qemu: Implement NVDIMM

So, majority of the code is just ready as-is. Well, with one
slight change: differentiate between dimm and nvdimm in places
like device alias generation, generating the command line and so
on.

Speaking of the command line, we also need to append 'nvdimm=on'
to the '-machine' argument so that the nvdimm feature is
advertised in the ACPI tables properly.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>

src/qemu/qemu_alias.c

@@ -352,17 +352,23 @@ qemuAssignDeviceMemoryAlias(virDomainDefPtr def,
     size_t i;
     int maxidx = 0;
     int idx;
+    const char *prefix;
+
+    if (mem->model == VIR_DOMAIN_MEMORY_MODEL_DIMM)
+        prefix = "dimm";
+    else
+        prefix = "nvdimm";
 
     if (oldAlias) {
         for (i = 0; i < def->nmems; i++) {
-            if ((idx = qemuDomainDeviceAliasIndex(&def->mems[i]->info, "dimm")) >= maxidx)
+            if ((idx = qemuDomainDeviceAliasIndex(&def->mems[i]->info, prefix)) >= maxidx)
                 maxidx = idx + 1;
         }
     } else {
         maxidx = mem->info.addr.dimm.slot;
     }
 
-    if (virAsprintf(&mem->info.alias, "dimm%d", maxidx) < 0)
+    if (virAsprintf(&mem->info.alias, "%s%d", prefix, maxidx) < 0)
         return -1;
 
     return 0;

src/qemu/qemu_command.c

@@ -3217,7 +3217,8 @@ qemuBuildMemoryBackendStr(virJSONValuePtr *backendProps,
     const long system_page_size = virGetSystemPageSizeKB();
     virDomainMemoryAccess memAccess = VIR_DOMAIN_MEMORY_ACCESS_DEFAULT;
     size_t i;
-    char *mem_path = NULL;
+    char *memPath = NULL;
+    bool prealloc = false;
     virBitmapPtr nodemask = NULL;
     int ret = -1;
     virJSONValuePtr props = NULL;
@@ -3298,26 +3299,31 @@ qemuBuildMemoryBackendStr(virJSONValuePtr *backendProps,
     if (!(props = virJSONValueNewObject()))
         return -1;
 
-    if (pagesize || def->mem.source == VIR_DOMAIN_MEMORY_SOURCE_FILE) {
+    if (pagesize || mem->nvdimmPath ||
+        def->mem.source == VIR_DOMAIN_MEMORY_SOURCE_FILE) {
         *backendType = "memory-backend-file";
 
-        if (def->mem.source == VIR_DOMAIN_MEMORY_SOURCE_FILE) {
-            /* we can have both pagesize and mem source, then check mem source first */
-            if (virJSONValueObjectAdd(props,
-                                      "s:mem-path", cfg->memoryBackingDir,
-                                      NULL) < 0)
+        if (mem->nvdimmPath) {
+            if (VIR_STRDUP(memPath, mem->nvdimmPath) < 0)
+                goto cleanup;
+            prealloc = true;
+        } else if (def->mem.source == VIR_DOMAIN_MEMORY_SOURCE_FILE) {
+            /* We can have both pagesize and mem source,
+             * then check mem source first. */
+            if (VIR_STRDUP(memPath, cfg->memoryBackingDir) < 0)
                 goto cleanup;
         } else {
-            if (qemuGetDomainHupageMemPath(def, cfg, pagesize, &mem_path) < 0)
-                goto cleanup;
-
-            if (virJSONValueObjectAdd(props,
-                                      "b:prealloc", true,
-                                      "s:mem-path", mem_path,
-                                      NULL) < 0)
+            if (qemuGetDomainHupageMemPath(def, cfg, pagesize, &memPath) < 0)
                 goto cleanup;
+            prealloc = true;
         }
 
