qemu: Add support for 'restrictive' mode in numatune

Signed-off-by: Luyao Zhong <luyao.zhong@intel.com>
Signed-off-by: Martin Kletzander <mkletzan@redhat.com>
Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>

src/qemu/qemu_command.c

@@ -3302,7 +3302,10 @@ qemuBuildMemoryBackendProps(virJSONValue **backendProps,
             return -1;
     }
 
-    if (nodemask) {
+    /* If mode is "restrictive", we should only use cgroups setting allowed memory
+     * nodes, and skip passing the host-nodes and policy parameters to QEMU command
+     * line which means we will use system default memory policy. */
+    if (nodemask && mode != VIR_DOMAIN_NUMATUNE_MEM_RESTRICTIVE) {
         if (!virNumaNodesetIsAvailable(nodemask))
             return -1;
         if (virJSONValueObjectAdd(props,

src/qemu/qemu_process.c

@@ -2692,6 +2692,7 @@ qemuProcessSetupPid(virDomainObj *vm,
     g_autoptr(virBitmap) hostcpumap = NULL;
     g_autofree char *mem_mask = NULL;
     int ret = -1;
+    size_t i;
 
     if ((period || quota) &&
         !virCgroupHasController(priv->cgroup, VIR_CGROUP_CONTROLLER_CPU)) {
@@ -2732,6 +2733,37 @@ qemuProcessSetupPid(virDomainObj *vm,
                                                 &mem_mask, -1) < 0)
             goto cleanup;
 
+        /* For restrictive numatune mode we need to set cpuset.mems for vCPU
+         * threads based on the node they are in as there is nothing else uses
+         * for such restriction (e.g. numa_set_membind). */
+        if (nameval == VIR_CGROUP_THREAD_VCPU) {
+            virDomainNuma *numatune = vm->def->numa;
+
+            /* Look for the guest NUMA node of this vCPU */
+            for (i = 0; i < virDomainNumaGetNodeCount(numatune); i++) {
+                g_autoptr(virBitmap) node_cpus = NULL;
+                node_cpus = virDomainNumaGetNodeCpumask(numatune, i);
+
+                if (!virBitmapIsBitSet(node_cpus, id))
+                    continue;
+
+                /* Update the mem_mask for this vCPU if the mode of its node is
+                 * 'restrictive'. */
+                if (virDomainNumatuneGetMode(numatune, i, &mem_mode) == 0 &&
+                    mem_mode == VIR_DOMAIN_NUMATUNE_MEM_RESTRICTIVE) {
+                    VIR_FREE(mem_mask);
+
+                    if (virDomainNumatuneMaybeFormatNodeset(numatune,
+                                                            priv->autoNodeset,
+                                                            &mem_mask, i) < 0) {
+                        goto cleanup;
+                    }
+                }
+
+                break;
+            }
+        }
+
         if (virCgroupNewThread(priv->cgroup, nameval, id, true, &cgroup) < 0)
             goto cleanup;
 

tests/qemuxml2argvdata/numatune-memnode-restrictive-mode.x86_64-latest.args

@@ -0,0 +1,38 @@
+LC_ALL=C \
+PATH=/bin \
+HOME=/tmp/lib/domain--1-QEMUGuest \
+USER=test \
+LOGNAME=test \
+XDG_DATA_HOME=/tmp/lib/domain--1-QEMUGuest/.local/share \
+XDG_CACHE_HOME=/tmp/lib/domain--1-QEMUGuest/.cache \
+XDG_CONFIG_HOME=/tmp/lib/domain--1-QEMUGuest/.config \
+/usr/bin/qemu-system-x86_64 \
+-name guest=QEMUGuest,debug-threads=on \
+-S \
+-object '{"qom-type":"secret","id":"masterKey0","format":"raw","file":"/tmp/lib/domain--1-QEMUGuest/master-key.aes"}' \
+-machine pc,accel=tcg,usb=off,dump-guest-core=off \
+-cpu qemu64 \
+-m 24105 \
+-overcommit mem-lock=off \
+-smp 32,sockets=32,cores=1,threads=1 \
+-object '{"qom-type":"memory-backend-ram","id":"ram-node0","size":20971520}' \
+-numa node,nodeid=0,cpus=0,memdev=ram-node0 \
+-object '{"qom-type":"memory-backend-ram","id":"ram-node1","size":676331520}' \
+-numa node,nodeid=1,cpus=1-27,cpus=29,memdev=ram-node1 \
+-object '{"qom-type":"memory-backend-ram","id":"ram-node2","size":24578621440}' \
+-numa node,nodeid=2,cpus=28,cpus=30-31,memdev=ram-node2 \
+-uuid 9f4b6512-e73a-4a25-93e8-5307802821ce \
+-display none \
+-no-user-config \
+-nodefaults \
+-chardev socket,id=charmonitor,fd=1729,server=on,wait=off \
+-mon chardev=charmonitor,id=monitor,mode=control \
+-rtc base=utc \
+-no-shutdown \
+-no-acpi \
+-boot strict=on \
+-device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2 \
+-audiodev id=audio1,driver=none \
+-device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x2 \
+-sandbox on,obsolete=deny,elevateprivileges=deny,spawn=deny,resourcecontrol=deny \
+-msg timestamp=on

tests/qemuxml2argvtest.c

@@ -2172,6 +2172,7 @@ mymain(void)
     DO_TEST_CAPS_VER("numatune-memnode", "5.2.0");
     DO_TEST_CAPS_LATEST("numatune-memnode");
     DO_TEST_PARSE_ERROR("numatune-memnode-invalid-mode", NONE);
+    DO_TEST_CAPS_LATEST("numatune-memnode-restrictive-mode");
 
     DO_TEST("numatune-memnode-no-memory",
             QEMU_CAPS_NUMA,