*/
#include "qemu/osdep.h"
+#include "qemu/units.h"
#include "sysemu/hostmem.h"
#include "sysemu/numa.h"
#include "sysemu/sysemu.h"
};
static int have_memdevs;
+bool numa_uses_legacy_mem(void)
+{
+ return !have_memdevs;
+}
+
static int have_mem;
static int max_numa_nodeid; /* Highest specified NUMA node ID, plus one.
* For all nodes, nodeid < max_numa_nodeid
return;
}
- if (!mc->cpu_index_to_instance_props || !mc->get_default_cpu_node_id) {
- error_setg(errp, "NUMA is not supported by this machine-type");
- return;
- }
for (cpus = node->cpus; cpus; cpus = cpus->next) {
CpuInstanceProperties props;
if (cpus->value >= max_cpus) {
}
if (node->has_mem) {
+ if (!mc->numa_mem_supported) {
+ error_setg(errp, "Parameter -numa node,mem is not supported by this"
+ " machine type");
+ error_append_hint(errp, "Use -numa node,memdev instead\n");
+ return;
+ }
+
numa_info[nodenr].node_mem = node->mem;
if (!qtest_enabled()) {
warn_report("Parameter -numa node,mem is deprecated,"
numa_info[nodenr].node_mem = object_property_get_uint(o, "size", NULL);
numa_info[nodenr].node_memdev = MEMORY_BACKEND(o);
}
+
+ /*
+ * If not set the initiator, set it to MAX_NODES. And if
+ * HMAT is enabled and this node has no cpus, QEMU will raise error.
+ */
+ numa_info[nodenr].initiator = MAX_NODES;
+ if (node->has_initiator) {
+ if (!ms->numa_state->hmat_enabled) {
+ error_setg(errp, "ACPI Heterogeneous Memory Attribute Table "
+ "(HMAT) is disabled, enable it with -machine hmat=on "
+ "before using any of hmat specific options");
+ return;
+ }
+
+ if (node->initiator >= MAX_NODES) {
+ error_report("The initiator id %" PRIu16 " expects an integer "
+ "between 0 and %d", node->initiator,
+ MAX_NODES - 1);
+ return;
+ }
+
+ numa_info[nodenr].initiator = node->initiator;
+ }
numa_info[nodenr].present = true;
max_numa_nodeid = MAX(max_numa_nodeid, nodenr + 1);
ms->numa_state->num_nodes++;
ms->numa_state->have_numa_distance = true;
}
-void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp)
+void parse_numa_hmat_lb(NumaState *numa_state, NumaHmatLBOptions *node,
+ Error **errp)
{
- Error *err = NULL;
- MachineClass *mc = MACHINE_GET_CLASS(ms);
+ int i, first_bit, last_bit;
+ uint64_t max_entry, temp_base, bitmap_copy;
+ NodeInfo *numa_info = numa_state->nodes;
+ HMAT_LB_Info *hmat_lb =
+ numa_state->hmat_lb[node->hierarchy][node->data_type];
+ HMAT_LB_Data lb_data = {};
+ HMAT_LB_Data *lb_temp;
+
+ /* Error checking */
+ if (node->initiator > numa_state->num_nodes) {
+ error_setg(errp, "Invalid initiator=%d, it should be less than %d",
+ node->initiator, numa_state->num_nodes);
+ return;
+ }
+ if (node->target > numa_state->num_nodes) {
+ error_setg(errp, "Invalid target=%d, it should be less than %d",
+ node->target, numa_state->num_nodes);
+ return;
+ }
+ if (!numa_info[node->initiator].has_cpu) {
+ error_setg(errp, "Invalid initiator=%d, it isn't an "
+ "initiator proximity domain", node->initiator);
+ return;
+ }
+ if (!numa_info[node->target].present) {
+ error_setg(errp, "The target=%d should point to an existing node",
+ node->target);
+ return;
+ }
+
+ if (!hmat_lb) {
+ hmat_lb = g_malloc0(sizeof(*hmat_lb));
+ numa_state->hmat_lb[node->hierarchy][node->data_type] = hmat_lb;
+ hmat_lb->list = g_array_new(false, true, sizeof(HMAT_LB_Data));
