linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alan Cox <alan@lxorguk.ukuu.org.uk>
To: zandy@cs.wisc.edu (Victor Zandy)
Cc: linux-kernel@vger.kernel.org
Subject: Re: BUG: Global FPU corruption in 2.2
Date: Tue, 24 Apr 2001 19:37:38 +0100 (BST)	[thread overview]
Message-ID: <E14s7gz-0002fh-00@the-village.bc.nu> (raw)
In-Reply-To: <cpxitjurwei.fsf@goat.cs.wisc.edu> from "Victor Zandy" at Apr 24, 2001 01:21:41 PM

> >         child->flags |= PF_PTRACED; 
> > 
> > without waiting for the child to have stopped. 
> 
> I can see how this could case PF_USEDFPU to be cleared inadvertently,
> but I do not have any ideas for testing this.  Is it clear that this
> is the source of the problem?

There is no guarantee that |= is implemented atomically - in fact its quite
likely to read

		get child->flags
		or PF_PTRACED
		write child->flags

and a PF_USEDFPU on another processor at the same instant -would- end up being
lost.

There are two fixes

1.	Make all the ops atomic (foo_bit())
2.	Split the flags

The preferable one for performance is certainly to backport the 2.4 changes


  reply	other threads:[~2001-04-24 18:36 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-04-24 18:21 BUG: Global FPU corruption in 2.2 Victor Zandy
2001-04-24 18:37 ` Alan Cox [this message]
2001-04-24 19:17   ` Victor Zandy
2001-04-24 19:51     ` Alan Cox
  -- strict thread matches above, loose matches on Subject: below --
2001-04-24 13:05 Victor Zandy
2001-04-24 16:24 ` Linus Torvalds
2001-04-24 16:47 ` Christian Ehrhardt
2001-04-24 18:09   ` Victor Zandy
2001-04-24  8:56 alad
2001-04-24  7:56 alad
2001-04-24  5:33 alad
2001-04-19 16:05 Victor Zandy
2001-04-19 20:18 ` Michal Jaegermann
2001-04-20 18:50 ` Victor Zandy
2001-04-20 19:07   ` Richard B. Johnson
2001-04-20 19:20     ` Victor Zandy
2001-04-20 19:44       ` Richard B. Johnson
2001-04-20 19:23     ` Ulrich Drepper
2001-04-20 19:37       ` Richard B. Johnson
2001-04-20 20:20         ` Victor Zandy
2001-04-20 21:44         ` Ulrich Drepper
2001-04-22  1:46           ` Richard B. Johnson
2001-04-22  2:18             ` Alan Cox
2001-04-22  2:30               ` Richard B. Johnson
2001-04-22 18:39           ` David Konerding
2001-04-22 18:59             ` Alan Cox
2001-04-22 20:59 ` kees
2001-04-23 16:11 ` Christian Ehrhardt
2001-04-24 16:10   ` Linus Torvalds
2001-04-24 16:25     ` Alan Cox
2001-04-24 16:56     ` Christian Ehrhardt
2001-04-24 20:15       ` Michal Jaegermann
2001-04-23 18:44 ` Erik Paulson

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=E14s7gz-0002fh-00@the-village.bc.nu \
    --to=alan@lxorguk.ukuu.org.uk \
    --cc=linux-kernel@vger.kernel.org \
    --cc=zandy@cs.wisc.edu \
    /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).