KVM: arm64: Check advertised Stage-2 page size capability

With ARMv8.5-GTG, the hardware (or more likely a hypervisor) can
advertise the supported Stage-2 page sizes.

Let's check this at boot time.

Reviewed-by: Suzuki K Poulose <[email protected]>
Reviewed-by: Alexandru Elisei <[email protected]>
Signed-off-by: Marc Zyngier <[email protected]>
Signed-off-by: Will Deacon <[email protected]>

Author: Marc Zyngier

arch/arm64/include/asm/kvm_host.h

@@ -670,7 +670,7 @@ static inline int kvm_arm_have_ssbd(void)
 void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
 
-void kvm_set_ipa_limit(void);
+int kvm_set_ipa_limit(void);
 
 #define __KVM_HAVE_ARCH_VM_ALLOC
 struct kvm *kvm_arch_alloc_vm(void);

arch/arm64/include/asm/sysreg.h

@@ -703,6 +703,9 @@
 #define ID_AA64ZFR0_SVEVER_SVE2		0x1
 
 /* id_aa64mmfr0 */
+#define ID_AA64MMFR0_TGRAN4_2_SHIFT	40
+#define ID_AA64MMFR0_TGRAN64_2_SHIFT	36
+#define ID_AA64MMFR0_TGRAN16_2_SHIFT	32
 #define ID_AA64MMFR0_TGRAN4_SHIFT	28
 #define ID_AA64MMFR0_TGRAN64_SHIFT	24
 #define ID_AA64MMFR0_TGRAN16_SHIFT	20

arch/arm64/kernel/cpufeature.c

@@ -267,6 +267,24 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
+	/*
+	 * Page size not being supported at Stage-2 is not fatal. You
+	 * just give up KVM if PAGE_SIZE isn't supported there. Go fix
+	 * your favourite nesting hypervisor.
+	 *
+	 * There is a small corner case where the hypervisor explicitly
+	 * advertises a given granule size at Stage-2 (value 2) on some
+	 * vCPUs, and uses the fallback to Stage-1 (value 0) for other
+	 * vCPUs. Although this is not forbidden by the architecture, it
+	 * indicates that the hypervisor is being silly (or buggy).
+	 *
+	 * We make no effort to cope with this and pretend that if these
+	 * fields are inconsistent across vCPUs, then it isn't worth
+	 * trying to bring KVM up.
+	 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_2_SHIFT, 4, 1),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_2_SHIFT, 4, 1),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_2_SHIFT, 4, 1),
 	/*
 	 * We already refuse to boot CPUs that don't support our configured
 	 * page size, so we can only detect mismatches for a page size other

arch/arm64/kvm/reset.c

@@ -337,14 +337,45 @@ u32 get_kvm_ipa_limit(void)
 	return kvm_ipa_limit;
 }
 
-void kvm_set_ipa_limit(void)
+int kvm_set_ipa_limit(void)
 {
-	unsigned int ipa_max, pa_max, va_max, parange;
+	unsigned int ipa_max, pa_max, va_max, parange, tgran_2;
 	u64 mmfr0;
 
 	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 	parange = cpuid_feature_extract_unsigned_field(mmfr0,
 				ID_AA64MMFR0_PARANGE_SHIFT);
+
+	/*
+	 * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
+	 * Stage-2. If not, things will stop very quickly.
+	 */
+	switch (PAGE_SIZE) {
+	default:
+	case SZ_4K:
+		tgran_2 = ID_AA64MMFR0_TGRAN4_2_SHIFT;
+		break;
+	case SZ_16K:
+		tgran_2 = ID_AA64MMFR0_TGRAN16_2_SHIFT;
+		break;
+	case SZ_64K:
+		tgran_2 = ID_AA64MMFR0_TGRAN64_2_SHIFT;
+		break;
+	}
+
+	switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
+	default:
+	case 1:
+		kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
+		return -EINVAL;
+	case 0:
+		kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
+		break;
+	case 2:
+		kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
+		break;
+	}
+
 	pa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
 
 	/* Clamp the IPA limit to the PA size supported by the kernel */
@@ -378,6 +409,8 @@ void kvm_set_ipa_limit(void)
 	     "KVM IPA limit (%d bit) is smaller than default size\n", ipa_max);
 	kvm_ipa_limit = ipa_max;
 	kvm_info("IPA Size Limit: %dbits\n", kvm_ipa_limit);
+
+	return 0;
 }
 
 /*

virt/kvm/arm/arm.c

@@ -1387,9 +1387,7 @@ static inline void hyp_cpu_pm_exit(void)
 
 static int init_common_resources(void)
 {
-	kvm_set_ipa_limit();
-
-	return 0;
+	return kvm_set_ipa_limit();
 }
 
 static int init_subsystems(void)