From patchwork Mon Aug 13 14:57:54 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Marc Zyngier X-Patchwork-Id: 10564401 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 7EFF114E2 for ; Mon, 13 Aug 2018 15:00:47 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 6E40F2949F for ; Mon, 13 Aug 2018 15:00:47 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 6C989294C3; Mon, 13 Aug 2018 15:00:47 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id D29E12949F for ; Mon, 13 Aug 2018 15:00:46 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1730032AbeHMRnW (ORCPT ); Mon, 13 Aug 2018 13:43:22 -0400 Received: from usa-sjc-mx-foss1.foss.arm.com ([217.140.101.70]:60698 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729925AbeHMRnW (ORCPT ); Mon, 13 Aug 2018 13:43:22 -0400 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 10BBB168F; Mon, 13 Aug 2018 08:00:45 -0700 (PDT) Received: from approximate.Emea.Arm.com (approximate.Emea.Arm.com [10.4.13.119]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 1EA543F5D0; Mon, 13 Aug 2018 08:00:41 -0700 (PDT) From: Marc Zyngier To: Paolo Bonzini , =?utf-8?b?UmFkaW0gS3LEjW3DocWZ?= Cc: kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu, linux-arm-kernel@lists.infradead.org, Andre Przywara , Andrew Jones , Catalin Marinas , Christoffer Dall , Dongjiu Geng , Eric Auger , "Gustavo A . R . Silva" , James Morse , Jia He , Kees Cook , Mark Rutland , Punit Agrawal , Suzuki Poulose Subject: [PATCH 36/37] KVM: arm/arm64: Skip updating PMD entry if no change Date: Mon, 13 Aug 2018 15:57:54 +0100 Message-Id: <20180813145755.16566-37-marc.zyngier@arm.com> X-Mailer: git-send-email 2.18.0 In-Reply-To: <20180813145755.16566-1-marc.zyngier@arm.com> References: <20180813145755.16566-1-marc.zyngier@arm.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Punit Agrawal Contention on updating a PMD entry by a large number of vcpus can lead to duplicate work when handling stage 2 page faults. As the page table update follows the break-before-make requirement of the architecture, it can lead to repeated refaults due to clearing the entry and flushing the tlbs. This problem is more likely when - * there are large number of vcpus * the mapping is large block mapping such as when using PMD hugepages (512MB) with 64k pages. Fix this by skipping the page table update if there is no change in the entry being updated. Cc: stable@vger.kernel.org Fixes: ad361f093c1e ("KVM: ARM: Support hugetlbfs backed huge pages") Reviewed-by: Suzuki Poulose Acked-by: Christoffer Dall Signed-off-by: Punit Agrawal Signed-off-by: Marc Zyngier --- virt/kvm/arm/mmu.c | 38 +++++++++++++++++++++++++++----------- 1 file changed, 27 insertions(+), 11 deletions(-) diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 97d27cd9c654..13dfe36501aa 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1044,19 +1044,35 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache pmd = stage2_get_pmd(kvm, cache, addr); VM_BUG_ON(!pmd); - /* - * Mapping in huge pages should only happen through a fault. If a - * page is merged into a transparent huge page, the individual - * subpages of that huge page should be unmapped through MMU - * notifiers before we get here. - * - * Merging of CompoundPages is not supported; they should become - * splitting first, unmapped, merged, and mapped back in on-demand. - */ - VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd)); - old_pmd = *pmd; if (pmd_present(old_pmd)) { + /* + * Multiple vcpus faulting on the same PMD entry, can + * lead to them sequentially updating the PMD with the + * same value. Following the break-before-make + * (pmd_clear() followed by tlb_flush()) process can + * hinder forward progress due to refaults generated + * on missing translations. + * + * Skip updating the page table if the entry is + * unchanged. + */ + if (pmd_val(old_pmd) == pmd_val(*new_pmd)) + return 0; + + /* + * Mapping in huge pages should only happen through a + * fault. If a page is merged into a transparent huge + * page, the individual subpages of that huge page + * should be unmapped through MMU notifiers before we + * get here. + * + * Merging of CompoundPages is not supported; they + * should become splitting first, unmapped, merged, + * and mapped back in on-demand. + */ + VM_BUG_ON(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd)); + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); } else {