Merge remote-tracking branch 'ehabkost/tags/x86-and-machine-pull-request' into staging

x86 and machine queue, 2017-05-11

Highlights:
* New "-numa cpu" option
* NUMA distance configuration
* migration/i386 vmstatification

# gpg: Signature made Thu 11 May 2017 08:16:07 PM BST
# gpg:                using RSA key 0x2807936F984DC5A6
# gpg: Good signature from "Eduardo Habkost <ehabkost@redhat.com>"
# gpg: Note: This key has expired!
# Primary key fingerprint: 5A32 2FD5 ABC4 D3DB ACCF  D1AA 2807 936F 984D C5A6

* ehabkost/tags/x86-and-machine-pull-request: (29 commits)
  migration/i386: Remove support for pre-0.12 formats
  vmstatification: i386 FPReg
  migration/i386: Remove old non-softfloat 64bit FP support
  tests: check -numa node,cpu=props_list usecase
  numa: add '-numa cpu,...' option for property based node mapping
  numa: remove node_cpu bitmaps as they are no longer used
  numa: use possible_cpus for not mapped CPUs check
  machine: call machine init from wrapper
  numa: remove no longer need numa_post_machine_init()
  tests: numa: add case for QMP command query-cpus
  QMP: include CpuInstanceProperties into query_cpus output output
  virt-arm: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu()
  spapr: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu()
  pc: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu()
  numa: do default mapping based on possible_cpus instead of node_cpu bitmaps
  numa: mirror cpu to node mapping in MachineState::possible_cpus
  numa: add check that board supports cpu_index to node mapping
  virt-arm: add node-id property to CPU
  pc: add node-id property to CPU
  spapr: add node-id property to sPAPR core
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

4 files changed, 54 insertions, 19 deletions

diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index 1d8c645ed3..cc0418f327 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -2335,7 +2335,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
     srat->reserved1 = cpu_to_le32(1);
 
     for (i = 0; i < apic_ids->len; i++) {
-        int j = numa_get_node_for_cpu(i);
+        int node_id = apic_ids->cpus[i].props.has_node_id ?
+            apic_ids->cpus[i].props.node_id : 0;
         uint32_t apic_id = apic_ids->cpus[i].arch_id;
 
         if (apic_id < 255) {
@@ -2345,9 +2346,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
             core->type = ACPI_SRAT_PROCESSOR_APIC;
             core->length = sizeof(*core);
             core->local_apic_id = apic_id;
-            if (j < nb_numa_nodes) {
-                core->proximity_lo = j;
-            }
+            core->proximity_lo = node_id;
             memset(core->proximity_hi, 0, 3);
             core->local_sapic_eid = 0;
             core->flags = cpu_to_le32(1);
@@ -2358,9 +2357,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
             core->type = ACPI_SRAT_PROCESSOR_x2APIC;
             core->length = sizeof(*core);
             core->x2apic_id = cpu_to_le32(apic_id);
-            if (j < nb_numa_nodes) {
-                core->proximity_domain = cpu_to_le32(j);
-            }
+            core->proximity_domain = cpu_to_le32(node_id);
             core->flags = cpu_to_le32(1);
         }
     }
@@ -2707,6 +2704,10 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)
     if (pcms->numa_nodes) {
         acpi_add_table(table_offsets, tables_blob);
         build_srat(tables_blob, tables->linker, machine);
+        if (have_numa_distance) {
+            acpi_add_table(table_offsets, tables_blob);
+            build_slit(tables_blob, tables->linker);
+        }
     }
     if (acpi_get_mcfg(&mcfg)) {
         acpi_add_table(table_offsets, tables_blob);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index f3b372a18f..e36a375683 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -747,7 +747,9 @@ static FWCfgState *bochs_bios_init(AddressSpace *as, PCMachineState *pcms)
 {
     FWCfgState *fw_cfg;
     uint64_t *numa_fw_cfg;
-    int i, j;
+    int i;
+    const CPUArchIdList *cpus;
+    MachineClass *mc = MACHINE_GET_CLASS(pcms);
 
     fw_cfg = fw_cfg_init_io_dma(FW_CFG_IO_BASE, FW_CFG_IO_BASE + 4, as);
     fw_cfg_add_i16(fw_cfg, FW_CFG_NB_CPUS, pcms->boot_cpus);
@@ -782,12 +784,12 @@ static FWCfgState *bochs_bios_init(AddressSpace *as, PCMachineState *pcms)
      */
     numa_fw_cfg = g_new0(uint64_t, 1 + pcms->apic_id_limit + nb_numa_nodes);
     numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);
-    for (i = 0; i < max_cpus; i++) {
-        unsigned int apic_id = x86_cpu_apic_id_from_index(i);
+    cpus = mc->possible_cpu_arch_ids(MACHINE(pcms));
+    for (i = 0; i < cpus->len; i++) {
+        unsigned int apic_id = cpus->cpus[i].arch_id;
         assert(apic_id < pcms->apic_id_limit);
-        j = numa_get_node_for_cpu(i);
-        if (j < nb_numa_nodes) {
-            numa_fw_cfg[apic_id + 1] = cpu_to_le64(j);
+        if (cpus->cpus[i].props.has_node_id) {
+            numa_fw_cfg[apic_id + 1] = cpu_to_le64(cpus->cpus[i].props.node_id);
         }
     }
     for (i = 0; i < nb_numa_nodes; i++) {
@@ -1893,6 +1895,7 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev,
                             DeviceState *dev, Error **errp)
 {
     int idx;
+    int node_id;
     CPUState *cs;
     CPUArchId *cpu_slot;
     X86CPUTopoInfo topo;
@@ -1982,6 +1985,22 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev,
 
