KVM: x86/pmu: Apply "fast" RDPMC only to Intel PMUs

Move the handling of "fast" RDPMC instructions, which drop bits 63:32 of
the count, to Intel.  The "fast" flag, and all modifiers for that matter,
are Intel-only and aren't supported by AMD.

Opportunistically replace open coded bit crud with proper #defines, and
add comments to try and disentangle the flags vs. values mess for
non-architectural vs. architectural PMUs.

Fixes: ca72430 ("KVM: x86/vPMU: Implement AMD vPMU code for KVM")
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20240109230250.424295-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: sean-jc

arch/x86/kvm/pmu.c

@@ -576,10 +576,9 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 {
-	bool fast_mode = idx & (1u << 31);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
-	u64 mask = fast_mode ? ~0u : ~0ull;
+	u64 mask = ~0ull;
 
 	if (!pmu->version)
 		return 1;

arch/x86/kvm/vmx/pmu_intel.c

@@ -20,6 +20,15 @@
 #include "nested.h"
 #include "pmu.h"
 
+/*
+ * Perf's "BASE" is wildly misleading, architectural PMUs use bits 31:16 of ECX
+ * to encode the "type" of counter to read, i.e. this is not a "base".  And to
+ * further confuse things, non-architectural PMUs use bit 31 as a flag for
+ * "fast" reads, whereas the "type" is an explicit value.
+ */
+#define INTEL_RDPMC_FIXED	INTEL_PMC_FIXED_RDPMC_BASE
+#define INTEL_RDPMC_FAST	BIT(31)
+
 #define MSR_PMC_FULL_WIDTH_BIT      (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
 
 static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
@@ -59,11 +68,14 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 					    unsigned int idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	bool fixed = idx & (1u << 30);
+	bool fixed = idx & INTEL_RDPMC_FIXED;
 	struct kvm_pmc *counters;
 	unsigned int num_counters;
 
-	idx &= ~(3u << 30);
+	if (idx & INTEL_RDPMC_FAST)
+		*mask &= GENMASK_ULL(31, 0);
+
+	idx &= ~(INTEL_RDPMC_FIXED | INTEL_RDPMC_FAST);
 	if (fixed) {
 		counters = pmu->fixed_counters;
 		num_counters = pmu->nr_arch_fixed_counters;