KVM: arm64: nv: Advertise support for FEAT_HPMN0

Everything is in place now for KVM to actually handle MDCR_EL2.HPMN. Not
only that, the emulation is capable of doing FEAT_HPMN0. Advertise
support for the feature in the VM's ID registers. It is possible to
emulate FEAT_HPMN0 on hardware that doesn't support it since KVM
currently traps all PMU registers. Having said that, let's only
advertise the feature on supporting hardware in case KVM ever provides
'direct' PMU support to VMs w/o involving host perf.

Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20241025182354.3364124-12-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 676e2de..2cbd8ac 100644 (file)
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -917,12 +917,13 @@ static void limit_nv_id_regs(struct kvm *kvm)
                                  ID_AA64MMFR4_EL1_E2H0_NI_NV1);
        kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR4_EL1, val);
 
-       /* Only limited support for PMU, Debug, BPs and WPs */
+       /* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */
        val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1);
        val &= (NV_FTR(DFR0, PMUVer)    |
                NV_FTR(DFR0, WRPs)      |
                NV_FTR(DFR0, BRPs)      |
-               NV_FTR(DFR0, DebugVer));
+               NV_FTR(DFR0, DebugVer)  |
+               NV_FTR(DFR0, HPMN0));
 
        /* Cap Debug to ARMv8.1 */
        tmp = FIELD_GET(NV_FTR(DFR0, DebugVer), val);