acpi: provide _PXM method for CPU devices if QEMU is started numa enabled

Workaround for long standing issue where Linux kernel
assigns hotplugged CPU to 1st numa node as it discards
proximity for possible CPUs from SRAT after it's parsed.

_PXM method allows linux query proximity directly from
hotplugged CPU object, which allows Linux to assing CPU
to the correct numa node.

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 12 insertions, 0 deletions

diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c
index c13b65c..902f5c9 100644
--- a/hw/acpi/cpu.c
+++ b/hw/acpi/cpu.c
@@ -4,6 +4,7 @@
 #include "qapi/error.h"
 #include "qapi-event.h"
 #include "trace.h"
+#include "sysemu/numa.h"
 
 #define ACPI_CPU_HOTPLUG_REG_LEN 12
 #define ACPI_CPU_SELECTOR_OFFSET_WR 0
@@ -503,6 +504,7 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
 
         /* build Processor object for each processor */
         for (i = 0; i < arch_ids->len; i++) {
+            int j;
             Aml *dev;
             Aml *uid = aml_int(i);
             GArray *madt_buf = g_array_new(0, 1, 1);
@@ -546,6 +548,16 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
                           aml_arg(1), aml_arg(2))
             );
             aml_append(dev, method);
+
+            /* Linux guests discard SRAT info for non-present CPUs
+             * as a result _PXM is required for all CPUs which might
+             * be hot-plugged. For simplicity, add it for all CPUs.
+             */
+            j = numa_get_node_for_cpu(i);
+            if (j < nb_numa_nodes) {
+                aml_append(dev, aml_name_decl("_PXM", aml_int(j)));
+            }
+
             aml_append(cpus_dev, dev);
         }
     }