From: Martin Schwidefsky <schwidefsky@de.ibm.com>
To: Dave Hansen <haveblue@us.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>,
linux-kernel@vger.kernel.org, virtualization@lists.osdl.org,
akpm@osdl.org, nickpiggin@yahoo.com.au, frankeh@watson.ibm.com
Subject: Re: [patch 3/9] Guest page hinting: volatile page cache.
Date: Fri, 01 Sep 2006 19:42:00 +0200 [thread overview]
Message-ID: <1157132520.21733.78.camel@localhost> (raw)
In-Reply-To: <1157130970.28577.150.camel@localhost.localdomain>
On Fri, 2006-09-01 at 10:16 -0700, Dave Hansen wrote:
> This feels like something that can be done with RCU. The
> __page_discard() is the write operation, right? So, take an rcu write
> lock inside of the page discard function, and read locks over the
> current places where PG_discarded is set.
>
> That should make sure that the discard operation itself can't be done
> concurrently with one of the __remove_from*() operations. Once the
> write lock has been acquired, you just check page->mapping to see if the
> a __remove_from*() operation has occurred while you waited.
The problem of page discard vs. normal page remove is that the page can
be remove and discarded at the same time. Both sides are writers in the
sense that they want to remove the page from page cache. RCU doesn't not
help with that kind of race.
--
blue skies,
Martin.
Martin Schwidefsky
Linux for zSeries Development & Services
IBM Deutschland Entwicklung GmbH
"Reality continues to ruin my life." - Calvin.
next prev parent reply other threads:[~2006-09-01 17:42 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-09-01 11:09 [patch 3/9] Guest page hinting: volatile page cache Martin Schwidefsky
2006-09-01 14:54 ` Dave Hansen
2006-09-01 15:29 ` Martin Schwidefsky
2006-09-01 15:37 ` Dave Hansen
2006-09-01 14:57 ` Dave Hansen
2006-09-01 15:31 ` Martin Schwidefsky
2006-09-01 15:48 ` Andy Whitcroft
2006-09-01 16:04 ` Martin Schwidefsky
2006-09-01 16:18 ` Dave Hansen
2006-09-01 16:25 ` Martin Schwidefsky
2006-09-01 16:37 ` Dave Hansen
2006-09-01 16:56 ` Martin Schwidefsky
2006-09-01 17:16 ` Dave Hansen
2006-09-01 17:42 ` Martin Schwidefsky [this message]
2006-09-01 18:03 ` Dave Hansen
2006-09-01 18:04 ` Martin Schwidefsky
2006-09-01 18:23 ` Dave Hansen
2006-09-01 18:31 ` Martin Schwidefsky
2006-09-01 18:41 ` Dave Hansen
2006-09-04 11:21 ` Martin Schwidefsky
2006-09-05 18:27 ` Dave Hansen
2006-09-06 10:49 ` Martin Schwidefsky
2006-09-01 16:29 ` Dave Hansen
2006-09-01 17:02 ` Martin Schwidefsky
2006-09-01 17:05 ` Dave Hansen
2006-09-13 18:21 ` Zachary Amsden
2006-09-14 8:56 ` Martin Schwidefsky
2006-09-14 9:23 ` Zachary Amsden
2006-09-15 8:36 ` Martin Schwidefsky
-- strict thread matches above, loose matches on Subject: below --
2006-09-15 17:50 Chuck Ebbert
2006-09-18 8:08 ` Martin Schwidefsky
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=1157132520.21733.78.camel@localhost \
--to=schwidefsky@de.ibm.com \
--cc=akpm@osdl.org \
--cc=apw@shadowen.org \
--cc=frankeh@watson.ibm.com \
--cc=haveblue@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
--cc=virtualization@lists.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 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).