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, 8 insertions, 11 deletions

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!