From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
Martin Pohlack <mpohlack@amazon.com>
Cc: Elena Ufimtseva <elena.ufimtseva@oracle.com>,
jeremy@goop.org, hanweidong@huawei.com, jbeulich@suse.com,
john.liuqiming@huawei.com,
Paul Voccio <paul.voccio@rackspace.com>,
Daniel Kiper <daniel.kiper@oracle.com>,
Major Hayden <major.hayden@rackspace.com>,
liuyingdong@huawei.com, aliguori@amazon.com,
xiantao.zxt@alibaba-inc.com, lars.kurth@citrix.com,
Steven Wilson <steven.wilson@rackspace.com>,
peter.huangpeng@huawei.com, msw@amazon.com,
xen-devel@lists.xenproject.org,
Rick Harris <rick.harris@rackspace.com>,
boris.ostrovsky@oracle.com,
Josh Kearney <josh.kearney@rackspace.com>,
jinsong.liu@alibaba-inc.com,
Antony Messerli <amesserl@rackspace.com>,
konrad@darnok.org, fanhenglong@huawei.com
Subject: Re: [RFC v2] xSplice design
Date: Fri, 5 Jun 2015 16:15:29 +0100 [thread overview]
Message-ID: <5571BD11.4070909@citrix.com> (raw)
In-Reply-To: <20150605150029.GC10207@l.oracle.com>
On 05/06/15 16:00, Konrad Rzeszutek Wilk wrote:
>> As you discussed, if you allocate hotpatch memory withing +-2GB of the
>> > patch location, no further trampoline indirection is required, a
>> > 5-byte JMP does the trick on x86. We found that to be sufficient in
>> > our experiments.
> And worst case if you do need more than +-2GB you can just have
> two jumps. Kind of silly but possible.
>
> Thank you for your input and lookign forward to your reply!
The Xen combined text/rodata/data/init/bss size is currently less than
4MB. The alignment for superpages bumps this to 12MB (so plenty of free
space), and arbitrary extra space can be inserted if wanted. Xen has
(just less than) 1GB of virtual space reserved for this area.
If a hotpatch is going to blow these limits, you have bigger problems to
worry about.
~Andrew
next prev parent reply other threads:[~2015-06-05 15:15 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-15 19:44 [RFC v2] xSplice design Konrad Rzeszutek Wilk
2015-05-18 12:41 ` Jan Beulich
2015-06-05 14:49 ` Konrad Rzeszutek Wilk
2015-06-05 15:16 ` Jan Beulich
2015-06-05 16:00 ` Konrad Rzeszutek Wilk
2015-06-05 16:14 ` Jan Beulich
2015-05-18 12:54 ` Liuqiming (John)
2015-05-18 13:11 ` Daniel Kiper
2015-06-05 14:50 ` Konrad Rzeszutek Wilk
2015-05-19 19:13 ` Lars Kurth
2015-05-20 15:11 ` Martin Pohlack
2015-06-05 15:00 ` Konrad Rzeszutek Wilk
2015-06-05 15:15 ` Andrew Cooper [this message]
2015-06-05 15:27 ` Jan Beulich
2015-06-08 8:34 ` Martin Pohlack
2015-06-08 8:51 ` Jan Beulich
2015-06-08 14:38 ` Martin Pohlack
2015-06-08 15:19 ` Konrad Rzeszutek Wilk
2015-06-12 11:51 ` Martin Pohlack
2015-06-12 14:06 ` Konrad Rzeszutek Wilk
2015-06-12 11:39 ` Martin Pohlack
2015-06-12 14:03 ` Konrad Rzeszutek Wilk
2015-06-12 14:31 ` Martin Pohlack
2015-06-12 14:43 ` Jan Beulich
2015-06-12 17:31 ` Martin Pohlack
2015-06-12 18:46 ` Konrad Rzeszutek Wilk
2015-06-12 16:09 ` Konrad Rzeszutek Wilk
2015-06-12 16:17 ` Andrew Cooper
2015-06-12 16:39 ` Konrad Rzeszutek Wilk
2015-06-12 18:36 ` Martin Pohlack
2015-06-12 18:51 ` Konrad Rzeszutek Wilk
2015-07-06 19:36 ` Konrad Rzeszutek Wilk
2015-10-27 12:05 ` Ross Lagerwall
2015-10-29 16:55 ` Ross Lagerwall
2015-10-30 10:39 ` Martin Pohlack
2015-10-30 14:03 ` Ross Lagerwall
2015-10-30 14:06 ` Martin Pohlack
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=5571BD11.4070909@citrix.com \
--to=andrew.cooper3@citrix.com \
--cc=aliguori@amazon.com \
--cc=amesserl@rackspace.com \
--cc=boris.ostrovsky@oracle.com \
--cc=daniel.kiper@oracle.com \
--cc=elena.ufimtseva@oracle.com \
--cc=fanhenglong@huawei.com \
--cc=hanweidong@huawei.com \
--cc=jbeulich@suse.com \
--cc=jeremy@goop.org \
--cc=jinsong.liu@alibaba-inc.com \
--cc=john.liuqiming@huawei.com \
--cc=josh.kearney@rackspace.com \
--cc=konrad.wilk@oracle.com \
--cc=konrad@darnok.org \
--cc=lars.kurth@citrix.com \
--cc=liuyingdong@huawei.com \
--cc=major.hayden@rackspace.com \
--cc=mpohlack@amazon.com \
--cc=msw@amazon.com \
--cc=paul.voccio@rackspace.com \
--cc=peter.huangpeng@huawei.com \
--cc=rick.harris@rackspace.com \
--cc=steven.wilson@rackspace.com \
--cc=xen-devel@lists.xenproject.org \
--cc=xiantao.zxt@alibaba-inc.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 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).