@@ -42,6 +42,7 @@
#include "qemu/option.h"
#include "qemu/config-file.h"
#include "qemu/cutils.h"
+#include "hw/acpi/hmat.h"
QemuOptsList qemu_numa_opts = {
.name = "numa",
@@ -186,6 +187,152 @@ void parse_numa_distance(MachineState *ms, NumaDistOptions *dist, Error **errp)
ms->numa_state->have_numa_distance = true;
}
+static uint64_t hmat_get_base(uint64_t lb_data, int unit)
+{
+ uint64_t base = 1;
+
+ while (lb_data >= UINT16_MAX && QEMU_IS_ALIGNED(lb_data, unit)) {
+ lb_data /= unit;
+ base *= unit;
+ }
+
+ if (lb_data < UINT16_MAX) {
+ return base;
+ } else {
+ return 0;
+ }
+}
+
+void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node,
+ Error **errp)
+{
+ int nb_numa_nodes = ms->numa_state->num_nodes;
+ NodeInfo *numa_info = ms->numa_state->nodes;
+ HMAT_LB_Info *hmat_lb = NULL;
+ uint64_t base_lat = 0, base_bw = 0, bw_mb;
+
+ if (node->data_type <= HMATLB_DATA_TYPE_WRITE_LATENCY) {
+ 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;
+ }
+ }
+
+ if (node->data_type >= HMATLB_DATA_TYPE_ACCESS_BANDWIDTH) {
+ 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 (node->initiator >= nb_numa_nodes) {
+ error_setg(errp, "Invalid initiator=%"
+ PRIu16 ", it should be less than %d.",
+ node->initiator, nb_numa_nodes);
+ return;
+ }
+ if (!numa_info[node->initiator].has_cpu) {
+ error_setg(errp, "Invalid initiator=%"
+ PRIu16 ", it isn't an initiator proximity domain.",
+ node->initiator);
+ return;
+ }
+
+ if (node->target >= nb_numa_nodes) {
+ error_setg(errp, "Invalid target=%"
+ PRIu16 ", it should be less than %d.",
+ node->target, nb_numa_nodes);
+ return;
+ }
+ if (!numa_info[node->target].present) {
+ error_setg(errp, "Invalid target=%"
+ PRIu16 ", it hasn't a valid NUMA node.",
+ node->target);
+ return;
+ }
+
+ if (node->has_latency) {
+ hmat_lb = ms->numa_state->hmat_lb[node->hierarchy][node->data_type];
+
+ if (!hmat_lb) {
+ hmat_lb = g_malloc0(sizeof(*hmat_lb));
+ ms->numa_state->hmat_lb[node->hierarchy][node->data_type] = hmat_lb;
+ } else if (hmat_lb->latency[node->initiator][node->target]) {
+ error_setg(errp, "Duplicate configuration of the latency for "
+ "initiator=%" PRIu16 " and target=%" PRIu16 ".",
+ node->initiator, node->target);
+ return;
+ }
+
+ base_lat = hmat_get_base(node->latency, 1000);
+ if (base_lat == 0) {
+ error_setg(errp, "Latency value %" PRIu64 " overflow, max value"
+ " is %" PRIu16, node->latency, UINT16_MAX - 1);
+ return;
+ }
+
+ /* Only the first time of setting the base unit is valid. */
+ if (hmat_lb->base_lat == 0) {
+ hmat_lb->base_lat = base_lat;
+ } else if (hmat_lb->base_lat != base_lat) {
+ error_setg(errp, "Invalid base latency unit %" PRIu64 ", all "
+ "latencies must be specified in the same units.", base_lat);
+ return;
+ }
+
+ hmat_lb->latency[node->initiator][node->target] =
+ node->latency / base_lat;
+ }
+
+ if (node->has_bandwidth) {
+ hmat_lb = ms->numa_state->hmat_lb[node->hierarchy][node->data_type];
+ bw_mb = node->bandwidth / 1024 / 1024;
+
+ if (!hmat_lb) {
+ hmat_lb = g_malloc0(sizeof(*hmat_lb));
+ ms->numa_state->hmat_lb[node->hierarchy][node->data_type] = hmat_lb;
