From mboxrd@z Thu Jan 1 00:00:00 1970 From: Glauber Costa Subject: Re: [patch 15/18] KVM: x86: implement PVCLOCK_TSC_STABLE_BIT pvclock flag Date: Tue, 30 Oct 2012 12:34:25 +0400 Message-ID: <508F9111.3030003@parallels.com> References: <20121024131340.742340256@redhat.com> <20121024131621.986748651@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit Cc: , , , , , , To: Marcelo Tosatti Return-path: Received: from mx2.parallels.com ([64.131.90.16]:33342 "EHLO mx2.parallels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754450Ab2J3Ieg (ORCPT ); Tue, 30 Oct 2012 04:34:36 -0400 In-Reply-To: <20121024131621.986748651@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On 10/24/2012 05:13 PM, Marcelo Tosatti wrote: > KVM added a global variable to guarantee monotonicity in the guest. > One of the reasons for that is that the time between > > 1. ktime_get_ts(×pec); > 2. rdtscll(tsc); > > Is variable. That is, given a host with stable TSC, suppose that > two VCPUs read the same time via ktime_get_ts() above. > > The time required to execute 2. is not the same on those two instances > executing in different VCPUS (cache misses, interrupts...). > > If the TSC value that is used by the host to interpolate when > calculating the monotonic time is the same value used to calculate > the tsc_timestamp value stored in the pvclock data structure, and > a single tuple is visible to all > vcpus simultaneously, this problem disappears. See comment on top > of pvclock_update_vm_gtod_copy for details. > > Monotonicity is then guaranteed by synchronicity of the host TSCs > and guest TSCs. > > Set TSC stable pvclock flag in that case, allowing the guest to read > clock from userspace. > > Signed-off-by: Marcelo Tosatti If you are using a master copy, with a stable host-side tsc, you can get rid of the normal REQ_CLOCK updates during vcpu load.