From: Martin Schwidefsky <schwidefsky@de.ibm.com>
To: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Avi Kivity <avi@redhat.com>,
Nick Piggin <nickpiggin@yahoo.com.au>,
Hugh Dickens <hugh@veritas.com>,
Linux Memory Management List <linux-mm@kvack.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Rik van Riel <riel@redhat.com>,
Marcelo Tosatti <mtosatti@redhat.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: Re: Populating multiple ptes at fault time
Date: Fri, 26 Sep 2008 12:26:27 +0200 [thread overview]
Message-ID: <1222424787.22679.17.camel@localhost> (raw)
In-Reply-To: <48DBD94A.50905@goop.org>
On Thu, 2008-09-25 at 11:32 -0700, Jeremy Fitzhardinge wrote:
> Very few places actually care about the state of the A/D bits; would it
> be expensive to make those places explicitly ask for synchronization
> before testing the bits (or alternatively, have an explicit query
> operation rather than just poking about in the ptes). Martin, does this
> help with s390's per-page (vs per-pte) A/D state?
With the kvm support the situation on s390 recently has grown a tad more
complicated. We now have dirty bits in the per-page storage key and in
the pgste (page table entry extension) for the kvm guests. For the A/D
bits in the storage key the new pte operations won't help, for the kvm
related bits they could make a difference.
--
blue skies,
Martin.
"Reality continues to ruin my life." - Calvin.
WARNING: multiple messages have this Message-ID (diff)
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
To: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Avi Kivity <avi@redhat.com>,
Nick Piggin <nickpiggin@yahoo.com.au>,
Hugh Dickens <hugh@veritas.com>,
Linux Memory Management List <linux-mm@kvack.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Rik van Riel <riel@redhat.com>,
Marcelo Tosatti <mtosatti@redhat.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: Re: Populating multiple ptes at fault time
Date: Fri, 26 Sep 2008 12:26:27 +0200 [thread overview]
Message-ID: <1222424787.22679.17.camel@localhost> (raw)
In-Reply-To: <48DBD94A.50905@goop.org>
On Thu, 2008-09-25 at 11:32 -0700, Jeremy Fitzhardinge wrote:
> Very few places actually care about the state of the A/D bits; would it
> be expensive to make those places explicitly ask for synchronization
> before testing the bits (or alternatively, have an explicit query
> operation rather than just poking about in the ptes). Martin, does this
> help with s390's per-page (vs per-pte) A/D state?
With the kvm support the situation on s390 recently has grown a tad more
complicated. We now have dirty bits in the per-page storage key and in
the pgste (page table entry extension) for the kvm guests. For the A/D
bits in the storage key the new pte operations won't help, for the kvm
related bits they could make a difference.
--
blue skies,
Martin.
"Reality continues to ruin my life." - Calvin.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2008-09-26 10:43 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-09-17 17:47 Populating multiple ptes at fault time Jeremy Fitzhardinge
2008-09-17 17:47 ` Jeremy Fitzhardinge
