* THE SOFTWARE.
*/
+#include "qemu/osdep.h"
#include "sysemu/numa.h"
#include "exec/cpu-common.h"
+#include "exec/ramlist.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"
#include "hw/boards.h"
#include "sysemu/hostmem.h"
#include "qmp-commands.h"
int nb_numa_nodes;
NodeInfo numa_info[MAX_NODES];
+void numa_set_mem_node_id(ram_addr_t addr, uint64_t size, uint32_t node)
+{
+ struct numa_addr_range *range;
+
+ /*
+ * Memory-less nodes can come here with 0 size in which case,
+ * there is nothing to do.
+ */
+ if (!size) {
+ return;
+ }
+
+ range = g_malloc0(sizeof(*range));
+ range->mem_start = addr;
+ range->mem_end = addr + size - 1;
+ QLIST_INSERT_HEAD(&numa_info[node].addr, range, entry);
+}
+
+void numa_unset_mem_node_id(ram_addr_t addr, uint64_t size, uint32_t node)
+{
+ struct numa_addr_range *range, *next;
+
+ QLIST_FOREACH_SAFE(range, &numa_info[node].addr, entry, next) {
+ if (addr == range->mem_start && (addr + size - 1) == range->mem_end) {
+ QLIST_REMOVE(range, entry);
+ g_free(range);
+ return;
+ }
+ }
+}
+
+static void numa_set_mem_ranges(void)
+{
+ int i;
+ ram_addr_t mem_start = 0;
+
+ /*
+ * Deduce start address of each node and use it to store
+ * the address range info in numa_info address range list
+ */
+ for (i = 0; i < nb_numa_nodes; i++) {
+ numa_set_mem_node_id(mem_start, numa_info[i].node_mem, i);
+ mem_start += numa_info[i].node_mem;
+ }
+}
+
+/*
+ * Check if @addr falls under NUMA @node.
+ */
+static bool numa_addr_belongs_to_node(ram_addr_t addr, uint32_t node)
+{
+ struct numa_addr_range *range;
+
+ QLIST_FOREACH(range, &numa_info[node].addr, entry) {
+ if (addr >= range->mem_start && addr <= range->mem_end) {
+ return true;
+ }
+ }
+ return false;
+}
+
+/*
+ * Given an address, return the index of the NUMA node to which the
+ * address belongs to.
+ */
+uint32_t numa_get_node(ram_addr_t addr, Error **errp)
+{
+ uint32_t i;
+
+ /* For non NUMA configurations, check if the addr falls under node 0 */
+ if (!nb_numa_nodes) {
+ if (numa_addr_belongs_to_node(addr, 0)) {
+ return 0;
+ }
+ }
+
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (numa_addr_belongs_to_node(addr, i)) {
+ return i;
+ }
+ }
+
+ error_setg(errp, "Address 0x" RAM_ADDR_FMT " doesn't belong to any "
+ "NUMA node", addr);
+ return -1;
+}
+
static void numa_node_parse(NumaNodeOptions *node, QemuOpts *opts, Error **errp)
{
uint16_t nodenr;
Error *err = NULL;
{
- OptsVisitor *ov = opts_visitor_new(opts);
- visit_type_NumaOptions(opts_get_visitor(ov), &object, NULL, &err);
- opts_visitor_cleanup(ov);
+ Visitor *v = opts_visitor_new(opts);
+ visit_type_NumaOptions(v, NULL, &object, &err);
+ visit_free(v);
}
if (err) {
- goto error;
+ goto end;
}
- switch (object->kind) {
- case NUMA_OPTIONS_KIND_NODE:
- numa_node_parse(object->node, opts, &err);
+ switch (object->type) {
+ case NUMA_OPTIONS_TYPE_NODE:
+ numa_node_parse(&object->u.node, opts, &err);
