From patchwork Wed Feb 19 07:53:52 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hu Tao X-Patchwork-Id: 321764 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 419E82C0306 for ; Wed, 19 Feb 2014 18:57:05 +1100 (EST) Received: from localhost ([::1]:56971 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WG21J-0007Rv-U3 for incoming@patchwork.ozlabs.org; Wed, 19 Feb 2014 02:56:41 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:49473) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WG20o-0007Rg-PN for qemu-devel@nongnu.org; Wed, 19 Feb 2014 02:56:15 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1WG20k-0003Ut-4z for qemu-devel@nongnu.org; Wed, 19 Feb 2014 02:56:10 -0500 Received: from [222.73.24.84] (port=23891 helo=song.cn.fujitsu.com) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WG20i-0003T0-W1 for qemu-devel@nongnu.org; Wed, 19 Feb 2014 02:56:06 -0500 X-IronPort-AV: E=Sophos;i="4.97,504,1389715200"; d="scan'208";a="9558769" Received: from unknown (HELO tang.cn.fujitsu.com) ([10.167.250.3]) by song.cn.fujitsu.com with ESMTP; 19 Feb 2014 15:52:04 +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 s1J7tp4O012636; Wed, 19 Feb 2014 15:55:53 +0800 Received: from G08FNSTD100614.fnst.cn.fujitsu.com ([10.167.226.102]) by fnstmail02.fnst.cn.fujitsu.com (Lotus Domino Release 8.5.3) with ESMTP id 2014021915534202-35696 ; Wed, 19 Feb 2014 15:53:42 +0800 From: Hu Tao To: qemu-devel@nongnu.org Date: Wed, 19 Feb 2014 15:53:52 +0800 Message-Id: X-Mailer: git-send-email 1.8.5.2.229.g4448466 In-Reply-To: References: X-MIMETrack: Itemize by SMTP Server on mailserver/fnst(Release 8.5.3|September 15, 2011) at 2014/02/19 15:53:42, Serialize by Router on mailserver/fnst(Release 8.5.3|September 15, 2011) at 2014/02/19 15:53:45, Serialize complete at 2014/02/19 15:53:45 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 222.73.24.84 Cc: pbonzini@redhat.com, lersek@redhat.com, Wanlong Gao , imammedo@redhat.com Subject: [Qemu-devel] [PATCH v18 01/14] NUMA: move numa related code to new file numa.c 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 From: Wanlong Gao Signed-off-by: Wanlong Gao Signed-off-by: Paolo Bonzini Signed-off-by: Hu Tao --- Makefile.target | 2 +- cpus.c | 14 ---- include/sysemu/cpus.h | 1 - include/sysemu/sysemu.h | 3 + numa.c | 183 ++++++++++++++++++++++++++++++++++++++++++++++++ vl.c | 139 +----------------------------------- 6 files changed, 188 insertions(+), 154 deletions(-) create mode 100644 numa.c diff --git a/Makefile.target b/Makefile.target index af6ac7e..0197c17 100644 --- a/Makefile.target +++ b/Makefile.target @@ -109,7 +109,7 @@ endif #CONFIG_BSD_USER ######################################################### # System emulator target ifdef CONFIG_SOFTMMU -obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o +obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o numa.o obj-y += qtest.o obj-y += hw/ obj-$(CONFIG_FDT) += device_tree.o diff --git a/cpus.c b/cpus.c index 945d85b..891d062 100644 --- a/cpus.c +++ b/cpus.c @@ -1299,20 +1299,6 @@ static void tcg_exec_all(void) exit_request = 0; } -void set_numa_modes(void) -{ - CPUState *cpu; - int i; - - CPU_FOREACH(cpu) { - for (i = 0; i < nb_numa_nodes; i++) { - if (test_bit(cpu->cpu_index, node_cpumask[i])) { - cpu->numa_node = i; - } - } - } -} - void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg) { /* XXX: implement xxx_cpu_list for targets that still miss it */ diff --git a/include/sysemu/cpus.h b/include/sysemu/cpus.h index 6502488..4f79081 100644 --- a/include/sysemu/cpus.h +++ b/include/sysemu/cpus.h @@ -23,7 +23,6 @@ extern int smp_threads; #define smp_threads 1 #endif -void set_numa_modes(void); void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg); #endif diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 495dae8..2509649 