Introduce new max_vcpu_ids in KVM for x86 architecture. Userspace
can assign maximum possible vcpu id for current VM session using
KVM_CAP_MAX_VCPU_ID of KVM_ENABLE_CAP ioctl().
This is done for x86 only because the sole use case is to guide
memory allocation for PID-pointer table, a structure needed to
enable VMX IPI.
By default, max_vcpu_ids set as KVM_MAX_VCPU_IDS.
Suggested-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Reviewed-by: Maxim Levitsky <mlevitsk@xxxxxxxxxx>
Signed-off-by: Zeng Guang <guang.zeng@xxxxxxxxx>
---
Documentation/virt/kvm/api.rst | 17 +++++++++++++++++
arch/x86/include/asm/kvm_host.h | 6 ++++++
arch/x86/kvm/x86.c | 18 +++++++++++++++++-
3 files changed, 40 insertions(+), 1 deletion(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index d13fa6600467..bb0b0f3edefe 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7136,6 +7136,23 @@ The valid bits in cap.args[0] are:
IA32_MISC_ENABLE[bit 18] is cleared.
=================================== ============================================
+7.32 KVM_CAP_MAX_VCPU_ID
+------------------------
+
+:Architectures: x86
+:Target: VM
+:Parameters: args[0] - maximum APIC ID value set for current VM
+:Returns: 0 on success, -EINVAL if args[0] is beyond KVM_MAX_VCPU_IDS
+ supported in KVM or if vCPU has been created.
+
+Userspace is able to calculate the limit to APIC ID values from designated CPU
+topology. This capability allows userspace to specify maximum possible APIC ID
+assigned for current VM session prior to the creation of vCPUs. KVM can manage
+memory allocation of VM-scope structures which depends on the value of APIC ID.
+
+Calling KVM_CHECK_EXTENSION for this capability returns the value of maximum APIC
+ID that KVM supports at runtime. It sets as KVM_MAX_VCPU_IDS in VM initialization.
+
8. Other capabilities.
======================
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d23e80a56eb8..cdd14033988d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1238,6 +1238,12 @@ struct kvm_arch {
hpa_t hv_root_tdp;
spinlock_t hv_root_tdp_lock;
#endif
+ /*
+ * VM-scope maximum vCPU ID. Used to determine the size of structures
+ * that increase along with the maximum vCPU ID, in which case, using
+ * the global KVM_MAX_VCPU_IDS may lead to significant memory waste.
+ */
+ u32 max_vcpu_ids;
};
struct kvm_vm_stat {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0c0ca599a353..d1a39285deab 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4320,7 +4320,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = KVM_MAX_VCPUS;
break;
case KVM_CAP_MAX_VCPU_ID:
- r = KVM_MAX_VCPU_IDS;
+ r = kvm->arch.max_vcpu_ids;
break;
case KVM_CAP_PV_MMU: /* obsolete */
r = 0;
@@ -6064,6 +6064,18 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
}
mutex_unlock(&kvm->lock);
break;
+ case KVM_CAP_MAX_VCPU_ID:
+ r = -EINVAL;
+ if (cap->args[0] > KVM_MAX_VCPU_IDS)
+ break;
+
+ mutex_lock(&kvm->lock);
+ if (!kvm->created_vcpus) {
+ kvm->arch.max_vcpu_ids = cap->args[0];
+ r = 0;
+ }
+ mutex_unlock(&kvm->lock);
+ break;
default:
r = -EINVAL;
break;
@@ -11180,6 +11192,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
struct page *page;
int r;
+ if (vcpu->vcpu_id >= vcpu->kvm->arch.max_vcpu_ids)
+ return -EINVAL;
+
vcpu->arch.last_vmentry_cpu = -1;
vcpu->arch.regs_avail = ~0;
vcpu->arch.regs_dirty = ~0;
@@ -11704,6 +11719,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
spin_lock_init(&kvm->arch.hv_root_tdp_lock);
kvm->arch.hv_root_tdp = INVALID_PAGE;
#endif
+ kvm->arch.max_vcpu_ids = KVM_MAX_VCPU_IDS;
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
--
2.27.0
