KVM: VMX: Enable bus lock VM exit

Virtual Machine can exploit bus locks to degrade the performance of
system. Bus lock can be caused by split locked access to writeback(WB)
memory or by using locks on uncacheable(UC) memory. The bus lock is
typically >1000 cycles slower than an atomic operation within a cache
line. It also disrupts performance on other cores (which must wait for
the bus lock to be released before their memory operations can
complete).

To address the threat, bus lock VM exit is introduced to notify the VMM
when a bus lock was acquired, allowing it to enforce throttling or other
policy based mitigations.

A VMM can enable VM exit due to bus locks by setting a new "Bus Lock
Detection" VM-execution control(bit 30 of Secondary Processor-based VM
execution controls). If delivery of this VM exit was preempted by a
higher priority VM exit (e.g. EPT misconfiguration, EPT violation, APIC
access VM exit, APIC write VM exit, exception bitmap exiting), bit 26 of
exit reason in vmcs field is set to 1.

In current implementation, the KVM exposes this capability through
KVM_CAP_X86_BUS_LOCK_EXIT. The user can get the supported mode bitmap
(i.e. off and exit) and enable it explicitly (disabled by default). If
bus locks in guest are detected by KVM, exit to user space even when
current exit reason is handled by KVM internally. Set a new field
KVM_RUN_BUS_LOCK in vcpu->run->flags to inform the user space that there
is a bus lock detected in guest.

Document for Bus Lock VM exit is now available at the latest "Intel
Architecture Instruction Set Extensions Programming Reference".

Document Link:
https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html

Co-developed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20201106090315.18606-4-chenyi.qiang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 65 insertions, 3 deletions

diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 3a1861403d73..5366ccdd134c 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -262,6 +262,12 @@ static inline bool cpu_has_vmx_tsc_scaling(void)
 		SECONDARY_EXEC_TSC_SCALING;
 }
 
+static inline bool cpu_has_vmx_bus_lock_detection(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+	    SECONDARY_EXEC_BUS_LOCK_DETECTION;
+}
+
 static inline bool cpu_has_vmx_apicv(void)
 {
 	return cpu_has_vmx_apic_register_virt() &&
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 880a2617820c..af8d3a2db3d2 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2428,7 +2428,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 			SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
 			SECONDARY_EXEC_PT_USE_GPA |
 			SECONDARY_EXEC_PT_CONCEAL_VMX |
-			SECONDARY_EXEC_ENABLE_VMFUNC;
+			SECONDARY_EXEC_ENABLE_VMFUNC |
+			SECONDARY_EXEC_BUS_LOCK_DETECTION;
 		if (cpu_has_sgx())
 			opt2 |= SECONDARY_EXEC_ENCLS_EXITING;
 		if (adjust_vmx_controls(min2, opt2,
@@ -4269,6 +4270,9 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 	vmx_adjust_sec_exec_control(vmx, &exec_control, waitpkg, WAITPKG,
 				    ENABLE_USR_WAIT_PAUSE, false);
 
+	if (!vcpu->kvm->arch.bus_lock_detection_enabled)
+		exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION;
+
 	vmx->secondary_exec_control = exec_control;
 }
 
@@ -5600,6 +5604,13 @@ static int handle_encls(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
+{
+	vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
+	vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
+	return 0;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -5656,6 +5667,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_VMFUNC]		      = handle_vmx_instruction,
 	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
 	[EXIT_REASON_ENCLS]		      = handle_encls,
+	[EXIT_REASON_BUS_LOCK]                = handle_bus_lock_vmexit,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -5908,7 +5920,7 @@ void dump_vmcs(void)
  * The guest has exited.  See if we can fix it or if we need userspace
  * assistance.
  */
-static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
+static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	union vmx_exit_reason exit_reason = vmx->exit_reason;
@@ -6061,6 +6073,25 @@ unexpected_vmexit:
 	return 0;
 }
 
+static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
+{
+	int ret = __vmx_handle_exit(vcpu, exit_fastpath);
+
+	/*
+	 * Even when current exit reason is handled by KVM internally, we
+	 * still need to exit to user space when bus lock detected to inform
+	 * that there is a bus lock in guest.
+	 */
+	if (to_vmx(vcpu)->exit_reason.bus_lock_detected) {
+		if (ret > 0)
+			vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
+
+		vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
+		return 0;
+	}
+	return ret;
+}
+
 /*
  * Software based L1D cache flush which is used when microcode providing
  * the cache control MSR is not loaded.
@@ -7812,6 +7843,8 @@ static __init int hardware_setup(void)
 		kvm_tsc_scaling_ratio_frac_bits = 48;
 	}
 
+	kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection();
+
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
 	if (enable_ept)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 4dd71b7494ea..cf335e94f198 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -83,7 +83,7 @@ union vmx_exit_reason {
 		u32	reserved23		: 1;
 		u32	reserved24		: 1;
 		u32	reserved25		: 1;
-		u32	reserved26		: 1;
+		u32	bus_lock_detected	: 1;
 		u32	enclave_mode		: 1;
 		u32	smi_pending_mtf		: 1;
 		u32	smi_from_vmx_root	: 1;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 90a2335498a2..8719877fe799 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,6 +136,8 @@ u64  __read_mostly kvm_max_tsc_scaling_ratio;
 EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio);
 u64 __read_mostly kvm_default_tsc_scaling_ratio;
 EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
+bool __read_mostly kvm_has_bus_lock_exit;
+EXPORT_SYMBOL_GPL(kvm_has_bus_lock_exit);
 
 /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
 static u32 __read_mostly tsc_tolerance_ppm = 250;
@@ -3843,6 +3845,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_STEAL_TIME:
 		r = sched_info_on();
 		break;
+	case KVM_CAP_X86_BUS_LOCK_EXIT:
+		if (kvm_has_bus_lock_exit)
+			r = KVM_BUS_LOCK_DETECTION_OFF |
+			    KVM_BUS_LOCK_DETECTION_EXIT;
+		else
+			r = 0;
+		break;
 	default:
 		break;
 	}
@@ -5298,6 +5307,20 @@ split_irqchip_unlock:
 		kvm->arch.user_space_msr_mask = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_X86_BUS_LOCK_EXIT:
+		r = -EINVAL;
+		if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE)
+			break;
+
+		if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) &&
+		    (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT))
+			break;
+
+		if (kvm_has_bus_lock_exit &&
+		    cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)
+			kvm->arch.bus_lock_detection_enabled = true;
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;