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -136,6 +136,9 @@ extern QEMUClockType rtc_clock; extern int nb_numa_nodes; extern uint64_t node_mem[MAX_NODES]; extern unsigned long *node_cpumask[MAX_NODES]; +void numa_add(const char *optarg); +void set_numa_nodes(void); +void set_numa_modes(void); #define MAX_OPTION_ROMS 16 typedef struct QEMUOptionRom { diff --git a/numa.c b/numa.c new file mode 100644 index 0000000..7845036 --- /dev/null +++ b/numa.c @@ -0,0 +1,183 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2013 Fujitsu Ltd. + * Author: Wanlong Gao + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "sysemu/sysemu.h" + +static void numa_node_parse_cpus(int nodenr, const char *cpus) +{ + char *endptr; + unsigned long long value, endvalue; + + /* Empty CPU range strings will be considered valid, they will simply + * not set any bit in the CPU bitmap. + */ + if (!*cpus) { + return; + } + + if (parse_uint(cpus, &value, &endptr, 10) < 0) { + goto error; + } + if (*endptr == '-') { + if (parse_uint_full(endptr + 1, &endvalue, 10) < 0) { + goto error; + } + } else if (*endptr == '\0') { + endvalue = value; + } else { + goto error; + } + + if (endvalue >= MAX_CPUMASK_BITS) { + endvalue = MAX_CPUMASK_BITS - 1; + fprintf(stderr, + "qemu: NUMA: A max of %d VCPUs are supported\n", + MAX_CPUMASK_BITS); + } + + if (endvalue < value) { + goto error; + } + + bitmap_set(node_cpumask[nodenr], value, endvalue-value+1); + return; + +error: + fprintf(stderr, "qemu: Invalid NUMA CPU range: %s\n", cpus); + exit(1); +} + +void numa_add(const char *optarg) +{ + char option[128]; + char *endptr; + unsigned long long nodenr; + + optarg = get_opt_name(option, 128, optarg, ','); + if (*optarg == ',') { + optarg++; + } + if (!strcmp(option, "node")) { + + if (nb_numa_nodes >= MAX_NODES) { + fprintf(stderr, "qemu: too many NUMA nodes\n"); + exit(1); + } + + if (get_param_value(option, 128, "nodeid", optarg) == 0) { + nodenr = nb_numa_nodes; + } else { + if (parse_uint_full(option, &nodenr, 10) < 0) { + fprintf(stderr, "qemu: Invalid NUMA nodeid: %s\n", option); + exit(1); + } + } + + if (nodenr >= MAX_NODES) { + fprintf(stderr, "qemu: invalid NUMA nodeid: %llu\n", nodenr); + exit(1); + } + + if (get_param_value(option, 128, "mem", optarg) == 0) { + node_mem[nodenr] = 0; + } else { + int64_t sval; + sval = strtosz(option, &endptr); + if (sval < 0 || *endptr) { + fprintf(stderr, "qemu: invalid numa mem size: %s\n", optarg); + exit(1); + } + node_mem[nodenr] = sval; + } + if (get_param_value(option, 128, "cpus", optarg) != 0) { + numa_node_parse_cpus(nodenr, option); + } + nb_numa_nodes++; + } else { + fprintf(stderr, "Invalid -numa option: %s\n", option); + exit(1); + } +} + +void set_numa_nodes(void) +{ + if (nb_numa_nodes > 0) { + int i; + + if (nb_numa_nodes > MAX_NODES) { + nb_numa_nodes = MAX_NODES; + } + + /* If no memory size if given for any node, assume the default case + * and distribute the available memory equally across all nodes + */ + for (i = 0; i < nb_numa_nodes; i++) { + if (node_mem[i] != 0) { + break; + } + } + if (i == nb_numa_nodes) { + uint64_t usedmem = 0; + + /* On Linux, the each node's border has to be 8MB aligned, + * the final node gets the rest. + */ + for (i = 0; i < nb_numa_nodes - 1; i++) { + node_mem[i] = (ram_size / nb_numa_nodes) & ~((1 << 23UL) - 1); + usedmem += node_mem[i]; + } + node_mem[i] = ram_size - usedmem; + } + + for (i = 0; i < nb_numa_nodes; i++) { + if (!bitmap_empty(node_cpumask[i], MAX_CPUMASK_BITS)) { + break; + } + } + /* assigning the VCPUs round-robin is easier to implement, guest OSes + * must cope with this anyway, because there are BIOSes out there in + * real machines which also use this scheme. + */ + if (i == nb_numa_nodes) { + for (i = 0; i < max_cpus; i++) { + set_bit(i, node_cpumask[i % nb_numa_nodes]); + } + } + } +} + +void