From: Avi Kivity <avi@redhat.com>
To: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Anton D Kachalov <mouse@mayc.ru>,
"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
Lennart Sorensen <lsorense@csclub.uwaterloo.ca>
Subject: [Qemu-devel] Re: POLL: Why do you use kqemu?
Date: Mon, 08 Jun 2009 16:06:44 +0300 [thread overview]
Message-ID: <4A2D0CE4.9080405@redhat.com> (raw)
In-Reply-To: <4A2D07A3.8090101@siemens.com>
Jan Kiszka wrote:
> And the fact that kqemu has to use tcg in order to achieve a reasonable
> performance is rather a disadvantage. The complexity and overhead for
> synchronizing tcg with the in-kernel accelerator is enormous. If there
> were a feasible way to overcome this with kqemu, it would benefit a lot.
> But unfortunately there is none (given you don't want to invest
> reasonable efforts).
>
Note that kvm suffers from something similar (to a smaller magnitude) as
well: if a guest pages in its page tables, kvm knows nothing about it
and will thus have outdated shadows. To date we haven't encountered a
problem with it, but it's conceivable. I think Windows can page its
page tables, but maybe it's disabled by default, or maybe it doesn't dma
directly into the page tables.
Not sure how to fix. Maybe write protect the host page tables when we
shadow a page table, and get an mmu notifier to tell us when its made
writable? Seems expensive. Burying head in sand is much easier.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2009-06-08 13:07 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-03 21:57 [Qemu-devel] POLL: Why do you use kqemu? Anthony Liguori
2009-06-04 16:55 ` Anton D Kachalov
2009-06-05 0:44 ` Johannes Schindelin
2009-06-05 7:45 ` Gerd Hoffmann
2009-06-05 8:40 ` Tomasz Chmielewski
2009-06-05 9:08 ` Anton D Kachalov
2009-06-05 9:15 ` Gerd Hoffmann
2009-06-05 20:14 ` Lennart Sorensen
2009-06-05 23:23 ` Johannes Schindelin
2009-06-08 0:13 ` Jamie Lokier
2009-06-08 5:59 ` Avi Kivity
2009-06-08 11:57 ` Jamie Lokier
2009-06-08 12:03 ` Avi Kivity
2009-06-08 12:16 ` Jamie Lokier
2009-06-08 12:28 ` Avi Kivity
2009-06-08 12:44 ` [Qemu-devel] " Jan Kiszka
2009-06-08 13:06 ` Avi Kivity [this message]
2009-06-08 13:18 ` Jan Kiszka
2009-06-08 13:24 ` Avi Kivity
2009-06-08 13:44 ` Jan Kiszka
2009-06-08 14:03 ` Avi Kivity
2009-06-08 12:36 ` Jan Kiszka
2009-06-08 18:25 ` [Qemu-devel] " Lennart Sorensen
2009-06-06 13:27 ` Andreas Färber
2009-06-06 16:02 ` Avi Kivity
2009-06-06 16:29 ` Blue Swirl
2009-06-06 17:02 ` [Qemu-devel] " Jan Kiszka
2009-06-06 17:25 ` Blue Swirl
2009-06-06 17:32 ` Jan Kiszka
2009-06-06 19:15 ` Andreas Färber
2009-06-07 5:43 ` Avi Kivity
2009-06-07 5:01 ` Avi Kivity
2009-06-07 7:35 ` Jan Kiszka
2009-06-07 7:46 ` Avi Kivity
2009-06-07 8:33 ` Blue Swirl
2009-06-07 8:50 ` Jan Kiszka
2009-06-07 9:01 ` Blue Swirl
2009-06-07 9:25 ` Jan Kiszka
2009-06-07 9:37 ` Avi Kivity
2009-06-07 9:47 ` Jan Kiszka
2009-06-07 9:52 ` Avi Kivity
2009-06-07 9:56 ` Jan Kiszka
2009-06-07 10:06 ` Avi Kivity
2009-06-07 11:13 ` Blue Swirl
2009-06-07 11:23 ` Gleb Natapov
2009-06-07 11:26 ` Blue Swirl
2009-06-07 11:29 ` Gleb Natapov
2009-06-07 11:39 ` Avi Kivity
2009-06-07 12:40 ` Blue Swirl
2009-06-07 12:43 ` Avi Kivity
2009-06-07 12:52 ` Gleb Natapov
2009-06-07 12:56 ` Avi Kivity
2009-06-07 13:18 ` Blue Swirl
2009-06-07 13:35 ` Jan Kiszka
2009-06-07 13:35 ` Avi Kivity
2009-06-07 18:37 ` Anthony Liguori
2009-06-07 18:40 ` Blue Swirl
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=4A2D0CE4.9080405@redhat.com \
--to=avi@redhat.com \
--cc=jan.kiszka@siemens.com \
--cc=lsorense@csclub.uwaterloo.ca \
--cc=mouse@mayc.ru \
--cc=qemu-devel@nongnu.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).