themselves.
Eh, it definitely does, in nptl/sysdeps/unix/sysv/linux/getpid.c:
pid_t result = THREAD_GETMEM (THREAD_SELF, pid);
if (__builtin_expect (result <= 0, 0))
result = really_getpid (result);
A few places, including the fork code, fix it:
/* Adjust the PID field for the new process. */
THREAD_SETMEM (self, pid, THREAD_GETMEM (self, tid));
But not direct calls to clone(2).
Robert Love
next prev parent reply other threads:[~2004-06-05 21:48 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-06-05 15:28 clone() <-> getpid() bug in 2.6? Russell Leighton
2004-06-05 20:45 ` Linus Torvalds
2004-06-05 20:55 ` Arjan van de Ven
2004-06-05 21:13 ` Linus Torvalds
2004-06-05 21:48 ` Robert Love [this message]
2004-06-05 22:44 ` Linus Torvalds
2004-06-05 21:53 ` Chris Wedgwood
2004-06-05 22:47 ` Robert Love
2004-06-05 22:57 ` David S. Miller
2004-06-05 23:01 ` Linus Torvalds
2004-06-05 23:07 ` Davide Libenzi
2004-06-05 23:18 ` Linus Torvalds
2004-06-05 23:26 ` Davide Libenzi
2004-06-06 5:08 ` Kalin KOZHUHAROV
2004-06-06 5:13 ` Chris Wedgwood
2004-06-06 5:34 ` Kalin KOZHUHAROV
2004-06-06 6:07 ` Linus Torvalds
2004-06-06 6:43 ` Kalin KOZHUHAROV
2004-06-06 7:57 ` Erik Andersen
2004-06-06 16:57 ` Linus Torvalds
2004-06-06 18:53 ` Simon Kirby
2004-06-06 19:00 ` Linus Torvalds
2004-06-06 9:52 ` Bernd Eckenfels
2004-06-06 13:07 ` Paul Rolland
2004-06-06 17:20 ` Patrick J. LoPresti
2004-06-06 17:31 ` Paul Rolland
2004-06-06 17:43 ` Davide Libenzi
2004-06-06 18:17 ` Rik van Riel
2004-06-06 18:37 ` Patrick J. LoPresti
2004-06-06 16:33 ` chris
[not found] ` <200406062022.54320.vda@port.imtp.ilyichevsk.odessa.ua>
2004-06-06 17:55 ` Linus Torvalds
2004-06-07 18:20 ` Bruce Guenter
2004-06-08 11:06 ` Kalin KOZHUHAROV
2004-06-05 23:19 ` Robert Love
2004-06-06 14:29 ` Russell Leighton
2004-06-06 15:38 ` Using getpid() often, another way? [was Re: clone() <-> getpid() bug in 2.6?] Russell Leighton
2004-06-06 15:44 ` Robert Love
2004-06-07 0:20 ` Russell Leighton
2004-06-06 15:58 ` Arjan van de Ven
2004-06-06 23:49 ` Russell Leighton
2004-06-07 12:13 ` Arjan van de Ven
2004-06-07 13:48 ` Sean Neakums
2004-06-07 14:00 ` Christoph Hellwig
2004-06-07 14:10 ` Sean Neakums
2004-06-07 18:42 ` David Mosberger
2004-06-07 23:02 ` Russell Leighton
2004-06-07 23:27 ` David Mosberger
2004-06-08 6:01 ` Arjan van de Ven
2004-06-08 9:48 ` Eric W. Biederman
2004-06-07 0:09 ` Russell Leighton
2004-06-07 12:20 ` Arjan van de Ven
2004-06-06 17:19 ` Linus Torvalds
2004-06-12 9:15 ` Dominik Straßer
2004-06-12 13:47 ` Linus Torvalds
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=1086472082.7940.48.camel@localhost \
--to=rml@ximian.com \
--cc=arjanv@redhat.com \
--cc=drepper@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=russ@elegant-software.com \
--cc=torvalds@osdl.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.