From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paolo Bonzini Subject: Re: [patch -rt 2/2] KVM: lapic: mark LAPIC timer handler as irqsafe Date: Thu, 04 Dec 2014 14:53:26 +0100 Message-ID: <54806756.30503@redhat.com> References: <20141125172108.992070524@redhat.com> <20141125172329.580701786@redhat.com> <5474D476.3020506@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Cc: kvm@vger.kernel.org To: linux-kernel@vger.kernel.org Return-path: In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On 25/11/2014 21:24, Thomas Gleixner wrote: > On Tue, 25 Nov 2014, Rik van Riel wrote: >> On 11/25/2014 12:21 PM, Marcelo Tosatti wrote: >>> Since lapic timer handler only wakes up a simple waitqueue, >>> it can be executed from hardirq context. >>> >>> Reduces average cyclictest latency by 3us. >> >> Can this patch be merged in the KVM tree, and go >> upstream via Paolo? > > Not really as it has RT dependencies .... Can hrtimer_start_expires even return ETIME on a non-RT kernel? If yes, I can take patch 2. If not, it's better to keep both patches in the RT tree. Paolo