From: Hollis Blanchard <hollis_blanchard@mentor.com>
To: Liu Yu <yu.liu-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Cc: kvm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
kvm-ppc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
agraf-l3A5Bk7waGM@public.gmane.org
Subject: Re: [PATCH 0/2] kvm/e500v2: MMU optimization
Date: Wed, 08 Sep 2010 16:07:07 +0000 [thread overview]
Message-ID: <4C87B4AB.7010009@mentor.com> (raw)
In-Reply-To: <1283938806-2981-1-git-send-email-yu.liu-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
On 09/08/2010 02:40 AM, Liu Yu wrote:
> The patchset aims at mapping guest TLB1 to host TLB0.
> And it includes:
> [PATCH 1/2] kvm/e500v2: Remove shadow tlb
> [PATCH 2/2] kvm/e500v2: mapping guest TLB1 to host TLB0
>
> The reason we need patch 1 is because patch 1 make things simple and flexible.
> Only applying patch 1 aslo make kvm work.
I've always thought the best long-term "optimization" on these cores is
to share in the host PID allocation (i.e. __init_new_context()). This
way, the TID in guest mappings would not overlap the TID in host
mappings, and guest mappings could be demand-faulted rather than swapped
wholesale. To do that, you would need to track the host PID in KVM data
structures, I guess in the tlbe_ref structure.
--
Hollis Blanchard
Mentor Graphics, Embedded Systems Division
WARNING: multiple messages have this Message-ID (diff)
From: Hollis Blanchard <hollis_blanchard-nmGgyN9QBj3QT0dZR+AlfA@public.gmane.org>
To: Liu Yu <yu.liu-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Cc: kvm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
kvm-ppc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
agraf-l3A5Bk7waGM@public.gmane.org
Subject: Re: [PATCH 0/2] kvm/e500v2: MMU optimization
Date: Wed, 08 Sep 2010 09:07:07 -0700 [thread overview]
Message-ID: <4C87B4AB.7010009@mentor.com> (raw)
In-Reply-To: <1283938806-2981-1-git-send-email-yu.liu-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
On 09/08/2010 02:40 AM, Liu Yu wrote:
> The patchset aims at mapping guest TLB1 to host TLB0.
> And it includes:
> [PATCH 1/2] kvm/e500v2: Remove shadow tlb
> [PATCH 2/2] kvm/e500v2: mapping guest TLB1 to host TLB0
>
> The reason we need patch 1 is because patch 1 make things simple and flexible.
> Only applying patch 1 aslo make kvm work.
I've always thought the best long-term "optimization" on these cores is
to share in the host PID allocation (i.e. __init_new_context()). This
way, the TID in guest mappings would not overlap the TID in host
mappings, and guest mappings could be demand-faulted rather than swapped
wholesale. To do that, you would need to track the host PID in KVM data
structures, I guess in the tlbe_ref structure.
