!115 SPR: KVM: Add Bus Lock Debug Exception

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

Intel-Kernel Issue
[#I5RHW7](https://gitee.com/openeuler/intel-kernel/issues/I5RHW7)

Test
Guest supports for Bus Lock Debug Exception feature.

Known Issue
N/A

Default config change
N/A 
 
Link:https://gitee.com/openeuler/kernel/pulls/115 
Reviewed-by: Zheng Zengkai <zhengzengkai@huawei.com> 
Reviewed-by: Kevin Zhu <zhukeqian1@huawei.com> 
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com> 

10 files changed, 68 insertions, 44 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9f3ba4f3a45bd8..40960a171da3a2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -202,13 +202,22 @@ enum x86_intercept_stage;
 
 #define KVM_NR_DB_REGS	4
 
+#define DR6_BUS_LOCK    (1 << 11)
 #define DR6_BD		(1 << 13)
 #define DR6_BS		(1 << 14)
 #define DR6_BT		(1 << 15)
 #define DR6_RTM		(1 << 16)
-#define DR6_FIXED_1	0xfffe0ff0
-#define DR6_INIT	0xffff0ff0
-#define DR6_VOLATILE	0x0001e00f
+/*
+ * DR6_ACTIVE_LOW combines fixed-1 and active-low bits.
+ * We can regard all the bits in DR6_FIXED_1 as active_low bits;
+ * they will never be 0 for now, but when they are defined
+ * in the future it will require no code change.
+ *
+ * DR6_ACTIVE_LOW is also used as the init/reset value for DR6.
+ */
+#define DR6_ACTIVE_LOW	0xffff0ff0
+#define DR6_VOLATILE	0x0001e80f
+#define DR6_FIXED_1	(DR6_ACTIVE_LOW & ~DR6_VOLATILE)
 
 #define DR7_BP_EN_MASK	0x000000ff
 #define DR7_GE		(1 << 9)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 37f3c38d645f87..55b98f755cb925 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1150,22 +1150,23 @@ static void bus_lock_init(void)
 {
 	u64 val;
 
-	/*
-	 * Warn and fatal are handled by #AC for split lock if #AC for
-	 * split lock is supported.
-	 */
-	if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) ||
-	    (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
-	    (sld_state == sld_warn || sld_state == sld_fatal)) ||
-	    sld_state == sld_off)
+	if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
 		return;
 
-	/*
-	 * Enable #DB for bus lock. All bus locks are handled in #DB except
-	 * split locks are handled in #AC in the fatal case.
-	 */
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, val);
-	val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
+
+	if ((boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
+	    (sld_state == sld_warn || sld_state == sld_fatal)) ||
+	    sld_state == sld_off) {
+		/*
+		 * Warn and fatal are handled by #AC for split lock if #AC for
+		 * split lock is supported.
+		 */
+		val &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
+	} else {
+		val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
+	}
+
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, val);
 }
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 29a463658e673e..4638672db180bb 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -441,7 +441,7 @@ void kvm_set_cpu_caps(void)
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
 		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
 		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ |
-		F(SGX_LC)
+		F(SGX_LC) | F(BUS_LOCK_DETECT)
 	);
 	/* Set LA57 based on hardware capability. */
 	if (cpuid_ecx(7) & F(LA57))
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 71e1a2d39f2189..9c2a43ac803207 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4261,7 +4261,7 @@ static int check_dr_read(struct x86_emulate_ctxt *ctxt)
 
 		ctxt->ops->get_dr(ctxt, 6, &dr6);
 		dr6 &= ~DR_TRAP_BITS;
-		dr6 |= DR6_BD | DR6_RTM;
+		dr6 |= DR6_BD | DR6_ACTIVE_LOW;
 		ctxt->ops->set_dr(ctxt, 6, dr6);
 		return emulate_db(ctxt);
 	}
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 23910e6a3f011c..1734c6ce976de2 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -405,7 +405,7 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	svm->vmcb->save.ds = vmcb12->save.ds;
 	svm->vmcb->save.gdtr = vmcb12->save.gdtr;
 	svm->vmcb->save.idtr = vmcb12->save.idtr;
-	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags);
+	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
 
