From patchwork Tue Jun 18 08:09:48 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wanlong Gao X-Patchwork-Id: 252123 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)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id 287A72C0082 for ; Tue, 18 Jun 2013 18:13:11 +1000 (EST) Received: from localhost ([::1]:33976 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Uor2K-0006pw-Rt for incoming@patchwork.ozlabs.org; Tue, 18 Jun 2013 04:13:08 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:32796) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Uor1p-0006pm-Cy for qemu-devel@nongnu.org; Tue, 18 Jun 2013 04:12:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Uor1m-0001Sm-Q3 for qemu-devel@nongnu.org; Tue, 18 Jun 2013 04:12:37 -0400 Received: from [222.73.24.84] (port=18122 helo=song.cn.fujitsu.com) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Uor1m-0001Oz-1j for qemu-devel@nongnu.org; Tue, 18 Jun 2013 04:12:34 -0400 X-IronPort-AV: E=Sophos;i="4.87,887,1363104000"; d="scan'208";a="7587531" Received: from unknown (HELO tang.cn.fujitsu.com) ([10.167.250.3]) by song.cn.fujitsu.com with ESMTP; 18 Jun 2013 16:09:10 +0800 Received: from fnstmail02.fnst.cn.fujitsu.com (tang.cn.fujitsu.com [127.0.0.1]) by tang.cn.fujitsu.com (8.14.3/8.13.1) with ESMTP id r5I8BwjG003313; Tue, 18 Jun 2013 16:12:03 +0800 Received: from G08FNSTD121251.fnst.cn.fujitsu.com ([10.167.233.84]) by fnstmail02.fnst.cn.fujitsu.com (Lotus Domino Release 8.5.3) with ESMTP id 2013061816100015-2230904 ; Tue, 18 Jun 2013 16:10:00 +0800 From: Wanlong Gao To: qemu-devel@nongnu.org Date: Tue, 18 Jun 2013 16:09:48 +0800 Message-Id: <1371542991-15911-5-git-send-email-gaowanlong@cn.fujitsu.com> X-Mailer: git-send-email 1.8.3.rc2.10.g0c2b1cf In-Reply-To: <1371542991-15911-1-git-send-email-gaowanlong@cn.fujitsu.com> References: <1371542991-15911-1-git-send-email-gaowanlong@cn.fujitsu.com> X-MIMETrack: Itemize by SMTP Server on mailserver/fnst(Release 8.5.3|September 15, 2011) at 2013/06/18 16:10:00, Serialize by Router on mailserver/fnst(Release 8.5.3|September 15, 2011) at 2013/06/18 16:10:02, Serialize complete at 2013/06/18 16:10:02 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 222.73.24.84 Cc: andre.przywara@amd.com, aliguori@us.ibm.com, ehabkost@redhat.com, pbonzini@redhat.com, y-goto@jp.fujitsu.com, afaerber@suse.de, gaowanlong@cn.fujitsu.com Subject: [Qemu-devel] [PATCH 4/7] NUMA: set guest numa nodes memory policy 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 Set the guest numa nodes memory policies using the mbind(2) system call node by node. After this patch, we are able to set guest nodes memory policies through the QEMU options, this arms to solve the guest cross nodes memory access performance issue. And as you all know, if PCI-passthrough is used, direct-attached-device uses DMA transfer between device and qemu process. All pages of the guest will be pinned by get_user_pages(). KVM_ASSIGN_PCI_DEVICE ioctl kvm_vm_ioctl_assign_device() =>kvm_assign_device() => kvm_iommu_map_memslots() => kvm_iommu_map_pages() => kvm_pin_pages() So, with direct-attached-device, all guest page's page count will be +1 and any page migration will not work. AutoNUMA won't too. So, we should set the guest nodes memory allocation policies before the pages are really mapped. Signed-off-by: Andre Przywara Signed-off-by: Wanlong Gao --- cpus.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) diff --git a/cpus.c b/cpus.c index e123d3f..b868932 100644 --- a/cpus.c +++ b/cpus.c @@ -60,6 +60,15 @@ #endif /* CONFIG_LINUX */ +#ifdef CONFIG_NUMA +#include +#include +#ifndef MPOL_F_RELATIVE_NODES +#define MPOL_F_RELATIVE_NODES (1 << 14) +#define MPOL_F_STATIC_NODES (1 << 15) +#endif +#endif + static CPUArchState *next_cpu; static bool cpu_thread_is_idle(CPUArchState *env) @@ -1186,6 +1195,75 @@ static void tcg_exec_all(void) exit_request = 0; } +#ifdef CONFIG_NUMA +static int node_parse_bind_mode(unsigned int nodeid) +{ + int bind_mode; + + switch (numa_info[nodeid].flags & NODE_HOST_POLICY_MASK) { + case NODE_HOST_BIND: + bind_mode = MPOL_BIND; + break; + case NODE_HOST_INTERLEAVE: + bind_mode = MPOL_INTERLEAVE; + break; + case NODE_HOST_PREFERRED: + bind_mode = MPOL_PREFERRED; + break; + default: + bind_mode = MPOL_DEFAULT; + return bind_mode; + } + + bind_mode |= (numa_info[nodeid].flags & NODE_HOST_RELATIVE) ? + MPOL_F_RELATIVE_NODES : MPOL_F_STATIC_NODES; + + return bind_mode; +} +#endif + +static int set_node_mpol(unsigned int nodeid) +{ +#ifdef CONFIG_NUMA + void *ram_ptr; + RAMBlock *block; + ram_addr_t len, ram_offset = 0; + int bind_mode; + int i; + + QTAILQ_FOREACH(block, &ram_list.blocks, next) { + if (!strcmp(block->mr->name, "pc.ram")) { + break; + } + } + + if (block->host == NULL) + return -1; + + ram_ptr = block->host; + for (i = 0; i < nodeid; i++) { + len = numa_info[i].node_mem; + ram_offset += len; + } + + len = numa_info[i].node_mem; + bind_mode = node_parse_bind_mode(i); + + /* This is a workaround for a long standing bug in Linux' + * mbind implementation, which cuts off the last specified + * node. To stay compatible should this bug be fixed, we + * specify one more node and zero this one out. + */ + clear_bit(numa_num_configured_nodes() + 1, numa_info[i].host_mem); + if (mbind(ram_ptr + ram_offset, len, bind_mode, + numa_info[i].host_mem, numa_num_configured_nodes() + 1, 0)) { + perror("mbind"); + return -1; + } +#endif + return 0; +} + void set_numa_modes(void) { CPUArchState *env; @@ -1200,6 +1278,14 @@ void set_numa_modes(void) } } } + +#ifdef CONFIG_NUMA + for (i = 0; i < nb_numa_nodes; i++) { + if (set_node_mpol(i) == -1) { + fprintf(stderr, "qemu: can't set host memory policy for node%d", i); + } + } +#endif } void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)