From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Keir Fraser <keir.fraser@eu.citrix.com>
Cc: Avi Kivity <avi@qumranet.com>, Ingo Molnar <mingo@elte.hu>,
Xen Devel <xen-devel@lists.xensource.com>,
Andi Kleen <andi@firstfloor.org>,
linux-kernel@vger.kernel.org, "H. Peter Anvin" <hpa@zytor.com>
Subject: Re: [Xen-devel] Re: [PATCH 1 of 7] x86: add _PAGE_IOMAP pte flag for IO mappings
Date: Tue, 09 Sep 2008 08:48:06 -0700 [thread overview]
Message-ID: <48C69AB6.20500@goop.org> (raw)
In-Reply-To: <C4EC54D0.26EEA%keir.fraser@eu.citrix.com>
Keir Fraser wrote:
> That's basically what our _PAGE_IO flag (in our old Linux patchset) means.
> We use it to cause pte_pfn() to return an invalid pfn and hence avoid
> reference counting that way. Since kernel mappings are never reference
> counted (I think?) perhaps we could use _PAGE_SPECIAL even if it is
> restricted to use on user mappings.
Well, _PAGE_IOMAP's most important semantic from Xen's perspective is
that the frame number is considered to already be an MFN and so isn't
converted. It may be that _PAGE_SPECIAL is also useful for its "no
refcount" properties, but we could set both in that case.
At present we can't set _PAGE_SPECIAL on kernel mappings because we
assume its usermode only, and its shared with _PAGE_CPA_TEST which is
kernel-only. Most _PAGE_IOMAP mappings are in kernel space, but I
wouldn't discount user mappings if we end up allowing direct access to
passthrough devices.
J
WARNING: multiple messages have this Message-ID (diff)
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Keir Fraser <keir.fraser@eu.citrix.com>
Cc: Xen Devel <xen-devel@lists.xensource.com>,
linux-kernel@vger.kernel.org, Avi Kivity <avi@qumranet.com>,
Andi Kleen <andi@firstfloor.org>,
"H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@elte.hu>
Subject: Re: Re: [PATCH 1 of 7] x86: add _PAGE_IOMAP pte flag for IO mappings
Date: Tue, 09 Sep 2008 08:48:06 -0700 [thread overview]
Message-ID: <48C69AB6.20500@goop.org> (raw)
In-Reply-To: <C4EC54D0.26EEA%keir.fraser@eu.citrix.com>
Keir Fraser wrote:
> That's basically what our _PAGE_IO flag (in our old Linux patchset) means.
> We use it to cause pte_pfn() to return an invalid pfn and hence avoid
> reference counting that way. Since kernel mappings are never reference
> counted (I think?) perhaps we could use _PAGE_SPECIAL even if it is
> restricted to use on user mappings.
Well, _PAGE_IOMAP's most important semantic from Xen's perspective is
that the frame number is considered to already be an MFN and so isn't
converted. It may be that _PAGE_SPECIAL is also useful for its "no
refcount" properties, but we could set both in that case.
At present we can't set _PAGE_SPECIAL on kernel mappings because we
assume its usermode only, and its shared with _PAGE_CPA_TEST which is
kernel-only. Most _PAGE_IOMAP mappings are in kernel space, but I
wouldn't discount user mappings if we end up allowing direct access to
passthrough devices.
