[PULL v2 03/58] hw/acpi/nvdimm: add a helper to augment SRAT generation

[Michael S. Tsirkin]

From: Vishal Verma <vishal.l.verma@intel.com>

NVDIMMs can belong to their own proximity domains, as described by the
NFIT. In such cases, the SRAT needs to have Memory Affinity structures
in the SRAT for these NVDIMMs, otherwise Linux doesn't populate node
data structures properly during NUMA initialization. See the following
for an example failure case.

https://lore.kernel.org/linux-nvdimm/20200416225438.15208-1-vishal.l.verma@intel.com/

Introduce a new helper, nvdimm_build_srat(), and call it for both the
i386 and arm versions of 'build_srat()' to augment the SRAT with
memory affinity information for NVDIMMs.

The relevant command line options to exercise this are below. Nodes 0-1
contain CPUs and regular memory, and nodes 2-3 are the NVDIMM address
space.

    -object memory-backend-ram,id=mem0,size=2048M
    -numa node,nodeid=0,memdev=mem0,
    -numa cpu,node-id=0,socket-id=0
    -object memory-backend-ram,id=mem1,size=2048M
    -numa node,nodeid=1,memdev=mem1,
    -numa cpu,node-id=1,socket-id=1
    -numa node,nodeid=2,
    -object 
memory-backend-file,id=nvmem0,share,mem-path=nvdimm-0,size=16384M,align=1G
    -device nvdimm,memdev=nvmem0,id=nv0,label-size=2M,node=2
    -numa node,nodeid=3,
    -object 
memory-backend-file,id=nvmem1,share,mem-path=nvdimm-1,size=16384M,align=1G
    -device nvdimm,memdev=nvmem1,id=nv1,label-size=2M,node=3

Cc: Jingqi Liu <jingqi.liu@intel.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Jingqi Liu <jingqi.liu@intel.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Message-Id: <20200606000911.9896-3-vishal.l.verma@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/hw/mem/nvdimm.h  |  1 +
 hw/acpi/nvdimm.c         | 23 +++++++++++++++++++++++
 hw/arm/virt-acpi-build.c |  4 ++++
 hw/i386/acpi-build.c     |  5 +++++
 4 files changed, 33 insertions(+)

diff --git a/include/hw/mem/nvdimm.h b/include/hw/mem/nvdimm.h
index a3c08955e8..b67a1aedf6 100644
--- a/include/hw/mem/nvdimm.h
+++ b/include/hw/mem/nvdimm.h
@@ -155,6 +155,7 @@ typedef struct NVDIMMState NVDIMMState;
 void nvdimm_init_acpi_state(NVDIMMState *state, MemoryRegion *io,
                             struct AcpiGenericAddress dsm_io,
                             FWCfgState *fw_cfg, Object *owner);
+void nvdimm_build_srat(GArray *table_data);
 void nvdimm_build_acpi(GArray *table_offsets, GArray *table_data,
                        BIOSLinker *linker, NVDIMMState *state,
                        uint32_t ram_slots);
diff --git a/hw/acpi/nvdimm.c b/hw/acpi/nvdimm.c
index 9316d12b70..8f7cc16add 100644
--- a/hw/acpi/nvdimm.c
+++ b/hw/acpi/nvdimm.c
@@ -28,6 +28,7 @@
 
 #include "qemu/osdep.h"
 #include "qemu/uuid.h"
+#include "qapi/error.h"
 #include "hw/acpi/acpi.h"
 #include "hw/acpi/aml-build.h"
 #include "hw/acpi/bios-linker-loader.h"
@@ -1334,6 +1335,28 @@ static void nvdimm_build_ssdt(GArray *table_offsets, 
GArray *table_data,
     free_aml_allocator();
 }
 
+void nvdimm_build_srat(GArray *table_data)
+{
+    GSList *device_list = nvdimm_get_device_list();
+
+    for (; device_list; device_list = device_list->next) {
+        AcpiSratMemoryAffinity *numamem = NULL;
+        DeviceState *dev = device_list->data;
+        Object *obj = OBJECT(dev);
+        uint64_t addr, size;
+        int node;
+
+        node = object_property_get_int(obj, PC_DIMM_NODE_PROP, &error_abort);
+        addr = object_property_get_uint(obj, PC_DIMM_ADDR_PROP, &error_abort);
+        size = object_property_get_uint(obj, PC_DIMM_SIZE_PROP, &error_abort);
+
+        numamem = acpi_data_push(table_data, sizeof *numamem);
+        build_srat_memory(numamem, addr, size, node,
+                          MEM_AFFINITY_ENABLED | MEM_AFFINITY_NON_VOLATILE);
+    }
+    g_slist_free(device_list);
+}
+
 void nvdimm_build_acpi(GArray *table_offsets, GArray *table_data,
                        BIOSLinker *linker, NVDIMMState *state,
                        uint32_t ram_slots)
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 1b0a584c7b..2cbccd5fe2 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -539,6 +539,10 @@ build_srat(GArray *table_data, BIOSLinker *linker, 
VirtMachineState *vms)
         }
     }
 
+    if (ms->nvdimms_state->is_enabled) {
+        nvdimm_build_srat(table_data);
+    }
+
     if (ms->device_memory) {
         numamem = acpi_data_push(table_data, sizeof *numamem);
         build_srat_memory(numamem, ms->device_memory->base,
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index 2e15f6848e..d996525e2c 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -2428,6 +2428,11 @@ build_srat(GArray *table_data, BIOSLinker *linker, 
MachineState *machine)
                               MEM_AFFINITY_ENABLED);
         }
     }
+
+    if (machine->nvdimms_state->is_enabled) {
+        nvdimm_build_srat(table_data);
+    }
+
     slots = (table_data->len - numa_start) / sizeof *numamem;
     for (; slots < pcms->numa_nodes + 2; slots++) {
         numamem = acpi_data_push(table_data, sizeof *numamem);
-- 
MST