Merge branch 'kvm-redo-enable-virt' into HEAD

Register KVM's cpuhp and syscore callbacks when enabling virtualization in
hardware, as the sole purpose of said callbacks is to disable and re-enable
virtualization as needed.

The primary motivation for this series is to simplify dealing with enabling
virtualization for Intel's TDX, which needs to enable virtualization
when kvm-intel.ko is loaded, i.e. long before the first VM is created.

That said, this is a nice cleanup on its own.  By registering the callbacks
on-demand, the callbacks themselves don't need to check kvm_usage_count,
because their very existence implies a non-zero count.

Patch 1 (re)adds a dedicated lock for kvm_usage_count.  This avoids a
lock ordering issue between cpus_read_lock() and kvm_lock.  The lock
ordering issue still exist in very rare cases, and will be fixed for
good by switching vm_list to an (S)RCU-protected list.

Signed-off-by: Paolo Bonzini <[email protected]>

1 files changed, 18 insertions, 8 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c983c8e434b8..0f7342b574f9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -355,7 +355,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 
 	/*
 	 * Disabling irqs at this point since the following code could be
-	 * interrupted and executed through kvm_arch_hardware_disable()
+	 * interrupted and executed through kvm_arch_disable_virtualization_cpu()
 	 */
 	local_irq_save(flags);
 	if (msrs->registered) {
@@ -9753,7 +9753,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 
 	guard(mutex)(&vendor_module_lock);
 
-	if (kvm_x86_ops.hardware_enable) {
+	if (kvm_x86_ops.enable_virtualization_cpu) {
 		pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name);
 		return -EEXIST;
 	}
@@ -9880,7 +9880,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 	return 0;
 
 out_unwind_ops:
-	kvm_x86_ops.hardware_enable = NULL;
+	kvm_x86_ops.enable_virtualization_cpu = NULL;
 	kvm_x86_call(hardware_unsetup)();
 out_mmu_exit:
 	kvm_mmu_vendor_module_exit();
@@ -9921,7 +9921,7 @@ void kvm_x86_vendor_exit(void)
 	WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key));
 #endif
 	mutex_lock(&vendor_module_lock);
-	kvm_x86_ops.hardware_enable = NULL;
+	kvm_x86_ops.enable_virtualization_cpu = NULL;
 	mutex_unlock(&vendor_module_lock);
 }
 EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit);
@@ -12516,7 +12516,17 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector);
 
-int kvm_arch_hardware_enable(void)
+void kvm_arch_enable_virtualization(void)
+{
+	cpu_emergency_register_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu);
+}
+
+void kvm_arch_disable_virtualization(void)
+{
+	cpu_emergency_unregister_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu);
+}
+
+int kvm_arch_enable_virtualization_cpu(void)
 {
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
@@ -12532,7 +12542,7 @@ int kvm_arch_hardware_enable(void)
 	if (ret)
 		return ret;
 
-	ret = kvm_x86_call(hardware_enable)();
+	ret = kvm_x86_call(enable_virtualization_cpu)();
 	if (ret != 0)
 		return ret;
 
@@ -12612,9 +12622,9 @@ int kvm_arch_hardware_enable(void)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void)
+void kvm_arch_disable_virtualization_cpu(void)
 {
-	kvm_x86_call(hardware_disable)();
+	kvm_x86_call(disable_virtualization_cpu)();
 	drop_user_return_notifiers();
 }