+        if (virJSONValueObjectAdd(props,
+                                  "B:prealloc", prealloc,
+                                  "s:mem-path", memPath,
+                                  NULL) < 0)
+            goto cleanup;
+
         switch (memAccess) {
         case VIR_DOMAIN_MEMORY_ACCESS_SHARED:
             if (virJSONValueObjectAdd(props, "b:share", true, NULL) < 0)
@@ -3373,6 +3379,7 @@ qemuBuildMemoryBackendStr(virJSONValuePtr *backendProps,
 
     /* If none of the following is requested... */
     if (!needHugepage && !mem->sourceNodes && !nodeSpecified &&
+        !mem->nvdimmPath &&
         memAccess == VIR_DOMAIN_MEMORY_ACCESS_DEFAULT &&
         def->mem.source != VIR_DOMAIN_MEMORY_SOURCE_FILE && !force) {
         /* report back that using the new backend is not necessary
@@ -3402,8 +3409,7 @@ qemuBuildMemoryBackendStr(virJSONValuePtr *backendProps,
 
  cleanup:
     virJSONValueFree(props);
-    VIR_FREE(mem_path);
-
+    VIR_FREE(memPath);
     return ret;
 }
 
@@ -3490,6 +3496,7 @@ char *
 qemuBuildMemoryDeviceStr(virDomainMemoryDefPtr mem)
 {
     virBuffer buf = VIR_BUFFER_INITIALIZER;
+    const char *device;
 
     if (!mem->info.alias) {
         virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
@@ -3498,8 +3505,15 @@ qemuBuildMemoryDeviceStr(virDomainMemoryDefPtr mem)
     }
 
     switch ((virDomainMemoryModel) mem->model) {
+    case VIR_DOMAIN_MEMORY_MODEL_NVDIMM:
     case VIR_DOMAIN_MEMORY_MODEL_DIMM:
-        virBufferAddLit(&buf, "pc-dimm,");
+
+        if (mem->model == VIR_DOMAIN_MEMORY_MODEL_DIMM)
+            device = "pc-dimm";
+        else
+            device = "nvdimm";
+
+        virBufferAsprintf(&buf, "%s,", device);
 
         if (mem->targetNode >= 0)
             virBufferAsprintf(&buf, "node=%d,", mem->targetNode);
@@ -3515,12 +3529,6 @@ qemuBuildMemoryDeviceStr(virDomainMemoryDefPtr mem)
 
         break;
 
-    case VIR_DOMAIN_MEMORY_MODEL_NVDIMM:
-        virReportError(VIR_ERR_NO_SUPPORT, "%s",
-                       _("nvdimm not supported yet"));
-        return NULL;
-        break;
-
     case VIR_DOMAIN_MEMORY_MODEL_NONE:
     case VIR_DOMAIN_MEMORY_MODEL_LAST:
         break;
@@ -7071,6 +7079,7 @@ qemuBuildMachineCommandLine(virCommandPtr cmd,
 {
     virBuffer buf = VIR_BUFFER_INITIALIZER;
     bool obsoleteAccel = false;
+    size_t i;
     int ret = -1;
 
     /* This should *never* be NULL, since we always provide
@@ -7107,6 +7116,15 @@ qemuBuildMachineCommandLine(virCommandPtr cmd,
                              "with this QEMU binary"));
             return -1;
         }
+
+        for (i = 0; i < def->nmems; i++) {
+            if (def->mems[i]->model == VIR_DOMAIN_MEMORY_MODEL_NVDIMM) {
+                virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
+                               _("nvdimm not is not available "
+                                 "with this QEMU binary"));
+                return -1;
+            }
+        }
     } else {
         virTristateSwitch vmport = def->features[VIR_DOMAIN_FEATURE_VMPORT];
         virTristateSwitch smm = def->features[VIR_DOMAIN_FEATURE_SMM];
@@ -7227,6 +7245,18 @@ qemuBuildMachineCommandLine(virCommandPtr cmd,
             }
         }
 
