[Qemu-devel] [PATCH 10/21] acpi_piix4: add infrastructure to send CPU hot-plug GPE to guest

[Igor Mammedov <imammedo@redhat.com>]

* 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>
---
v4:
  * added spec for QEMU-Seabios interface
  * added PIIX4_ prefix to PROC_ defines
v3:
  * s/get_firmware_id()/get_arch_id()/ due rebase
  * s/cpu_add_notifier/cpu_added_notifier/
v2:
  * use CPUClass.get_firmware_id() to make code target independent
  * bump up vmstate_acpi version
---
 docs/specs/acpi_cpu_hotplug.txt |   22 +++++++
 hw/acpi/piix4.c                 |  117 ++++++++++++++++++++++++++++++++++++++-
 2 files changed, 136 insertions(+), 3 deletions(-)
 create mode 100644 docs/specs/acpi_cpu_hotplug.txt

diff --git a/docs/specs/acpi_cpu_hotplug.txt b/docs/specs/acpi_cpu_hotplug.txt
new file mode 100644
index 0000000..5dec0c5
--- /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 88386d7..b845123 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;
 };
 
+struct cpu_status {
+    uint8_t sts[PIIX4_PROC_LEN];
+};
+
 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;
+
+    struct cpu_status 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 */
@@ -257,6 +269,18 @@ static int acpi_load_old(QEMUFile *f, void *opaque, int version_id)
     return ret;
 }
 
+#define VMSTATE_CPU_STATUS_ARRAY(_field, _state)                             \
+ {                                                                           \
+     .name       = (stringify(_field)),                                      \
+     .version_id = 0,                                                        \
+     .num        = PIIX4_PROC_LEN,                                           \
+     .info       = &vmstate_info_uint8,                                      \
+     .size       = sizeof(uint8_t),                                          \
+     .flags      = VMS_ARRAY,                                                \
+     .offset     = vmstate_offset_array(_state, _field, uint8_t,             \
+                                        PIIX4_PROC_LEN),                     \
+ }
+
 /* qemu-kvm 1.2 uses version 3 but advertised as 2
  * To support incoming qemu-kvm 1.2 migration, change version_id
  * and minimum_version_id to 2 below (which breaks migration from
@@ -265,7 +289,7 @@ static int acpi_load_old(QEMUFile *f, void *opaque, int version_id)
  */
 static const VMStateDescription vmstate_acpi = {
     .name = "piix4_pm",
-    .version_id = 3,
+    .version_id = 4,
     .minimum_version_id = 3,
     .minimum_version_id_old = 1,
     .load_state_old = acpi_load_old,
@@ -281,6 +305,7 @@ static const VMStateDescription vmstate_acpi = {
         VMSTATE_STRUCT(ar.gpe, PIIX4PMState, 2, vmstate_gpe, ACPIGPE),
         VMSTATE_STRUCT(pci0_status, PIIX4PMState, 2, vmstate_pci_status,
                        struct pci_status),
+        VMSTATE_CPU_STATUS_ARRAY(gpe_cpu.sts, PIIX4PMState),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -585,6 +610,85 @@ static const MemoryRegionOps piix4_pci_ops = {
     },
 };
 
+static uint64_t cpu_status_read(void *opaque, hwaddr addr, unsigned width)
+{
+    PIIX4PMState *s = opaque;
+    struct cpu_status *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)
+{
+    struct cpu_status *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 int piix4_init_cpu_status(Object *obj, void *opaque)
+{
+    struct cpu_status *g = (struct cpu_status *)opaque;
+    Object *cpu_obj = object_dynamic_cast(obj, TYPE_CPU);
+
+    if (cpu_obj) {
+        struct Error *error = NULL;
+        CPUClass *k = CPU_GET_CLASS(cpu_obj);
+        int64_t id = k->get_arch_id(CPU(cpu_obj));
+
+        if (error) {
+            fprintf(stderr, "failed to initilize CPU status for ACPI: %s\n",
+                    error_get_pretty(error));
+            error_free(error);
+            abort();
+        }
+        g_assert((id / 8) < PIIX4_PROC_LEN);
+        g->sts[id / 8] |= (1 << (id % 8));
+    }
+    return object_child_foreach(obj, piix4_init_cpu_status, opaque);
+}
+
 static int piix4_device_hotplug(DeviceState *qdev, PCIDevice *dev,
                                 PCIHotplugState state);
 
@@ -600,6 +704,13 @@ 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);
+
+    piix4_init_cpu_status(qdev_get_machine(), &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)
-- 
1.7.1