+ } else if (hmat_lb->bandwidth[node->initiator][node->target]) {
+ error_setg(errp, "Duplicate configuration of the bandwidth for "
+ "initiator=%" PRIu16 " and target=%" PRIu16 ".",
+ node->initiator, node->target);
+ return;
+ }
+
+ base_bw = hmat_get_base(bw_mb, 1024);
+ if (base_bw == 0) {
+ error_setg(errp, "Bandwidth value %" PRIu64 " overflow, max value"
+ " is %" PRIu16, bw_mb, UINT16_MAX - 1);
+ return;
+ }
+
+ /* Only the first time of setting the base unit is valid. */
+ if (hmat_lb->base_bw == 0) {
+ hmat_lb->base_bw = base_bw;
+ } else if (hmat_lb->base_bw != base_bw) {
+ error_setg(errp, "Invalid base bandwidth unit %" PRIu64 ", all "
+ "bandwidths must be specified in the same units.", base_bw);
+ return;
+ }
+
+ hmat_lb->bandwidth[node->initiator][node->target] = bw_mb;
+ }
+
+ if (hmat_lb) {
+ hmat_lb->hierarchy = node->hierarchy;
+ hmat_lb->data_type = node->data_type;
+ }
+}
+
void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp)
{
Error *err = NULL;
@@ -224,6 +371,12 @@ void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp)
machine_set_cpu_numa_node(ms, qapi_NumaCpuOptions_base(&object->u.cpu),
&err);
break;
+ case NUMA_OPTIONS_TYPE_HMAT_LB:
+ parse_numa_hmat_lb(ms, &object->u.hmat_lb, &err);
+ if (err) {
+ goto end;
+ }
+ break;
default:
abort();
}
@@ -251,6 +404,17 @@ static int parse_numa(void *opaque, QemuOpts *opts, Error **errp)
qemu_strtosz_MiB(mem_str, NULL, &object->u.node.mem);
}
+ if (object->type == NUMA_OPTIONS_TYPE_HMAT_LB) {
+ if (object->u.hmat_lb.has_latency) {
+ const char *lat_str = qemu_opt_get(opts, "latency");
+ qemu_strtotime_ps(lat_str, NULL, &object->u.hmat_lb.latency);
+ }
+ if (object->u.hmat_lb.has_bandwidth) {
+ const char *bw_str = qemu_opt_get(opts, "bandwidth");
+ qemu_strtosz_MiB(bw_str, NULL, &object->u.hmat_lb.bandwidth);
+ }
+ }
+
set_numa_options(ms, object, &err);
end:
@@ -75,6 +75,8 @@ typedef struct NumaState NumaState;
void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp);
void parse_numa_opts(MachineState *ms);
+void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node,
+ Error **errp);
void numa_complete_configuration(MachineState *ms);
void query_numa_node_mem(NumaNodeMem node_mem[], MachineState *ms);
extern QemuOptsList qemu_numa_opts;
@@ -426,10 +426,12 @@
#
# @cpu: property based CPU(s) to node mapping (Since: 2.10)
#
+# @hmat-lb: memory latency and bandwidth information (Since: 4.2)
+#
# Since: 2.1
##
{ 'enum': 'NumaOptionsType',
- 'data': [ 'node', 'dist', 'cpu' ] }
+ 'data': [ 'node', 'dist', 'cpu', 'hmat-lb' ] }
##
# @NumaOptions:
@@ -444,7 +446,8 @@
'data': {
'node': 'NumaNodeOptions',
'dist': 'NumaDistOptions',
- 'cpu': 'NumaCpuOptions' }}
+ 'cpu': 'NumaCpuOptions',
+ 'hmat-lb': 'NumaHmatLBOptions' }}
##
# @NumaNodeOptions:
@@ -557,6 +560,94 @@
'base': 'CpuInstanceProperties',
'data' : {} }
+##
+# @HmatLBMemoryHierarchy:
+#
+# The memory hierarchy in the System Locality Latency
+# and Bandwidth Information Structure of HMAT (Heterogeneous
+# Memory Attribute Table)
+#
+# For more information of @HmatLBMemoryHierarchy see
+# the chapter 5.2.27.4: Table 5-142: Field "Flags" of ACPI 6.3 spec.