+ }
+ hmat_lb->hierarchy = node->hierarchy;
+ hmat_lb->data_type = node->data_type;
+ lb_data.initiator = node->initiator;
+ lb_data.target = node->target;
+
+ if (node->data_type <= HMATLB_DATA_TYPE_WRITE_LATENCY) {
+ /* Input latency data */
+
+ if (!node->has_latency) {
+ error_setg(errp, "Missing 'latency' option");
+ return;
+ }
+ if (node->has_bandwidth) {
+ error_setg(errp, "Invalid option 'bandwidth' since "
+ "the data type is latency");
+ return;
+ }
+
+ /* Detect duplicate configuration */
+ for (i = 0; i < hmat_lb->list->len; i++) {
+ lb_temp = &g_array_index(hmat_lb->list, HMAT_LB_Data, i);
+
+ if (node->initiator == lb_temp->initiator &&
+ node->target == lb_temp->target) {
+ error_setg(errp, "Duplicate configuration of the latency for "
+ "initiator=%d and target=%d", node->initiator,
+ node->target);
+ return;
+ }
+ }
+
+ hmat_lb->base = hmat_lb->base ? hmat_lb->base : UINT64_MAX;
+
+ if (node->latency) {
+ /* Calculate the temporary base and compressed latency */
+ max_entry = node->latency;
+ temp_base = 1;
+ while (QEMU_IS_ALIGNED(max_entry, 10)) {
+ max_entry /= 10;
+ temp_base *= 10;
+ }
- if (!mc->numa_mem_supported) {
+ /* Calculate the max compressed latency */
+ temp_base = MIN(hmat_lb->base, temp_base);
+ max_entry = node->latency / hmat_lb->base;
+ max_entry = MAX(hmat_lb->range_bitmap, max_entry);
+
+ /*
+ * For latency hmat_lb->range_bitmap record the max compressed
+ * latency which should be less than 0xFFFF (UINT16_MAX)
+ */
+ if (max_entry >= UINT16_MAX) {
+ error_setg(errp, "Latency %" PRIu64 " between initiator=%d and "
+ "target=%d should not differ from previously entered "
+ "min or max values on more than %d", node->latency,
+ node->initiator, node->target, UINT16_MAX - 1);
+ return;
+ } else {
+ hmat_lb->base = temp_base;
+ hmat_lb->range_bitmap = max_entry;
+ }
+
+ /*
+ * Set lb_info_provided bit 0 as 1,
+ * latency information is provided
+ */
+ numa_info[node->target].lb_info_provided |= BIT(0);
+ }
+ lb_data.data = node->latency;
+ } else if (node->data_type >= HMATLB_DATA_TYPE_ACCESS_BANDWIDTH) {
+ /* Input bandwidth data */
+ if (!node->has_bandwidth) {
+ error_setg(errp, "Missing 'bandwidth' option");
+ return;
+ }
+ if (node->has_latency) {
+ error_setg(errp, "Invalid option 'latency' since "
+ "the data type is bandwidth");
+ return;
+ }
+ if (!QEMU_IS_ALIGNED(node->bandwidth, MiB)) {
+ error_setg(errp, "Bandwidth %" PRIu64 " between initiator=%d and "
+ "target=%d should be 1MB aligned", node->bandwidth,
+ node->initiator, node->target);
+ return;
+ }
+
+ /* Detect duplicate configuration */
+ for (i = 0; i < hmat_lb->list->len; i++) {
+ lb_temp = &g_array_index(hmat_lb->list, HMAT_LB_Data, i);
+
+ if (node->initiator == lb_temp->initiator &&
+ node->target == lb_temp->target) {
+ error_setg(errp, "Duplicate configuration of the bandwidth for "
+ "initiator=%d and target=%d", node->initiator,
+ node->target);
+ return;
+ }
+ }
+
+ hmat_lb->base = hmat_lb->base ? hmat_lb->base : 1;
+
+ if (node->bandwidth) {
+ /* Keep bitmap unchanged when bandwidth out of range */
+ bitmap_copy = hmat_lb->range_bitmap;
+ bitmap_copy |= node->bandwidth;
+ first_bit = ctz64(bitmap_copy);
+ temp_base = UINT64_C(1) << first_bit;
+ max_entry = node->bandwidth / temp_base;
