From mboxrd@z Thu Jan 1 00:00:00 1970 From: Xiao Guangrong Subject: Re: [PATCH v3 1/3] KVM: fix rcu usage warning in kvm_arch_vcpu_ioctl_set_sregs() Date: Thu, 20 Jan 2011 11:03:31 +0800 Message-ID: <4D37A603.4040602@cn.fujitsu.com> References: <4D2D5AA6.9080804@cn.fujitsu.com> <4D3673A7.4090402@cn.fujitsu.com> <20110119181347.GA13142@amt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Cc: Avi Kivity , LKML , KVM To: Marcelo Tosatti Return-path: Received: from cn.fujitsu.com ([222.73.24.84]:52998 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1752071Ab1ATDDJ (ORCPT ); Wed, 19 Jan 2011 22:03:09 -0500 In-Reply-To: <20110119181347.GA13142@amt.cnet> Sender: kvm-owner@vger.kernel.org List-ID: On 01/20/2011 02:13 AM, Marcelo Tosatti wrote: > On Wed, Jan 19, 2011 at 01:16:23PM +0800, Xiao Guangrong wrote: >> On 01/12/2011 03:39 PM, Xiao Guangrong wrote: >>> Fix: >>> >>> [ 1001.499596] =================================================== >>> [ 1001.499599] [ INFO: suspicious rcu_dereference_check() usage. ] >>> [ 1001.499601] --------------------------------------------------- >>> [ 1001.499604] include/linux/kvm_host.h:301 invoked rcu_dereference_check() without protection! >>> ...... >>> [ 1001.499636] Pid: 6035, comm: qemu-system-x86 Not tainted 2.6.37-rc6+ #62 >>> [ 1001.499638] Call Trace: >>> [ 1001.499644] [] lockdep_rcu_dereference+0x9d/0xa5 >>> [ 1001.499653] [] gfn_to_memslot+0x8d/0xc8 [kvm] >>> [ 1001.499661] [] gfn_to_hva+0x16/0x3f [kvm] >>> [ 1001.499669] [] kvm_read_guest_page+0x1e/0x5e [kvm] >>> [ 1001.499681] [] kvm_read_guest_page_mmu+0x53/0x5e [kvm] >>> [ 1001.499699] [] load_pdptrs+0x3f/0x9c [kvm] >>> [ 1001.499705] [] ? vmx_set_cr0+0x507/0x517 [kvm_intel] >>> [ 1001.499717] [] kvm_arch_vcpu_ioctl_set_sregs+0x1f3/0x3c0 [kvm] >>> [ 1001.499727] [] kvm_vcpu_ioctl+0x6a5/0xbc5 [kvm] >>> >>> Signed-off-by: Xiao Guangrong >> >> Ping ...? > > Applied this fix. For the make_all_cpus_request optimization, can you > show numbers with this new version? Because now there is LOCK# similarly > to the spinlock. Marcelo, Sure :-), there is the simply test result of kernbench: Before patch: real 5m6.493s user 3m57.847s sys 9m7.115s real 5m1.750s user 4m0.109s sys 9m10.192s After patch: real 5m0.140s user 3m57.956s sys 8m58.339s real 4m56.314s user 4m0.303s sys 8m55.774s