acpi_piix4: Add infrastructure to send CPU hot-plug GPE to guest

* introduce processor status bitmask visible to guest at 0xaf00 addr,
  where ACPI asl code expects it
* set bit corresponding to APIC ID in processor status bitmask on
  receiving CPU hot-plug notification
* trigger CPU hot-plug SCI, to notify guest about CPU hot-plug event

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Andreas Färber <afaerber@suse.de>

2 files changed, 110 insertions, 2 deletions

diff --git a/docs/specs/acpi_cpu_hotplug.txt b/docs/specs/acpi_cpu_hotplug.txt
new file mode 100644
index 0000000000..5dec0c5010
--- /dev/null
+++ b/docs/specs/acpi_cpu_hotplug.txt
@@ -0,0 +1,22 @@
+QEMU<->ACPI BIOS CPU hotplug interface
+--------------------------------------
+
+QEMU supports CPU hotplug via ACPI. This document
+describes the interface between QEMU and the ACPI BIOS.
+
+ACPI GPE block (IO ports 0xafe0-0xafe3, byte access):
+-----------------------------------------
+
+Generic ACPI GPE block. Bit 2 (GPE.2) used to notify CPU
+hot-add/remove event to ACPI BIOS, via SCI interrupt.
+
+CPU present bitmap (IO port 0xaf00-0xae1f, 1-byte access):
+---------------------------------------------------------------
+One bit per CPU. Bit position reflects corresponding CPU APIC ID.
+Read-only.
+
+CPU hot-add/remove notification:
+-----------------------------------------------------
+QEMU sets/clears corresponding CPU bit on hot-add/remove event.
+CPU present map read by ACPI BIOS GPE.2 handler to notify OS of CPU
+hot-(un)plug events.
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index 88386d7ea7..c4af1ccbb0 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -48,19 +48,28 @@
 #define PCI_EJ_BASE 0xae08
 #define PCI_RMV_BASE 0xae0c
 
+#define PIIX4_PROC_BASE 0xaf00
+#define PIIX4_PROC_LEN 32
+
 #define PIIX4_PCI_HOTPLUG_STATUS 2
+#define PIIX4_CPU_HOTPLUG_STATUS 4
 
 struct pci_status {
     uint32_t up; /* deprecated, maintained for migration compatibility */
     uint32_t down;
 };
 
+typedef struct CPUStatus {
+    uint8_t sts[PIIX4_PROC_LEN];
+} CPUStatus;
+
 typedef struct PIIX4PMState {
     PCIDevice dev;
 
     MemoryRegion io;
     MemoryRegion io_gpe;
     MemoryRegion io_pci;
+    MemoryRegion io_cpu;
     ACPIREGS ar;
 
     APMState apm;
@@ -82,6 +91,9 @@ typedef struct PIIX4PMState {
     uint8_t disable_s3;
     uint8_t disable_s4;
     uint8_t s4_val;
+
+    CPUStatus gpe_cpu;
+    Notifier cpu_added_notifier;
 } PIIX4PMState;
 
 static void piix4_acpi_system_hot_add_init(MemoryRegion *parent,
@@ -100,8 +112,8 @@ static void pm_update_sci(PIIX4PMState *s)
                    ACPI_BITMASK_POWER_BUTTON_ENABLE |
                    ACPI_BITMASK_GLOBAL_LOCK_ENABLE |
                    ACPI_BITMASK_TIMER_ENABLE)) != 0) ||
-        (((s->ar.gpe.sts[0] & s->ar.gpe.en[0])
-          & PIIX4_PCI_HOTPLUG_STATUS) != 0);
+        (((s->ar.gpe.sts[0] & s->ar.gpe.en[0]) &
+          (PIIX4_PCI_HOTPLUG_STATUS | PIIX4_CPU_HOTPLUG_STATUS)) != 0);
 
     qemu_set_irq(s->irq, sci_level);
     /* schedule a timer interruption if needed */
@@ -585,6 +597,73 @@ static const MemoryRegionOps piix4_pci_ops = {
     },
 };
 
+static uint64_t cpu_status_read(void *opaque, hwaddr addr, unsigned int size)
+{
+    PIIX4PMState *s = opaque;
+    CPUStatus *cpus = &s->gpe_cpu;
+    uint64_t val = cpus->sts[addr];
+
+    return val;
+}
+
+static void cpu_status_write(void *opaque, hwaddr addr, uint64_t data,
+                             unsigned int size)
+{
+    /* TODO: implement VCPU removal on guest signal that CPU can be removed */
+}
+
+static const MemoryRegionOps cpu_hotplug_ops = {
+    .read = cpu_status_read,
+    .write = cpu_status_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        .min_access_size = 1,
+        .max_access_size = 1,
+    },
+};
+
+typedef enum {
+    PLUG,
+    UNPLUG,
+} HotplugEventType;
+
+static void piix4_cpu_hotplug_req(PIIX4PMState *s, CPUState *cpu,
+                                  HotplugEventType action)
+{
+    CPUStatus *g = &s->gpe_cpu;
+    ACPIGPE *gpe = &s->ar.gpe;
+    CPUClass *k = CPU_GET_CLASS(cpu);
+    int64_t cpu_id;
+
+    assert(s != NULL);
+
+    *gpe->sts = *gpe->sts | PIIX4_CPU_HOTPLUG_STATUS;
+    cpu_id = k->get_arch_id(CPU(cpu));
+    if (action == PLUG) {
+        g->sts[cpu_id / 8] |= (1 << (cpu_id % 8));
+    } else {
+        g->sts[cpu_id / 8] &= ~(1 << (cpu_id % 8));
+    }
+    pm_update_sci(s);
+}
+
+static void piix4_cpu_added_req(Notifier *n, void *opaque)
+{
+    PIIX4PMState *s = container_of(n, PIIX4PMState, cpu_added_notifier);
+
+    piix4_cpu_hotplug_req(s, CPU(opaque), PLUG);
+}
+
+static void piix4_init_cpu_status(CPUState *cpu, void *data)
+{
+    CPUStatus *g = (CPUStatus *)data;
+    CPUClass *k = CPU_GET_CLASS(cpu);
+    int64_t id = k->get_arch_id(cpu);
+
+    g_assert((id / 8) < PIIX4_PROC_LEN);
+    g->sts[id / 8] |= (1 << (id % 8));
+}
+
 static int piix4_device_hotplug(DeviceState *qdev, PCIDevice *dev,
                                 PCIHotplugState state);
 
@@ -600,6 +679,13 @@ static void piix4_acpi_system_hot_add_init(MemoryRegion *parent,
     memory_region_add_subregion(parent, PCI_HOTPLUG_ADDR,
                                 &s->io_pci);
     pci_bus_hotplug(bus, piix4_device_hotplug, &s->dev.qdev);
+
+    qemu_for_each_cpu(piix4_init_cpu_status, &s->gpe_cpu);
+    memory_region_init_io(&s->io_cpu, &cpu_hotplug_ops, s, "apci-cpu-hotplug",
+                          PIIX4_PROC_LEN);
+    memory_region_add_subregion(parent, PIIX4_PROC_BASE, &s->io_cpu);
+    s->cpu_added_notifier.notify = piix4_cpu_added_req;
+    qemu_register_cpu_added_notifier(&s->cpu_added_notifier);
 }
 
 static void enable_device(PIIX4PMState *s, int slot)