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 vcpu and parking it on success or return error otherwise.
This enables graceful error delivery for any vcpu hotplug failures while
the guest can keep running.
Based on api refactoring to create/park vcpus introduced in 1/8 of patch series:
https://lore.kernel.org/qemu-devel/20240312020000.12992-2-salil.mehta@huawei.com/
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 <anushree.mathur@linux.vnet.ibm.com>
Suggested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Suggested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off by: Harsh Prateek Bora <harshpb@linux.ibm.com>
---
---
target/ppc/kvm.c | 42 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 42 insertions(+)
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 8231feb2d4..c887f6dfa0 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"
#define PROC_DEVTREE_CPU "/proc/device-tree/cpus/"
@@ -2339,6 +2341,43 @@ static void alter_insns(uint64_t *word, uint64_t flags, bool on)
}
}
+static int max_cpu_index = 0;
+
+static bool kvmppc_cpu_realize(CPUState *cs, Error **errp)
+{
+ int ret;
+
+ cs->cpu_index = max_cpu_index++;
+
+ POWERPC_CPU(cs)->vcpu_id = cs->cpu_index;
+
+ if (cs->parent_obj.hotplugged) {
+ /* create and park to fail gracefully in case vcpu hotplug fails */
+ ret = kvm_create_vcpu(cs);
+ if (!ret) {
+ kvm_park_vcpu(cs);
+ } else {
+ max_cpu_index--;
+ error_setg(errp, "%s: vcpu hotplug failed with %d",
+ __func__, ret);
+ return false;
+ }
+ }
+ return true;
+}
+
+static void kvmppc_cpu_unrealize(CPUState *cpu)
+{
+ if (POWERPC_CPU(cpu)->vcpu_id == (max_cpu_index - 1)) {
+ /* only reclaim vcpuid if its the last one assigned
+ * as reclaiming random vcpuid for parked vcpus may lead
+ * to unexpected behaviour due to an existing kernel bug
+ * when drc_index doesnt get reclaimed as expected.
+ */
+ max_cpu_index--;
+ }
+}
+
static void kvmppc_host_cpu_class_init(ObjectClass *oc, void *data)
{
PowerPCCPUClass *pcc = POWERPC_CPU_CLASS(oc);
@@ -2963,4 +3002,7 @@ bool kvm_arch_cpu_check_are_resettable(void)
void kvm_arch_accel_class_init(ObjectClass *oc)
{
+ AccelClass *ac = ACCEL_CLASS(oc);
+ ac->cpu_common_realize = kvmppc_cpu_realize;
+ ac->cpu_common_unrealize = kvmppc_cpu_unrealize;
}