Date: Sat, 17 Mar 2012 16:00:15 -0400 From: Richard Yao <ryao@cs.stonybrook.edu> To: <alc@freebsd.org> Cc: Alan Cox <alan.l.cox@gmail.com>, freebsd-stable@freebsd.org Subject: Re: AMD Erratum 383 crashes FreeBSD 9-Stable Message-ID: <4F64ED4F.1020803@cs.stonybrook.edu> In-Reply-To: <4F64E856.3040303@cs.stonybrook.edu> References: <4F64C50F.70409@cs.stonybrook.edu> <4F64C57F.6040403@cs.stonybrook.edu> <CAJUyCcME8YgJkCmfCodJba0noKyGr8RMnJwSMrT_fECj8U7d=Q@mail.gmail.com> <4F64E856.3040303@cs.stonybrook.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
--------------enigC909810FF4A687C8F386C0B3 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Alan, thanks for the information. This is a definitely libvirtd bug. Passing '-cpu host' fixes the problem. I replaced libvirtd with Gentoo's kvm-tools, which makes it easy to specify this, so problem solved. I would send a report to the libvirt developers, but I have encountered more problems in libvirt than I have time to describe, so that will not happen right away. On 03/17/12 15:39, Richard Yao wrote: > On 03/17/12 15:21, Alan Cox wrote: >> When the FreeBSD kernel detects that it is running on an affected >> processor, it automatically enables the recommended workaround. Howev= er, >> because you are running within a virtual machine, the automatic detect= ion >> may not be working. Alternatively, you may be using a newer processor= >> revision that still suffers from the bug, but the kernel doesn't enabl= e the >> workaround for. Can you tell us how the FreeBSD guest sees the underl= ying >> processor, e.g., the first few lines of dmesg from the guest? >> >> Alan >> >=20 > I am currently passing "-cpu > Opteron_G3,+3dnowext,+3dnow,+3dnowprefetch,+cmp_legacy" to KVM at > libvirtd's suggestion. I assume this is why the workaround is not being= > triggered. >=20 > # dmesg > Copyright (c) 1992-2012 The FreeBSD Project. > Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 199= 4 > The Regents of the University of California. All rights reserve= d. > FreeBSD is a registered trademark of The FreeBSD Foundation. > FreeBSD 9.0-RELEASE #0: Sun Jan 15 22:48:55 UTC 2012 > root@zfsguru:/usr/obj/usr/src/sys/OFED amd64 > module_register: module pci/mps already exists! > Module pci/mps failed to register: 17 > CPU: AMD Opteron 23xx (Gen 3 Class Opteron) (3210.85-MHz K8-class CPU) > Origin =3D "AuthenticAMD" Id =3D 0xf61 Family =3D f Model =3D 6 S= tepping =3D 1 >=20 > Features=3D0x783fbfd<FPU,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,M= CA,CMOV,PAT,PSE36,MMX,FXSR,SSE,SSE2> > Features2=3D0x80802001<SSE3,CX16,POPCNT,HV> > AMD Features=3D0xe0100800<SYSCALL,NX,LM,3DNow!+,3DNow!> > AMD Features2=3D0x1e7<LAHF,CMP,SVM,ABM,SSE4A,MAS,Prefetch> >=20 --------------enigC909810FF4A687C8F386C0B3 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iQIcBAEBAgAGBQJPZO1SAAoJELFAT5FmjZuE8UsQAMWsraKH5s6GzDMixW2kxwfU C5xPugnZ+4cv6EZQZPFOyGC/CBRKFmSLGM5RASMXG4ca10y1oq3M/hJaNz18zmsa REQndNm+Z8IsVxL4m5Aj77xIU6g0q8zaeA00OvavtC8/u1dO0XpxPNV0jAZhkOI6 JP9W0QdIJc8BDeuEBptNCeZCYPCjQTxqSDGI+pJP4ymMtpsT7PLB90ObkZfJe3BX b/A7pLRbmGEnf7zXQxNJ4WlQ9ec6eagSu/wQHyPJEOIOdmVK4VwkSo5QyFBMVs2o nbBxu9oXFH0+r+03YrCaMLrnXiEhKXuF9B9KlAR63rdy9A2Aj4pLJotg3GW0wN4z fDvxXIVHsdgC7pE6AZY5a/lwfR9mGnpNxd7WTziWqN172EcMhrBinGT5MUJJW5vH +/tJiVl6WYW+tKrVtzOEdfcusRDmWYiNZlBnDS+VuH7kR8Pke9Tz61eP83KYluEX GJ6h4gxxlMD95Wiv3r5haDOnhM1jjSPhKMELWtMqiKBG+gj6Kg6bWeccxsnev6SD B5ZXK6B96WaHSlvfDytsKy6e9q/qfIBquN+B1/XSpuPtNO3srSm4CAX8C4UnR+PR bvW5EAwXtSe9zhDKp9RLBQuo7LOnc+zQQq14HJUmY+0XAPFQvQ17Pad85nf1mWJt aCdJxQESM7nQS2Q+zNyj =fh1e -----END PGP SIGNATURE----- --------------enigC909810FF4A687C8F386C0B3--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4F64ED4F.1020803>