Signed-off-by: Wanlong Gao <gaowanlong@cn.fujitsu.com> Signed-off-by: Igor Mammedov <imammedo@redhat.com> Tested-by: Eduardo Habkost <ehabkost@redhat.com> Reviewed-by: Eduardo Habkost <ehabkost@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Hu Tao <hutao@cn.fujitsu.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
196 lines
5.7 KiB
C
196 lines
5.7 KiB
C
/*
|
|
* NUMA parameter parsing routines
|
|
*
|
|
* Copyright (c) 2014 Fujitsu Ltd.
|
|
*
|
|
* 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"
|
|
#include "exec/cpu-common.h"
|
|
#include "qemu/bitmap.h"
|
|
#include "qom/cpu.h"
|
|
#include "qemu/error-report.h"
|
|
#include "include/exec/cpu-common.h" /* for RAM_ADDR_FMT */
|
|
#include "qapi-visit.h"
|
|
#include "qapi/opts-visitor.h"
|
|
#include "qapi/dealloc-visitor.h"
|
|
#include "qapi/qmp/qerror.h"
|
|
|
|
QemuOptsList qemu_numa_opts = {
|
|
.name = "numa",
|
|
.implied_opt_name = "type",
|
|
.head = QTAILQ_HEAD_INITIALIZER(qemu_numa_opts.head),
|
|
.desc = { { 0 } } /* validated with OptsVisitor */
|
|
};
|
|
|
|
static void numa_node_parse(NumaNodeOptions *node, QemuOpts *opts, Error **errp)
|
|
{
|
|
uint16_t nodenr;
|
|
uint16List *cpus = NULL;
|
|
|
|
if (node->has_nodeid) {
|
|
nodenr = node->nodeid;
|
|
} else {
|
|
nodenr = nb_numa_nodes;
|
|
}
|
|
|
|
if (nodenr >= MAX_NODES) {
|
|
error_setg(errp, "Max number of NUMA nodes reached: %"
|
|
PRIu16 "\n", nodenr);
|
|
return;
|
|
}
|
|
|
|
for (cpus = node->cpus; cpus; cpus = cpus->next) {
|
|
if (cpus->value > MAX_CPUMASK_BITS) {
|
|
error_setg(errp, "CPU number %" PRIu16 " is bigger than %d",
|
|
cpus->value, MAX_CPUMASK_BITS);
|
|
return;
|
|
}
|
|
bitmap_set(numa_info[nodenr].node_cpu, cpus->value, 1);
|
|
}
|
|
|
|
if (node->has_mem) {
|
|
uint64_t mem_size = node->mem;
|
|
const char *mem_str = qemu_opt_get(opts, "mem");
|
|
/* Fix up legacy suffix-less format */
|
|
if (g_ascii_isdigit(mem_str[strlen(mem_str) - 1])) {
|
|
mem_size <<= 20;
|
|
}
|
|
numa_info[nodenr].node_mem = mem_size;
|
|
}
|
|
}
|
|
|
|
int numa_init_func(QemuOpts *opts, void *opaque)
|
|
{
|
|
NumaOptions *object = NULL;
|
|
Error *err = NULL;
|
|
|
|
{
|
|
OptsVisitor *ov = opts_visitor_new(opts);
|
|
visit_type_NumaOptions(opts_get_visitor(ov), &object, NULL, &err);
|
|
opts_visitor_cleanup(ov);
|
|
}
|
|
|
|
if (err) {
|
|
goto error;
|
|
}
|
|
|
|
switch (object->kind) {
|
|
case NUMA_OPTIONS_KIND_NODE:
|
|
numa_node_parse(object->node, opts, &err);
|
|
if (err) {
|
|
goto error;
|
|
}
|
|
nb_numa_nodes++;
|
|
break;
|
|
default:
|
|
abort();
|
|
}
|
|
|
|
return 0;
|
|
|
|
error:
|
|
qerror_report_err(err);
|
|
error_free(err);
|
|
|
|
if (object) {
|
|
QapiDeallocVisitor *dv = qapi_dealloc_visitor_new();
|
|
visit_type_NumaOptions(qapi_dealloc_get_visitor(dv),
|
|
&object, NULL, NULL);
|
|
qapi_dealloc_visitor_cleanup(dv);
|
|
}
|
|
|
|
return -1;
|
|
}
|
|
|
|
void set_numa_nodes(void)
|
|
{
|
|
if (nb_numa_nodes > 0) {
|
|
uint64_t numa_total;
|
|
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 (numa_info[i].node_mem != 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++) {
|
|
numa_info[i].node_mem = (ram_size / nb_numa_nodes) &
|
|
~((1 << 23UL) - 1);
|
|
usedmem += numa_info[i].node_mem;
|
|
}
|
|
numa_info[i].node_mem = ram_size - usedmem;
|
|
}
|
|
|
|
numa_total = 0;
|
|
for (i = 0; i < nb_numa_nodes; i++) {
|
|
numa_total += numa_info[i].node_mem;
|
|
}
|
|
if (numa_total != ram_size) {
|
|
error_report("total memory for NUMA nodes (%" PRIu64 ")"
|
|
" should equal RAM size (" RAM_ADDR_FMT ")",
|
|
numa_total, ram_size);
|
|
exit(1);
|
|
}
|
|
|
|
for (i = 0; i < nb_numa_nodes; i++) {
|
|
if (!bitmap_empty(numa_info[i].node_cpu, 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, numa_info[i % nb_numa_nodes].node_cpu);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
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, numa_info[i].node_cpu)) {
|
|
cpu->numa_node = i;
|
|
}
|
|
}
|
|
}
|
|
}
|