KVM: Move kvm_arch_vcpu_precreate() under kvm->lock

kvm_arch_vcpu_precreate() targets to handle arch specific VM resource
to be prepared prior to the actual creation of vCPU. For example, x86
platform may need do per-VM allocation based on max_vcpu_ids at the
first vCPU creation. It probably leads to concurrency control on this
allocation as multiple vCPU creation could happen simultaneously. From
the architectual point of view, it's necessary to execute
kvm_arch_vcpu_precreate() under protect of kvm->lock.

Currently only arm64, x86 and s390 have non-nop implementations at the
stage of vCPU pre-creation. Remove the lock acquiring in s390's design
and make sure all architecture can run kvm_arch_vcpu_precreate() safely
under kvm->lock without recrusive lock issue.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Zeng Guang <guang.zeng@intel.com>
Message-Id: <20220419154409.11842-1-guang.zeng@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ff457a7..72bd5c9 100644 (file)
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3238,9 +3238,7 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
        if (!sclp.has_esca || !sclp.has_64bscao)
                return false;
 
-       mutex_lock(&kvm->lock);
        rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
-       mutex_unlock(&kvm->lock);
 
        return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
 }

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 501606e..9c2e2b6 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11242,7 +11242,7 @@ static int sync_regs(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 {
-       if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
+       if (kvm_check_tsc_unstable() && kvm->created_vcpus)
                pr_warn_once("kvm: SMP vm created on host with unstable TSC; "
                             "guest TSC will not be reliable\n");
 

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7f79abd..6dbdcbd 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3768,13 +3768,15 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
                return -EINVAL;
        }
 
+       r = kvm_arch_vcpu_precreate(kvm, id);
+       if (r) {
+               mutex_unlock(&kvm->lock);
+               return r;
+       }
+
        kvm->created_vcpus++;
        mutex_unlock(&kvm->lock);
 
-       r = kvm_arch_vcpu_precreate(kvm, id);
-       if (r)
-               goto vcpu_decrement;
-
        vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
        if (!vcpu) {
                r = -ENOMEM;