From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: RFC: PIC: enhance IPI avoidance Date: Sun, 13 Jul 2008 19:12:22 +0300 Message-ID: <487A2966.4070403@qumranet.com> References: <20080711210843.GA30887@dmt.cnet> <487A26AB.9000305@qumranet.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Cc: "Yang, Sheng" , kvm-devel To: Marcelo Tosatti Return-path: Received: from il.qumranet.com ([212.179.150.194]:15779 "EHLO il.qumranet.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751381AbYGMQM0 (ORCPT ); Sun, 13 Jul 2008 12:12:26 -0400 In-Reply-To: <487A26AB.9000305@qumranet.com> Sender: kvm-owner@vger.kernel.org List-ID: Avi Kivity wrote: > Marcelo Tosatti wrote: >> The PIC code makes little effort to avoid kvm_vcpu_kick(), resulting in >> unnecessary guest exits in some conditions. >> >> For example, if the timer interrupt is routed through the IOAPIC, IRR >> for IRQ 0 will get set but not cleared, since the APIC is handling the >> acks. >> >> This means that everytime an interrupt < 16 is triggered, the priority >> logic will find IRQ0 pending and send an IPI to vcpu0 (in case IRQ0 is >> not masked, which is Linux's case). >> >> Introduce a new variable isr_ack to represent the IRQ's for which the >> guest has been signalled / cleared the ISR. Use it to avoid more than >> one IPI per trigger-ack cycle, in addition to the avoidance when ISR is >> set in get_priority(). >> > > Looks good. ... but perhaps it can be done less intrusively. Presumably the PIC is masked through the local apic LVT? If so we can check that instead. So when the lapic detects that extint delivery is disabled, it can call kvm_pic_disable_delivery(), or something, to reduce pic chatter. -- error compiling committee.c: too many arguments to function