From: NIIBE Yutaka <gniibe@fsij.org>
To: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: linux-parisc@vger.kernel.org,
pkg-gauche-devel@lists.alioth.debian.org, 561203@bugs.debian.org
Subject: Re: threads and fork on machine with VIPT-WB cache
Date: Fri, 02 Apr 2010 12:48:11 +0900 [thread overview]
Message-ID: <4BB568FB.1090908@fsij.org> (raw)
In-Reply-To: <1270179025.18981.19.camel@mulgrave.site>
Thanks for your quick reply.
James Bottomley wrote:
> In COW breaking, the page table entry is copied, so A and B no longer
> have page table entries at the same physical location. If the COW is
> intact, A and B have the same physical page, but it's also accessed by
> the same virtual address, hence no aliasing.
Let me explain more.
In the scenario, I assume:
No aliasing between A and B.
We have aliasing between kernel access and user access.
Before COW breaking A and B share same data (with no aliasing same
space identifier color), and B sees data in cache, while memory has
stale data.
At COW breaking, kernel copies the memory, it doesn't see new data
in cache because of aliasing.
Isn't it possible?
--
next prev parent reply other threads:[~2010-04-02 3:48 UTC|newest]
Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <4BA43CE5.4020807@fsij.org>
[not found] ` <87hbo4ek8l.fsf@thialfi.karme.de>
[not found] ` <4BB18B46.2070203@fsij.org>
[not found] ` <4BB53D26.60601@fsij.org>
2010-04-02 2:41 ` threads and fork on machine with VIPT-WB cache NIIBE Yutaka
2010-04-02 3:30 ` James Bottomley
2010-04-02 3:48 ` NIIBE Yutaka [this message]
2010-04-02 8:05 ` NIIBE Yutaka
2010-04-02 19:35 ` John David Anglin
2010-04-08 21:11 ` Helge Deller
2010-04-08 21:54 ` John David Anglin
2010-04-08 22:44 ` John David Anglin
2010-04-09 14:14 ` Carlos O'Donell
2010-04-09 15:13 ` John David Anglin
2010-04-09 15:48 ` James Bottomley
2010-04-09 16:22 ` John David Anglin
2010-04-09 16:31 ` James Bottomley
2010-04-10 20:46 ` Helge Deller
2010-04-10 21:56 ` John David Anglin
2010-04-10 22:53 ` John David Anglin
2010-04-11 18:50 ` Helge Deller
2010-04-11 22:25 ` John David Anglin
2010-04-12 21:02 ` Helge Deller
2010-04-12 21:41 ` John David Anglin
2010-04-13 11:55 ` Helge Deller
2010-04-13 14:03 ` John David Anglin
2010-04-15 22:35 ` John David Anglin
2010-04-19 16:26 ` John David Anglin
2010-04-20 17:59 ` Helge Deller
2010-04-20 18:52 ` John David Anglin
2010-05-09 12:43 ` John David Anglin
2010-05-09 14:14 ` Carlos O'Donell
2010-05-10 9:56 ` Helge Deller
2010-05-10 14:56 ` John David Anglin
2010-05-10 19:20 ` Helge Deller
2010-05-10 21:07 ` John David Anglin
2010-05-11 16:37 ` John David Anglin
2010-05-11 21:39 ` John David Anglin
2010-05-11 20:44 ` Helge Deller
2010-05-11 20:41 ` Helge Deller
2010-05-11 21:26 ` John David Anglin
2010-05-11 21:41 ` Helge Deller
2010-05-15 21:02 ` John David Anglin
2010-05-16 20:22 ` Helge Deller
2010-05-16 21:38 ` John David Anglin
2010-05-22 17:25 ` John David Anglin
2010-05-23 13:11 ` Carlos O'Donell
2010-05-23 14:43 ` John David Anglin
2010-05-01 18:34 ` Thibaut VARENE
2010-05-01 20:17 ` John David Anglin
2010-05-02 10:53 ` Thibaut VARÈNE
2010-04-11 16:36 ` [PATCH] Call pagefault_disable/pagefault_enable in kmap_atomic/kunmap_atomic John David Anglin
2010-04-11 17:03 ` [PATCH] Remove unnecessary macros from entry.S John David Anglin
2010-04-11 17:08 ` [PATCH] Delete unnecessary nop's in entry.S John David Anglin
2010-04-11 17:12 ` [PATCH] Avoid interruption in critical region " John David Anglin
2010-04-11 18:24 ` James Bottomley
2010-04-11 18:45 ` John David Anglin
2010-04-11 18:53 ` James Bottomley
2010-04-11 17:26 ` [PATCH] LWS fixes for syscall.S John David Anglin
2010-06-02 15:33 ` Bug#561203: threads and fork on machine with VIPT-WB cache Modestas Vainius
2010-06-02 17:16 ` John David Anglin
2010-06-02 17:56 ` Bug#561203: " dann frazier
2010-06-03 8:50 ` Modestas Vainius
2010-06-04 1:03 ` NIIBE Yutaka
2010-06-04 5:21 ` dann frazier
2010-06-04 10:44 ` Thibaut VARENE
2010-06-07 17:11 ` dann frazier
2010-06-07 18:27 ` Thibaut VARÈNE
2010-06-07 23:33 ` dann frazier
2010-06-06 1:01 ` Modestas Vainius
2010-04-02 12:22 ` James Bottomley
2010-04-05 0:39 ` NIIBE Yutaka
2010-04-05 2:51 ` John David Anglin
2010-04-05 2:58 ` John David Anglin
2010-04-05 16:18 ` James Bottomley
2010-04-06 4:57 ` NIIBE Yutaka
2010-04-06 13:37 ` James Bottomley
2010-04-06 13:44 ` James Bottomley
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=4BB568FB.1090908@fsij.org \
--to=gniibe@fsij.org \
--cc=561203@bugs.debian.org \
--cc=James.Bottomley@HansenPartnership.com \
--cc=linux-parisc@vger.kernel.org \
--cc=pkg-gauche-devel@lists.alioth.debian.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.