pc: Add 'etc/boot-cpus' fw_cfg file for machine with more than 255 CPUs

Currently firmware uses 1 byte at 0x5F offset in RTC CMOS
to get number of CPUs present at boot. However 1 byte is
not enough to handle more than 255 CPUs.  So add a new
fw_cfg file that would allow QEMU to tell it.
For compat reasons add file only for machine types that
support more than 255 CPUs.

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>

2 files changed, 31 insertions, 15 deletions

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 83ad556657..f9f85bfc1a 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1085,17 +1085,6 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level)
     }
 }
 
-static int pc_present_cpus_count(PCMachineState *pcms)
-{
-    int i, boot_cpus = 0;
-    for (i = 0; i < pcms->possible_cpus->len; i++) {
-        if (pcms->possible_cpus->cpus[i].cpu) {
-            boot_cpus++;
-        }
-    }
-    return boot_cpus;
-}
-
 static X86CPU *pc_new_cpu(const char *typename, int64_t apic_id,
                           Error **errp)
 {
@@ -1232,6 +1221,19 @@ static void pc_build_feature_control_file(PCMachineState *pcms)
     fw_cfg_add_file(pcms->fw_cfg, "etc/msr_feature_control", val, sizeof(*val));
 }
 
+static void rtc_set_cpus_count(ISADevice *rtc, uint16_t cpus_count)
+{
+    if (cpus_count > 0xff) {
+        /* If the number of CPUs can't be represented in 8 bits, the
+         * BIOS must use "etc/boot-cpus". Set RTC field to 0 just
+         * to make old BIOSes fail more predictably.
+         */
+        rtc_set_memory(rtc, 0x5f, 0);
+    } else {
+        rtc_set_memory(rtc, 0x5f, cpus_count - 1);
+    }
+}
+
 static
 void pc_machine_done(Notifier *notifier, void *data)
 {
@@ -1240,7 +1242,7 @@ void pc_machine_done(Notifier *notifier, void *data)
     PCIBus *bus = pcms->bus;
 
     /* set the number of CPUs */
-    rtc_set_memory(pcms->rtc, 0x5f, pc_present_cpus_count(pcms) - 1);
+    rtc_set_cpus_count(pcms->rtc, le16_to_cpu(pcms->boot_cpus_le));
 
     if (bus) {
         int extra_hosts = 0;
@@ -1261,8 +1263,15 @@ void pc_machine_done(Notifier *notifier, void *data)
 
     acpi_setup();
     if (pcms->fw_cfg) {
+        MachineClass *mc = MACHINE_GET_CLASS(pcms);
+
         pc_build_smbios(pcms->fw_cfg);
         pc_build_feature_control_file(pcms);
+
+        if (mc->max_cpus > 255) {
+            fw_cfg_add_file(pcms->fw_cfg, "etc/boot-cpus", &pcms->boot_cpus_le,
+                            sizeof(pcms->boot_cpus_le));
+        }
     }
 }
 
@@ -1786,9 +1795,11 @@ static void pc_cpu_plug(HotplugHandler *hotplug_dev,
         }
     }
 
+    /* increment the number of CPUs */
+    pcms->boot_cpus_le = cpu_to_le16(le16_to_cpu(pcms->boot_cpus_le) + 1);
     if (dev->hotplugged) {
-        /* increment the number of CPUs */
-        rtc_set_memory(pcms->rtc, 0x5f, rtc_get_memory(pcms->rtc, 0x5f) + 1);
+        /* Update the number of CPUs in CMOS */
+        rtc_set_cpus_count(pcms->rtc, le16_to_cpu(pcms->boot_cpus_le));
     }
 
     found_cpu = pc_find_cpu_slot(pcms, CPU(dev), NULL);
@@ -1842,7 +1853,10 @@ static void pc_cpu_unplug_cb(HotplugHandler *hotplug_dev,
     found_cpu->cpu = NULL;
     object_unparent(OBJECT(dev));
 
-    rtc_set_memory(pcms->rtc, 0x5f, rtc_get_memory(pcms->rtc, 0x5f) - 1);
+    /* decrement the number of CPUs */
+    pcms->boot_cpus_le = cpu_to_le16(le16_to_cpu(pcms->boot_cpus_le) - 1);
+    /* Update the number of CPUs in CMOS */
+    rtc_set_cpus_count(pcms->rtc, le16_to_cpu(pcms->boot_cpus_le));
  out:
     error_propagate(errp, local_err);
 }
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index b16c448249..17fff80c8a 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -37,6 +37,7 @@
 /**
  * PCMachineState:
  * @acpi_dev: link to ACPI PM device that performs ACPI hotplug handling
+ * @boot_cpus_le: number of present VCPUs, referenced by 'etc/boot-cpus' fw_cfg
  */
 struct PCMachineState {
     /*< private >*/
@@ -69,6 +70,7 @@ struct PCMachineState {
     bool apic_xrupt_override;
     unsigned apic_id_limit;
     CPUArchIdList *possible_cpus;
+    uint16_t boot_cpus_le;
 
     /* NUMA information: */
     uint64_t numa_nodes;