KVM: nVMX: Disable PMU MSR interception as appropriate while running L2

Merge KVM's PMU MSR interception bitmaps with those of L1, i.e. merge the
bitmaps of vmcs01 and vmcs12, e.g. so that KVM doesn't interpose on MSR
accesses unnecessarily if L1 exposes a mediated PMU (or equivalent) to L2.

Signed-off-by: Mingwei Zhang <mizhang@google.com>
Co-developed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
[sean: rewrite changelog and comment, omit MSRs that are always intercepted]
Tested-by: Xudong Hao <xudong.hao@intel.com>
Tested-by: Manali Shukla <manali.shukla@amd.com>
Link: https://patch.msgid.link/20251206001720.468579-32-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: mzhang3579

arch/x86/kvm/vmx/nested.c

@@ -630,6 +630,34 @@ static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx,
 #define nested_vmx_merge_msr_bitmaps_rw(msr) \
 	nested_vmx_merge_msr_bitmaps(msr, MSR_TYPE_RW)
 
+static void nested_vmx_merge_pmu_msr_bitmaps(struct kvm_vcpu *vcpu,
+					     unsigned long *msr_bitmap_l1,
+					     unsigned long *msr_bitmap_l0)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int i;
+
+	/*
+	 * Skip the merges if the vCPU doesn't have a mediated PMU MSR, i.e. if
+	 * none of the MSRs can possibly be passed through to L1.
+	 */
+	if (!kvm_vcpu_has_mediated_pmu(vcpu))
+		return;
+
+	for (i = 0; i < pmu->nr_arch_gp_counters; i++) {
+		nested_vmx_merge_msr_bitmaps_rw(MSR_IA32_PERFCTR0 + i);
+		nested_vmx_merge_msr_bitmaps_rw(MSR_IA32_PMC0 + i);
+	}
+
+	for (i = 0; i < pmu->nr_arch_fixed_counters; i++)
+		nested_vmx_merge_msr_bitmaps_rw(MSR_CORE_PERF_FIXED_CTR0 + i);
+
+	nested_vmx_merge_msr_bitmaps_rw(MSR_CORE_PERF_GLOBAL_CTRL);
+	nested_vmx_merge_msr_bitmaps_read(MSR_CORE_PERF_GLOBAL_STATUS);
+	nested_vmx_merge_msr_bitmaps_write(MSR_CORE_PERF_GLOBAL_OVF_CTRL);
+}
+
 /*
  * Merge L0's and L1's MSR bitmap, return false to indicate that
  * we do not use the hardware.
@@ -745,6 +773,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
 					 MSR_IA32_PL3_SSP, MSR_TYPE_RW);
 
+	nested_vmx_merge_pmu_msr_bitmaps(vcpu, msr_bitmap_l1, msr_bitmap_l0);
+
 	kvm_vcpu_unmap(vcpu, &map);
 
 	vmx->nested.force_msr_bitmap_recalc = false;