+#
+# @memory: the structure represents the memory performance
+#
+# @first-level: first level memory of memory side cached memory
+#
+# @second-level: second level memory of memory side cached memory
+#
+# @third-level: third level memory of memory side cached memory
+#
+# Since: 4.2
+##
+{ 'enum': 'HmatLBMemoryHierarchy',
+ 'data': [ 'memory', 'first-level', 'second-level', 'third-level' ] }
+
+##
+# @HmatLBDataType:
+#
+# Data type in the System Locality Latency
+# and Bandwidth Information Structure of HMAT (Heterogeneous
+# Memory Attribute Table)
+#
+# For more information of @HmatLBDataType see
+# the chapter 5.2.27.4: Table 5-142: Field "Data Type" of ACPI 6.3 spec.
+#
+# @access-latency: access latency (nanoseconds)
+#
+# @read-latency: read latency (nanoseconds)
+#
+# @write-latency: write latency (nanoseconds)
+#
+# @access-bandwidth: access bandwidth (MB/s)
+#
+# @read-bandwidth: read bandwidth (MB/s)
+#
+# @write-bandwidth: write bandwidth (MB/s)
+#
+# Since: 4.2
+##
+{ 'enum': 'HmatLBDataType',
+ 'data': [ 'access-latency', 'read-latency', 'write-latency',
+ 'access-bandwidth', 'read-bandwidth', 'write-bandwidth' ] }
+
+##
+# @NumaHmatLBOptions:
+#
+# Set the system locality latency and bandwidth information
+# between Initiator and Target proximity Domains.
+#
+# For more information of @NumaHmatLBOptions see
+# the chapter 5.2.27.4: Table 5-142 of ACPI 6.3 spec.
+#
+# @initiator: the Initiator Proximity Domain.
+#
+# @target: the Target Proximity Domain.
+#
+# @hierarchy: the Memory Hierarchy. Indicates the performance
+# of memory or side cache.
+#
+# @data-type: presents the type of data, access/read/write
+# latency or hit latency.
+#
+# @latency: the value of latency from @initiator to @target proximity domain,
+# the latency units are "ps(picosecond)", "ns(nanosecond)" or
+# "us(microsecond)".
+#
+# @bandwidth: the value of bandwidth between @initiator and @target proximity
+# domain, the bandwidth units are "MB(/s)","GB(/s)" or "TB(/s)".
+#
+# Since: 4.2
+##
+{ 'struct': 'NumaHmatLBOptions',
+ 'data': {
+ 'initiator': 'uint16',
+ 'target': 'uint16',
+ 'hierarchy': 'HmatLBMemoryHierarchy',
+ 'data-type': 'HmatLBDataType',
+ '*latency': 'time',
+ '*bandwidth': 'size' }}
+
##
# @HostMemPolicy:
#
@@ -168,16 +168,19 @@ DEF("numa", HAS_ARG, QEMU_OPTION_numa,
"-numa node[,mem=size][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n"
"-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n"
"-numa dist,src=source,dst=destination,val=distance\n"
- "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n",
+ "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n"
+ "-numa hmat-lb,initiator=node,target=node,hierarchy=memory|first-level|second-level|third-level,data-type=access-latency|read-latency|write-latency[,latency=lat][,bandwidth=bw]\n",
QEMU_ARCH_ALL)
STEXI
@item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}]
@itemx -numa node[,memdev=@var{id}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}]
@itemx -numa dist,src=@var{source},dst=@var{destination},val=@var{distance}
@itemx -numa cpu,node-id=@var{node}[,socket-id=@var{x}][,core-id=@var{y}][,thread-id=@var{z}]
+@itemx -numa hmat-lb,initiator=@var{node},target=@var{node},hierarchy=@var{str},data-type=@var{str}[,latency=@var{lat}][,bandwidth=@var{bw}]
@findex -numa
Define a NUMA node and assign RAM and VCPUs to it.