 	/*
 	 * Force-set EFER_SVME even though it is checked earlier on the
@@ -425,8 +425,8 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	svm->vmcb->save.rax = vmcb12->save.rax;
 	svm->vmcb->save.rsp = vmcb12->save.rsp;
 	svm->vmcb->save.rip = vmcb12->save.rip;
-	svm->vmcb->save.dr7 = vmcb12->save.dr7;
-	svm->vcpu.arch.dr6  = vmcb12->save.dr6;
+	svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1;
+	svm->vcpu.arch.dr6  = vmcb12->save.dr6 | DR6_ACTIVE_LOW;
 	svm->vmcb->save.cpl = vmcb12->save.cpl;
 }
 
@@ -699,14 +699,14 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->vmcb->save.ds = hsave->save.ds;
 	svm->vmcb->save.gdtr = hsave->save.gdtr;
 	svm->vmcb->save.idtr = hsave->save.idtr;
-	kvm_set_rflags(&svm->vcpu, hsave->save.rflags);
+	kvm_set_rflags(&svm->vcpu, hsave->save.rflags | X86_EFLAGS_FIXED);
 	svm_set_efer(&svm->vcpu, hsave->save.efer);
 	svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE);
 	svm_set_cr4(&svm->vcpu, hsave->save.cr4);
 	kvm_rax_write(&svm->vcpu, hsave->save.rax);
 	kvm_rsp_write(&svm->vcpu, hsave->save.rsp);
 	kvm_rip_write(&svm->vcpu, hsave->save.rip);
-	svm->vmcb->save.dr7 = 0;
+	svm->vmcb->save.dr7 = DR7_FIXED_1;
 	svm->vmcb->save.cpl = 0;
 	svm->vmcb->control.exit_int_info = 0;
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index eaf4a58dd4559d..f52668cef207a8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1788,7 +1788,7 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 	get_debugreg(vcpu->arch.db[2], 2);
 	get_debugreg(vcpu->arch.db[3], 3);
 	/*
-	 * We cannot reset svm->vmcb->save.dr6 to DR6_FIXED_1|DR6_RTM here,
+	 * We cannot reset svm->vmcb->save.dr6 to DR6_ACTIVE_LOW here,
 	 * because db_interception might need it.  We can do it before vmentry.
 	 */
 	vcpu->arch.dr6 = svm->vmcb->save.dr6;
@@ -1836,7 +1836,7 @@ static int db_interception(struct vcpu_svm *svm)
 	if (!(svm->vcpu.guest_debug &
 	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
 		!svm->nmi_singlestep) {
-		u32 payload = (svm->vmcb->save.dr6 ^ DR6_RTM) & ~DR6_FIXED_1;
+		u32 payload = svm->vmcb->save.dr6 ^ DR6_ACTIVE_LOW;
 		kvm_queue_exception_p(&svm->vcpu, DB_VECTOR, payload);
 		return 1;
 	}
@@ -3595,7 +3595,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
 		svm_set_dr6(svm, vcpu->arch.dr6);
 	else
-		svm_set_dr6(svm, DR6_FIXED_1 | DR6_RTM);
+		svm_set_dr6(svm, DR6_ACTIVE_LOW);
 
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index c1120b570cc88e..49271b8e687164 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -411,6 +411,9 @@ static inline u64 vmx_supported_debugctl(void)
 {
 	u64 debugctl = 0;
 
+	if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
+		debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
+
 	if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
 		debugctl |= DEBUGCTLMSR_LBR_MASK;
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index a18ebd2ce09694..ac56ccff6f393a 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -412,8 +412,8 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit
 		if (nr == DB_VECTOR) {
 			if (!has_payload) {
 				payload = vcpu->arch.dr6;
-				payload &= ~(DR6_FIXED_1 | DR6_BT);
-				payload ^= DR6_RTM;
+				payload &= ~DR6_BT;
+				payload ^= DR6_ACTIVE_LOW;
 			}
 			*exit_qual = payload;
 		} else
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 487c854998a105..3be5d9a760fe45 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2076,6 +2076,9 @@ static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
 	if (!intel_pmu_lbr_is_enabled(vcpu))
 		debugctl &= ~DEBUGCTLMSR_LBR_MASK;
 