set_numa_modes(void) +{ + CPUState *cpu; + int i; + + CPU_FOREACH(cpu) { + for (i = 0; i < nb_numa_nodes; i++) { + if (test_bit(cpu->cpu_index, node_cpumask[i])) { + cpu->numa_node = i; + } + } + } +} diff --git a/vl.c b/vl.c index 316de54..0adac0c 100644 --- a/vl.c +++ b/vl.c @@ -1211,102 +1211,6 @@ char *get_boot_devices_list(size_t *size) return list; } -static void numa_node_parse_cpus(int nodenr, const char *cpus) -{ - char *endptr; - unsigned long long value, endvalue; - - /* Empty CPU range strings will be considered valid, they will simply - * not set any bit in the CPU bitmap. - */ - if (!*cpus) { - return; - } - - if (parse_uint(cpus, &value, &endptr, 10) < 0) { - goto error; - } - if (*endptr == '-') { - if (parse_uint_full(endptr + 1, &endvalue, 10) < 0) { - goto error; - } - } else if (*endptr == '\0') { - endvalue = value; - } else { - goto error; - } - - if (endvalue >= MAX_CPUMASK_BITS) { - endvalue = MAX_CPUMASK_BITS - 1; - fprintf(stderr, - "qemu: NUMA: A max of %d VCPUs are supported\n", - MAX_CPUMASK_BITS); - } - - if (endvalue < value) { - goto error; - } - - bitmap_set(node_cpumask[nodenr], value, endvalue-value+1); - return; - -error: - fprintf(stderr, "qemu: Invalid NUMA CPU range: %s\n", cpus); - exit(1); -} - -static void numa_add(const char *optarg) -{ - char option[128]; - char *endptr; - unsigned long long nodenr; - - optarg = get_opt_name(option, 128, optarg, ','); - if (*optarg == ',') { - optarg++; - } - if (!strcmp(option, "node")) { - - if (nb_numa_nodes >= MAX_NODES) { - fprintf(stderr, "qemu: too many NUMA nodes\n"); - exit(1); - } - - if (get_param_value(option, 128, "nodeid", optarg) == 0) { - nodenr = nb_numa_nodes; - } else { - if (parse_uint_full(option, &nodenr, 10) < 0) { - fprintf(stderr, "qemu: Invalid NUMA nodeid: %s\n", option); - exit(1); - } - } - - if (nodenr >= MAX_NODES) { - fprintf(stderr, "qemu: invalid NUMA nodeid: %llu\n", nodenr); - exit(1); - } - - if (get_param_value(option, 128, "mem", optarg) == 0) { - node_mem[nodenr] = 0; - } else { - int64_t sval; - sval = strtosz(option, &endptr); - if (sval < 0 || *endptr) { - fprintf(stderr, "qemu: invalid numa mem size: %s\n", optarg); - exit(1); - } - node_mem[nodenr] = sval; - } - if (get_param_value(option, 128, "cpus", optarg) != 0) { - numa_node_parse_cpus(nodenr, option); - } - nb_numa_nodes++; - } else { - fprintf(stderr, "Invalid -numa option: %s\n", option); - exit(1); - } -} - static QemuOptsList qemu_smp_opts = { .name = "smp-opts", .implied_opt_name = "cpus", @@ -4139,48 +4043,7 @@ int main(int argc, char **argv, char **envp) register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, NULL); - if (nb_numa_nodes > 0) { - int i; - - if (nb_numa_nodes > MAX_NODES) { - nb_numa_nodes = MAX_NODES; - } - - /* If no memory size if given for any node, assume the default case - * and distribute the available memory equally across all nodes - */ - for (i = 0; i < nb_numa_nodes; i++) { - if (node_mem[i] != 0) - break; - } - if (i == nb_numa_nodes) { - uint64_t usedmem = 0; - - /* On Linux, the each node's border has to be 8MB aligned, - * the final node gets the rest. - */ - for (i = 0; i < nb_numa_nodes - 1; i++) { - node_mem[i] = (ram_size / nb_numa_nodes) & ~((1 << 23UL) - 1); - usedmem += node_mem[i]; - } - node_mem[i] = ram_size - usedmem; - } - - for (i = 0; i < nb_numa_nodes; i++) { - if (!bitmap_empty(node_cpumask[i], MAX_CPUMASK_BITS)) { - break; - } - } - /* assigning the VCPUs round-robin is easier to implement, guest OSes - * must cope with this anyway, because there are BIOSes out there in - * real machines which also use this scheme. - */ - if (i == nb_numa_nodes) { - for (i = 0; i < max_cpus; i++) { - set_bit(i, node_cpumask[i % nb_numa_nodes]); - } - } - } + set_numa_nodes(); if (qemu_opts_foreach(qemu_find_opts("mon"), mon_init_func, NULL, 1) != 0) { exit(1);