From nobody Fri May 3 22:24:50 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (209.51.188.17 [209.51.188.17]) by mx.zohomail.com with SMTPS id 154728244048530.976127420592093; Sat, 12 Jan 2019 00:40:40 -0800 (PST) Received: from localhost ([127.0.0.1]:57826 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1giEqA-0007oL-24 for importer@patchew.org; Sat, 12 Jan 2019 03:40:26 -0500 Received: from eggs.gnu.org ([209.51.188.92]:48785) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1giEpG-0007Tm-A3 for qemu-devel@nongnu.org; Sat, 12 Jan 2019 03:39:31 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1giEpE-0004YM-H4 for qemu-devel@nongnu.org; Sat, 12 Jan 2019 03:39:30 -0500 Received: from szxga05-in.huawei.com ([45.249.212.191]:2237 helo=huawei.com) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1giEpC-0004TZ-Ur for qemu-devel@nongnu.org; Sat, 12 Jan 2019 03:39:28 -0500 Received: from DGGEMS404-HUB.china.huawei.com (unknown [172.30.72.58]) by Forcepoint Email with ESMTP id 85FF3D9AFE326FF9BABE; Sat, 12 Jan 2019 16:23:45 +0800 (CST) Received: from localhost (10.177.21.2) by DGGEMS404-HUB.china.huawei.com (10.3.19.204) with Microsoft SMTP Server id 14.3.408.0; Sat, 12 Jan 2019 16:23:35 +0800 From: Zhuangyanying To: , , Date: Sat, 12 Jan 2019 08:20:59 +0000 Message-ID: <1547281259-26180-1-git-send-email-ann.zhuangyanying@huawei.com> X-Mailer: git-send-email 2.6.4.windows.1 MIME-Version: 1.0 X-Originating-IP: [10.177.21.2] X-CFilter-Loop: Reflected X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] X-Received-From: 45.249.212.191 Subject: [Qemu-devel] [PATCH] KVM: MMU: fast cleanup D bit based on fast write protect X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: liu.jinsong@huawei.com, wangxinxin.wang@huawei.com, Zhuang Yanying , qemu-devel@nongnu.org, kvm@vger.kernel.org Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Zhuang Yanying Recently I tested live-migration with large-memory guests, find vcpu may ha= ng for a long time while starting migration, such as 9s for 2048G(linux-4.2= 0.1+qemu-3.1.0). The reason is memory_global_dirty_log_start() taking too long, and the vcpu= is waiting for BQL. The page-by-page D bit clearup is the main time consum= ption. I think that the idea of "KVM: MMU: fast write protect" by xiaoguangrong, e= specially the function kvm_mmu_write_protect_all_pages(), is very helpful. After a little modifcation, on his patch, can solve this problem, 9s to 0.5= s. At the begining of live migration, write protection is only applied to the = top-level SPTE. Then the write from vm trigger the EPT violation, with for_= each_shadow_entry write protection is performed at dirct_map. Finally the Dirty bit of the target page(at level 1 page table) is cleared,= and the dirty page tracking is started. Of coure, the page where GPA is lo= cated is marked dirty when mmu_set_spte. A similar implementation on xen, just emt instead of write protection. What do you think about this solution? --- mmu.c | 5 ++++- vmx.c | 3 +-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/mmu.c b/mmu.c index b079d74..f49d316 100755 --- a/mmu.c +++ b/mmu.c @@ -3210,7 +3210,10 @@ static bool mmu_load_shadow_page(struct kvm *kvm, st= ruct kvm_mmu_page *sp) break; =20 if (is_last_spte(spte, sp->role.level)) { - flush |=3D spte_write_protect(sptep, false); + if (sp->role.level =3D=3D PT_PAGE_TABLE_LEVEL) + flush |=3D spte_clear_dirty(sptep); + else + flush |=3D spte_write_protect(sptep, false); continue; } =20 diff --git a/vmx.c b/vmx.c index 95784bc..7ec717f 100755 --- a/vmx.c +++ b/vmx.c @@ -14421,8 +14421,7 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int= cpu) static void vmx_slot_enable_log_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_mmu_slot_leaf_clear_dirty(kvm, slot); - kvm_mmu_slot_largepage_remove_write_access(kvm, slot); + kvm_mmu_write_protect_all_pages(kvm, true); } =20 static void vmx_slot_disable_log_dirty(struct kvm *kvm, --=20 1.8.3.1