From owner-freebsd-bugs@freebsd.org  Thu Oct 12 09:02:55 2017
Return-Path: <owner-freebsd-bugs@freebsd.org>
Delivered-To: freebsd-bugs@mailman.ysv.freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org
 [IPv6:2001:1900:2254:206a::19:1])
 by mailman.ysv.freebsd.org (Postfix) with ESMTP id 48A24E48D9A
 for <freebsd-bugs@mailman.ysv.freebsd.org>;
 Thu, 12 Oct 2017 09:02:55 +0000 (UTC)
 (envelope-from bugzilla-noreply@freebsd.org)
Received: from kenobi.freebsd.org (kenobi.freebsd.org
 [IPv6:2001:1900:2254:206a::16:76])
 (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits))
 (Client did not present a certificate)
 by mx1.freebsd.org (Postfix) with ESMTPS id 2E92F6D9D9
 for <freebsd-bugs@FreeBSD.org>; Thu, 12 Oct 2017 09:02:55 +0000 (UTC)
 (envelope-from bugzilla-noreply@freebsd.org)
Received: from bugs.freebsd.org ([127.0.1.118])
 by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id v9C92qcU097225
 for <freebsd-bugs@FreeBSD.org>; Thu, 12 Oct 2017 09:02:55 GMT
 (envelope-from bugzilla-noreply@freebsd.org)
From: bugzilla-noreply@freebsd.org
To: freebsd-bugs@FreeBSD.org
Subject: [Bug 213155] possible kernel regression when running 11.x-RELEASE on
 KVM on AMD Opterons
Date: Thu, 12 Oct 2017 09:02:51 +0000
X-Bugzilla-Reason: AssignedTo
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: Base System
X-Bugzilla-Component: kern
X-Bugzilla-Version: 11.1-RELEASE
X-Bugzilla-Keywords: regression
X-Bugzilla-Severity: Affects Some People
X-Bugzilla-Who: marvin0815@gmail.com
X-Bugzilla-Status: New
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: ---
X-Bugzilla-Assigned-To: freebsd-bugs@FreeBSD.org
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-213155-8-xXM0RoXCFu@https.bugs.freebsd.org/bugzilla/>
In-Reply-To: <bug-213155-8@https.bugs.freebsd.org/bugzilla/>
References: <bug-213155-8@https.bugs.freebsd.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-BeenThere: freebsd-bugs@freebsd.org
X-Mailman-Version: 2.1.23
Precedence: list
List-Id: Bug reports <freebsd-bugs.freebsd.org>
List-Unsubscribe: <https://lists.freebsd.org/mailman/options/freebsd-bugs>,
 <mailto:freebsd-bugs-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-bugs/>
List-Post: <mailto:freebsd-bugs@freebsd.org>
List-Help: <mailto:freebsd-bugs-request@freebsd.org?subject=help>
List-Subscribe: <https://lists.freebsd.org/mailman/listinfo/freebsd-bugs>,
 <mailto:freebsd-bugs-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Thu, 12 Oct 2017 09:02:55 -0000

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D213155

--- Comment #20 from Oliver B=C3=B6ttcher <marvin0815@gmail.com> ---
I don't know if this is of any interest but I want to help to track down th=
is
issue.

I started to enable and disable several features in libvirt's machine confi=
g to
find out when it starts to hang.

Here are some remarks worth to mention:

This works:
  <cpu mode=3D'custom' match=3D'exact' check=3D'partial'>
    <model fallback=3D'allow'>Opteron_G3</model>
    <feature policy=3D'optional' name=3D'aes'/>
    <feature policy=3D'optional' name=3D'pclmuldq'/>
    <feature policy=3D'optional' name=3D'fma4'/>
    <feature policy=3D'optional' name=3D'avx'/>
    <feature policy=3D'optional' name=3D'ssse3'/>
    <feature policy=3D'optional' name=3D'sse4.2'/>
    <feature policy=3D'optional' name=3D'xop'/>
    <feature policy=3D'optional' name=3D'f16c'/>
    <feature policy=3D'optional' name=3D'pdpe1gb'/>
    <feature policy=3D'optional' name=3D'fma'/>
    <feature policy=3D'optional' name=3D'tbm'/>
    <feature policy=3D'optional' name=3D'sse4.1'/>
    <feature policy=3D'optional' name=3D'3dnowprefetch'/>
  </cpu>

This does not work:
  <cpu mode=3D'custom' match=3D'exact' check=3D'partial'>
    <model fallback=3D'allow'>Opteron_G3</model>
    <feature policy=3D'optional' name=3D'aes'/>
    <feature policy=3D'optional' name=3D'pclmuldq'/>
    <feature policy=3D'optional' name=3D'fma4'/>
    <feature policy=3D'optional' name=3D'avx'/>
    <feature policy=3D'optional' name=3D'ssse3'/>
    <feature policy=3D'optional' name=3D'sse4.2'/>
    <feature policy=3D'optional' name=3D'xop'/>
    <feature policy=3D'optional' name=3D'f16c'/>
    <feature policy=3D'optional' name=3D'pdpe1gb'/>
    <feature policy=3D'optional' name=3D'fma'/>
    <feature policy=3D'optional' name=3D'tbm'/>
    <feature policy=3D'optional' name=3D'sse4.1'/>
    <feature policy=3D'optional' name=3D'3dnowprefetch'/>
    <feature policy=3D'optional' name=3D'xsave'/>
  </cpu>

