arm64: kvm: Use cpus_have_final_cap() explicitly

Much of the arm64 KVM code uses cpus_have_const_cap() to check for
cpucaps, but this is unnecessary and it would be preferable to use
cpus_have_final_cap().

For historical reasons, cpus_have_const_cap() is more complicated than
it needs to be. Before cpucaps are finalized, it will perform a bitmap
test of the system_cpucaps bitmap, and once cpucaps are finalized it
will use an alternative branch. This used to be necessary to handle some
race conditions in the window between cpucap detection and the
subsequent patching of alternatives and static branches, where different
branches could be out-of-sync with one another (or w.r.t. alternative
sequences). Now that we use alternative branches instead of static
branches, these are all patched atomically w.r.t. one another, and there
are only a handful of cases that need special care in the window between
cpucap detection and alternative patching.

Due to the above, it would be nice to remove cpus_have_const_cap(), and
migrate callers over to alternative_has_cap_*(), cpus_have_final_cap(),
or cpus_have_cap() depending on when their requirements. This will
remove redundant instructions and improve code generation, and will make
it easier to determine how each callsite will behave before, during, and
after alternative patching.

KVM is initialized after cpucaps have been finalized and alternatives
have been patched. Since commit:

  d86de40dec ("arm64: cpufeature: upgrade hyp caps to final")

... use of cpus_have_const_cap() in hyp code is automatically converted
to use cpus_have_final_cap():

| static __always_inline bool cpus_have_const_cap(int num)
| {
| 	if (is_hyp_code())
| 		return cpus_have_final_cap(num);
| 	else if (system_capabilities_finalized())
| 		return __cpus_have_const_cap(num);
| 	else
| 		return cpus_have_cap(num);
| }

Thus, converting hyp code to use cpus_have_final_cap() directly will not
result in any functional change.

Non-hyp KVM code is also not executed until cpucaps have been finalized,
and it would be preferable to extent the same treatment to this code and
use cpus_have_final_cap() directly.

This patch converts instances of cpus_have_const_cap() in KVM-only code
over to cpus_have_final_cap(). As all of this code runs after cpucaps
have been finalized, there should be no functional change as a result of
this patch, but the redundant instructions generated by
cpus_have_const_cap() will be removed from the non-hyp KVM code.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/kvm_emulate.h

@@ -71,14 +71,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
 	if (has_vhe() || has_hvhe())
 		vcpu->arch.hcr_el2 |= HCR_E2H;
-	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) {
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) {
 		/* route synchronous external abort exceptions to EL2 */
 		vcpu->arch.hcr_el2 |= HCR_TEA;
 		/* trap error record accesses */
 		vcpu->arch.hcr_el2 |= HCR_TERR;
 	}
 
-	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
+	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) {
 		vcpu->arch.hcr_el2 |= HCR_FWB;
 	} else {
 		/*

arch/arm64/include/asm/kvm_host.h

@@ -1052,7 +1052,7 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
 
 static inline bool kvm_system_needs_idmapped_vectors(void)
 {
-	return cpus_have_const_cap(ARM64_SPECTRE_V3A);
+	return cpus_have_final_cap(ARM64_SPECTRE_V3A);
 }
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}

arch/arm64/include/asm/kvm_mmu.h

@@ -218,7 +218,7 @@ static inline void __clean_dcache_guest_page(void *va, size_t size)
 	 * faulting in pages. Furthermore, FWB implies IDC, so cleaning to
 	 * PoU is not required either in this case.
 	 */
-	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
 		return;
 
 	kvm_flush_dcache_to_poc(va, size);

arch/arm64/kvm/arm.c

@@ -284,7 +284,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_arm_pvtime_supported();
 		break;
 	case KVM_CAP_ARM_EL1_32BIT:
-		r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1);
+		r = cpus_have_final_cap(ARM64_HAS_32BIT_EL1);
 		break;
 	case KVM_CAP_GUEST_DEBUG_HW_BPS:
 		r = get_num_brps();
@@ -296,7 +296,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_arm_support_pmu_v3();
 		break;
 	case KVM_CAP_ARM_INJECT_SERROR_ESR:
-		r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN);
+		r = cpus_have_final_cap(ARM64_HAS_RAS_EXTN);
 		break;
 	case KVM_CAP_ARM_VM_IPA_SIZE:
 		r = get_kvm_ipa_limit();
@@ -1207,7 +1207,7 @@ static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu,
 	if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features))
 		return 0;
 
-	if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
+	if (!cpus_have_final_cap(ARM64_HAS_32BIT_EL1))
 		return -EINVAL;
 
 	/* MTE is incompatible with AArch32 */
@@ -1777,7 +1777,7 @@ static void hyp_install_host_vector(void)
 	 * Call initialization code, and switch to the full blown HYP code.
 	 * If the cpucaps haven't been finalized yet, something has gone very
 	 * wrong, and hyp will crash and burn when it uses any
-	 * cpus_have_const_cap() wrapper.
+	 * cpus_have_*_cap() wrapper.
 	 */
 	BUG_ON(!system_capabilities_finalized());
 	params = this_cpu_ptr_nvhe_sym(kvm_init_params);
@@ -2310,7 +2310,7 @@ static int __init init_hyp_mode(void)
 
 	if (is_protected_kvm_enabled()) {
 		if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) &&
-		    cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH))
+		    cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH))
 			pkvm_hyp_init_ptrauth();
 
 		init_cpu_logical_map();

arch/arm64/kvm/guest.c

@@ -815,7 +815,7 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events)
 {
 	events->exception.serror_pending = !!(vcpu->arch.hcr_el2 & HCR_VSE);
-	events->exception.serror_has_esr = cpus_have_const_cap(ARM64_HAS_RAS_EXTN);
+	events->exception.serror_has_esr = cpus_have_final_cap(ARM64_HAS_RAS_EXTN);
 
 	if (events->exception.serror_pending && events->exception.serror_has_esr)
 		events->exception.serror_esr = vcpu_get_vsesr(vcpu);
@@ -837,7 +837,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 	bool ext_dabt_pending = events->exception.ext_dabt_pending;
 
 	if (serror_pending && has_esr) {
-		if (!cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+		if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 			return -EINVAL;
 
 		if (!((events->exception.serror_esr) & ~ESR_ELx_ISS_MASK))

arch/arm64/kvm/hyp/pgtable.c

@@ -664,7 +664,7 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 
 static bool stage2_has_fwb(struct kvm_pgtable *pgt)
 {
-	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+	if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
 		return false;
 
 	return !(pgt->flags & KVM_PGTABLE_S2_NOFWB);

arch/arm64/kvm/mmu.c

@@ -1578,7 +1578,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	if (device)
 		prot |= KVM_PGTABLE_PROT_DEVICE;
-	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+	else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC))
 		prot |= KVM_PGTABLE_PROT_X;
 
 	/*

arch/arm64/kvm/sys_regs.c

@@ -207,7 +207,7 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
 	 * CPU left in the system, and certainly not from non-secure
 	 * software).
 	 */
-	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+	if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
 		kvm_set_way_flush(vcpu);
 
 	return true;

arch/arm64/kvm/vgic/vgic-v3.c

@@ -684,7 +684,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	if (kvm_vgic_global_state.vcpu_base == 0)
 		kvm_info("disabling GICv2 emulation\n");
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_30115)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_30115)) {
 		group0_trap = true;
 		group1_trap = true;
 	}