From mboxrd@z Thu Jan 1 00:00:00 1970 From: Roman Kagan Subject: [PATCH v2 0/5] kvm: deliver async_pf to L1 only Date: Mon, 12 Dec 2016 17:32:20 +0300 Message-ID: <20161212143225.10580-1-rkagan@virtuozzo.com> Mime-Version: 1.0 Content-Type: text/plain Cc: Denis Lunev , Roman Kagan To: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= , "Paolo Bonzini" , Return-path: Received: from mail-ve1eur01on0107.outbound.protection.outlook.com ([104.47.1.107]:3987 "EHLO EUR01-VE1-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751702AbcLLWHf (ORCPT ); Mon, 12 Dec 2016 17:07:35 -0500 Sender: kvm-owner@vger.kernel.org List-ID: Async pagefaults should only be injected into L1 guests. This series tries to make certain that async_pfs are not injected when L2 is executing on a vCPU, but also that L2 exits to L1 as soon as there are ready pages, to allow L1 to make better scheduling decisions. Roman Kagan (5): kvm/x86: skip async_pf when in guest mode kvm: add helper for testing ready async_pf's kvm: kick vcpu when async_pf is resolved kvm/vmx: kick L2 guest to L1 by ready async_pf kvm/svm: kick L2 guest to L1 by ready async_pf Signed-off-by: Roman Kagan --- v1 -> v2: - dropped bogus patch for async_pf msr check - included patch to skip async_pf in guest mode as it disappeard from kvm/queue - avoid breaking s390 build in patch 3 include/linux/kvm_host.h | 7 +++++++ arch/x86/kvm/mmu.c | 2 +- arch/x86/kvm/svm.c | 10 ++++++++++ arch/x86/kvm/vmx.c | 9 +++++---- arch/x86/kvm/x86.c | 5 +++-- virt/kvm/async_pf.c | 8 ++++++-- 6 files changed, 32 insertions(+), 9 deletions(-) -- 2.9.3