J
next prev parent reply other threads:[~2008-09-09 15:48 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-09-07 22:21 [PATCH 0 of 7] x86: lay groundwork for Xen domain 0 support Jeremy Fitzhardinge
2008-09-07 22:21 ` [PATCH 1 of 7] x86: add _PAGE_IOMAP pte flag for IO mappings Jeremy Fitzhardinge
2008-09-09 13:32 ` Avi Kivity
2008-09-09 13:32 ` Avi Kivity
2008-09-09 14:47 ` Jeremy Fitzhardinge
2008-09-09 14:47 ` Jeremy Fitzhardinge
2008-09-09 14:56 ` Avi Kivity
2008-09-09 14:56 ` Avi Kivity
2008-09-09 15:29 ` [Xen-devel] " Keir Fraser
2008-09-09 15:29 ` Keir Fraser
2008-09-09 15:48 ` Jeremy Fitzhardinge [this message]
2008-09-09 15:48 ` Jeremy Fitzhardinge
2008-09-09 16:05 ` [Xen-devel] " Keir Fraser
2008-09-09 16:05 ` Keir Fraser
2008-09-10 9:55 ` [Xen-devel] " Avi Kivity
2008-09-10 9:55 ` Avi Kivity
2008-09-10 16:38 ` [Xen-devel] " Jeremy Fitzhardinge
2008-09-10 16:38 ` Jeremy Fitzhardinge
2008-09-10 16:55 ` [Xen-devel] " Nick Piggin
2008-09-10 17:27 ` Jeremy Fitzhardinge
2008-09-07 22:21 ` [PATCH 2 of 7] x86: remove duplicate early_ioremap declarations Jeremy Fitzhardinge
2008-09-07 22:21 ` Jeremy Fitzhardinge
2008-09-07 22:21 ` [PATCH 3 of 7] x86: add early_memremap() Jeremy Fitzhardinge
2008-09-07 22:21 ` Jeremy Fitzhardinge
2008-09-07 22:21 ` [PATCH 4 of 7] x86: use early_memremap() in setup.c Jeremy Fitzhardinge
2008-09-07 22:21 ` [PATCH 5 of 7] x86-64: don't check for map replacement Jeremy Fitzhardinge
2008-09-07 22:21 ` [PATCH 6 of 7] x86: use early_ioremap in __acpi_map_table Jeremy Fitzhardinge
2008-09-07 23:44 ` Andi Kleen
2008-09-08 0:03 ` Jeremy Fitzhardinge
2008-09-08 0:03 ` Jeremy Fitzhardinge
2008-09-08 14:26 ` Ingo Molnar
2008-09-08 14:26 ` Ingo Molnar
2008-09-08 16:29 ` Jeremy Fitzhardinge
2008-09-08 16:29 ` Jeremy Fitzhardinge
2008-09-08 19:41 ` Jeremy Fitzhardinge
2008-09-08 19:41 ` Jeremy Fitzhardinge
2008-09-10 11:55 ` Ingo Molnar
2008-09-10 16:49 ` Jeremy Fitzhardinge
2008-09-11 7:33 ` Ingo Molnar
2008-09-11 18:36 ` Jeremy Fitzhardinge
2008-09-11 18:56 ` Ingo Molnar
2008-09-11 20:34 ` Yinghai Lu
2008-09-11 21:07 ` Jeremy Fitzhardinge
2008-09-12 9:49 ` Ingo Molnar
2008-09-12 17:31 ` Yinghai Lu
[not found] ` <20080911125748.GA14698@elte.hu>
2008-09-11 21:33 ` [PATCH] acpi: remove final __acpi_map_table mapping before setting acpi_gbl_permanent_mmap Jeremy Fitzhardinge
2008-09-07 22:21 ` [PATCH 7 of 7] x86: always explicitly map acpi memory Jeremy Fitzhardinge
2008-09-07 23:35 ` [Xen-devel] " Yinghai Lu
2008-09-07 23:35 ` Yinghai Lu
2008-09-08 0:02 ` [Xen-devel] " Jeremy Fitzhardinge
2008-09-08 0:02 ` Jeremy Fitzhardinge
2008-09-08 0:14 ` [Xen-devel] " Yinghai Lu
2008-09-08 0:14 ` Yinghai Lu
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=48C69AB6.20500@goop.org \
--to=jeremy@goop.org \
--cc=andi@firstfloor.org \
--cc=avi@qumranet.com \
--cc=hpa@zytor.com \
--cc=keir.fraser@eu.citrix.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=xen-devel@lists.xensource.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.