@@ -1600,13 +1600,14 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
val = sanitise_id_aa64pfr0_el1(vcpu, val);
break;
case SYS_ID_AA64PFR1_EL1:
- if (!kvm_has_mte(vcpu->kvm))
+ if (!kvm_has_mte(vcpu->kvm)) {
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
+ }
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
- val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
@@ -1953,11 +1954,32 @@ static int set_id_aa64pfr1_el1(struct kvm_vcpu *vcpu,
{
u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
u64 mpam_mask = ID_AA64PFR1_EL1_MPAM_frac_MASK;
+ u8 mte = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE, hw_val);
+ u8 user_mte_frac = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE_frac, user_val);
/* See set_id_aa64pfr0_el1 for comment about MPAM */
if ((hw_val & mpam_mask) == (user_val & mpam_mask))
user_val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK;
+ /*
+ * Previously MTE_frac was hidden from guest. However, if the
+ * hardware supports MTE2 but not MTE_ASYM_FAULT then a value
+ * of 0 for this field indicates that the hardware supports
+ * MTE_ASYNC. Whereas, 0xf indicates MTE_ASYNC is not supported.
+ *
+ * As KVM must accept values from KVM provided by user-space,
+ * when ID_AA64PFR1_EL1.MTE is 2 allow user-space to set
+ * ID_AA64PFR1_EL1.MTE_frac to 0. However, ignore it to avoid
+ * incorrectly claiming hardware support for MTE_ASYNC in the
+ * guest.
+ */
+
+ if (mte == ID_AA64PFR1_EL1_MTE_MTE2 &&
+ user_mte_frac == ID_AA64PFR1_EL1_MTE_frac_ASYNC) {
+ user_val &= ~ID_AA64PFR1_EL1_MTE_frac_MASK;
+ user_val |= hw_val & ID_AA64PFR1_EL1_MTE_frac_MASK;
+ }
+
return set_id_reg(vcpu, rd, user_val);
}
If MTE_frac is masked out unconditionally then the guest will always see ID_AA64PFR1_EL1_MTE_frac as 0. However, a value of 0 when ID_AA64PFR1_EL1_MTE is 2 indicates that MTE_ASYNC is supported. Hence, for a host with ID_AA64PFR1_EL1_MTE==2 and ID_AA64PFR1_EL1_MTE_frac==0xf (MTE_ASYNC unsupported) the guest would see MTE_ASYNC advertised as supported whilst the host does not support it. Hence, expose the sanitised value of MTE_frac to the guest and user-space. As MTE_frac was previously hidden, always 0, and KVM must accept values from KVM provided by user-space, when ID_AA64PFR1_EL1.MTE is 2 allow user-space to set ID_AA64PFR1_EL1.MTE_frac to 0. However, ignore it to avoid incorrectly claiming hardware support for MTE_ASYNC in the guest. Note that linux does not check the value of ID_AA64PFR1_EL1_MTE_frac and wrongly assumes that MTE async faults can be generated even on hardware that does nto support them. This issue is not addressed here. Signed-off-by: Ben Horgan <ben.horgan@arm.com> --- arch/arm64/kvm/sys_regs.c | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-)