--
Hollis Blanchard
Mentor Graphics, Embedded Systems Division
next prev parent reply other threads:[~2010-09-08 16:07 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-09-08 9:40 [PATCH 0/2] kvm/e500v2: MMU optimization Liu Yu
2010-09-08 9:40 ` Liu Yu
[not found] ` <1283938806-2981-1-git-send-email-yu.liu-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
2010-09-08 9:40 ` [PATCH 1/2] kvm/e500v2: Remove shadow tlb Liu Yu
2010-09-08 9:40 ` Liu Yu
2010-09-08 9:40 ` [PATCH 2/2] kvm/e500v2: mapping guest TLB1 to host TLB0 Liu Yu
2010-09-08 9:40 ` Liu Yu
[not found] ` <1283938806-2981-3-git-send-email-yu.liu-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
2010-09-09 23:24 ` Alexander Graf
2010-09-09 23:24 ` Alexander Graf
[not found] ` <E759E1E3-7457-41B7-B36E-75FA42E107B1-l3A5Bk7waGM@public.gmane.org>
2010-09-15 9:29 ` Alexander Graf
2010-09-15 9:29 ` Alexander Graf
2010-09-16 11:35 ` Liu Yu-B13201
2010-09-16 11:35 ` Liu Yu-B13201
[not found] ` <A9833F0F7901024DA08417AA5A9887D921DD39-bKEhWGtIRUJ4Lp7cDGe+DVjVikpgYyvb5NbjCUgZEJk@public.gmane.org>
2010-09-16 11:44 ` Alexander Graf
2010-09-16 11:44 ` Alexander Graf
2010-09-17 8:47 ` Liu Yu-B13201
2010-09-17 8:47 ` Liu Yu-B13201
[not found] ` <A9833F0F7901024DA08417AA5A9887D921DE82-bKEhWGtIRUJ4Lp7cDGe+DVjVikpgYyvb5NbjCUgZEJk@public.gmane.org>
2010-09-17 10:19 ` Alexander Graf
2010-09-17 10:19 ` Alexander Graf
2010-09-17 11:28 ` Liu Yu-B13201
2010-09-17 11:28 ` Liu Yu-B13201
[not found] ` <A9833F0F7901024DA08417AA5A9887D921DE99-bKEhWGtIRUJ4Lp7cDGe+DVjVikpgYyvb5NbjCUgZEJk@public.gmane.org>
2010-09-17 11:34 ` Alexander Graf
2010-09-17 11:34 ` Alexander Graf
2010-09-17 12:33 ` Liu Yu-B13201
2010-09-17 12:33 ` Liu Yu-B13201
2010-09-17 12:34 ` Alexander Graf
2010-09-17 12:34 ` Alexander Graf
[not found] ` <1283938806-2981-2-git-send-email-yu.liu-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
2010-09-08 16:06 ` [PATCH 1/2] kvm/e500v2: Remove shadow tlb Hollis Blanchard
2010-09-08 16:06 ` Hollis Blanchard
2010-09-09 11:16 ` Liu Yu-B13201
2010-09-09 11:16 ` Liu Yu-B13201
[not found] ` <A9833F0F7901024DA08417AA5A9887D91BF24A-bKEhWGtIRUJ4Lp7cDGe+DVjVikpgYyvb5NbjCUgZEJk@public.gmane.org>
2010-09-09 18:13 ` Hollis Blanchard
2010-09-09 18:13 ` Hollis Blanchard
[not found] ` <4C8923D2.5070308-nmGgyN9QBj3QT0dZR+AlfA@public.gmane.org>
2010-09-09 23:26 ` Alexander Graf
2010-09-09 23:26 ` Alexander Graf
[not found] ` <C1EBC75A-91B0-49D9-8AD5-571C6BAF22B7-l3A5Bk7waGM@public.gmane.org>
2010-09-09 23:39 ` Hollis Blanchard
2010-09-09 23:39 ` Hollis Blanchard
2010-09-09 23:42 ` Alexander Graf
2010-09-09 23:42 ` Alexander Graf
2010-09-08 16:07 ` Hollis Blanchard [this message]
2010-09-08 16:07 ` [PATCH 0/2] kvm/e500v2: MMU optimization Hollis Blanchard
[not found] ` <4C87B4AB.7010009-nmGgyN9QBj3QT0dZR+AlfA@public.gmane.org>
2010-09-09 11:03 ` Liu Yu-B13201
2010-09-09 11:03 ` Liu Yu-B13201
[not found] ` <A9833F0F7901024DA08417AA5A9887D91BF248-bKEhWGtIRUJ4Lp7cDGe+DVjVikpgYyvb5NbjCUgZEJk@public.gmane.org>
2010-09-09 16:23 ` Hollis Blanchard
2010-09-09 16:23 ` Hollis Blanchard
2010-09-10 2:59 ` Liu Yu-B13201
2010-09-10 2:59 ` Liu Yu-B13201
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=4C87B4AB.7010009@mentor.com \
--to=hollis_blanchard@mentor.com \
--cc=agraf-l3A5Bk7waGM@public.gmane.org \
--cc=kvm-ppc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=kvm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=yu.liu-KZfg59tc24xl57MIdRCFDg@public.gmane.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.