From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?UTF-8?Q?Dirk_M=c3=bcller?= Subject: Re: [PATCH] Use WARN_ON_ONCE for missing X86_FEATURE_NRIPS Date: Thu, 1 Oct 2015 14:45:32 +0200 Message-ID: <560D2AEC.1060605@suse.com> References: <560D1C6E.2060803@suse.com> <560D2622.4090906@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Joerg Roedel To: Paolo Bonzini , kvm@vger.kernel.org Return-path: Received: from smtp.nue.novell.com ([195.135.221.5]:35895 "EHLO smtp.nue.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754748AbbJAMqE (ORCPT ); Thu, 1 Oct 2015 08:46:04 -0400 In-Reply-To: <560D2622.4090906@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On 01.10.2015 14:25, Paolo Bonzini wrote: Hi Paolo, > Applied. Do you also know what caused the warning, and/or would you > like me to take a look? The trace we're getting is this: [] dump_trace+0x7d/0x2d0 [] show_stack_log_lvl+0x94/0x170 [] show_stack+0x21/0x50 [] dump_stack+0x41/0x51 [] warn_slowpath_common+0x82/0xc0 [] skip_emulated_instruction+0xe1/0x160 [kvm_amd] [] io_interception+0x3b/0x80 [kvm_amd] [] vcpu_enter_guest+0x6bc/0xc70 [kvm] [] kvm_arch_vcpu_ioctl_run+0x1d8/0x450 [kvm] [] kvm_vcpu_ioctl+0x2e1/0x580 [kvm] [] do_vfs_ioctl+0x2d4/0x4b0 [] SyS_ioctl+0x88/0xa0 [] system_call_fastpath+0x16/0x1b [<00007f8f7b5fabe7>] 0x7f8f7b5fabe6 The colleague who was investigating this is not here today, but from what I remember it seems to only happen when nested virtualisation is being used. I don't know more about it right now, bisecting pointed out f104765b4f81fd74d69e0eb161e89096deade2db . Since it was logging so rapidly on our autotester machines (which are running 200-250 VMs nested) that we are continuously run out of disk space I just tried to come up with a stop-gap fix until this has been properly analyzed. Thanks, Dirk