+ last_bit = 64 - clz64(bitmap_copy);
+
+ /*
+ * For bandwidth, first_bit record the base unit of bandwidth bits,
+ * last_bit record the last bit of the max bandwidth. The max
+ * compressed bandwidth should be less than 0xFFFF (UINT16_MAX)
+ */
+ if ((last_bit - first_bit) > UINT16_BITS ||
+ max_entry >= UINT16_MAX) {
+ error_setg(errp, "Bandwidth %" PRIu64 " between initiator=%d "
+ "and target=%d should not differ from previously "
+ "entered values on more than %d", node->bandwidth,
+ node->initiator, node->target, UINT16_MAX - 1);
+ return;
+ } else {
+ hmat_lb->base = temp_base;
+ hmat_lb->range_bitmap = bitmap_copy;
+ }
+
+ /*
+ * Set lb_info_provided bit 1 as 1,
+ * bandwidth information is provided
+ */
+ numa_info[node->target].lb_info_provided |= BIT(1);
+ }
+ lb_data.data = node->bandwidth;
+ } else {
+ assert(0);
+ }
+
+ g_array_append_val(hmat_lb->list, lb_data);
+}
+
+void parse_numa_hmat_cache(MachineState *ms, NumaHmatCacheOptions *node,
+ Error **errp)
+{
+ int nb_numa_nodes = ms->numa_state->num_nodes;
+ NodeInfo *numa_info = ms->numa_state->nodes;
+ NumaHmatCacheOptions *hmat_cache = NULL;
+
+ if (node->node_id >= nb_numa_nodes) {
+ error_setg(errp, "Invalid node-id=%" PRIu32 ", it should be less "
+ "than %d", node->node_id, nb_numa_nodes);
+ return;
+ }
+
+ if (numa_info[node->node_id].lb_info_provided != (BIT(0) | BIT(1))) {
+ error_setg(errp, "The latency and bandwidth information of "
+ "node-id=%" PRIu32 " should be provided before memory side "
+ "cache attributes", node->node_id);
+ return;
+ }
+
+ if (node->level < 1 || node->level >= HMAT_LB_LEVELS) {
+ error_setg(errp, "Invalid level=%" PRIu8 ", it should be larger than 0 "
+ "and less than or equal to %d", node->level,
+ HMAT_LB_LEVELS - 1);
+ return;
+ }
+
+ assert(node->associativity < HMAT_CACHE_ASSOCIATIVITY__MAX);
+ assert(node->policy < HMAT_CACHE_WRITE_POLICY__MAX);
+ if (ms->numa_state->hmat_cache[node->node_id][node->level]) {
+ error_setg(errp, "Duplicate configuration of the side cache for "
+ "node-id=%" PRIu32 " and level=%" PRIu8,
+ node->node_id, node->level);
+ return;
+ }
+
+ if ((node->level > 1) &&
+ ms->numa_state->hmat_cache[node->node_id][node->level - 1] == NULL) {
+ error_setg(errp, "Cache level=%u shall be defined first",
+ node->level - 1);
+ return;
+ }
+
+ if ((node->level > 1) &&
+ (node->size <=
+ ms->numa_state->hmat_cache[node->node_id][node->level - 1]->size)) {
+ error_setg(errp, "Invalid size=%" PRIu64 ", the size of level=%" PRIu8
+ " should be larger than the size(%" PRIu64 ") of "
+ "level=%u", node->size, node->level,
+ ms->numa_state->hmat_cache[node->node_id]
+ [node->level - 1]->size,
+ node->level - 1);
+ return;
+ }
+
+ if ((node->level < HMAT_LB_LEVELS - 1) &&
+ ms->numa_state->hmat_cache[node->node_id][node->level + 1] &&
+ (node->size >=
+ ms->numa_state->hmat_cache[node->node_id][node->level + 1]->size)) {
+ error_setg(errp, "Invalid size=%" PRIu64 ", the size of level=%" PRIu8
+ " should be less than the size(%" PRIu64 ") of "
+ "level=%u", node->size, node->level,
+ ms->numa_state->hmat_cache[node->node_id]
+ [node->level + 1]->size,
+ node->level + 1);
+ return;
+ }
+
+ hmat_cache = g_malloc0(sizeof(*hmat_cache));
+ memcpy(hmat_cache, node, sizeof(*hmat_cache));
