[PATCH v7 07/12] KVM: x86/pmu: Disable vPMU if the minimum num of counters isn't met

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,
	Like Xu <like.xu.linux@gmail.com>, Like Xu <likexu@tencent.com>,
	Jim Mattson <jmattson@google.com>,
	Sandipan Das <sandipan.das@amd.com>
Subject: [PATCH v7 07/12] KVM: x86/pmu: Disable vPMU if the minimum num of counters isn't met
Date: Fri,  2 Jun 2023 18:10:53 -0700	[thread overview]
Message-ID: <20230603011058.1038821-8-seanjc@google.com> (raw)
In-Reply-To: <20230603011058.1038821-1-seanjc@google.com>

From: Like Xu <likexu@tencent.com>

Disable PMU support when running on AMD and perf reports fewer than four
general purpose counters. All AMD PMUs must define at least four counters
due to AMD's legacy architecture hardcoding the number of counters
without providing a way to enumerate the number of counters to software,
e.g. from AMD's APM:

 The legacy architecture defines four performance counters (PerfCtrn)
 and corresponding event-select registers (PerfEvtSeln).

Virtualizing fewer than four counters can lead to guest instability as
software expects four counters to be available. Rather than bleed AMD
details into the common code, just define a const unsigned int and
provide a convenient location to document why Intel and AMD have different
mins (in particular, AMD's lack of any way to enumerate less than four
counters to the guest).

Keep the minimum number of counters at Intel at one, even though old P6
and Core Solo/Duo processor effectively require a minimum of two counters.
KVM can, and more importantly has up until this point, supported a vPMU so
long as the CPU has at least one counter.  Perf's support for P6/Core CPUs
does require two counters, but perf will happily chug along with a single
counter when running on a modern CPU.

Cc: Jim Mattson <jmattson@google.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Like Xu <likexu@tencent.com>
[sean: set Intel min to '1', not '2']
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/pmu.h           | 14 ++++++++++----
 arch/x86/kvm/svm/pmu.c       |  1 +
 arch/x86/kvm/vmx/pmu_intel.c |  1 +
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index f77bfc7ede42..7d9ba301c090 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -36,6 +36,7 @@ struct kvm_pmu_ops {
 
 	const u64 EVENTSEL_EVENT;
 	const int MAX_NR_GP_COUNTERS;
+	const int MIN_NR_GP_COUNTERS;
 };
 
 void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops);
@@ -174,6 +175,7 @@ extern struct x86_pmu_capability kvm_pmu_cap;
 static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops)
 {
 	bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL;
+	int min_nr_gp_ctrs = pmu_ops->MIN_NR_GP_COUNTERS;
 
 	/*
 	 * Hybrid PMUs don't play nice with virtualization without careful
@@ -188,11 +190,15 @@ static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops)
 		perf_get_x86_pmu_capability(&kvm_pmu_cap);
 
 		/*
-		 * For Intel, only support guest architectural pmu
-		 * on a host with architectural pmu.
+		 * WARN if perf did NOT disable hardware PMU if the number of
+		 * architecturally required GP counters aren't present, i.e. if
+		 * there are a non-zero number of counters, but fewer than what
+		 * is architecturally required.
 		 */
-		if ((is_intel && !kvm_pmu_cap.version) ||
-		    !kvm_pmu_cap.num_counters_gp)
+		if (!kvm_pmu_cap.num_counters_gp ||
+		    WARN_ON_ONCE(kvm_pmu_cap.num_counters_gp < min_nr_gp_ctrs))
+			enable_pmu = false;
+		else if (is_intel && !kvm_pmu_cap.version)
 			enable_pmu = false;
 	}
 
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 70143275e0a7..e5c69062a909 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -224,4 +224,5 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = {
 	.reset = amd_pmu_reset,
 	.EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT,
 	.MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC,
+	.MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS,
 };
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index b2f279f934b1..30ec9ccdea47 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -777,4 +777,5 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = {
 	.cleanup = intel_pmu_cleanup,
 	.EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT,
 	.MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC,
+	.MIN_NR_GP_COUNTERS = 1,
 };
-- 
2.41.0.rc2.161.g9c6817b8e7-goog

