[Qemu-devel] [RFC PATCH v1 10/13] cpus, spapr: reclaim allocated vCPU objects

[Bharata B Rao <bharata@linux.vnet.ibm.com>]

From: Gu Zheng <guz.fnst@cn.fujitsu.com>

Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
               (added spapr bits)
---
 cpus.c               | 44 ++++++++++++++++++++++++++++++++++++++++
 hw/ppc/spapr.c       | 14 ++++++++++++-
 include/qom/cpu.h    | 11 ++++++++++
 include/sysemu/kvm.h |  1 +
 kvm-all.c            | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 125 insertions(+), 2 deletions(-)

diff --git a/cpus.c b/cpus.c
index 1b5168a..98b7199 100644
--- a/cpus.c
+++ b/cpus.c
@@ -871,6 +871,24 @@ void async_run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data)
     qemu_cpu_kick(cpu);
 }
 
+static void qemu_kvm_destroy_vcpu(CPUState *cpu)
+{
+    CPU_REMOVE(cpu);
+
+    if (kvm_destroy_vcpu(cpu) < 0) {
+        fprintf(stderr, "kvm_destroy_vcpu failed.\n");
+        exit(1);
+    }
+
+    object_unparent(OBJECT(cpu));
+}
+
+static void qemu_tcg_destroy_vcpu(CPUState *cpu)
+{
+    CPU_REMOVE(cpu);
+    object_unparent(OBJECT(cpu));
+}
+
 static void flush_queued_work(CPUState *cpu)
 {
     struct qemu_work_item *wi;
@@ -964,6 +982,11 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
             }
         }
         qemu_kvm_wait_io_event(cpu);
+        if (cpu->exit && !cpu_can_run(cpu)) {
+            qemu_kvm_destroy_vcpu(cpu);
+            qemu_mutex_unlock(&qemu_global_mutex);
+            return NULL;
+        }
     }
 
     return NULL;
@@ -1018,6 +1041,7 @@ static void tcg_exec_all(void);
 static void *qemu_tcg_cpu_thread_fn(void *arg)
 {
     CPUState *cpu = arg;
+    CPUState *remove_cpu = NULL;
 
     qemu_tcg_init_cpu_signals();
     qemu_thread_get_self(cpu->thread);
@@ -1052,6 +1076,16 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
             }
         }
         qemu_tcg_wait_io_event();
+        CPU_FOREACH(cpu) {
+            if (cpu->exit && !cpu_can_run(cpu)) {
+                remove_cpu = cpu;
+                break;
+            }
+        }
+        if (remove_cpu) {
+            qemu_tcg_destroy_vcpu(remove_cpu);
+            remove_cpu = NULL;
+        }
     }
 
     return NULL;
@@ -1208,6 +1242,13 @@ void resume_all_vcpus(void)
     }
 }
 
+void cpu_remove(CPUState *cpu)
+{
+    cpu->stop = true;
+    cpu->exit = true;
+    qemu_cpu_kick(cpu);
+}
+
 /* For temporary buffers for forming a name */
 #define VCPU_THREAD_NAME_SIZE 16
 
@@ -1402,6 +1443,9 @@ static void tcg_exec_all(void)
                 break;
             }
         } else if (cpu->stop || cpu->stopped) {
+            if (cpu->exit) {
+                next_cpu = CPU_NEXT(cpu);
+            }
             break;
         }
     }
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index ec793b1..44405b2 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1910,7 +1910,19 @@ static void spapr_cpu_hotplug_add(DeviceState *dev, CPUState *cs)
 
 static void spapr_cpu_release(DeviceState *dev, void *opaque)
 {
-    /* Release vCPU */
+    CPUState *cs;
+    int i;
+    int id = ppc_get_vcpu_dt_id(POWERPC_CPU(CPU(dev)));
+
+    for (i = id; i < id + smp_threads; i++) {
+        CPU_FOREACH(cs) {
+            PowerPCCPU *cpu = POWERPC_CPU(cs);
+
+            if (i == ppc_get_vcpu_dt_id(cpu)) {
+                cpu_remove(cs);
+            }
+        }
+    }
 }
 
 static void spapr_cpu_hotplug_remove(DeviceState *dev, CPUState *cs)
diff --git a/include/qom/cpu.h b/include/qom/cpu.h
index 2098f1c..30fd0cd 100644
--- a/include/qom/cpu.h
+++ b/include/qom/cpu.h
@@ -206,6 +206,7 @@ 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 has exited due to an unplug operation.
  * @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.
@@ -249,6 +250,7 @@ struct CPUState {
     bool created;
     bool stop;
     bool stopped;
+    bool exit;
     volatile sig_atomic_t exit_request;
     uint32_t interrupt_request;
     int singlestep_enabled;
@@ -305,6 +307,7 @@ struct CPUState {
 QTAILQ_HEAD(CPUTailQ, CPUState);
 extern struct CPUTailQ cpus;
 #define CPU_NEXT(cpu) QTAILQ_NEXT(cpu, node)
+#define CPU_REMOVE(cpu) QTAILQ_REMOVE(&cpus, cpu, node)
 #define CPU_FOREACH(cpu) QTAILQ_FOREACH(cpu, &cpus, node)
 #define CPU_FOREACH_SAFE(cpu, next_cpu) \
     QTAILQ_FOREACH_SAFE(cpu, &cpus, node, next_cpu)
@@ -610,6 +613,14 @@ void cpu_exit(CPUState *cpu);
 void cpu_resume(CPUState *cpu);
 
