Received-SPF: pass (google.com: domain of linux-kernel+bounces-21506-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Reply-To: Sean Christopherson <seanjc@google.com>
Date: Tue,  9 Jan 2024 15:02:37 -0800
In-Reply-To: <20240109230250.424295-1-seanjc@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240109230250.424295-1-seanjc@google.com>
Message-ID: <20240109230250.424295-18-seanjc@google.com>
Subject: [PATCH v10 17/29] KVM: selftests: Test Intel PMU architectural events
 on fixed counters
From: Sean Christopherson <seanjc@google.com>
To: Sean Christopherson <seanjc@google.com>, Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org, 
	Kan Liang <kan.liang@linux.intel.com>, Dapeng Mi <dapeng1.mi@linux.intel.com>, 
	Jim Mattson <jmattson@google.com>, Jinrong Liang <cloudliang@tencent.com>, 
	Aaron Lewis <aaronlewis@google.com>, Like Xu <likexu@tencent.com>
Content-Type: text/plain; charset="UTF-8"

From: Jinrong Liang <cloudliang@tencent.com>

Extend the PMU counters test to validate architectural events using fixed
counters.  The core logic is largely the same, the biggest difference
being that if a fixed counter exists, its associated event is available
(the SDM doesn't explicitly state this to be true, but it's KVM's ABI and
letting software program a fixed counter that doesn't actually count would
be quite bizarre).

Note, fixed counters rely on PERF_GLOBAL_CTRL.

Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Co-developed-by: Like Xu <likexu@tencent.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Signed-off-by: Jinrong Liang <cloudliang@tencent.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86_64/pmu_counters_test.c  | 54 +++++++++++++++----
 1 file changed, 45 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
index 5b8687bb4639..663e8fbe7ff8 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
@@ -150,26 +150,46 @@ static void __guest_test_arch_event(uint8_t idx, struct kvm_x86_pmu_feature even
 	guest_assert_event_count(idx, event, pmc, pmc_msr);
 }
 
+#define X86_PMU_FEATURE_NULL						\
+({									\
+	struct kvm_x86_pmu_feature feature = {};			\
+									\
+	feature;							\
+})
+
+static bool pmu_is_null_feature(struct kvm_x86_pmu_feature event)
+{
+	return !(*(u64 *)&event);
+}
+
 static void guest_test_arch_event(uint8_t idx)
 {
 	const struct {
 		struct kvm_x86_pmu_feature gp_event;
+		struct kvm_x86_pmu_feature fixed_event;
 	} intel_event_to_feature[] = {
-		[INTEL_ARCH_CPU_CYCLES_INDEX]		 = { X86_PMU_FEATURE_CPU_CYCLES },
-		[INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX]	 = { X86_PMU_FEATURE_INSNS_RETIRED },
-		[INTEL_ARCH_REFERENCE_CYCLES_INDEX]	 = { X86_PMU_FEATURE_REFERENCE_CYCLES },
-		[INTEL_ARCH_LLC_REFERENCES_INDEX]	 = { X86_PMU_FEATURE_LLC_REFERENCES },
-		[INTEL_ARCH_LLC_MISSES_INDEX]		 = { X86_PMU_FEATURE_LLC_MISSES },
-		[INTEL_ARCH_BRANCHES_RETIRED_INDEX]	 = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED },
-		[INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED },
-		[INTEL_ARCH_TOPDOWN_SLOTS_INDEX]	 = { X86_PMU_FEATURE_TOPDOWN_SLOTS },
+		[INTEL_ARCH_CPU_CYCLES_INDEX]		 = { X86_PMU_FEATURE_CPU_CYCLES, X86_PMU_FEATURE_CPU_CYCLES_FIXED },
+		[INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX]	 = { X86_PMU_FEATURE_INSNS_RETIRED, X86_PMU_FEATURE_INSNS_RETIRED_FIXED },
+		/*
+		 * Note, the fixed counter for reference cycles is NOT the same
+		 * as the general purpose architectural event.  The fixed counter
+		 * explicitly counts at the same frequency as the TSC, whereas
+		 * the GP event counts at a fixed, but uarch specific, frequency.
+		 * Bundle them here for simplicity.
+		 */
+		[INTEL_ARCH_REFERENCE_CYCLES_INDEX]	 = { X86_PMU_FEATURE_REFERENCE_CYCLES, X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED },
+		[INTEL_ARCH_LLC_REFERENCES_INDEX]	 = { X86_PMU_FEATURE_LLC_REFERENCES, X86_PMU_FEATURE_NULL },
+		[INTEL_ARCH_LLC_MISSES_INDEX]		 = { X86_PMU_FEATURE_LLC_MISSES, X86_PMU_FEATURE_NULL },
+		[INTEL_ARCH_BRANCHES_RETIRED_INDEX]	 = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED, X86_PMU_FEATURE_NULL },
+		[INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED, X86_PMU_FEATURE_NULL },
+		[INTEL_ARCH_TOPDOWN_SLOTS_INDEX]	 = { X86_PMU_FEATURE_TOPDOWN_SLOTS, X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED },
 	};
 
 	uint32_t nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
 	uint32_t pmu_version = guest_get_pmu_version();
 	/* PERF_GLOBAL_CTRL exists only for Architectural PMU Version 2+. */
 	bool guest_has_perf_global_ctrl = pmu_version >= 2;
-	struct kvm_x86_pmu_feature gp_event;
+	struct kvm_x86_pmu_feature gp_event, fixed_event;
 	uint32_t base_pmc_msr;
 	unsigned int i;
 
@@ -199,6 +219,22 @@ static void guest_test_arch_event(uint8_t idx)
 		__guest_test_arch_event(idx, gp_event, i, base_pmc_msr + i,
 					MSR_P6_EVNTSEL0 + i, eventsel);
 	}
+
+	if (!guest_has_perf_global_ctrl)
+		return;
+
+	fixed_event = intel_event_to_feature[idx].fixed_event;
+	if (pmu_is_null_feature(fixed_event) || !this_pmu_has(fixed_event))
+		return;
+
+	i = fixed_event.f.bit;
+
+	wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL));
+
+	__guest_test_arch_event(idx, fixed_event, i | INTEL_RDPMC_FIXED,
+				MSR_CORE_PERF_FIXED_CTR0 + i,
+				MSR_CORE_PERF_GLOBAL_CTRL,
+				FIXED_PMC_GLOBAL_CTRL_ENABLE(i));
 }
 
 static void guest_test_arch_events(void)
-- 
2.43.0.472.g3155946c3a-goog