2008-09-17 18:28 ` Rik van Riel
2008-09-17 18:28 ` Rik van Riel
2008-09-17 21:47 ` Jeremy Fitzhardinge
2008-09-17 21:47 ` Jeremy Fitzhardinge
2008-09-17 20:02 ` Chris Snook
2008-09-17 20:02 ` Chris Snook
2008-09-17 21:45 ` Jeremy Fitzhardinge
2008-09-17 21:45 ` Jeremy Fitzhardinge
2008-09-18 18:16 ` Christoph Lameter
2008-09-18 18:16 ` Christoph Lameter
2008-09-18 18:53 ` Jeremy Fitzhardinge
2008-09-18 18:53 ` Jeremy Fitzhardinge
2008-09-18 19:39 ` Christoph Lameter
2008-09-18 19:39 ` Christoph Lameter
2008-09-18 22:21 ` KOSAKI Motohiro
2008-09-18 22:21 ` KOSAKI Motohiro
2008-09-18 20:52 ` Martin Bligh
2008-09-18 20:52 ` Martin Bligh
2008-09-18 20:53 ` Chris Snook
2008-09-18 20:53 ` Chris Snook
2008-09-18 21:11 ` Martin Bligh
2008-09-18 21:11 ` Martin Bligh
2008-09-18 21:13 ` Christoph Lameter
2008-09-18 21:13 ` Christoph Lameter
2008-09-18 21:21 ` Martin Bligh
2008-09-18 21:21 ` Martin Bligh
2008-09-18 21:32 ` Christoph Lameter
2008-09-18 21:32 ` Christoph Lameter
2008-09-18 21:49 ` MinChan Kim
2008-09-18 21:49 ` MinChan Kim
2008-09-18 21:58 ` Christoph Lameter
2008-09-18 21:58 ` Christoph Lameter
2008-09-18 22:08 ` Martin Bligh
2008-09-18 22:08 ` Martin Bligh
2008-09-18 22:11 ` Christoph Lameter
2008-09-18 22:11 ` Christoph Lameter
2008-09-18 22:18 ` Martin Bligh
2008-09-18 22:18 ` Martin Bligh
2008-09-18 22:22 ` Jeremy Fitzhardinge
2008-09-18 22:22 ` Jeremy Fitzhardinge
2008-09-18 22:23 ` Chris Snook
2008-09-18 22:23 ` Chris Snook
2008-09-18 23:16 ` MinChan Kim
2008-09-18 23:16 ` MinChan Kim
2008-09-17 22:02 ` Avi Kivity
2008-09-17 22:02 ` Avi Kivity
2008-09-17 22:30 ` Jeremy Fitzhardinge
2008-09-17 22:30 ` Jeremy Fitzhardinge
2008-09-17 22:47 ` Avi Kivity
2008-09-17 22:47 ` Avi Kivity
2008-09-17 23:02 ` Jeremy Fitzhardinge
2008-09-17 23:02 ` Jeremy Fitzhardinge
2008-09-18 20:26 ` Avi Kivity
2008-09-18 20:26 ` Avi Kivity
2008-09-18 22:18 ` Jeremy Fitzhardinge
2008-09-18 22:18 ` Jeremy Fitzhardinge
2008-09-18 23:38 ` Avi Kivity
2008-09-18 23:38 ` Avi Kivity
2008-09-19 0:00 ` Jeremy Fitzhardinge
2008-09-19 0:00 ` Jeremy Fitzhardinge
2008-09-19 0:20 ` Avi Kivity
2008-09-19 0:20 ` Avi Kivity
2008-09-19 0:42 ` Jeremy Fitzhardinge
2008-09-19 0:42 ` Jeremy Fitzhardinge
2008-09-24 12:31 ` Avi Kivity
2008-09-24 12:31 ` Avi Kivity
2008-09-25 18:32 ` Jeremy Fitzhardinge
2008-09-25 18:32 ` Jeremy Fitzhardinge
2008-09-26 10:26 ` Martin Schwidefsky [this message]
2008-09-26 10:26 ` Martin Schwidefsky
2008-09-19 17:45 ` Benjamin Herrenschmidt
2008-09-19 17:45 ` Benjamin Herrenschmidt
2008-09-17 23:50 ` MinChan Kim
2008-09-17 23:50 ` MinChan Kim
2008-09-18 6:58 ` KOSAKI Motohiro
2008-09-18 6:58 ` KOSAKI Motohiro
2008-09-18 7:26 ` KAMEZAWA Hiroyuki
2008-09-18 7:26 ` KAMEZAWA Hiroyuki
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=1222424787.22679.17.camel@localhost \
--to=schwidefsky@de.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=avi@redhat.com \
--cc=benh@kernel.crashing.org \
--cc=hugh@veritas.com \
--cc=jeremy@goop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mtosatti@redhat.com \
--cc=nickpiggin@yahoo.com.au \
--cc=riel@redhat.com \
/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.