 /**
+ * cpu_remove:
+ * @cpu: The CPU to remove.
+ *
+ * Requests the CPU to be removed.
+ */
+void cpu_remove(CPUState *cpu);
+
+/**
  * qemu_init_vcpu:
  * @cpu: The vCPU to initialize.
  *
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index 104cf35..da064c1 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -186,6 +186,7 @@ int kvm_has_gsi_routing(void);
 int kvm_has_intx_set_mask(void);
 
 int kvm_init_vcpu(CPUState *cpu);
+int kvm_destroy_vcpu(CPUState *cpu);
 int kvm_cpu_exec(CPUState *cpu);
 
 #ifdef NEED_CPU_H
diff --git a/kvm-all.c b/kvm-all.c
index 18cc6b4..6f543ce 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -71,6 +71,12 @@ typedef struct KVMSlot
 
 typedef struct kvm_dirty_log KVMDirtyLog;
 
+struct KVMParkedVcpu {
+    unsigned long vcpu_id;
+    int kvm_fd;
+    QLIST_ENTRY(KVMParkedVcpu) node;
+};
+
 struct KVMState
 {
     AccelState parent_obj;
@@ -107,6 +113,7 @@ struct KVMState
     QTAILQ_HEAD(msi_hashtab, KVMMSIRoute) msi_hashtab[KVM_MSI_HASHTAB_SIZE];
     bool direct_msi;
 #endif
+    QLIST_HEAD(, KVMParkedVcpu) kvm_parked_vcpus;
 };
 
 #define TYPE_KVM_ACCEL ACCEL_CLASS_NAME("kvm")
@@ -247,6 +254,53 @@ static int kvm_set_user_memory_region(KVMState *s, KVMSlot *slot)
     return kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
 }
 
+int kvm_destroy_vcpu(CPUState *cpu)
+{
+    KVMState *s = kvm_state;
+    long mmap_size;
+    struct KVMParkedVcpu *vcpu = NULL;
+    int ret = 0;
+
+    DPRINTF("kvm_destroy_vcpu\n");
+
+    mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
+    if (mmap_size < 0) {
+        ret = mmap_size;
+        DPRINTF("kvm_destroy_vcpu failed\n");
+        goto err;
+    }
+
+    ret = munmap(cpu->kvm_run, mmap_size);
+    if (ret < 0) {
+        goto err;
+    }
+
+    vcpu = g_malloc0(sizeof(*vcpu));
+    vcpu->vcpu_id = kvm_arch_vcpu_id(cpu);
+    vcpu->kvm_fd = cpu->kvm_fd;
+    QLIST_INSERT_HEAD(&kvm_state->kvm_parked_vcpus, vcpu, node);
+
+err:
+    return ret;
+}
+
+static int kvm_get_vcpu(KVMState *s, unsigned long vcpu_id)
+{
+    struct KVMParkedVcpu *cpu;
+
+    QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) {
+        if (cpu->vcpu_id == vcpu_id) {
+            int kvm_fd;
+
+            QLIST_REMOVE(cpu, node);
+            kvm_fd = cpu->kvm_fd;
+            g_free(cpu);
+            return kvm_fd;
+        }
+    }
+
+    return kvm_vm_ioctl(s, KVM_CREATE_VCPU, (void *)vcpu_id);
+}
 int kvm_init_vcpu(CPUState *cpu)
 {
     KVMState *s = kvm_state;
@@ -255,7 +309,7 @@ int kvm_init_vcpu(CPUState *cpu)
 
     DPRINTF("kvm_init_vcpu\n");
 
-    ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, (void *)kvm_arch_vcpu_id(cpu));
+    ret = kvm_get_vcpu(s, kvm_arch_vcpu_id(cpu));
     if (ret < 0) {
         DPRINTF("kvm_create_vcpu failed\n");
         goto err;
@@ -1441,6 +1495,7 @@ static int kvm_init(MachineState *ms)
 #ifdef KVM_CAP_SET_GUEST_DEBUG
     QTAILQ_INIT(&s->kvm_sw_breakpoints);
 #endif
+    QLIST_INIT(&s->kvm_parked_vcpus);
     s->vmfd = -1;
     s->fd = qemu_open("/dev/kvm", O_RDWR);
     if (s->fd == -1) {
-- 
2.1.0