The PMU for all possible vCPUs must be initialized during VM initialization.
Refactor the existing code to accommodate possible vCPUs. This assumes that all
processors being used are identical. It is an architectural constraint of ARM
CPUs that all vCPUs MUST have identical feature sets, at least until the ARM
specification is updated to allow otherwise.

Past discussion for reference:
Link: https://lists.gnu.org/archive/html/qemu-devel/2020-06/msg00131.html

Co-developed-by: Keqian Zhu <zhukeqian1@huawei.com>
Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
 hw/arm/virt.c         | 9 +++++----
 include/hw/arm/virt.h | 1 +
 include/hw/core/cpu.h | 5 +++++
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index b9df428049..6ac2d8826e 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2035,12 +2035,13 @@ static void finalize_gic_version(VirtMachineState *vms)
  */
 static void virt_cpu_post_init(VirtMachineState *vms, MemoryRegion *sysmem)
 {
+    CPUArchIdList *possible_cpus = vms->parent.possible_cpus;
     int max_cpus = MACHINE(vms)->smp.max_cpus;
-    bool aarch64, pmu, steal_time;
+    bool aarch64, steal_time;
     CPUState *cpu;
 
     aarch64 = object_property_get_bool(OBJECT(first_cpu), "aarch64", NULL);
-    pmu = object_property_get_bool(OBJECT(first_cpu), "pmu", NULL);
+    vms->pmu = object_property_get_bool(OBJECT(first_cpu), "pmu", NULL);
     steal_time = object_property_get_bool(OBJECT(first_cpu),
                                           "kvm-steal-time", NULL);
 
@@ -2067,8 +2068,8 @@ static void virt_cpu_post_init(VirtMachineState *vms, MemoryRegion *sysmem)
             memory_region_add_subregion(sysmem, pvtime_reg_base, pvtime);
         }
 
-        CPU_FOREACH(cpu) {
-            if (pmu) {
+        CPU_FOREACH_POSSIBLE(cpu, possible_cpus) {
+            if (vms->pmu) {
                 assert(arm_feature(&ARM_CPU(cpu)->env, ARM_FEATURE_PMU));
                 if (kvm_irqchip_in_kernel()) {
                     kvm_arm_pmu_set_irq(ARM_CPU(cpu), VIRTUAL_PMU_IRQ);
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index b5bfb75f71..98ce68eae1 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -161,6 +161,7 @@ struct VirtMachineState {
     bool mte;
     bool dtb_randomness;
     bool second_ns_uart_present;
+    bool pmu;
     OnOffAuto acpi;
     VirtGICType gic_version;
     VirtIOMMUType iommu;
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index 0be1984698..4a74c383ab 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -618,6 +618,11 @@ extern CPUTailQ cpus_queue;
 #define CPU_FOREACH_SAFE(cpu, next_cpu) \
     QTAILQ_FOREACH_SAFE_RCU(cpu, &cpus_queue, node, next_cpu)
 
+#define CPU_FOREACH_POSSIBLE(cpu, poslist) \
+    for (int iter = 0; \
+         iter < (poslist)->len && ((cpu) = (poslist)->cpus[iter].cpu, 1); \
+         iter++)
+
 extern __thread CPUState *current_cpu;
 
 /**
-- 
2.34.1