+ ms->numa_state->hmat_cache[node->node_id][node->level] = hmat_cache;
+}
+
+void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp)
+{
+ if (!ms->numa_state) {
error_setg(errp, "NUMA is not supported by this machine-type");
- goto end;
+ return;
}
switch (object->type) {
case NUMA_OPTIONS_TYPE_NODE:
- parse_numa_node(ms, &object->u.node, &err);
- if (err) {
- goto end;
- }
+ parse_numa_node(ms, &object->u.node, errp);
break;
case NUMA_OPTIONS_TYPE_DIST:
- parse_numa_distance(ms, &object->u.dist, &err);
- if (err) {
- goto end;
- }
+ parse_numa_distance(ms, &object->u.dist, errp);
break;
case NUMA_OPTIONS_TYPE_CPU:
if (!object->u.cpu.has_node_id) {
- error_setg(&err, "Missing mandatory node-id property");
- goto end;
+ error_setg(errp, "Missing mandatory node-id property");
+ return;
}
if (!ms->numa_state->nodes[object->u.cpu.node_id].present) {
- error_setg(&err, "Invalid node-id=%" PRId64 ", NUMA node must be "
- "defined with -numa node,nodeid=ID before it's used with "
- "-numa cpu,node-id=ID", object->u.cpu.node_id);
- goto end;
+ error_setg(errp, "Invalid node-id=%" PRId64 ", NUMA node must be "
+ "defined with -numa node,nodeid=ID before it's used with "
+ "-numa cpu,node-id=ID", object->u.cpu.node_id);
+ return;
+ }
+
+ machine_set_cpu_numa_node(ms,
+ qapi_NumaCpuOptions_base(&object->u.cpu),
+ errp);
+ break;
+ case NUMA_OPTIONS_TYPE_HMAT_LB:
+ if (!ms->numa_state->hmat_enabled) {
+ error_setg(errp, "ACPI Heterogeneous Memory Attribute Table "
+ "(HMAT) is disabled, enable it with -machine hmat=on "
+ "before using any of hmat specific options");
+ return;
+ }
+
+ parse_numa_hmat_lb(ms->numa_state, &object->u.hmat_lb, errp);
+ break;
+ case NUMA_OPTIONS_TYPE_HMAT_CACHE:
+ if (!ms->numa_state->hmat_enabled) {
+ error_setg(errp, "ACPI Heterogeneous Memory Attribute Table "
+ "(HMAT) is disabled, enable it with -machine hmat=on "
+ "before using any of hmat specific options");
+ return;
}
- machine_set_cpu_numa_node(ms, qapi_NumaCpuOptions_base(&object->u.cpu),
- &err);
+ parse_numa_hmat_cache(ms, &object->u.hmat_cache, errp);
break;
default:
abort();
}
-
-end:
- error_propagate(errp, err);
}
static int parse_numa(void *opaque, QemuOpts *opts, Error **errp)
Error *err = NULL;
Visitor *v = opts_visitor_new(opts);
- visit_type_NumaOptions(v, NULL, &object, &err);
+ visit_type_NumaOptions(v, NULL, &object, errp);
visit_free(v);
- if (err) {
- goto end;
+ if (!object) {
+ return -1;
}
/* Fix up legacy suffix-less format */
set_numa_options(ms, object, &err);
-end:
qapi_free_NumaOptions(object);
if (err) {
error_propagate(errp, err);
}
}
-void numa_legacy_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
- int nb_nodes, ram_addr_t size)
+static void numa_init_memdev_container(MachineState *ms, MemoryRegion *ram)
{
int i;
- uint64_t usedmem = 0;
-
- /* Align each node according to the alignment
- * requirements of the machine class
- */
+ uint64_t addr = 0;
- for (i = 0; i < nb_nodes - 1; i++) {
- nodes[i].node_mem = (size / nb_nodes) &
- ~((1 << mc->numa_mem_align_shift) - 1);
- usedmem += nodes[i].node_mem;
+ for (i = 0; i < ms->numa_state->num_nodes; i++) {
+ uint64_t size = ms->numa_state->nodes[i].node_mem;
+ HostMemoryBackend *backend = ms->numa_state->nodes[i].node_memdev;
+ if (!backend) {
+ continue;
+ }
