[PATCH RFC 3/3] KVM: x86/pmu: Add Intel Guest Branch Trace Store Support

[Like Xu]

From: Like Xu <likexu@xxxxxxxxxxx>

The processor supports the Branch Trace Store facility (BTS) if it has DS
buffer and the MISC_ENABLE_BTS_UNAVAIL (RO) bit is cleared. The processor
can supports the CPL-qualified branch trace mechanism (DSCPL) if
CPUID.01H:ECX[bit 4] = 1.

To support guest BTS, we need expose three IA32_DEBUGCTL bits to the guest:
The TR bit makes processor to send the branch record out on the system bus
as a branch trace message (BTM) when it detects a taken branch, interrupt,
or exception. The BTS bit makes processor to log BTMs to a memory-resident
BTS buffer that is part of the DS save area. The BTINT bit makes processor
generates an interrupt when the BTS buffer is full.

A simple perf test case could be:
	perf record --per-thread -e intel_bts// ./workload
and a valid sample looks like:
	branches:            401243 cmp_end+0x0 (./workload)
			=> ffffffffb6e01410 asm_exc_nmi+0x0 ([kernel.kallsyms])

Signed-off-by: Like Xu <likexu@xxxxxxxxxxx>
---
 arch/x86/events/intel/bts.c     |  2 ++
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/pmu.h              |  3 +++
 arch/x86/kvm/vmx/capabilities.h |  7 +++++++
 arch/x86/kvm/vmx/vmx.c          | 32 ++++++++++++++++++++++++++++----
 5 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index ffdcde5b97b1..32a7bfe24deb 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -463,6 +463,8 @@ int intel_bts_interrupt(void)
 	 */
 	if (ds && (ds->bts_index >= ds->bts_interrupt_threshold))
 		handled = 1;
+	else if (perf_guest_state() && perf_handle_guest_intr(GUEST_INTEL_BTS))
+		return 1;
 
 	/*
 	 * this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 166a77a61f2d..3b0116340399 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1663,6 +1663,7 @@ struct kvm_x86_nested_ops {
 
 enum {
 	GUEST_INTEL_PT = 0,
+	GUEST_INTEL_BTS,
 	GUEST_INVALID
 };
 
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 889d064d5ddd..bd3eb5339376 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -11,6 +11,9 @@
 #define MSR_IA32_MISC_ENABLE_PMU_RO_MASK (MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL |	\
 					  MSR_IA32_MISC_ENABLE_BTS_UNAVAIL)
 
+#define DEBUGCTLMSR_BTS_MASK		(DEBUGCTLMSR_TR | DEBUGCTLMSR_BTS | DEBUGCTLMSR_BTINT)
+#define DEBUGCTLMSR_DSCPL_MASK		(DEBUGCTLMSR_BTS_OFF_OS | DEBUGCTLMSR_BTS_OFF_USR)
+
 /* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */
 #define fixed_ctrl_field(ctrl_reg, idx) (((ctrl_reg) >> ((idx)*4)) & 0xf)
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 4dc4bbe18821..cd3b97528ab0 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -435,6 +435,13 @@ static inline u64 vmx_supported_debugctl(void)
 	if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
 		debugctl |= DEBUGCTLMSR_LBR_MASK;
 
+	if (vmx_pebs_supported() && boot_cpu_has(X86_FEATURE_BTS)) {
+		debugctl |= DEBUGCTLMSR_BTS_MASK;
+		/* CPL-Qualified Branch Trace Mechanism */
+		if (boot_cpu_has(X86_FEATURE_DSCPL))
+			debugctl |= DEBUGCTLMSR_DSCPL_MASK;
+	}
+
 	return debugctl;
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3622323d57c2..cd396ca3c001 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2016,6 +2016,13 @@ static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
 		debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
 
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_DS) ||
+	    (vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_BTS_UNAVAIL)) {
+		debugctl &= ~(DEBUGCTLMSR_BTS_MASK | DEBUGCTLMSR_DSCPL_MASK);
+	} else if (!guest_cpuid_has(vcpu, X86_FEATURE_DSCPL)) {
+		debugctl &= ~DEBUGCTLMSR_DSCPL_MASK;
+	}
+
 	return debugctl;
 }
 
@@ -7691,6 +7698,8 @@ static __init void vmx_set_cpu_caps(void)
 	if (vmx_pebs_supported()) {
 		kvm_cpu_cap_check_and_set(X86_FEATURE_DS);
 		kvm_cpu_cap_check_and_set(X86_FEATURE_DTES64);
+		if (kvm_cpu_cap_has(X86_FEATURE_DS))
+			kvm_cpu_cap_check_and_set(X86_FEATURE_DSCPL);
 	}
 
 	if (!enable_pmu)
@@ -8149,6 +8158,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 static unsigned int vmx_handle_guest_intr(unsigned int vector)
 {
 	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+	u64 data;
 
 	/* '0' on failure so that the !PT case can use a RET0 static call. */
 	if (!vcpu || !kvm_handling_nmi_from_guest(vcpu))
@@ -8157,10 +8167,24 @@ static unsigned int vmx_handle_guest_intr(unsigned int vector)
 	if (vector >= GUEST_INVALID)
 		return 0;
 
-	kvm_make_request(KVM_REQ_PMI, vcpu);
-	__set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT,
-		  (unsigned long *)&vcpu->arch.pmu.global_status);
-	return 1;
+	switch (vector) {
+	case GUEST_INTEL_PT:
+		__set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT,
+			  (unsigned long *)&vcpu->arch.pmu.global_status);
+		kvm_make_request(KVM_REQ_PMI, vcpu);
+		return 1;
+	case GUEST_INTEL_BTS:
+		data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+		if ((data & DEBUGCTLMSR_BTS_MASK) == DEBUGCTLMSR_BTS_MASK) {
+			kvm_make_request(KVM_REQ_PMI, vcpu);
+			return 1;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
 }
 
 static __init void vmx_setup_user_return_msrs(void)
-- 
2.37.3