!116 SPR: KVM: Add Bus Lock VM Exit

Merge Pull Request from: @allen-shi 
 
This PR is to add KVM support for Bus Lock VM Exit.

Intel-Kernel Issue
[#I5RJCB](https://gitee.com/openeuler/intel-kernel/issues/I5RJCB)

Test
Bus Lock VM Exit feature is supported.

Known Issue
N/A

Default config change
N/A 
 
Link:https://gitee.com/openeuler/kernel/pulls/116 
Reviewed-by: Kevin Zhu <zhukeqian1@huawei.com> 
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com> 

Documentation/virt/kvm/api.rst

@@ -5033,9 +5033,11 @@ local APIC is not used.
 	__u16 flags;
 
 More architecture-specific flags detailing state of the VCPU that may
-affect the device's behavior.  The only currently defined flag is
-KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the
-VCPU is in system management mode.
+affect the device's behavior. Current defined flags:
+  /* x86, set if the VCPU is in system management mode */
+  #define KVM_RUN_X86_SMM     (1 << 0)
+  /* x86, set if bus lock detected in VM */
+  #define KVM_RUN_BUS_LOCK    (1 << 1)
 
 ::
 
@@ -6197,7 +6199,7 @@ KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications which user space
 can then handle to implement model specific MSR handling and/or user notifications
 to inform a user that an MSR was not handled.
 
-7.25 KVM_CAP_SGX_ATTRIBUTE
+7.22 KVM_CAP_SGX_ATTRIBUTE
 ----------------------
 
 :Architectures: x86
@@ -6241,6 +6243,43 @@ if the value was set to zero or KVM_ENABLE_CAP was not invoked, KVM
 uses the return value of KVM_CHECK_EXTENSION(KVM_CAP_MAX_VCPU_ID) as
 the maximum APIC ID.
 
+7.24 KVM_CAP_X86_BUS_LOCK_EXIT
+-------------------------------
+
+:Architectures: x86
+:Target: VM
+:Parameters: args[0] defines the policy used when bus locks detected in guest
+:Returns: 0 on success, -EINVAL when args[0] contains invalid bits
+
+Valid bits in args[0] are::
+
+  #define KVM_BUS_LOCK_DETECTION_OFF      (1 << 0)
+  #define KVM_BUS_LOCK_DETECTION_EXIT     (1 << 1)
+
+Enabling this capability on a VM provides userspace with a way to select
+a policy to handle the bus locks detected in guest. Userspace can obtain
+the supported modes from the result of KVM_CHECK_EXTENSION and define it
+through the KVM_ENABLE_CAP.
+
+KVM_BUS_LOCK_DETECTION_OFF and KVM_BUS_LOCK_DETECTION_EXIT are supported
+currently and mutually exclusive with each other. More bits can be added in
+the future.
+
+With KVM_BUS_LOCK_DETECTION_OFF set, bus locks in guest will not cause vm exits
+so that no additional actions are needed. This is the default mode.
+
+With KVM_BUS_LOCK_DETECTION_EXIT set, vm exits happen when bus lock detected
+in VM. KVM just exits to userspace when handling them. Userspace can enforce
+its own throttling or other policy based mitigations.
+
+This capability is aimed to address the thread that VM can exploit bus locks to
+degree the performance of the whole system. Once the userspace enable this
+capability and select the KVM_BUS_LOCK_DETECTION_EXIT mode, KVM will set the
+KVM_RUN_BUS_LOCK flag in vcpu-run->flags field and exit to userspace. Concerning
+the bus lock vm exit can be preempted by a higher priority VM exit, the exit
+notifications to userspace can be KVM_EXIT_BUS_LOCK or other reasons.
+KVM_RUN_BUS_LOCK flag is used to distinguish between them.
+
 8. Other capabilities.
 ======================
 

arch/x86/include/asm/kvm_host.h

@@ -52,6 +52,9 @@
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 					KVM_DIRTY_LOG_INITIALLY_SET)
 
+#define KVM_BUS_LOCK_DETECTION_VALID_MODE	(KVM_BUS_LOCK_DETECTION_OFF | \
+						 KVM_BUS_LOCK_DETECTION_EXIT)
+
 /* x86-specific vcpu->requests bit members */
 #define KVM_REQ_MIGRATE_TIMER		KVM_ARCH_REQ(0)
 #define KVM_REQ_REPORT_TPR_ACCESS	KVM_ARCH_REQ(1)
@@ -1435,6 +1438,8 @@ extern u8   kvm_tsc_scaling_ratio_frac_bits;
 extern u64  kvm_max_tsc_scaling_ratio;
 /* 1ull << kvm_tsc_scaling_ratio_frac_bits */
 extern u64  kvm_default_tsc_scaling_ratio;
+/* bus lock detection supported? */
+extern bool kvm_has_bus_lock_exit;
 
 extern u64 kvm_mce_cap_supported;
 

arch/x86/include/asm/vmx.h

@@ -74,6 +74,7 @@
 #define SECONDARY_EXEC_PT_USE_GPA		VMCS_CONTROL_BIT(PT_USE_GPA)
 #define SECONDARY_EXEC_TSC_SCALING              VMCS_CONTROL_BIT(TSC_SCALING)
 #define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE	VMCS_CONTROL_BIT(USR_WAIT_PAUSE)
+#define SECONDARY_EXEC_BUS_LOCK_DETECTION	VMCS_CONTROL_BIT(BUS_LOCK_DETECTION)
 
 /*
  * Definitions of Tertiary Processor-Based VM-Execution Controls.

