From patchwork Mon Feb 29 02:37:23 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Fam Zheng X-Patchwork-Id: 589673 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [IPv6:2001:4830:134:3::11]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id E932F140557 for ; Mon, 29 Feb 2016 13:38:37 +1100 (AEDT) Received: from localhost ([::1]:33584 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aaDjI-0001Ib-1Q for incoming@patchwork.ozlabs.org; Sun, 28 Feb 2016 21:38:36 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:33990) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aaDih-0008Tu-IA for qemu-devel@nongnu.org; Sun, 28 Feb 2016 21:38:00 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1aaDid-0007yv-Ik for qemu-devel@nongnu.org; Sun, 28 Feb 2016 21:37:59 -0500 Received: from mx1.redhat.com ([209.132.183.28]:45508) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aaDid-0007yr-Dn for qemu-devel@nongnu.org; Sun, 28 Feb 2016 21:37:55 -0500 Received: from int-mx11.intmail.prod.int.phx2.redhat.com (int-mx11.intmail.prod.int.phx2.redhat.com [10.5.11.24]) by mx1.redhat.com (Postfix) with ESMTPS id 14C701E5E for ; Mon, 29 Feb 2016 02:37:55 +0000 (UTC) Received: from fam-t430.redhat.com (vpn1-5-71.pek2.redhat.com [10.72.5.71]) by int-mx11.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id u1T2bOsn012949; Sun, 28 Feb 2016 21:37:52 -0500 From: Fam Zheng To: qemu-devel@nongnu.org Date: Mon, 29 Feb 2016 10:37:23 +0800 Message-Id: <1456713443-16834-7-git-send-email-famz@redhat.com> In-Reply-To: <1456713443-16834-1-git-send-email-famz@redhat.com> References: <1456713443-16834-1-git-send-email-famz@redhat.com> X-Scanned-By: MIMEDefang 2.68 on 10.5.11.24 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x X-Received-From: 209.132.183.28 Cc: Paolo Bonzini Subject: [Qemu-devel] [PATCH 6/6] exec: Introduce AddressSpaceDispatch.mru_section X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Under heavy workloads the lookup will likely end up with the same MemoryRegionSection from last time. Using a pointer to cache the result, like ram_list.mru_block, significantly reduce computation cost of address_space_translate. During address space topology update, as->dispatch will be reallocated so the pointer is invalidated automatically. Perf reports a visible drop on the cpu usage. Before: + 2.06% phys_page_find + 0.95% address_space_translate_internal + 0.80% address_space_translate After: + 0.78% address_space_translate + 0.77% address_space_translate_internal + 0.69% address_space_lookup_region Signed-off-by: Fam Zheng --- exec.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/exec.c b/exec.c index ad8b826..3232861 100644 --- a/exec.c +++ b/exec.c @@ -135,6 +135,7 @@ typedef struct PhysPageMap { struct AddressSpaceDispatch { struct rcu_head rcu; + MemoryRegionSection *mru_section; /* This is a multi-level map on the physical address space. * The bottom level has pointers to MemoryRegionSections. */ @@ -342,14 +343,26 @@ static MemoryRegionSection *address_space_lookup_region(AddressSpaceDispatch *d, hwaddr addr, bool resolve_subpage) { - MemoryRegionSection *section; + MemoryRegionSection *section = atomic_read(&d->mru_section); subpage_t *subpage; + bool update; - section = phys_page_find(d->phys_map, addr, d->map.nodes, d->map.sections); + if (section && section != &d->map.sections[PHYS_SECTION_UNASSIGNED] && + range_covers_byte(section->offset_within_address_space, + section->size.lo, addr)) { + update = false; + } else { + section = phys_page_find(d->phys_map, addr, d->map.nodes, + d->map.sections); + update = true; + } if (resolve_subpage && section->mr->subpage) { subpage = container_of(section->mr, subpage_t, iomem); section = &d->map.sections[subpage->sub_section[SUBPAGE_IDX(addr)]]; } + if (update) { + atomic_set(&d->mru_section, section); + } return section; }