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 <pbonzini@redhat.com>

8 files changed, 44 insertions, 35 deletions

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 68ad4f923664..03b7e13f15bb 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -14,8 +14,8 @@ BUILD_BUG_ON(1)
  * be __static_call_return0.
  */
 KVM_X86_OP(check_processor_compatibility)
-KVM_X86_OP(hardware_enable)
-KVM_X86_OP(hardware_disable)
+KVM_X86_OP(enable_virtualization_cpu)
+KVM_X86_OP(disable_virtualization_cpu)
 KVM_X86_OP(hardware_unsetup)
 KVM_X86_OP(has_emulated_msr)
 KVM_X86_OP(vcpu_after_set_cpuid)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e4fc362ba3da..52443ccda320 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -36,6 +36,7 @@
 #include <asm/kvm_page_track.h>
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/hyperv-tlfs.h>
+#include <asm/reboot.h>
 
 #define __KVM_HAVE_ARCH_VCPU_DEBUGFS
 
@@ -1629,8 +1630,10 @@ struct kvm_x86_ops {
 
 	int (*check_processor_compatibility)(void);
 
-	int (*hardware_enable)(void);
-	void (*hardware_disable)(void);
+	int (*enable_virtualization_cpu)(void);
+	void (*disable_virtualization_cpu)(void);
+	cpu_emergency_virt_cb *emergency_disable_virtualization_cpu;
+
 	void (*hardware_unsetup)(void);
 	bool (*has_emulated_msr)(struct kvm *kvm, u32 index);
 	void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 6536873f8fc0..d0ef2a678d66 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,8 +25,8 @@ void __noreturn machine_real_restart(unsigned int type);
 #define MRR_BIOS	0
 #define MRR_APM		1
 
-#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD)
 typedef void (cpu_emergency_virt_cb)(void);
+#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD)
 void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback);
 void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback);
 void cpu_emergency_disable_virtualization(void);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5ab2c92c7331..6b804ec3d1dc 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -592,14 +592,14 @@ static inline void kvm_cpu_svm_disable(void)
 	}
 }
 
-static void svm_emergency_disable(void)
+static void svm_emergency_disable_virtualization_cpu(void)
 {
 	kvm_rebooting = true;
 
 	kvm_cpu_svm_disable();
 }
 
-static void svm_hardware_disable(void)
+static void svm_disable_virtualization_cpu(void)
 {
 	/* Make sure we clean up behind us */
 	if (tsc_scaling)
@@ -610,7 +610,7 @@ static void svm_hardware_disable(void)
 	amd_pmu_disable_virt();
 }
 
-static int svm_hardware_enable(void)
+static int svm_enable_virtualization_cpu(void)
 {
 
 	struct svm_cpu_data *sd;
@@ -1533,7 +1533,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	 * TSC_AUX is always virtualized for SEV-ES guests when the feature is
 	 * available. The user return MSR support is not required in this case
 	 * because TSC_AUX is restored on #VMEXIT from the host save area
-	 * (which has been initialized in svm_hardware_enable()).
+	 * (which has been initialized in svm_enable_virtualization_cpu()).
 	 */
 	if (likely(tsc_aux_uret_slot >= 0) &&
 	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
@@ -3144,7 +3144,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 * feature is available. The user return MSR support is not
 		 * required in this case because TSC_AUX is restored on #VMEXIT
 		 * from the host save area (which has been initialized in
-		 * svm_hardware_enable()).
+		 * svm_enable_virtualization_cpu()).
 		 */
 		if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm))
 			break;
@@ -4992,8 +4992,9 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.check_processor_compatibility = svm_check_processor_compat,
 
 	.hardware_unsetup = svm_hardware_unsetup,
-	.hardware_enable = svm_hardware_enable,
-	.hardware_disable = svm_hardware_disable,
+	.enable_virtualization_cpu = svm_enable_virtualization_cpu,
+	.disable_virtualization_cpu = svm_disable_virtualization_cpu,
+	.emergency_disable_virtualization_cpu = svm_emergency_disable_virtualization_cpu,
 	.has_emulated_msr = svm_has_emulated_msr,
 
 	.vcpu_create = svm_vcpu_create,
@@ -5425,8 +5426,6 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = {
 static void __svm_exit(void)
 {
 	kvm_x86_vendor_exit();
-
-	cpu_emergency_unregister_virt_callback(svm_emergency_disable);
 }
 
 static int __init svm_init(void)
@@ -5442,8 +5441,6 @@ static int __init svm_init(void)
 	if (r)
 		return r;
 
-	cpu_emergency_register_virt_callback(svm_emergency_disable);
-
 	/*
 	 * Common KVM initialization _must_ come last, after this, /dev/kvm is
 	 * exposed to userspace!
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 0bf35ebe8a1b..7e2e78a14257 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -23,8 +23,10 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.hardware_unsetup = vmx_hardware_unsetup,
 
-	.hardware_enable = vmx_hardware_enable,
-	.hardware_disable = vmx_hardware_disable,
+	.enable_virtualization_cpu = vmx_enable_virtualization_cpu,
+	.disable_virtualization_cpu = vmx_disable_virtualization_cpu,
+	.emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu,
+
 	.has_emulated_msr = vmx_has_emulated_msr,
 
 	.vm_size = sizeof(struct kvm_vmx),
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f18c2d8c7476..89682832dded 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -755,7 +755,7 @@ fault:
 	return -EIO;
 }
 
-static void vmx_emergency_disable(void)
+void vmx_emergency_disable_virtualization_cpu(void)
 {
 	int cpu = raw_smp_processor_id();
 	struct loaded_vmcs *v;
@@ -2844,7 +2844,7 @@ fault:
 	return -EFAULT;
 }
 
-int vmx_hardware_enable(void)
+int vmx_enable_virtualization_cpu(void)
 {
 	int cpu = raw_smp_processor_id();
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2881,7 +2881,7 @@ static void vmclear_local_loaded_vmcss(void)
 		__loaded_vmcs_clear(v);
 }
 
-void vmx_hardware_disable(void)
+void vmx_disable_virtualization_cpu(void)
 {
 	vmclear_local_loaded_vmcss();
 
@@ -8584,8 +8584,6 @@ static void __vmx_exit(void)
 {
 	allow_smaller_maxphyaddr = false;
 
-	cpu_emergency_unregister_virt_callback(vmx_emergency_disable);
-
 	vmx_cleanup_l1d_flush();
 }
 
@@ -8632,8 +8630,6 @@ static int __init vmx_init(void)
 		pi_init_cpu(cpu);
 	}
 
-	cpu_emergency_register_virt_callback(vmx_emergency_disable);
-
 	vmx_check_vmcs12_offsets();
 
 	/*
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index ce3221cd1d01..b6a7cfc6ae31 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -13,8 +13,9 @@ extern struct kvm_x86_init_ops vt_init_ops __initdata;
 
 void vmx_hardware_unsetup(void);
 int vmx_check_processor_compat(void);
-int vmx_hardware_enable(void);
-void vmx_hardware_disable(void);
+int vmx_enable_virtualization_cpu(void);
+void vmx_disable_virtualization_cpu(void);
+void vmx_emergency_disable_virtualization_cpu(void);
 int vmx_vm_init(struct kvm *kvm);
 void vmx_vm_destroy(struct kvm *kvm);
 int vmx_vcpu_precreate(struct kvm *kvm);
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();
 }