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
+		debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
+
 	return debugctl;
 }
 
@@ -5149,7 +5152,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 			kvm_queue_exception_p(vcpu, DB_VECTOR, dr6);
 			return 1;
 		}
-		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM;
+		kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW;
 		kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
 		fallthrough;
 	case BP_VECTOR:
@@ -5394,7 +5397,7 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 		 * guest debugging itself.
 		 */
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
-			vcpu->run->debug.arch.dr6 = DR6_BD | DR6_RTM | DR6_FIXED_1;
+			vcpu->run->debug.arch.dr6 = DR6_BD | DR6_ACTIVE_LOW;
 			vcpu->run->debug.arch.dr7 = dr7;
 			vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu);
 			vcpu->run->debug.arch.exception = DB_VECTOR;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 523c3bb8e9ecf1..b52b8f73562815 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -553,19 +553,24 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
 		 */
 		vcpu->arch.dr6 &= ~DR_TRAP_BITS;
 		/*
-		 * DR6.RTM is set by all #DB exceptions that don't clear it.
+		 * In order to reflect the #DB exception payload in guest
+		 * dr6, three components need to be considered: active low
+		 * bit, FIXED_1 bits and active high bits (e.g. DR6_BD,
+		 * DR6_BS and DR6_BT)
+		 * DR6_ACTIVE_LOW contains the FIXED_1 and active low bits.
+		 * In the target guest dr6:
+		 * FIXED_1 bits should always be set.
+		 * Active low bits should be cleared if 1-setting in payload.
+		 * Active high bits should be set if 1-setting in payload.
+		 *
+		 * Note, the payload is compatible with the pending debug
+		 * exceptions/exit qualification under VMX, that active_low bits
+		 * are active high in payload.
+		 * So they need to be flipped for DR6.
 		 */
-		vcpu->arch.dr6 |= DR6_RTM;
+		vcpu->arch.dr6 |= DR6_ACTIVE_LOW;
 		vcpu->arch.dr6 |= payload;
-		/*
-		 * Bit 16 should be set in the payload whenever the #DB
-		 * exception should clear DR6.RTM. This makes the payload
-		 * compatible with the pending debug exceptions under VMX.
-		 * Though not currently documented in the SDM, this also
-		 * makes the payload compatible with the exit qualification
-		 * for #DB exceptions under VMX.
-		 */
-		vcpu->arch.dr6 ^= payload & DR6_RTM;
+		vcpu->arch.dr6 ^= payload & DR6_ACTIVE_LOW;
 
 		/*
 		 * The #DB payload is defined as compatible with the 'pending
@@ -1177,6 +1182,9 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM))
 		fixed |= DR6_RTM;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
+		fixed |= DR6_BUS_LOCK;
 	return fixed;
 }
 
@@ -7332,7 +7340,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu)
 	struct kvm_run *kvm_run = vcpu->run;
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-		kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM;
+		kvm_run->debug.arch.dr6 = DR6_BS | DR6_ACTIVE_LOW;
 		kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu);
 		kvm_run->debug.arch.exception = DB_VECTOR;
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
@@ -7376,7 +7384,7 @@ static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r)
 					   vcpu->arch.eff_db);
 
 		if (dr6 != 0) {
-			kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM;
+			kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW;
 			kvm_run->debug.arch.pc = eip;
 			kvm_run->debug.arch.exception = DB_VECTOR;
 			kvm_run->exit_reason = KVM_EXIT_DEBUG;
@@ -10207,7 +10215,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
-	vcpu->arch.dr6 = DR6_INIT;
+	vcpu->arch.dr6 = DR6_ACTIVE_LOW;
 	vcpu->arch.dr7 = DR7_FIXED_1;
 	kvm_update_dr7(vcpu);