arch/x86/include/asm/vmxfeatures.h

@@ -84,6 +84,7 @@
 #define VMX_FEATURE_TSC_SCALING		( 2*32+ 25) /* Scale hardware TSC when read in guest */
 #define VMX_FEATURE_USR_WAIT_PAUSE	( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */
 #define VMX_FEATURE_ENCLV_EXITING	( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */
+#define VMX_FEATURE_BUS_LOCK_DETECTION	( 2*32+ 30) /* "" VM-Exit when bus lock caused */
 
 /* Tertiary Processor-Based VM-Execution Controls, word 3 */
 #define VMX_FEATURE_IPI_VIRT		( 3*32+  4) /* Enable IPI virtualization */

arch/x86/include/uapi/asm/kvm.h

@@ -111,6 +111,7 @@ struct kvm_ioapic_state {
 #define KVM_NR_IRQCHIPS          3
 
 #define KVM_RUN_X86_SMM		 (1 << 0)
+#define KVM_RUN_X86_BUS_LOCK     (1 << 1)
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {

arch/x86/include/uapi/asm/vmx.h

@@ -89,6 +89,7 @@
 #define EXIT_REASON_XRSTORS             64
 #define EXIT_REASON_UMWAIT              67
 #define EXIT_REASON_TPAUSE              68
+#define EXIT_REASON_BUS_LOCK            74
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -149,7 +150,8 @@
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
-	{ EXIT_REASON_TPAUSE,                "TPAUSE" }
+	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
+	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }

arch/x86/kvm/vmx/capabilities.h

@@ -273,6 +273,12 @@ 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() &&

arch/x86/kvm/vmx/nested.c

@@ -5854,6 +5854,12 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 	case EXIT_REASON_VMFUNC:
 		/* VM functions are emulated through L2->L0 vmexits. */
 		return true;
+	case EXIT_REASON_BUS_LOCK:
+		/*
+		 * At present, bus lock VM exit is never exposed to L1.
+		 * Handle L2's bus locks in L0 directly.
+		 */
+		return true;
 	default:
 		break;
 	}

arch/x86/kvm/vmx/vmx.c

@@ -2625,7 +2625,8 @@ 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,
@@ -4500,6 +4501,9 @@ 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;
 }
 
@@ -5925,6 +5929,17 @@ static int handle_encls(struct kvm_vcpu *vcpu)
 }
 #endif /* CONFIG_X86_SGX_KVM */
 
+static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK
+	 * VM-Exits. Unconditionally set the flag here and leave the handling to
+	 * vmx_handle_exit().
+	 */
+	to_vmx(vcpu)->exit_reason.bus_lock_detected = true;
+	return 1;
+}
+
 /*
  * 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
@@ -5981,6 +5996,7 @@ 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 =
@@ -6239,7 +6255,7 @@ 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;
@@ -6392,6 +6408,24 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	return 0;
 }
 
+static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
+{
+	int ret = __vmx_handle_exit(vcpu, exit_fastpath);
+
+	/*
+	 * 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.
@@ -8180,6 +8214,8 @@ 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)

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;

arch/x86/kvm/x86.c

@@ -141,6 +141,8 @@ 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;
@@ -3919,6 +3921,13 @@ 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;
 	}
@@ -5335,6 +5344,20 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		}
 		mutex_unlock(&kvm->lock);
 		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;
@@ -8280,12 +8303,15 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 	struct kvm_run *kvm_run = vcpu->run;
 
 	kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
-	kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
+
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
 	kvm_run->ready_for_interrupt_injection =
 		pic_in_kernel(vcpu->kvm) ||
 		kvm_vcpu_ready_for_interrupt_injection(vcpu);
+
+	if (is_smm(vcpu))
+		kvm_run->flags |= KVM_RUN_X86_SMM;
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -9387,6 +9413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	vcpu_load(vcpu);
 	kvm_sigset_activate(vcpu);
+	kvm_run->flags = 0;
 	kvm_load_guest_fpu(vcpu);
 
 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {

include/uapi/linux/kvm.h

@@ -251,6 +251,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_X86_RDMSR        29
 #define KVM_EXIT_X86_WRMSR        30
 #define KVM_EXIT_RISCV_SBI        31
+#define KVM_EXIT_X86_BUS_LOCK     33
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -1061,6 +1062,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_X86_USER_SPACE_MSR 188
 #define KVM_CAP_X86_MSR_FILTER 189
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_X86_BUS_LOCK_EXIT 193
 #define KVM_CAP_SGX_ATTRIBUTE 196
 
 #define KVM_CAP_ARM_CPU_FEATURE 555
@@ -1737,4 +1739,7 @@ struct kvm_hyperv_eventfd {
 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
 #define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
 
+#define KVM_BUS_LOCK_DETECTION_OFF             (1 << 0)
+#define KVM_BUS_LOCK_DETECTION_EXIT            (1 << 1)
+
 #endif /* __LINUX_KVM_H */

tools/arch/x86/include/uapi/asm/kvm.h

@@ -111,6 +111,7 @@ struct kvm_ioapic_state {
 #define KVM_NR_IRQCHIPS          3
 
 #define KVM_RUN_X86_SMM		 (1 << 0)
+#define KVM_RUN_X86_BUS_LOCK     (1 << 1)
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {

tools/arch/x86/include/uapi/asm/vmx.h

@@ -88,6 +88,7 @@
 #define EXIT_REASON_XRSTORS             64
 #define EXIT_REASON_UMWAIT              67
 #define EXIT_REASON_TPAUSE              68
+#define EXIT_REASON_BUS_LOCK            74
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -148,7 +149,8 @@
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
-	{ EXIT_REASON_TPAUSE,                "TPAUSE" }
+	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
+	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }