numa: Enable numa for SGX EPC sections

The basic SGX did not enable numa for SGX EPC sections, which
result in all EPC sections located in numa node 0. This patch
enable SGX numa function in the guest and the EPC section can
work with RAM as one numa node.

The Guest kernel related log:
[    0.009981] ACPI: SRAT: Node 0 PXM 0 [mem 0x180000000-0x183ffffff]
[    0.009982] ACPI: SRAT: Node 1 PXM 1 [mem 0x184000000-0x185bfffff]
The SRAT table can normally show SGX EPC sections menory info in different
numa nodes.

The SGX EPC numa related command:
 ......
 -m 4G,maxmem=20G \
 -smp sockets=2,cores=2 \
 -cpu host,+sgx-provisionkey \
 -object memory-backend-ram,size=2G,host-nodes=0,policy=bind,id=node0 \
 -object memory-backend-epc,id=mem0,size=64M,prealloc=on,host-nodes=0,policy=bind \
 -numa node,nodeid=0,cpus=0-1,memdev=node0 \
 -object memory-backend-ram,size=2G,host-nodes=1,policy=bind,id=node1 \
 -object memory-backend-epc,id=mem1,size=28M,prealloc=on,host-nodes=1,policy=bind \
 -numa node,nodeid=1,cpus=2-3,memdev=node1 \
 -M sgx-epc.0.memdev=mem0,sgx-epc.0.node=0,sgx-epc.1.memdev=mem1,sgx-epc.1.node=1 \
 ......

Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20211101162009.62161-2-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

hw/core/numa.c

@@ -784,9 +784,8 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[])
                 break;
             case MEMORY_DEVICE_INFO_KIND_SGX_EPC:
                 se = value->u.sgx_epc.data;
-                /* TODO: once we support numa, assign to right node */
-                node_mem[0].node_mem += se->size;
-                node_mem[0].node_plugged_mem += se->size;
+                node_mem[se->node].node_mem += se->size;
+                node_mem[se->node].node_plugged_mem = 0;
                 break;
             default:
                 g_assert_not_reached();

hw/i386/acpi-build.c

@@ -2068,6 +2068,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
         nvdimm_build_srat(table_data);
     }
 
+    sgx_epc_build_srat(table_data);
+
     /*
      * TODO: this part is not in ACPI spec and current linux kernel boots fine
      * without these entries. But I recall there were issues the last time I

hw/i386/sgx-epc.c

@@ -21,6 +21,7 @@
 
 static Property sgx_epc_properties[] = {
     DEFINE_PROP_UINT64(SGX_EPC_ADDR_PROP, SGXEPCDevice, addr, 0),
+    DEFINE_PROP_UINT32(SGX_EPC_NUMA_NODE_PROP, SGXEPCDevice, node, 0),
     DEFINE_PROP_LINK(SGX_EPC_MEMDEV_PROP, SGXEPCDevice, hostmem,
                      TYPE_MEMORY_BACKEND_EPC, HostMemoryBackendEpc *),
     DEFINE_PROP_END_OF_LIST(),
@@ -139,6 +140,8 @@ static void sgx_epc_md_fill_device_info(const MemoryDeviceState *md,
     se->memaddr = epc->addr;
     se->size = object_property_get_uint(OBJECT(epc), SGX_EPC_SIZE_PROP,
                                         NULL);
+    se->node = object_property_get_uint(OBJECT(epc), SGX_EPC_NUMA_NODE_PROP,
+                                        NULL);
     se->memdev = object_get_canonical_path(OBJECT(epc->hostmem));
 
     info->u.sgx_epc.data = se;

hw/i386/sgx-stub.c

@@ -6,6 +6,10 @@
 #include "qapi/error.h"
 #include "qapi/qapi-commands-misc-target.h"
 
+void sgx_epc_build_srat(GArray *table_data)
+{
+}
+
 SGXInfo *qmp_query_sgx(Error **errp)
 {
     error_setg(errp, "SGX support is not compiled in");

hw/i386/sgx.c

@@ -23,6 +23,7 @@
 #include "sysemu/hw_accel.h"
 #include "sysemu/reset.h"
 #include <sys/ioctl.h>
+#include "hw/acpi/aml-build.h"
 
 #define SGX_MAX_EPC_SECTIONS            8
 #define SGX_CPUID_EPC_INVALID           0x0
@@ -36,6 +37,46 @@
 