+        for (i = 0; i < def->nmems; i++) {
+            if (def->mems[i]->model == VIR_DOMAIN_MEMORY_MODEL_NVDIMM) {
+                if (!virQEMUCapsGet(qemuCaps, QEMU_CAPS_DEVICE_NVDIMM)) {
+                    virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
+                                   _("nvdimm isn't supported by this QEMU binary"));
+                    goto cleanup;
+                }
+                virBufferAddLit(&buf, ",nvdimm=on");
+                break;
+            }
+        }
+
         virCommandAddArgBuffer(cmd, &buf);
     }
 

src/qemu/qemu_domain.c

@@ -5935,6 +5935,7 @@ qemuDomainDefValidateMemoryHotplugDevice(const virDomainMemoryDef *mem,
 {
     switch ((virDomainMemoryModel) mem->model) {
     case VIR_DOMAIN_MEMORY_MODEL_DIMM:
+    case VIR_DOMAIN_MEMORY_MODEL_NVDIMM:
         if (mem->info.type != VIR_DOMAIN_DEVICE_ADDRESS_TYPE_DIMM &&
             mem->info.type != VIR_DOMAIN_DEVICE_ADDRESS_TYPE_NONE) {
             virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
@@ -5967,11 +5968,6 @@ qemuDomainDefValidateMemoryHotplugDevice(const virDomainMemoryDef *mem,
         }
         break;
 
-    case VIR_DOMAIN_MEMORY_MODEL_NVDIMM:
-        virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
-                       _("nvdimm hotplug not supported yet"));
-        return -1;
-
     case VIR_DOMAIN_MEMORY_MODEL_NONE:
     case VIR_DOMAIN_MEMORY_MODEL_LAST:
         return -1;
@@ -6002,6 +5998,8 @@ qemuDomainDefValidateMemoryHotplug(const virDomainDef *def,
     unsigned int nmems = def->nmems;
     unsigned long long hotplugSpace;
     unsigned long long hotplugMemory = 0;
+    bool needPCDimmCap = false;
+    bool needNvdimmCap = false;
     size_t i;
 
     hotplugSpace = def->mem.max_memory - virDomainDefGetMemoryInitial(def);
@@ -6025,12 +6023,6 @@ qemuDomainDefValidateMemoryHotplug(const virDomainDef *def,
         return 0;
     }
 
-    if (!virQEMUCapsGet(qemuCaps, QEMU_CAPS_DEVICE_PC_DIMM)) {
-        virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
-                       _("memory hotplug isn't supported by this QEMU binary"));
-        return -1;
-    }
-
     if (!ARCH_IS_PPC64(def->os.arch)) {
         /* due to guest support, qemu would silently enable NUMA with one node
          * once the memory hotplug backend is enabled. To avoid possible
@@ -6054,12 +6046,40 @@ qemuDomainDefValidateMemoryHotplug(const virDomainDef *def,
     for (i = 0; i < def->nmems; i++) {
         hotplugMemory += def->mems[i]->size;
 
+        switch ((virDomainMemoryModel) def->mems[i]->model) {
+        case VIR_DOMAIN_MEMORY_MODEL_DIMM:
+            needPCDimmCap = true;
+            break;
+
+        case VIR_DOMAIN_MEMORY_MODEL_NVDIMM:
+            needNvdimmCap = true;
+            break;
+
+        case VIR_DOMAIN_MEMORY_MODEL_NONE:
+        case VIR_DOMAIN_MEMORY_MODEL_LAST:
+            break;
+        }
+
         /* already existing devices don't need to be checked on hotplug */
         if (!mem &&
             qemuDomainDefValidateMemoryHotplugDevice(def->mems[i], def) < 0)
             return -1;
     }
 
