Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Jinrong Liang <ljr.kernel@gmail.com>
To:     Sean Christopherson <seanjc@google.com>
Cc:     Paolo Bonzini <pbonzini@redhat.com>, Like Xu <likexu@tencent.com>,
        David Matlack <dmatlack@google.com>,
        Aaron Lewis <aaronlewis@google.com>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jinrong Liang <cloudliang@tencent.com>, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH v3 11/11] KVM: selftests: Test AMD Guest PerfMonV2
Date:   Mon, 14 Aug 2023 19:51:08 +0800
Message-Id: <20230814115108.45741-12-cloudliang@tencent.com>
In-Reply-To: <20230814115108.45741-1-cloudliang@tencent.com>
References: <20230814115108.45741-1-cloudliang@tencent.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Jinrong Liang <cloudliang@tencent.com>

Add test case for AMD Guest PerfMonV2. Also test Intel
MSR_CORE_PERF_GLOBAL_STATUS and MSR_CORE_PERF_GLOBAL_OVF_CTRL.

Signed-off-by: Jinrong Liang <cloudliang@tencent.com>
---
 .../kvm/x86_64/pmu_basic_functionality_test.c | 48 ++++++++++++++++++-
 1 file changed, 46 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/pmu_basic_functionality_test.c b/tools/testing/selftests/kvm/x86_64/pmu_basic_functionality_test.c
index cb2a7ad5c504..02bd1fe3900b 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_basic_functionality_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_basic_functionality_test.c
@@ -58,7 +58,9 @@ static uint64_t run_vcpu(struct kvm_vcpu *vcpu, uint64_t *ucall_arg)
 
 static void guest_measure_loop(uint64_t event_code)
 {
+	uint64_t global_ovf_ctrl_msr, global_status_msr, global_ctrl_msr;
 	uint8_t nr_gp_counters, pmu_version = 1;
+	uint8_t gp_counter_bit_width = 48;
 	uint64_t event_sel_msr;
 	uint32_t counter_msr;
 	unsigned int i;
@@ -68,6 +70,12 @@ static void guest_measure_loop(uint64_t event_code)
 		pmu_version = this_cpu_property(X86_PROPERTY_PMU_VERSION);
 		event_sel_msr = MSR_P6_EVNTSEL0;
 
+		if (pmu_version > 1) {
+			global_ovf_ctrl_msr = MSR_CORE_PERF_GLOBAL_OVF_CTRL;
+			global_status_msr = MSR_CORE_PERF_GLOBAL_STATUS;
+			global_ctrl_msr = MSR_CORE_PERF_GLOBAL_CTRL;
+		}
+
 		if (rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES)
 			counter_msr = MSR_IA32_PMC0;
 		else
@@ -76,6 +84,17 @@ static void guest_measure_loop(uint64_t event_code)
 		nr_gp_counters = AMD64_NR_COUNTERS;
 		event_sel_msr = MSR_K7_EVNTSEL0;
 		counter_msr = MSR_K7_PERFCTR0;
+
+		if (this_cpu_has(X86_FEATURE_AMD_PMU_EXT_CORE) &&
+		    this_cpu_has(X86_FEATURE_AMD_PERFMON_V2)) {
+			nr_gp_counters = this_cpu_property(X86_PROPERTY_AMD_PMU_NR_CORE_COUNTERS);
+			global_ovf_ctrl_msr = MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR;
+			global_status_msr = MSR_AMD64_PERF_CNTR_GLOBAL_STATUS;
+			global_ctrl_msr = MSR_AMD64_PERF_CNTR_GLOBAL_CTL;
+			event_sel_msr = MSR_F15H_PERF_CTL0;
+			counter_msr = MSR_F15H_PERF_CTR0;
+			pmu_version = 2;
+		}
 	}
 
 	for (i = 0; i < nr_gp_counters; i++) {
@@ -84,14 +103,39 @@ static void guest_measure_loop(uint64_t event_code)
 		      ARCH_PERFMON_EVENTSEL_ENABLE | event_code);
 
 		if (pmu_version > 1) {
-			wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, BIT_ULL(i));
+			wrmsr(global_ctrl_msr, BIT_ULL(i));
 			__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
-			wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+			wrmsr(global_ctrl_msr, 0);
 			GUEST_SYNC(_rdpmc(i));
 		} else {
 			__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
 			GUEST_SYNC(_rdpmc(i));
 		}
+
+		if (pmu_version > 1 && _rdpmc(i)) {
+			wrmsr(global_ctrl_msr, 0);
+			wrmsr(counter_msr + i, 0);
+			__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+			GUEST_ASSERT(!_rdpmc(i));
+
+			wrmsr(global_ctrl_msr, BIT_ULL(i));
+			__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+			GUEST_ASSERT(_rdpmc(i));
+
+			if (host_cpu_is_intel)
+				gp_counter_bit_width =
+					this_cpu_property(X86_PROPERTY_PMU_GP_COUNTERS_BIT_WIDTH);
+
+			wrmsr(global_ctrl_msr, 0);
+			wrmsr(counter_msr + i, (1ULL << gp_counter_bit_width) - 2);
+			wrmsr(global_ctrl_msr, BIT_ULL(i));
+			__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+			GUEST_ASSERT(rdmsr(global_status_msr) & BIT_ULL(i));
+
+			wrmsr(global_ctrl_msr, 0);
+			wrmsr(global_ovf_ctrl_msr, BIT_ULL(i));
+			GUEST_ASSERT(!(rdmsr(global_status_msr) & BIT_ULL(i)));
+		}
 	}
 
 	if (host_cpu_is_amd || pmu_version < 2)
-- 
2.39.3