+ MemoryRegion *seg = machine_consume_memdev(ms, backend);
+ memory_region_add_subregion(ram, addr, seg);
+ addr += size;
}
- nodes[i].node_mem = size - usedmem;
-}
-
-void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
- int nb_nodes, ram_addr_t size)
-{
- int i;
- uint64_t usedmem = 0, node_mem;
- uint64_t granularity = size / nb_nodes;
- uint64_t propagate = 0;
-
- for (i = 0; i < nb_nodes - 1; i++) {
- node_mem = (granularity + propagate) &
- ~((1 << mc->numa_mem_align_shift) - 1);
- propagate = granularity + propagate - node_mem;
- nodes[i].node_mem = node_mem;
- usedmem += node_mem;
- }
- nodes[i].node_mem = size - usedmem;
}
void numa_complete_configuration(MachineState *ms)
NodeInfo *numa_info = ms->numa_state->nodes;
/*
- * If memory hotplug is enabled (slots > 0) but without '-numa'
- * options explicitly on CLI, guestes will break.
+ * If memory hotplug is enabled (slot > 0) or memory devices are enabled
+ * (ms->maxram_size > ms->ram_size) but without '-numa' options explicitly on
+ * CLI, guests will break.
*
* Windows: won't enable memory hotplug without SRAT table at all
*
* assume there is just one node with whole RAM.
*/
if (ms->numa_state->num_nodes == 0 &&
- ((ms->ram_slots > 0 &&
- mc->auto_enable_numa_with_memhp) ||
- mc->auto_enable_numa)) {
+ ((ms->ram_slots && mc->auto_enable_numa_with_memhp) ||
+ (ms->maxram_size > ms->ram_size && mc->auto_enable_numa_with_memdev) ||
+ mc->auto_enable_numa)) {
NumaNodeOptions node = { };
parse_numa_node(ms, &node, &error_abort);
- numa_info[0].node_mem = ram_size;
+ numa_info[0].node_mem = ms->ram_size;
}
assert(max_numa_nodeid <= MAX_NODES);
if (ms->numa_state->num_nodes > 0) {
uint64_t numa_total;
- if (ms->numa_state->num_nodes > MAX_NODES) {
- ms->numa_state->num_nodes = MAX_NODES;
- }
-
- /* If no memory size is given for any node, assume the default case
- * and distribute the available memory equally across all nodes
- */
- for (i = 0; i < ms->numa_state->num_nodes; i++) {
- if (numa_info[i].node_mem != 0) {
- break;
- }
- }
- if (i == ms->numa_state->num_nodes) {
- assert(mc->numa_auto_assign_ram);
- mc->numa_auto_assign_ram(mc, numa_info,
- ms->numa_state->num_nodes, ram_size);
- if (!qtest_enabled()) {
- warn_report("Default splitting of RAM between nodes is deprecated,"
- " Use '-numa node,memdev' to explictly define RAM"
- " allocation per node");
- }
- }
-
numa_total = 0;
for (i = 0; i < ms->numa_state->num_nodes; i++) {
numa_total += numa_info[i].node_mem;
}
- if (numa_total != ram_size) {
+ if (numa_total != ms->ram_size) {
error_report("total memory for NUMA nodes (0x%" PRIx64 ")"
" should equal RAM size (0x" RAM_ADDR_FMT ")",
- numa_total, ram_size);
+ numa_total, ms->ram_size);
exit(1);
}
+ if (!numa_uses_legacy_mem() && mc->default_ram_id) {
+ if (ms->ram_memdev_id) {
+ error_report("'-machine memory-backend' and '-numa memdev'"
+ " properties are mutually exclusive");
+ exit(1);
+ }
+ ms->ram = g_new(MemoryRegion, 1);
+ memory_region_init(ms->ram, OBJECT(ms), mc->default_ram_id,
+ ms->ram_size);
+ numa_init_memdev_container(ms, ms->ram);
+ }
/* QEMU needs at least all unique node pair distances to build
* the whole NUMA distance table. QEMU treats the distance table
* as symmetric by default, i.e. distance A->B == distance B->A.
