2017-10-25 13:09:17 |
bugproxy |
bug |
|
|
added bug |
2017-10-25 13:09:19 |
bugproxy |
tags |
|
architecture-ppc64le bugnameltc-160018 severity-critical targetmilestone-inin16043 |
|
2017-10-25 13:09:20 |
bugproxy |
attachment added |
|
Backported patch KVM: PPC: Book3S: Treat VTB as a per-subcore register, not per-thread https://bugs.launchpad.net/bugs/1727331/+attachment/4994438/+files/ubuntu-4.4-commit-88b02cf97bb7-backport.patch |
|
2017-10-25 13:09:23 |
bugproxy |
ubuntu: assignee |
|
Ubuntu on IBM Power Systems Bug Triage (ubuntu-power-triage) |
|
2017-10-25 13:09:28 |
bugproxy |
affects |
ubuntu |
kernel-package (Ubuntu) |
|
2017-10-25 13:12:04 |
Frank Heimes |
affects |
kernel-package (Ubuntu) |
linux (Ubuntu) |
|
2017-10-25 13:12:30 |
Frank Heimes |
bug task added |
|
ubuntu-power-systems |
|
2017-10-25 13:12:45 |
Frank Heimes |
ubuntu-power-systems: importance |
Undecided |
Critical |
|
2017-10-25 13:13:10 |
Frank Heimes |
ubuntu-power-systems: assignee |
|
Canonical Kernel Team (canonical-kernel-team) |
|
2017-10-25 13:38:26 |
Frank Heimes |
bug |
|
|
added subscriber Christian Ehrhardt |
2017-10-25 18:18:57 |
Joseph Salisbury |
linux (Ubuntu): importance |
Undecided |
Critical |
|
2017-10-25 18:19:01 |
Joseph Salisbury |
linux (Ubuntu): status |
New |
Triaged |
|
2017-10-25 18:19:52 |
Joseph Salisbury |
tags |
architecture-ppc64le bugnameltc-160018 severity-critical targetmilestone-inin16043 |
architecture-ppc64le bugnameltc-160018 kernel-da-key severity-critical targetmilestone-inin16043 |
|
2017-10-27 07:14:49 |
Frank Heimes |
ubuntu-power-systems: status |
New |
Triaged |
|
2017-10-30 17:47:03 |
Joseph Salisbury |
nominated for series |
|
Ubuntu Xenial |
|
2017-10-30 17:47:03 |
Joseph Salisbury |
bug task added |
|
linux (Ubuntu Xenial) |
|
2017-10-30 17:47:12 |
Joseph Salisbury |
linux (Ubuntu Xenial): status |
New |
In Progress |
|
2017-10-30 17:47:16 |
Joseph Salisbury |
linux (Ubuntu Xenial): importance |
Undecided |
Critical |
|
2017-10-30 17:47:19 |
Joseph Salisbury |
linux (Ubuntu Xenial): assignee |
|
Joseph Salisbury (jsalisbury) |
|
2017-10-30 17:47:22 |
Joseph Salisbury |
linux (Ubuntu): assignee |
Ubuntu on IBM Power Systems Bug Triage (ubuntu-power-triage) |
Joseph Salisbury (jsalisbury) |
|
2017-10-30 17:47:27 |
Joseph Salisbury |
linux (Ubuntu): status |
Triaged |
In Progress |
|
2017-10-30 18:02:39 |
Frank Heimes |
ubuntu-power-systems: status |
Triaged |
In Progress |
|
2017-11-03 17:05:12 |
Joseph Salisbury |
description |
Environment:
Host OS: Ubuntu 16.04 (4.4.0-97-generic)
Guest OS: Ubuntu 16.04
Host is running NovaLink and GPFS. Guest gets filesystem from gpfs cluster.
Issue:
While booting the guest OS went into recovery. dmesg shows CPU soft lockup. This issue is easily recreatable when multiple VMs (about 10) are being started simultaneously.
.......................................................................................................................
- Paul Mackerras <pmac@au1.ibm.com> - 2017-10-24 00:42:25 ==
Looking at kernel sources:
The Ubuntu host kernel (4.4.0-97) does not include the patch "KVM: PPC: Book3S: Treat VTB as a per-subcore register, not per-thread", which is commit 88b02cf97bb7 in the upstream Linux kernel repository. The symptom of not having this patch is that guests running with threads > 1 (that is, in SMT2, SMT4 or SMT8 mode) can give spurious soft-lockup messages when they are not in fact locked up, if the guest kernel uses the VTB (virtual timebase) register in its softlockup detector code.
