From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marcelo Tosatti Subject: Re: [patch 2/2] target-i386: block migration and savevm if invariant tsc is exposed Date: Tue, 22 Apr 2014 18:27:59 -0300 Message-ID: <20140422212759.GB28571@amt.cnet> References: <20140422191042.005048158@amt.cnet> <20140422191200.416302523@amt.cnet> <20140422203807.GJ3363@otherpad.lan.raisama.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Paolo Bonzini , Andreas =?iso-8859-1?Q?F=E4rber?= , qemu-devel@nongnu.org, kvm@vger.kernel.org, Igor Mammedov To: Eduardo Habkost Return-path: Content-Disposition: inline In-Reply-To: <20140422203807.GJ3363@otherpad.lan.raisama.net> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+gceq-qemu-devel=gmane.org@nongnu.org Sender: qemu-devel-bounces+gceq-qemu-devel=gmane.org@nongnu.org List-Id: kvm.vger.kernel.org On Tue, Apr 22, 2014 at 05:38:07PM -0300, Eduardo Habkost wrote: > On Tue, Apr 22, 2014 at 04:10:44PM -0300, Marcelo Tosatti wrote: > > Invariant TSC documentation mentions that "invariant TSC will run at a > > constant rate in all ACPI P-, C-. and T-states". > > > > This is not the case if migration to a host with different TSC frequency > > is allowed, or if savevm is performed. So block migration/savevm. > > > > Also do not expose invariant tsc flag by default. > > What do you mean "do not expose invtsc by default", exactly? It is > already not exposed by default because the default CPU model is qemu64 > and qemu64 doesn't have it enabled. Should be "do not expose invtsc by default with -cpu host". Since it blocks migration, i considered it a special flag that should be set when user is aware that migration is going to be blocked. Makes sense?