/* due to bug in libvirt, it doesn't pass node-id from props on
* device_add as expected, so we have to fix it up here */
if (slot->props.has_node_id) {
- object_property_set_int(OBJECT(dev), slot->props.node_id,
- "node-id", errp);
+ object_property_set_int(OBJECT(dev), "node-id",
+ slot->props.node_id, errp);
}
} else if (node_id != slot->props.node_id) {
error_setg(errp, "invalid node-id, must be %"PRId64,
}
}
-static void allocate_system_memory_nonnuma(MemoryRegion *mr, Object *owner,
- const char *name,
- uint64_t ram_size)
-{
- if (mem_path) {
-#ifdef __linux__
- Error *err = NULL;
- memory_region_init_ram_from_file(mr, owner, name, ram_size, 0, 0,
- mem_path, &err);
- if (err) {
- error_report_err(err);
- if (mem_prealloc) {
- exit(1);
- }
- warn_report("falling back to regular RAM allocation");
- error_printf("This is deprecated. Make sure that -mem-path "
- " specified path has sufficient resources to allocate"
- " -m specified RAM amount");
- /* Legacy behavior: if allocation failed, fall back to
- * regular RAM allocation.
- */
- mem_path = NULL;
- memory_region_init_ram_nomigrate(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_nomigrate(mr, owner, name, ram_size, &error_fatal);
- }
- vmstate_register_ram_global(mr);
-}
-
-void memory_region_allocate_system_memory(MemoryRegion *mr, Object *owner,
- const char *name,
- uint64_t ram_size)
-{
- uint64_t addr = 0;
- int i;
- MachineState *ms = MACHINE(qdev_get_machine());
-
- if (ms->numa_state == NULL ||
- ms->numa_state->num_nodes == 0 || !have_memdevs) {
- allocate_system_memory_nonnuma(mr, owner, name, ram_size);
- return;
- }
-
- memory_region_init(mr, owner, name, ram_size);
- for (i = 0; i < ms->numa_state->num_nodes; i++) {
- uint64_t size = ms->numa_state->nodes[i].node_mem;
- HostMemoryBackend *backend = ms->numa_state->nodes[i].node_memdev;
- if (!backend) {
- continue;
- }
- MemoryRegion *seg = host_memory_backend_get_memory(backend);
-
- if (memory_region_is_mapped(seg)) {
- char *path = object_get_canonical_path_component(OBJECT(backend));
- error_report("memory backend %s is used multiple times. Each "
- "-numa option must use a different memdev value.",
- path);
- g_free(path);
- exit(1);
- }
-
- host_memory_backend_set_mapped(backend, true);
- memory_region_add_subregion(mr, addr, seg);
- vmstate_register_ram_global(seg);
- addr += size;
- }
-}
-
static void numa_stat_memory_devices(NumaNodeMem node_mem[])
{
MemoryDeviceInfoList *info_list = qmp_memory_device_list();
MemoryDeviceInfoList *info;
PCDIMMDeviceInfo *pcdimm_info;
VirtioPMEMDeviceInfo *vpi;
+ VirtioMEMDeviceInfo *vmi;
for (info = info_list; info; info = info->next) {
MemoryDeviceInfo *value = info->value;
node_mem[0].node_mem += vpi->size;
node_mem[0].node_plugged_mem += vpi->size;
break;
+ case MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM:
+ vmi = value->u.virtio_mem.data;
+ node_mem[vmi->node].node_mem += vmi->size;
+ node_mem[vmi->node].node_plugged_mem += vmi->size;
+ break;
default:
g_assert_not_reached();
}
projects / qemu.git / blobdiff