[v4,3/3] target/ppc: handle vcpu hotplug failure gracefully

Commit Message

Harsh Prateek Bora June 18, 2024, 8:23 a.m. UTC

On ppc64, the PowerVM hypervisor runs with limited memory and a VCPU
creation during hotplug may fail during kvm_ioctl for KVM_CREATE_VCPU,
leading to termination of guest since errp is set to &error_fatal while
calling kvm_init_vcpu. This unexpected behaviour can be avoided by
pre-creating and parking vcpu on success or return error otherwise.
This enables graceful error delivery for any vcpu hotplug failures while
the guest can keep running.

Also introducing KVM AccelCPUClass to init cpu_target_realize for kvm.

Tested OK by repeatedly doing a hotplug/unplug of vcpus as below:

 #virsh setvcpus hotplug 40
 #virsh setvcpus hotplug 70
error: internal error: unable to execute QEMU command 'device_add':
kvmppc_cpu_realize: vcpu hotplug failed with -12

Reported-by: Anushree Mathur <[e-mail]>
Suggested-by: Shivaprasad G Bhat <[e-mail]>
Suggested-by: Vaibhav Jain <[e-mail]>
Tested-by: Anushree Mathur <[e-mail]>
Reviewed-by: Nicholas Piggin <[e-mail]>
Signed-off by: Harsh Prateek Bora <[e-mail]>
---
 target/ppc/kvm.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

Patch

diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 005f2239f3..77a3ebae22 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -48,6 +48,8 @@ 
 #include "qemu/mmap-alloc.h"
 #include "elf.h"
 #include "sysemu/kvm_int.h"
+#include "sysemu/kvm.h"
+#include "hw/core/accel-cpu.h"
 
 #include CONFIG_DEVICES
 
@@ -2346,6 +2348,30 @@  static void alter_insns(uint64_t *word, uint64_t flags, bool on)
     }
 }
 
+static bool kvmppc_cpu_realize(CPUState *cs, Error **errp)
+{
+    int ret;
+    const char *vcpu_str = (cs->parent_obj.hotplugged == true) ?
+                           "hotplug" : "create";
+    cs->cpu_index = cpu_get_free_index();
+
+    POWERPC_CPU(cs)->vcpu_id = cs->cpu_index;
+
+    /* create and park to fail gracefully in case vcpu hotplug fails */
+    ret = kvm_create_and_park_vcpu(cs);
+    if (ret) {
+        /*
+         * This causes QEMU to terminate if initial CPU creation
+         * fails, and only CPU hotplug failure if the error happens
+         * there.
+         */
+        error_setg(errp, "%s: vcpu %s failed with %d",
+                         __func__, vcpu_str, ret);
+        return false;
+    }
+    return true;
+}
+
 static void kvmppc_host_cpu_class_init(ObjectClass *oc, void *data)
 {
     PowerPCCPUClass *pcc = POWERPC_CPU_CLASS(oc);
@@ -2966,3 +2992,23 @@  void kvmppc_set_reg_tb_offset(PowerPCCPU *cpu, int64_t tb_offset)
 void kvm_arch_accel_class_init(ObjectClass *oc)
 {
 }
+
+static void kvm_cpu_accel_class_init(ObjectClass *oc, void *data)
+{
+    AccelCPUClass *acc = ACCEL_CPU_CLASS(oc);
+
+    acc->cpu_target_realize = kvmppc_cpu_realize;
+}
+
+static const TypeInfo kvm_cpu_accel_type_info = {
+    .name = ACCEL_CPU_NAME("kvm"),
+
+    .parent = TYPE_ACCEL_CPU,
+    .class_init = kvm_cpu_accel_class_init,
+    .abstract = true,
+};
+static void kvm_cpu_accel_register_types(void)
+{
+    type_register_static(&kvm_cpu_accel_type_info);
+}
+type_init(kvm_cpu_accel_register_types);