if (err) {
- goto error;
+ goto end;
}
nb_numa_nodes++;
break;
abort();
}
- return 0;
-
-error:
- error_report_err(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);
+end:
+ qapi_free_NumaOptions(object);
+ if (err) {
+ error_report_err(err);
+ return -1;
}
- return -1;
+ return 0;
}
static char *enumerate_cpus(unsigned long *cpus, int max_cpus)
static void validate_numa_cpus(void)
{
int i;
- DECLARE_BITMAP(seen_cpus, MAX_CPUMASK_BITS);
+ unsigned long *seen_cpus = bitmap_new(max_cpus);
- bitmap_zero(seen_cpus, MAX_CPUMASK_BITS);
for (i = 0; i < nb_numa_nodes; i++) {
- if (bitmap_intersects(seen_cpus, numa_info[i].node_cpu,
- MAX_CPUMASK_BITS)) {
+ if (bitmap_intersects(seen_cpus, numa_info[i].node_cpu, max_cpus)) {
bitmap_and(seen_cpus, seen_cpus,
- numa_info[i].node_cpu, MAX_CPUMASK_BITS);
+ numa_info[i].node_cpu, max_cpus);
error_report("CPU(s) present in multiple NUMA nodes: %s",
- enumerate_cpus(seen_cpus, max_cpus));;
+ enumerate_cpus(seen_cpus, max_cpus));
+ g_free(seen_cpus);
exit(EXIT_FAILURE);
}
bitmap_or(seen_cpus, seen_cpus,
- numa_info[i].node_cpu, MAX_CPUMASK_BITS);
+ numa_info[i].node_cpu, max_cpus);
}
if (!bitmap_full(seen_cpus, max_cpus)) {
"in NUMA config");
g_free(msg);
}
+ g_free(seen_cpus);
}
void parse_numa_opts(MachineClass *mc)
{
int i;
+ for (i = 0; i < MAX_NODES; i++) {
+ numa_info[i].node_cpu = bitmap_new(max_cpus);
+ }
+
if (qemu_opts_foreach(qemu_find_opts("numa"), parse_numa, NULL, NULL)) {
exit(1);
}
if (i == nb_numa_nodes) {
uint64_t usedmem = 0;
- /* On Linux, each node's border has to be 8MB aligned,
- * the final node gets the rest.
+ /* Align each node according to the alignment
+ * requirements of the machine class
*/
for (i = 0; i < nb_numa_nodes - 1; i++) {
numa_info[i].node_mem = (ram_size / nb_numa_nodes) &
- ~((1 << 23UL) - 1);
+ ~((1 << mc->numa_mem_align_shift) - 1);
usedmem += numa_info[i].node_mem;
}
numa_info[i].node_mem = ram_size - usedmem;
}
for (i = 0; i < nb_numa_nodes; i++) {
- if (!bitmap_empty(numa_info[i].node_cpu, MAX_CPUMASK_BITS)) {
+ QLIST_INIT(&numa_info[i].addr);
+ }
+
+ numa_set_mem_ranges();
+
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (!bitmap_empty(numa_info[i].node_cpu, max_cpus)) {
break;
}
}
}
validate_numa_cpus();
+ } else {
+ numa_set_mem_node_id(0, ram_size, 0);
}
}
CPU_FOREACH(cpu) {
for (i = 0; i < nb_numa_nodes; i++) {
+ assert(cpu->cpu_index < max_cpus);
if (test_bit(cpu->cpu_index, numa_info[i].node_cpu)) {
cpu->numa_node = i;
}
Error *err = NULL;
memory_region_init_ram_from_file(mr, owner, name, ram_size, false,
mem_path, &err);
-
- /* Legacy behavior: if allocation failed, fall back to
- * regular RAM allocation.
- */
if (err) {
error_report_err(err);
- memory_region_init_ram(mr, owner, name, ram_size, &error_abort);
+ if (mem_prealloc) {
+ exit(1);
+ }
+
+ /* Legacy behavior: if allocation failed, fall back to
+ * regular RAM allocation.