All these features are the differences between Opteron_G3 and Opteron_G5. O=
ddly
enough, enabling xsave gives a kernel panic.

panic: CPU0 does not support X87 or SSE: 0

(See screenshot attached. Note this is HardenedBSD but also affects FBSD
11.1-RELEASE)

So I started to build up my config to start with model=3Dqemu64 and enable =
all
features as stated for Opteron_G5 in /usr/share/libvirt/cpu_map.xml

  <cpu mode=3D'custom' match=3D'exact' check=3D'partial'>
    <model fallback=3D'allow'>qemu64</model>
    <feature policy=3D'optional' name=3D'3dnowprefetch'/>
    <feature policy=3D'optional' name=3D'abm'/>
    <feature policy=3D'optional' name=3D'aes'/>
    <feature policy=3D'optional' name=3D'apic'/>
    <feature policy=3D'optional' name=3D'avx'/>
    <feature policy=3D'optional' name=3D'clflush'/>
    <feature policy=3D'optional' name=3D'cmov'/>
    <feature policy=3D'optional' name=3D'cx16'/>
    <feature policy=3D'optional' name=3D'cx8'/>
    <feature policy=3D'optional' name=3D'de'/>
    <feature policy=3D'optional' name=3D'f16c'/>
    <feature policy=3D'optional' name=3D'fma'/>
    <feature policy=3D'optional' name=3D'fma4'/>
    <feature policy=3D'optional' name=3D'fpu'/>
    <feature policy=3D'optional' name=3D'fxsr'/>
    <feature policy=3D'optional' name=3D'lahf_lm'/>
    <feature policy=3D'optional' name=3D'lm'/>
    <feature policy=3D'optional' name=3D'mca'/>
    <feature policy=3D'optional' name=3D'mce'/>
    <feature policy=3D'optional' name=3D'misalignsse'/>
    <feature policy=3D'optional' name=3D'mmx'/>
    <feature policy=3D'optional' name=3D'msr'/>
    <feature policy=3D'optional' name=3D'mtrr'/>
    <feature policy=3D'optional' name=3D'nx'/>
    <feature policy=3D'optional' name=3D'pae'/>
    <feature policy=3D'optional' name=3D'pat'/>
    <feature policy=3D'optional' name=3D'pclmuldq'/>
    <feature policy=3D'optional' name=3D'pdpe1gb'/>
    <feature policy=3D'optional' name=3D'pge'/>
    <feature policy=3D'optional' name=3D'pni'/>
    <feature policy=3D'optional' name=3D'popcnt'/>
    <feature policy=3D'optional' name=3D'pse'/>
    <feature policy=3D'optional' name=3D'pse36'/>
    <feature policy=3D'optional' name=3D'rdtscp'/>
    <feature policy=3D'optional' name=3D'sep'/>
    <feature policy=3D'optional' name=3D'sse'/>
    <feature policy=3D'optional' name=3D'sse2'/>
    <feature policy=3D'optional' name=3D'sse4.1'/>
    <feature policy=3D'optional' name=3D'sse4.2'/>
    <feature policy=3D'optional' name=3D'sse4a'/>
    <feature policy=3D'optional' name=3D'ssse3'/>
    <feature policy=3D'optional' name=3D'svm'/>
    <feature policy=3D'optional' name=3D'syscall'/>
    <feature policy=3D'optional' name=3D'tbm'/>
    <feature policy=3D'optional' name=3D'tsc'/>
    <feature policy=3D'optional' name=3D'xop'/>
    <feature policy=3D'optional' name=3D'xsave'/>
  </cpu>

/var/run/dmesg.boot:
CPU: QEMU Virtual CPU version 2.5+ (2300.30-MHz K8-class CPU)
  Origin=3D"AuthenticAMD"  Id=3D0x6d3  Family=3D0x6  Model=3D0xd  Stepping=
=3D3
=20
Features=3D0x783fbfd<FPU,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,C=
MOV,PAT,PSE36,MMX,FXSR,SSE,SSE2>
=20
Features2=3D0xbeb83203<SSE3,PCLMULQDQ,SSSE3,FMA,CX16,SSE4.1,SSE4.2,x2APIC,P=
OPCNT,AESNI,XSAVE,OSXSAVE,AVX,F16C,HV>
  AMD Features=3D0x24100800<SYSCALL,NX,Page1GB,LM>
  AMD Features2=3D0x2109e1<LAHF,ABM,SSE4A,MAS,Prefetch,XOP,FMA4,TBM>

I hope this helps someone.
Oliver

--=20
You are receiving this mail because:
You are the assignee for the bug.=