From: Sarah Newman <srn@prgmr.com>
To: "H. Peter Anvin" <hpa@zytor.com>, David Vrabel <david.vrabel@citrix.com>
Cc: Suresh Siddha <sbsiddha@gmail.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
linux-kernel@vger.kernel.org, xen-devel@lists.xen.org
Subject: Re: [Xen-devel] [PATCHv1] x86: don't schedule when handling #NM exception
Date: Sun, 16 Mar 2014 21:12:13 -0700 [thread overview]
Message-ID: <5326761D.5000905@prgmr.com> (raw)
In-Reply-To: <53266F56.9030909@zytor.com>
On 03/16/2014 08:43 PM, H. Peter Anvin wrote:
> On 03/16/2014 08:35 PM, Sarah Newman wrote:
>> Can you please review my patch first? It's only enabled when absolutely required.
>
> It doesn't help. It means you're running on Xen, and you will have
> processes subjected to random SIGKILL because they happen to touch the
> FPU when the atomic pool is low.
>
> However, there is probably a happy medium: you don't actually need eager
> FPU restore, you just need eager FPU *allocation*. We have been
> intending to allocate the FPU state at task creation time for eagerfpu,
> and Suresh Siddha has already produced such a patch; it just needs some
> minor fixups due to an __init failure.
>
> http://lkml.kernel.org/r/1391325599.6481.5.camel@europa
>
> In the Xen case we could turn on eager allocation but not eager fpu. In
> fact, it might be justified to *always* do eager allocation...
Unconditional eager allocation works. Can xen users count on this being included and applied to the
stable kernels?
Thanks, Sarah
next prev parent reply other threads:[~2014-03-17 4:12 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-10 16:17 [PATCHv1] x86: don't schedule when handling #NM exception David Vrabel
2014-03-10 16:40 ` H. Peter Anvin
2014-03-10 16:40 ` H. Peter Anvin
2014-03-10 17:15 ` David Vrabel
2014-03-10 17:15 ` David Vrabel
2014-03-10 17:25 ` H. Peter Anvin
2014-03-10 17:25 ` H. Peter Anvin
2014-03-17 3:13 ` Sarah Newman
2014-03-17 3:13 ` Sarah Newman
2014-03-17 3:30 ` [PATCH] x86: Control CR0 TS behavior using dev_na_ts_allowed Sarah Newman
2014-03-17 8:38 ` Jan Beulich
2014-03-17 12:42 ` George Dunlap
2014-03-17 13:35 ` Jan Beulich
2014-03-17 14:05 ` George Dunlap
2014-03-17 14:18 ` George Dunlap
2014-03-17 15:28 ` Jan Beulich
2014-03-18 18:07 ` Sarah Newman
2014-03-18 19:14 ` David Vrabel
2014-03-17 12:44 ` George Dunlap
2014-03-17 13:35 ` Jan Beulich
2014-03-18 17:48 ` Sarah Newman
2014-03-17 3:32 ` [PATCH] x86, fpu, xen: Allocate fpu state for xen pv based on PVABI behavior Sarah Newman
2014-03-17 3:32 ` Sarah Newman
2014-03-17 3:33 ` [PATCHv1] x86: don't schedule when handling #NM exception H. Peter Anvin
2014-03-17 3:35 ` Sarah Newman
2014-03-17 3:35 ` [Xen-devel] " Sarah Newman
2014-03-17 3:43 ` H. Peter Anvin
2014-03-17 3:43 ` [Xen-devel] " H. Peter Anvin
2014-03-17 4:12 ` Sarah Newman [this message]
2014-03-17 4:23 ` H. Peter Anvin
2014-03-17 4:23 ` [Xen-devel] " H. Peter Anvin
2014-03-20 0:00 ` Greg Kroah-Hartman
2014-03-20 0:00 ` [Xen-devel] " Greg Kroah-Hartman
2014-03-20 2:29 ` H. Peter Anvin
2014-03-20 2:29 ` H. Peter Anvin
2014-03-17 4:12 ` Sarah Newman
2014-03-17 13:29 ` [Xen-devel] " David Vrabel
2014-03-19 13:21 ` Konrad Rzeszutek Wilk
2014-03-19 13:21 ` [Xen-devel] " Konrad Rzeszutek Wilk
2014-03-19 15:02 ` H. Peter Anvin
2014-03-19 15:02 ` [Xen-devel] " H. Peter Anvin
2014-06-23 13:08 ` Konrad Rzeszutek Wilk
2014-06-23 13:08 ` [Xen-devel] " Konrad Rzeszutek Wilk
2015-03-05 22:08 ` H. Peter Anvin
2015-03-05 22:08 ` [Xen-devel] " H. Peter Anvin
2015-03-06 11:46 ` [PATCHv4] x86, fpu: remove the logic of non-eager fpu mem allocation at the first usage David Vrabel
2015-03-06 11:46 ` David Vrabel
2014-03-17 13:29 ` [PATCHv1] x86: don't schedule when handling #NM exception David Vrabel
2014-03-17 12:19 ` George Dunlap
2014-03-17 12:19 ` [Xen-devel] " George Dunlap
2014-03-17 16:55 ` H. Peter Anvin
2014-03-17 17:05 ` Jan Beulich
2014-03-17 17:12 ` H. Peter Anvin
2014-03-17 17:12 ` [Xen-devel] " H. Peter Anvin
2014-03-18 8:14 ` Ingo Molnar
2014-03-18 8:14 ` Ingo Molnar
2014-03-17 17:14 ` [Xen-devel] " George Dunlap
2014-03-18 18:17 ` Sarah Newman
2014-03-18 18:27 ` H. Peter Anvin
2014-03-18 18:27 ` H. Peter Anvin
2014-03-18 18:17 ` Sarah Newman
2014-03-17 17:14 ` George Dunlap
2014-03-17 17:05 ` Jan Beulich
2014-03-17 16:55 ` H. Peter Anvin
2014-03-17 3:33 ` H. Peter Anvin
2014-03-10 16:45 ` H. Peter Anvin
2014-03-10 16:45 ` H. Peter Anvin
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=5326761D.5000905@prgmr.com \
--to=srn@prgmr.com \
--cc=david.vrabel@citrix.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=sbsiddha@gmail.com \
--cc=tglx@linutronix.de \
--cc=xen-devel@lists.xen.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.