+ */
+ memory_region_init_ram(mr, owner, name, ram_size, &error_fatal);
}
#else
fprintf(stderr, "-mem-path not supported on this host\n");
exit(1);
#endif
} else {
- memory_region_init_ram(mr, owner, name, ram_size, &error_abort);
+ memory_region_init_ram(mr, owner, name, ram_size, &error_fatal);
}
vmstate_register_ram_global(mr);
}
memory_region_init(mr, owner, name, ram_size);
for (i = 0; i < MAX_NODES; i++) {
- Error *local_err = NULL;
uint64_t size = numa_info[i].node_mem;
HostMemoryBackend *backend = numa_info[i].node_memdev;
if (!backend) {
continue;
}
- MemoryRegion *seg = host_memory_backend_get_memory(backend, &local_err);
- if (local_err) {
- error_report_err(local_err);
- exit(1);
- }
+ MemoryRegion *seg = host_memory_backend_get_memory(backend,
+ &error_fatal);
if (memory_region_is_mapped(seg)) {
char *path = object_get_canonical_path_component(OBJECT(backend));
exit(1);
}
+ host_memory_backend_set_mapped(backend, true);
memory_region_add_subregion(mr, addr, seg);
vmstate_register_ram_global(seg);
addr += size;
MemoryDeviceInfo *value = info->value;
if (value) {
- switch (value->kind) {
+ switch (value->type) {
case MEMORY_DEVICE_INFO_KIND_DIMM:
- node_mem[value->dimm->node] += value->dimm->size;
+ node_mem[value->u.dimm.data->node] += value->u.dimm.data->size;
break;
default:
break;
{
MemdevList **list = opaque;
MemdevList *m = NULL;
- Error *err = NULL;
if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) {
m = g_malloc0(sizeof(*m));
m->value = g_malloc0(sizeof(*m->value));
- m->value->size = object_property_get_int(obj, "size",
- &err);
- if (err) {
- goto error;
- }
+ m->value->id = object_property_get_str(obj, "id", NULL);
+ m->value->has_id = !!m->value->id;
+ m->value->size = object_property_get_int(obj, "size",
+ &error_abort);
m->value->merge = object_property_get_bool(obj, "merge",
- &err);
- if (err) {
- goto error;
- }
-
+ &error_abort);
m->value->dump = object_property_get_bool(obj, "dump",
- &err);
- if (err) {
- goto error;
- }
-
+ &error_abort);
m->value->prealloc = object_property_get_bool(obj,
- "prealloc", &err);
- if (err) {
- goto error;
- }
-
+ "prealloc",
+ &error_abort);
m->value->policy = object_property_get_enum(obj,
"policy",
- HostMemPolicy_lookup,
- &err);
- if (err) {
- goto error;
- }
-
+ "HostMemPolicy",
+ &error_abort);
object_property_get_uint16List(obj, "host-nodes",
- &m->value->host_nodes, &err);
- if (err) {
- goto error;
- }
+ &m->value->host_nodes,
+ &error_abort);
m->next = *list;
*list = m;
}
return 0;
-error:
- g_free(m->value);
- g_free(m);
-
- return -1;
}
MemdevList *qmp_query_memdev(Error **errp)
{
- Object *obj;
+ Object *obj = object_get_objects_root();
MemdevList *list = NULL;
- obj = object_get_objects_root();
- if (obj == NULL) {
- return NULL;
+ object_child_foreach(obj, query_memdev, &list);
+ return list;
+}
+
+int numa_get_node_for_cpu(int idx)
+{
+ int i;
+
+ assert(idx < max_cpus);
+
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (test_bit(idx, numa_info[i].node_cpu)) {
+ break;
+ }
}
+ return i;
+}
+
+void ram_block_notifier_add(RAMBlockNotifier *n)
+{
+ QLIST_INSERT_HEAD(&ram_list.ramblock_notifiers, n, next);
+}
+
+void ram_block_notifier_remove(RAMBlockNotifier *n)
+{
+ QLIST_REMOVE(n, next);
+}
- if (object_child_foreach(obj, query_memdev, &list) != 0) {
- goto error;
+void ram_block_notify_add(void *host, size_t size)
+{
+ RAMBlockNotifier *notifier;
+
+ QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) {
+ notifier->ram_block_added(notifier, host, size);
}
+}
- return list;
+void ram_block_notify_remove(void *host, size_t size)
+{
+ RAMBlockNotifier *notifier;
-error:
- qapi_free_MemdevList(list);
- return NULL;
+ QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) {
+ notifier->ram_block_removed(notifier, host, size);
+ }
}
projects / mirror_qemu.git / blobdiff