 #define RETRY_NUM                       2
 
+static int sgx_epc_device_list(Object *obj, void *opaque)
+{
+    GSList **list = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_SGX_EPC)) {
+        *list = g_slist_append(*list, DEVICE(obj));
+    }
+
+    object_child_foreach(obj, sgx_epc_device_list, opaque);
+    return 0;
+}
+
+static GSList *sgx_epc_get_device_list(void)
+{
+    GSList *list = NULL;
+
+    object_child_foreach(qdev_get_machine(), sgx_epc_device_list, &list);
+    return list;
+}
+
+void sgx_epc_build_srat(GArray *table_data)
+{
+    GSList *device_list = sgx_epc_get_device_list();
+
+    for (; device_list; device_list = device_list->next) {
+        DeviceState *dev = device_list->data;
+        Object *obj = OBJECT(dev);
+        uint64_t addr, size;
+        int node;
+
+        node = object_property_get_uint(obj, SGX_EPC_NUMA_NODE_PROP,
+                                        &error_abort);
+        addr = object_property_get_uint(obj, SGX_EPC_ADDR_PROP, &error_abort);
+        size = object_property_get_uint(obj, SGX_EPC_SIZE_PROP, &error_abort);
+
+        build_srat_memory(table_data, addr, size, node, MEM_AFFINITY_ENABLED);
+    }
+    g_slist_free(device_list);
+}
+
 static uint64_t sgx_calc_section_metric(uint64_t low, uint64_t high)
 {
     return (low & MAKE_64BIT_MASK(12, 20)) +
@@ -226,6 +267,9 @@ void pc_machine_init_sgx_epc(PCMachineState *pcms)
         /* set the memdev link with memory backend */
         object_property_parse(obj, SGX_EPC_MEMDEV_PROP, list->value->memdev,
                               &error_fatal);
+        /* set the numa node property for sgx epc object */
+        object_property_set_uint(obj, SGX_EPC_NUMA_NODE_PROP, list->value->node,
+                             &error_fatal);
         object_property_set_bool(obj, "realized", true, &error_fatal);
         object_unref(obj);
     }

include/hw/i386/sgx-epc.h

@@ -25,6 +25,7 @@
 #define SGX_EPC_ADDR_PROP "addr"
 #define SGX_EPC_SIZE_PROP "size"
 #define SGX_EPC_MEMDEV_PROP "memdev"
+#define SGX_EPC_NUMA_NODE_PROP "node"
 
 /**
  * SGXEPCDevice:
@@ -38,6 +39,7 @@ typedef struct SGXEPCDevice {
 
     /* public */
     uint64_t addr;
+    uint32_t node;
     HostMemoryBackendEpc *hostmem;
 } SGXEPCDevice;
 
@@ -56,6 +58,7 @@ typedef struct SGXEPCState {
 } SGXEPCState;
 
 bool sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size);
+void sgx_epc_build_srat(GArray *table_data);
 
 static inline uint64_t sgx_epc_above_4g_end(SGXEPCState *sgx_epc)
 {

monitor/hmp-cmds.c

@@ -1810,6 +1810,7 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict)
                                se->id ? se->id : "");
                 monitor_printf(mon, "  memaddr: 0x%" PRIx64 "\n", se->memaddr);
                 monitor_printf(mon, "  size: %" PRIu64 "\n", se->size);
+                monitor_printf(mon, "  node: %" PRId64 "\n", se->node);
                 monitor_printf(mon, "  memdev: %s\n", se->memdev);
                 break;
             default:

qapi/machine.json

@@ -1207,12 +1207,15 @@
 #
 # @memdev: memory backend linked with device
 #
+# @node: the numa node
+#
 # Since: 6.2
 ##
 { 'struct': 'SgxEPCDeviceInfo',
   'data': { '*id': 'str',
             'memaddr': 'size',
             'size': 'size',
+            'node': 'int',
             'memdev': 'str'
           }
 }
@@ -1285,10 +1288,15 @@
 #
 # @memdev: memory backend linked with device
 #
+# @node: the numa node
+#
 # Since: 6.2
 ##
 { 'struct': 'SgxEPC',
-  'data': { 'memdev': 'str' } }
+  'data': { 'memdev': 'str',
+            'node': 'int'
+          }
+}
 
 ##
 # @SgxEPCProperties:

qemu-options.hx

@@ -127,11 +127,11 @@ SRST
 ERST
 
 DEF("M", HAS_ARG, QEMU_OPTION_M,
-    "                sgx-epc.0.memdev=memid\n",
+    "                sgx-epc.0.memdev=memid,sgx-epc.0.node=numaid\n",
     QEMU_ARCH_ALL)
 
 SRST
-``sgx-epc.0.memdev=@var{memid}``
+``sgx-epc.0.memdev=@var{memid},sgx-epc.0.node=@var{numaid}``
     Define an SGX EPC section.
 ERST