     cs = CPU(cpu);
     cs->cpu_index = idx;
+
+    node_id = cpu_slot->props.node_id;
+    if (!cpu_slot->props.has_node_id) {
+        /* by default CPUState::numa_node was 0 if it's not set via CLI
+         * keep it this way for now but in future we probably should
+         * refuse to start up with incomplete numa mapping */
+        node_id = 0;
+    }
+    if (cs->numa_node == CPU_UNSET_NUMA_NODE_ID) {
+        cs->numa_node = node_id;
+    } else if (cs->numa_node != node_id) {
+            error_setg(errp, "node-id %d must match numa node specified"
+                "with -numa option for cpu-index %d",
+                cs->numa_node, cs->cpu_index);
+            return;
+    }
 }
 
 static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev,
@@ -2243,12 +2262,14 @@ static void pc_machine_reset(void)
     }
 }
 
-static unsigned pc_cpu_index_to_socket_id(unsigned cpu_index)
+static CpuInstanceProperties
+pc_cpu_index_to_props(MachineState *ms, unsigned cpu_index)
 {
-    X86CPUTopoInfo topo;
-    x86_topo_ids_from_idx(smp_cores, smp_threads, cpu_index,
-                          &topo);
-    return topo.pkg_id;
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
+    const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms);
+
+    assert(cpu_index < possible_cpus->len);
+    return possible_cpus->cpus[cpu_index].props;
 }
 
 static const CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *ms)
@@ -2280,6 +2301,15 @@ static const CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *ms)
         ms->possible_cpus->cpus[i].props.core_id = topo.core_id;
         ms->possible_cpus->cpus[i].props.has_thread_id = true;
         ms->possible_cpus->cpus[i].props.thread_id = topo.smt_id;
+
+        /* default distribution of CPUs over NUMA nodes */
+        if (nb_numa_nodes) {
+            /* preset values but do not enable them i.e. 'has_node_id = false',
+             * numa init code will enable them later if manual mapping wasn't
+             * present on CLI */
+            ms->possible_cpus->cpus[i].props.node_id =
+                topo.pkg_id % nb_numa_nodes;
+        }
     }
     return ms->possible_cpus;
 }
@@ -2322,7 +2352,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
     pcmc->acpi_data_size = 0x20000 + 0x8000;
     pcmc->save_tsc_khz = true;
     mc->get_hotplug_handler = pc_get_hotpug_handler;
-    mc->cpu_index_to_socket_id = pc_cpu_index_to_socket_id;
+    mc->cpu_index_to_instance_props = pc_cpu_index_to_props;
     mc->possible_cpu_arch_ids = pc_possible_cpu_arch_ids;
     mc->has_hotpluggable_cpus = true;
     mc->default_boot_order = "cad";
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 9f102aa388..d468b963fb 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -54,6 +54,7 @@
 #endif
 #include "migration/migration.h"
 #include "kvm_i386.h"
+#include "sysemu/numa.h"
 
 #define MAX_IDE_BUS 2
 
@@ -442,6 +443,7 @@ static void pc_i440fx_2_9_machine_options(MachineClass *m)
     pc_i440fx_machine_options(m);
     m->alias = "pc";
     m->is_default = 1;
+    m->numa_auto_assign_ram = numa_legacy_auto_assign_ram;
 }
 
 DEFINE_I440FX_MACHINE(v2_9, "pc-i440fx-2.9", NULL,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index dd792a8547..66303a78cf 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -47,6 +47,7 @@
 #include "hw/usb.h"
 #include "qemu/error-report.h"
 #include "migration/migration.h"
+#include "sysemu/numa.h"
 
 /* ICH9 AHCI has 6 ports */
 #define MAX_SATA_PORTS     6
@@ -305,6 +306,7 @@ static void pc_q35_2_9_machine_options(MachineClass *m)
 {
     pc_q35_machine_options(m);
     m->alias = "q35";
+    m->numa_auto_assign_ram = numa_legacy_auto_assign_ram;
 }
 
 DEFINE_Q35_MACHINE(v2_9, "pc-q35-2.9", NULL,