From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paolo Bonzini Subject: Re: KVM: x86: update masterclock when kvmclock_offset is calculated Date: Tue, 03 Sep 2013 12:42:40 +0200 Message-ID: <5225BD20.1000902@redhat.com> References: <20130820182012.GA814@amt.cnet> <521644D0.9050902@redhat.com> <20130828025243.GA13653@amt.cnet> <521DEF00.2030200@redhat.com> <20130903030351.GA3167@amt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: kvm-devel , Gleb Natapov To: Marcelo Tosatti Return-path: Received: from mx1.redhat.com ([209.132.183.28]:5333 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755880Ab3ICKmm (ORCPT ); Tue, 3 Sep 2013 06:42:42 -0400 Received: from int-mx10.intmail.prod.int.phx2.redhat.com (int-mx10.intmail.prod.int.phx2.redhat.com [10.5.11.23]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id r83AggPw017313 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Tue, 3 Sep 2013 06:42:42 -0400 In-Reply-To: <20130903030351.GA3167@amt.cnet> Sender: kvm-owner@vger.kernel.org List-ID: Il 03/09/2013 05:03, Marcelo Tosatti ha scritto: > > Here is the code I was thinking of: > > > > spin_lock(&ka->pvclock_gtod_sync_lock); > > make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); > > > > /* > > * No guest entries from this point: VCPUs will be spinning > > * on pvclock_gtod_sync_lock in kvm_guest_time_update. > > */ > > pvclock_update_vm_gtod_copy(kvm); > > > > /* > > * Let kvm_guest_time_update continue: entering the guest > > * is now allowed too. > > */ > > spin_unlock(&ka->pvclock_gtod_sync_lock); > > > > KVM_REQ_CLOCK_UPDATE is used to cancel guest entry and execute > > kvm_guest_time_update. But kvm_guest_time_update will spin on > > pvclock_gtod_sync_lock until pvclock_update_vm_gtod_copy exits and > > kvm_gen_update_masterclock releases the spinlock. > > Not safe because there are places which set KVM_REQ_CLOCK_UPDATE without > kicking target vcpu out of guest mode. Unless you use a modified > make_all_cpus_request. make_all_cpus_request does force an exit, even if the bit is already set in vcpus->requests. But maybe here is where I'm missing something. > The point of REQ_MCLOCK_INPROGRESS request is to guarantee that the > following is not possible: > > - 2 vcpus in guest mode with per-vcpu kvmclock areas with > different {system_timestamp, tsc_offset} values. Understood. > To achieve that: > > - Kick all vcpus out of guest mode (via a request bit that can't be > cleared). > - Update the {system_timestamp, tsc_offset} values. > - Clear the request bit. After make_all_cpus_request, all VCPUs will be out of guest mode, and the request bit will not be cleared until pvclock_gtod_sync_lock is released. Paolo