From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: Bogdan Purcareata <bogdan.purcareata@freescale.com>,
linuxppc-dev@lists.ozlabs.org, linux-rt-users@vger.kernel.org,
agraf@suse.de, pbonzini@redhat.com
Cc: scottwood@freescale.com, mihai.caraman@freescale.com,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 2/2] powerpc/kvm: Limit MAX_VCPUS for guests running on RT Linux
Date: Wed, 18 Feb 2015 10:36:49 +0100 [thread overview]
Message-ID: <54E45D31.3020302@linutronix.de> (raw)
In-Reply-To: <1424251955-308-3-git-send-email-bogdan.purcareata@freescale.com>
On 02/18/2015 10:32 AM, Bogdan Purcareata wrote:
> Due to the introduction of the raw_spinlock for the KVM openpic, guests with a
> high number of VCPUs may induce great latencies on the underlying RT Linux
> system (e.g. cyclictest reports latencies of ~15ms for guests with 24 VCPUs).
> This can be further aggravated by sending a lot of external interrupts to the
> guest.
>
> A malicious app can abuse this scenario, causing a DoS of the host Linux.
> Until the KVM openpic code is refactored to use finer lock granularity, impose
> a limitation on the number of VCPUs a guest can have when running on a
> PREEMPT_RT_FULL system with KVM_MPIC emulation.
How is this possible? You take the raw lock, write a register, release
the raw lock. How can the guest lockup the host? Is this write blocking
in guest?
Sebastian
next prev parent reply other threads:[~2015-02-18 10:09 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-18 9:32 [PATCH 0/2] powerpc/kvm: Enable running guests on RT Linux Bogdan Purcareata
2015-02-18 9:32 ` [PATCH 1/2] powerpc/kvm: Convert openpic lock to raw_spinlock Bogdan Purcareata
2015-02-23 22:43 ` Scott Wood
2015-02-18 9:32 ` [PATCH 2/2] powerpc/kvm: Limit MAX_VCPUS for guests running on RT Linux Bogdan Purcareata
2015-02-18 9:36 ` Sebastian Andrzej Siewior [this message]
2015-02-20 13:45 ` Alexander Graf
2015-02-23 22:48 ` Scott Wood
2015-02-20 13:45 ` [PATCH 0/2] powerpc/kvm: Enable running guests " Alexander Graf
2015-02-20 14:12 ` Paolo Bonzini
2015-02-20 14:16 ` Alexander Graf
2015-02-20 14:54 ` Sebastian Andrzej Siewior
2015-02-20 14:57 ` Paolo Bonzini
2015-02-20 15:06 ` Sebastian Andrzej Siewior
2015-02-20 15:10 ` Paolo Bonzini
2015-02-20 15:17 ` Sebastian Andrzej Siewior
2015-02-23 8:12 ` Purcareata Bogdan
2015-02-23 7:50 ` Purcareata Bogdan
2015-02-23 7:29 ` Purcareata Bogdan
2015-02-23 23:27 ` Scott Wood
2015-02-25 16:36 ` Sebastian Andrzej Siewior
2015-02-26 13:02 ` Paolo Bonzini
2015-02-26 13:31 ` Sebastian Andrzej Siewior
2015-02-27 1:05 ` Scott Wood
2015-02-27 13:06 ` Paolo Bonzini
2015-03-27 17:07 ` Purcareata Bogdan
2015-04-02 23:11 ` Scott Wood
2015-04-03 8:07 ` Purcareata Bogdan
2015-04-03 21:26 ` Scott Wood
2015-04-09 7:44 ` Purcareata Bogdan
2015-04-09 23:53 ` Scott Wood
2015-04-20 10:53 ` Purcareata Bogdan
2015-04-21 0:52 ` Scott Wood
2015-04-22 12:06 ` Purcareata Bogdan
2015-04-23 0:30 ` Scott Wood
2015-04-23 12:31 ` Purcareata Bogdan
2015-04-23 21:26 ` Scott Wood
2015-04-27 6:45 ` Purcareata Bogdan
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=54E45D31.3020302@linutronix.de \
--to=bigeasy@linutronix.de \
--cc=agraf@suse.de \
--cc=bogdan.purcareata@freescale.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mihai.caraman@freescale.com \
--cc=pbonzini@redhat.com \
--cc=scottwood@freescale.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).