+    if (needPCDimmCap &&
+        !virQEMUCapsGet(qemuCaps, QEMU_CAPS_DEVICE_PC_DIMM)) {
+        virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
+                       _("memory hotplug isn't supported by this QEMU binary"));
+        return -1;
+    }
+
+    if (needNvdimmCap &&
+        !virQEMUCapsGet(qemuCaps, QEMU_CAPS_DEVICE_NVDIMM)) {
+        virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
+                       _("nvdimm isn't supported by this QEMU binary"));
+        return -1;
+    }
+
     if (hotplugMemory > hotplugSpace) {
         virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
                        _("memory device total size exceeds hotplug space"));

tests/qemuxml2argvdata/qemuxml2argv-memory-hotplug-nvdimm.args

@@ -0,0 +1,26 @@
+LC_ALL=C \
+PATH=/bin \
+HOME=/home/test \
+USER=test \
+LOGNAME=test \
+QEMU_AUDIO_DRV=none \
+/usr/bin/qemu \
+-name QEMUGuest1 \
+-S \
+-machine pc,accel=tcg,nvdimm=on \
+-m size=1048576k,slots=16,maxmem=1099511627776k \
+-smp 2,sockets=2,cores=1,threads=1 \
+-numa node,nodeid=0,cpus=0-1,mem=1024 \
+-object memory-backend-file,id=memnvdimm0,prealloc=yes,mem-path=/tmp/nvdimm,\
+size=536870912 \
+-device nvdimm,node=0,memdev=memnvdimm0,id=nvdimm0,slot=0 \
+-uuid c7a5fdbd-edaf-9455-926a-d65c16db1809 \
+-nographic \
+-nodefaults \
+-monitor unix:/tmp/lib/domain--1-QEMUGuest1/monitor.sock,server,nowait \
+-no-acpi \
+-boot c \
+-usb \
+-drive file=/dev/HostVG/QEMUGuest1,format=raw,if=none,id=drive-ide0-0-0 \
+-device ide-drive,bus=ide.0,unit=0,drive=drive-ide0-0-0,id=ide0-0-0 \
+-device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x3

tests/qemuxml2argvtest.c

@@ -2326,7 +2326,7 @@ mymain(void)
 
     DO_TEST_FAILURE("memory-align-fail", NONE);
     DO_TEST_FAILURE("memory-hotplug-nonuma", QEMU_CAPS_DEVICE_PC_DIMM);
-    DO_TEST_FAILURE("memory-hotplug", NONE);
+    DO_TEST("memory-hotplug", NONE);
     DO_TEST("memory-hotplug", QEMU_CAPS_DEVICE_PC_DIMM, QEMU_CAPS_NUMA);
     DO_TEST("memory-hotplug-dimm", QEMU_CAPS_DEVICE_PC_DIMM, QEMU_CAPS_NUMA,
             QEMU_CAPS_OBJECT_MEMORY_RAM, QEMU_CAPS_OBJECT_MEMORY_FILE);
@@ -2334,6 +2334,8 @@ mymain(void)
             QEMU_CAPS_OBJECT_MEMORY_RAM, QEMU_CAPS_OBJECT_MEMORY_FILE);
     DO_TEST("memory-hotplug-ppc64-nonuma", QEMU_CAPS_KVM, QEMU_CAPS_DEVICE_PC_DIMM, QEMU_CAPS_NUMA,
             QEMU_CAPS_OBJECT_MEMORY_RAM, QEMU_CAPS_OBJECT_MEMORY_FILE);
+    DO_TEST("memory-hotplug-nvdimm", QEMU_CAPS_MACHINE_OPT, QEMU_CAPS_DEVICE_NVDIMM,
+            QEMU_CAPS_NUMA, QEMU_CAPS_OBJECT_MEMORY_RAM, QEMU_CAPS_OBJECT_MEMORY_FILE);
 
     DO_TEST("machine-aeskeywrap-on-caps",
             QEMU_CAPS_MACHINE_OPT, QEMU_CAPS_AES_KEY_WRAP,