Set the NUMA distance from a source node to a destination node.
+Set the ACPI Heterogeneous Memory Attributes for the given nodes.
Legacy VCPU assignment uses @samp{cpus} option where
@var{firstcpu} and @var{lastcpu} are CPU indexes. Each
@@ -256,6 +259,50 @@ specified resources, it just assigns existing resources to NUMA
nodes. This means that one still has to use the @option{-m},
@option{-smp} options to allocate RAM and VCPUs respectively.
+Use @samp{hmat-lb} to set System Locality Latency and Bandwidth Information
+between initiator and target NUMA nodes in ACPI Heterogeneous Attribute Memory Table (HMAT).
+Initiator NUMA node can create memory requests, usually including one or more processors.
+Target NUMA node contains addressable memory.
+
+In @samp{hmat-lb} option, @var{node} are NUMA node IDs. @var{str} of 'hierarchy'
+is the memory hierarchy of the target NUMA node: if @var{str} is 'memory', the structure
+represents the memory performance; if @var{str} is 'first-level|second-level|third-level',
+this structure represents aggregated performance of memory side caches for each domain.
+@var{str} of 'data-type' is type of data represented by this structure instance:
+if 'hierarchy' is 'memory', 'data-type' is 'access|read|write' latency(nanoseconds)
+or 'access|read|write' bandwidth(MB/s) of the target memory; if 'hierarchy' is
+'first-level|second-level|third-level', 'data-type' is 'access|read|write' hit latency
+or 'access|read|write' hit bandwidth of the target memory side cache.
+
+@var{lat} of 'latency' is latency value, the possible value and units are
+NUM[ps|ns|us] (picosecond|nanosecond|microsecond), the recommended unit is 'ns'. @var{bw}
+is bandwidth value, the possible value and units are NUM[M|G|T], mean that
+the bandwidth value are NUM MB/s, GB/s or TB/s. Note that max NUM is 65534,
+if NUM is 0, means the corresponding latency or bandwidth information is not provided.
+And if input numbers without any unit, the latency unit will be 'ps' and the bandwidth
+will be MB/s.
+
+For example, the following option assigns NUMA node 0 and 1. Node 0 has 2 cpus and
+a ram, node 1 has only a ram. The processors in node 0 access memory in node
+0 with access-latency 5 nanoseconds, access-bandwidth is 200 MB/s;
+The processors in NUMA node 0 access memory in NUMA node 1 with access-latency 10
+nanoseconds, access-bandwidth is 100 MB/s.
+@example
+-machine hmat=on \
+-m 2G \
+-object memory-backend-ram,size=1G,id=m0 \
+-object memory-backend-ram,size=1G,id=m1 \
+-smp 2 \
+-numa node,nodeid=0,memdev=m0 \
+-numa node,nodeid=1,memdev=m1,initiator=0 \
+-numa cpu,node-id=0,socket-id=0 \
+-numa cpu,node-id=0,socket-id=1 \
+-numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-latency,latency=5ns \
+-numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-bandwidth,bandwidth=200M \
+-numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-latency,latency=10ns \
+-numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-bandwidth,bandwidth=100M
+@end example
+
ETEXI
DEF("add-fd", HAS_ARG, QEMU_OPTION_add_fd,