Before trying to push it further I would like to have your advise from a very specific trouble I encounter on any 12.2 (not yet tested on 12.3) kernel with amd platform 890 & 990 FX with phenom II (X4 or X6) or Phenom FX (8120 & 8350) I got a each boot time [ 24.297596] ------------[ cut here ]------------ [ 24.297613] WARNING: at /home/abuild/rpmbuild/BUILD/kernel- default-3.4.28/linux-3.4/mm/memcontrol.c:5007 mem_cgroup_create+0x3ac/0x510() [ 24.297620] Hardware name: GA-890GPA-UD3H [ 24.297625] Creating hierarchies with use_hierarchy==0 (flat hierarchy) is considered deprecated. If you believe that your setup is correct, we kindly ask you to contact linux-mm@kvack.org and let us know [ 24.297632] Modules linked in: xt_CLASSIFY xt_AUDIT xt_tcpudp ip6table_filter ip6_tables xt_state iptable_nat nf_nat ebtable_nat nf_conntrack_ipv4 ebtables nf_defrag_ipv4 nf_conntrack iptable_mangle nfnetlink af_packet ppp_generic slhc bridge stp iptable_filter ip_tables x_tables cpufreq_conservative cpufreq_userspace cpufreq_powersave quota_v2 quota_tree snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_hwdep snd_pcm_oss snd_pcm snd_seq snd_timer snd_seq_device firewire_ohci snd_mixer_oss snd firewire_core kvm_amd sp5100_tco shpchp edac_core soundcore ata_generic r8169 crc_itu_t pci_hotplug powernow_k8 mperf button edac_mce_amd sata_sil24 kvm k10temp serio_raw pcspkr i2c_piix4 sg e1000e snd_page_alloc wmi pata_jmicron edd microcode autofs4 usbhid dm_mod linear ohci_hcd ssb mmc_core pcmcia ehci_hcd pcmcia_core radeon xhci_hcd ttm usbcore drm_kms_helper drm usb_common i2c_algo_bit processor thermal_sys scsi_dh_rdac scsi_dh_hp_sw scsi_dh_emc scsi_dh_alua scsi_dh aacraid [ 24.297773] Pid: 2976, comm: libvirtd Not tainted 3.4.28-2.20-default #1 [ 24.297778] Call Trace: [ 24.297802] [<ffffffff81004598>] dump_trace+0x78/0x2c0 [ 24.297816] [<ffffffff81532e6a>] dump_stack+0x69/0x6f [ 24.297829] [<ffffffff8103ead9>] warn_slowpath_common+0x79/0xc0 [ 24.297840] [<ffffffff8103ebd5>] warn_slowpath_fmt+0x45/0x50 [ 24.297851] [<ffffffff8151c04c>] mem_cgroup_create+0x3ac/0x510 [ 24.297868] [<ffffffff810a7983>] cgroup_mkdir+0x103/0x3a0 [ 24.297881] [<ffffffff81160345>] vfs_mkdir+0xb5/0x170 [ 24.297894] [<ffffffff81164444>] sys_mkdirat+0xe4/0xf0 [ 24.297908] [<ffffffff81545c7d>] system_call_fastpath+0x1a/0x1f [ 24.297924] [<00007f424c541f77>] 0x7f424c541f76 [ 24.297929] ---[ end trace ac83d820627dc3ae ]--- On the 990FX 8350, with kernel 3.8+ I didn't have anymore this kind of trouble. Sometimes (but not easy to reproduce with a 100% accurate fashion) the virtual guest could crash or freeze (most of the time with iommu troubles) The different motherboard have all been updated to the latest bios available. (Asus, Gigabyte) I attach the full dmesg for inspection. If any of you is aware of something that could be tested or know already the issue and has a way to get it fixed, thanks to share your advise. -- Bruno Friedmann Ioda-Net Sàrl www.ioda-net.ch openSUSE Member GPG KEY : D5C9B751C4653227 irc: tigerfoot