[Qemu-devel] [RFC qom-next v5 7/8] piix4: implement function cpu_status_write() for vcpu ejection

[Chen Fan]

When OS ejected a vcpu (like: echo 1 > /sys/bus/acpi/devices/LNXCPUXX/eject),
it would call acpi EJ0 method, the firmware need to write the new cpumap, QEMU
would know which vcpu need to be ejected.

TODO: for now QEMU only supported that cpu was deleted sequentially from the 
last
one in OS, in the further OS should reject vcpu arbitrarily.

Signed-off-by: Chen Fan <address@hidden>
---
 cpus.c                            |  7 ++++++
 hw/acpi/piix4.c                   | 48 ++++++++++++++++++++++++++++++++++++++-
 hw/i386/acpi-dsdt-cpu-hotplug.dsl |  6 ++++-
 include/qom/cpu.h                 | 10 ++++++++
 4 files changed, 69 insertions(+), 2 deletions(-)

diff --git a/cpus.c b/cpus.c
index ca4c59f..5829d24 100644
--- a/cpus.c
+++ b/cpus.c
@@ -1117,6 +1117,13 @@ void resume_all_vcpus(void)
     }
 }
 
+void cpu_remove(CPUState *cpu)
+{
+    cpu->stop = true;
+    cpu->exit = true;
+    qemu_cpu_kick(cpu);
+}
+
 static void qemu_tcg_init_vcpu(CPUState *cpu)
 {
     /* share a single thread for all cpus with TCG */
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index d2cd4cd..6407f8d 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -62,6 +62,7 @@ struct pci_status {
 
 typedef struct CPUStatus {
     uint8_t sts[PIIX4_PROC_LEN];
+    uint8_t old_sts[PIIX4_PROC_LEN];
 } CPUStatus;
 
 typedef struct PIIX4PMState {
@@ -651,6 +652,23 @@ static const MemoryRegionOps piix4_pci_ops = {
     },
 };
 
+static void acpi_piix_eject_vcpu(PIIX4PMState *s, int64_t cpuid)
+{
+    CPUStatus *g = &s->gpe_cpu;
+    CPUState *cpu;
+
+    CPU_FOREACH(cpu) {
+        CPUClass *cc = CPU_GET_CLASS(cpu);
+        int64_t id = cc->get_arch_id(cpu);
+
+        if (cpuid == id) {
+            g->old_sts[cpuid / 8] &= ~(1 << (cpuid % 8));
+            cpu_remove(cpu);
+            break;
+        }
+    }
+}
+
 static uint64_t cpu_status_read(void *opaque, hwaddr addr, unsigned int size)
 {
     PIIX4PMState *s = opaque;
@@ -663,7 +681,27 @@ static uint64_t cpu_status_read(void *opaque, hwaddr addr, 
unsigned int size)
 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 */
+    PIIX4PMState *s = opaque;
+    CPUStatus *cpus = &s->gpe_cpu;
+    uint8_t val;
+    int i;
+    int64_t cpuid = -1;
+
+    val = cpus->old_sts[addr] ^ data;
+
+    if (val == 0) {
+        return;
+    }
+
+    for (i = 0; i < 8; i++) {
+        if (val & 1 << i) {
+            cpuid = 8 * addr + i;
+        }
+    }
+
+    if (cpuid != -1) {
+        acpi_piix_eject_vcpu(s, cpuid);
+    }
 }
 
 static const MemoryRegionOps cpu_hotplug_ops = {
@@ -683,13 +721,20 @@ static void piix4_cpu_hotplug_req(PIIX4PMState *s, 
CPUState *cpu,
     ACPIGPE *gpe = &s->ar.gpe;
     CPUClass *k = CPU_GET_CLASS(cpu);
     int64_t cpu_id;
+    int i;
 
     assert(s != NULL);
 
     *gpe->sts = *gpe->sts | PIIX4_CPU_HOTPLUG_STATUS;
     cpu_id = k->get_arch_id(CPU(cpu));
+
+    for (i = 0; i < PIIX4_PROC_LEN; i++) {
+        g->old_sts[i] = g->sts[i];
+    }
+
     if (action == PLUG) {
         g->sts[cpu_id / 8] |= (1 << (cpu_id % 8));
+        g->old_sts[cpu_id / 8] |= (1 << (cpu_id % 8));
     } else {
         g->sts[cpu_id / 8] &= ~(1 << (cpu_id % 8));
     }
@@ -728,6 +773,7 @@ static void piix4_acpi_system_hot_add_init(MemoryRegion 
*parent,
 
         g_assert((id / 8) < PIIX4_PROC_LEN);
         s->gpe_cpu.sts[id / 8] |= (1 << (id % 8));
+        s->gpe_cpu.old_sts[id / 8] |= (1 << (id % 8));
     }
     memory_region_init_io(&s->io_cpu, OBJECT(s), &cpu_hotplug_ops, s,
                           "acpi-cpu-hotplug", PIIX4_PROC_LEN);
diff --git a/hw/i386/acpi-dsdt-cpu-hotplug.dsl 
b/hw/i386/acpi-dsdt-cpu-hotplug.dsl
index c96ac42..8327b0d 100644
--- a/hw/i386/acpi-dsdt-cpu-hotplug.dsl
+++ b/hw/i386/acpi-dsdt-cpu-hotplug.dsl
@@ -49,7 +49,11 @@ Scope(\_SB) {
     }
     Method(CPEJ, 2, NotSerialized) {
         // _EJ0 method - eject callback
-        Sleep(200)
+        Store(Zero, Index(CPON, ToInteger(Arg0)))
+        Store(One, Local0)
+        ShiftLeft(Local0, Arg0, Local0)
+        Not(Local0, Local0)
+        And(PRS, Local0, PRS)
     }
 
     /* CPU hotplug notify method */
diff --git a/include/qom/cpu.h b/include/qom/cpu.h
index 0238532..4412fb0 100644
--- a/include/qom/cpu.h
+++ b/include/qom/cpu.h
@@ -146,6 +146,7 @@ struct kvm_run;
  * @halted: Nonzero if the CPU is in suspended state.
  * @stop: Indicates a pending stop request.
  * @stopped: Indicates the CPU has been artificially stopped.
+ * @exit: Indicates the CPU is in impending exit state.
  * @tcg_exit_req: Set to force TCG to stop executing linked TBs for this
  *           CPU and return to its top level loop.
  * @singlestep_enabled: Flags for single-stepping.
@@ -181,6 +182,7 @@ struct CPUState {
     bool created;
     bool stop;
     bool stopped;
+    bool exit;
     volatile sig_atomic_t exit_request;
     volatile sig_atomic_t tcg_exit_req;
     uint32_t interrupt_request;
@@ -487,6 +489,14 @@ void cpu_exit(CPUState *cpu);
 void cpu_resume(CPUState *cpu);
 
 /**
+ * qemu_remove_vcpu:
+ * @cpu: The vCPU to remove.
+ *
+ * Requests the CPU @cpu to be removed.
+ */
+void cpu_remove(CPUState *cpu);
+
+/**
  * qemu_init_vcpu:
  * @cpu: The vCPU to initialize.
  *
-- 
1.8.1.4