This is a backport of commit 88b02cf97bb7 from the upstream Linux kernel repository to the Ubuntu 4.4 kernel. It is the fix for the problem of seeing spurious soft lockup messages in guests running in an SMT mode greater than 1.
These tests were run on a system with 20 cores. Each VM had 1 core and 4 threads (SMT=4).
It is working very well with this patch |
== SRU Justification ==
Xenial does not include the patch:
"KVM: PPC: Book3S: Treat VTB as a per-subcore register, not per-thread",
which is commit 88b02cf97bb7 in the upstream Linux kernel repository. The
symptom of not having this patch is that guests running with threads > 1
(that is, in SMT2, SMT4 or SMT8 mode) can give spurious soft-lockup messages
when they are not in fact locked up, if the guest kernel uses the VTB
(virtual timebase) register in its softlockup detector code.
IBM provided this backport of commit 88b02cf97bb7.
== Fix ==
commit 88b02cf97bb7e742db3e31671d54177e3e19fd89
Author: Paul Mackerras <paulus@ozlabs.org>
Date: Thu Sep 15 13:42:52 2016 +1000
KVM: PPC: Book3S: Treat VTB as a per-subcore register, not per-thread
== Regression Potential ==
This patch is specific to powerpc. It was provided by and tested by IBM.
Environment:
Host OS: Ubuntu 16.04 (4.4.0-97-generic)
Guest OS: Ubuntu 16.04
Host is running NovaLink and GPFS. Guest gets filesystem from gpfs cluster.
Issue:
While booting the guest OS went into recovery. dmesg shows CPU soft lockup. This issue is easily recreatable when multiple VMs (about 10) are being started simultaneously.
.......................................................................................................................
- Paul Mackerras <pmac@au1.ibm.com> - 2017-10-24 00:42:25 ==
Looking at kernel sources:
The Ubuntu host kernel (4.4.0-97) does not include the patch "KVM: PPC: Book3S: Treat VTB as a per-subcore register, not per-thread", which is commit 88b02cf97bb7 in the upstream Linux kernel repository. The symptom of not having this patch is that guests running with threads > 1 (that is, in SMT2, SMT4 or SMT8 mode) can give spurious soft-lockup messages when they are not in fact locked up, if the guest kernel uses the VTB (virtual timebase) register in its softlockup detector code.
This is a backport of commit 88b02cf97bb7 from the upstream Linux kernel repository to the Ubuntu 4.4 kernel. It is the fix for the problem of seeing spurious soft lockup messages in guests running in an SMT mode greater than 1.
These tests were run on a system with 20 cores. Each VM had 1 core and 4 threads (SMT=4).
It is working very well with this patch |
|
2017-11-06 14:52:06 |
Manoj Iyer |
tags |
architecture-ppc64le bugnameltc-160018 kernel-da-key severity-critical targetmilestone-inin16043 |
architecture-ppc64le bugnameltc-160018 kernel-da-key severity-critical targetmilestone-inin16043 triage-g |
|
2017-11-20 10:26:02 |
Stefan Bader |
linux (Ubuntu Xenial): status |
In Progress |
Fix Committed |
|
2017-11-20 14:40:31 |
Manoj Iyer |
ubuntu-power-systems: status |
In Progress |
Fix Committed |
|
2017-11-21 16:37:58 |
Joseph Salisbury |
linux (Ubuntu): status |
In Progress |
Fix Committed |
|
2017-11-28 17:47:46 |
Khaled El Mously |
tags |
architecture-ppc64le bugnameltc-160018 kernel-da-key severity-critical targetmilestone-inin16043 triage-g |
architecture-ppc64le bugnameltc-160018 kernel-da-key severity-critical targetmilestone-inin16043 triage-g verification-needed-xenial |
|
2017-11-30 19:09:39 |
bugproxy |
tags |
architecture-ppc64le bugnameltc-160018 kernel-da-key severity-critical targetmilestone-inin16043 triage-g verification-needed-xenial |
architecture-ppc64le bugnameltc-160018 kernel-da-key severity-critical targetmilestone-inin16043 triage-g verification-done-xenial |
|
2017-12-07 17:43:39 |
Launchpad Janitor |
linux (Ubuntu Xenial): status |
Fix Committed |
Fix Released |
|
2017-12-07 17:43:39 |
Launchpad Janitor |
cve linked |
|
2017-1000405 |
|
2017-12-07 17:43:39 |
Launchpad Janitor |
cve linked |
|
2017-16939 |
|
2017-12-11 14:51:18 |
Frank Heimes |
linux (Ubuntu): status |
Fix Committed |
Fix Released |
|
2017-12-11 14:51:21 |
Frank Heimes |
ubuntu-power-systems: status |
Fix Committed |
Fix Released |
|