19 files changed, 190 insertions, 108 deletions

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 5c8ee5a541d2..4b6d2d52053e 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -6,5 +6,5 @@ generic-y += qspinlock.h
 generic-y += parport.h
 generic-y += user.h
 
-generated-y += cpucaps.h
+generated-y += cpucap-defs.h
 generated-y += sysreg-defs.h
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 94b486192e1f..210bb43cff2c 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -226,8 +226,8 @@ alternative_endif
 static __always_inline bool
 alternative_has_cap_likely(const unsigned long cpucap)
 {
-	compiletime_assert(cpucap < ARM64_NCAPS,
-			   "cpucap must be < ARM64_NCAPS");
+	if (!cpucap_is_possible(cpucap))
+		return false;
 
 	asm_volatile_goto(
 	ALTERNATIVE_CB("b	%l[l_no]", %[cpucap], alt_cb_patch_nops)
@@ -244,8 +244,8 @@ l_no:
 static __always_inline bool
 alternative_has_cap_unlikely(const unsigned long cpucap)
 {
-	compiletime_assert(cpucap < ARM64_NCAPS,
-			   "cpucap must be < ARM64_NCAPS");
+	if (!cpucap_is_possible(cpucap))
+		return false;
 
 	asm_volatile_goto(
 	ALTERNATIVE("nop", "b	%l[l_yes]", %[cpucap])
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 01281a5336cf..5f172611654b 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -79,6 +79,14 @@ static inline u64 gic_read_iar_cavium_thunderx(void)
 	return 0x3ff;
 }
 
+static u64 __maybe_unused gic_read_iar(void)
+{
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_CAVIUM_23154))
+		return gic_read_iar_cavium_thunderx();
+	else
+		return gic_read_iar_common();
+}
+
 static inline void gic_write_ctlr(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_CTLR_EL1);
diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h
index b0abc64f86b0..ecdb3cfcd0f8 100644
--- a/arch/arm64/include/asm/archrandom.h
+++ b/arch/arm64/include/asm/archrandom.h
@@ -63,7 +63,7 @@ static __always_inline bool __cpu_has_rng(void)
 {
 	if (unlikely(!system_capabilities_finalized() && !preemptible()))
 		return this_cpu_has_cap(ARM64_HAS_RNG);
-	return cpus_have_const_cap(ARM64_HAS_RNG);
+	return alternative_has_cap_unlikely(ARM64_HAS_RNG);
 }
 
 static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index d115451ed263..fefac75fa009 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -132,7 +132,7 @@ void flush_dcache_folio(struct folio *);
 
 static __always_inline void icache_inval_all_pou(void)
 {
-	if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+	if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC))
 		return;
 
 	asm("ic	ialluis");
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
new file mode 100644
index 000000000000..270680e2b5c4
--- /dev/null
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CPUCAPS_H
+#define __ASM_CPUCAPS_H
+
+#include <asm/cpucap-defs.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+/*
+ * Check whether a cpucap is possible at compiletime.
+ */
+static __always_inline bool
+cpucap_is_possible(const unsigned int cap)
+{
+	compiletime_assert(__builtin_constant_p(cap),
+			   "cap must be a constant");
+	compiletime_assert(cap < ARM64_NCAPS,
+			   "cap must be < ARM64_NCAPS");
+
+	switch (cap) {
+	case ARM64_HAS_PAN:
+		return IS_ENABLED(CONFIG_ARM64_PAN);
+	case ARM64_HAS_EPAN:
+		return IS_ENABLED(CONFIG_ARM64_EPAN);
+	case ARM64_SVE:
+		return IS_ENABLED(CONFIG_ARM64_SVE);
+	case ARM64_SME:
+	case ARM64_SME2:
+	case ARM64_SME_FA64:
+		return IS_ENABLED(CONFIG_ARM64_SME);
+	case ARM64_HAS_CNP:
+		return IS_ENABLED(CONFIG_ARM64_CNP);
+	case ARM64_HAS_ADDRESS_AUTH:
+	case ARM64_HAS_GENERIC_AUTH:
+		return IS_ENABLED(CONFIG_ARM64_PTR_AUTH);
+	case ARM64_HAS_GIC_PRIO_MASKING:
+		return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI);
+	case ARM64_MTE:
+		return IS_ENABLED(CONFIG_ARM64_MTE);
+	case ARM64_BTI:
+		return IS_ENABLED(CONFIG_ARM64_BTI);
+	case ARM64_HAS_TLB_RANGE:
+		return IS_ENABLED(CONFIG_ARM64_TLB_RANGE);
+	case ARM64_UNMAP_KERNEL_AT_EL0:
+		return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0);
+	case ARM64_WORKAROUND_843419:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419);
+	case ARM64_WORKAROUND_1742098:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_1742098);
+	case ARM64_WORKAROUND_2645198:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198);
+	case ARM64_WORKAROUND_2658417:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_2658417);
+	case ARM64_WORKAROUND_CAVIUM_23154:
+		return IS_ENABLED(CONFIG_CAVIUM_ERRATUM_23154);
+	case ARM64_WORKAROUND_NVIDIA_CARMEL_CNP:
+		return IS_ENABLED(CONFIG_NVIDIA_CARMEL_CNP_ERRATUM);
+	case ARM64_WORKAROUND_REPEAT_TLBI:
+		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI);
+	}
+
+	return true;
+}
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 19b4d001d845..f6d416fe49b0 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -440,6 +440,11 @@ unsigned long cpu_get_elf_hwcap2(void);
 #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
 #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
 
+static __always_inline bool boot_capabilities_finalized(void)
+{
+	return alternative_has_cap_likely(ARM64_ALWAYS_BOOT);
+}
+
 static __always_inline bool system_capabilities_finalized(void)
 {
 	return alternative_has_cap_likely(ARM64_ALWAYS_SYSTEM);
@@ -452,6 +457,8 @@ static __always_inline bool system_capabilities_finalized(void)
  */
 static __always_inline bool cpus_have_cap(unsigned int num)
 {
+	if (__builtin_constant_p(num) && !cpucap_is_possible(num))
+		return false;
 	if (num >= ARM64_NCAPS)
 		return false;
 	return arch_test_bit(num, system_cpucaps);
@@ -460,55 +467,37 @@ static __always_inline bool cpus_have_cap(unsigned int num)
 /*
  * Test for a capability without a runtime check.
  *
- * Before capabilities are finalized, this returns false.
- * After capabilities are finalized, this is patched to avoid a runtime check.
+ * Before boot capabilities are finalized, this will BUG().
+ * After boot capabilities are finalized, this is patched to avoid a runtime
+ * check.
  *
  * @num must be a compile-time constant.
  */
-static __always_inline bool __cpus_have_const_cap(int num)
+static __always_inline bool cpus_have_final_boot_cap(int num)
 {
-	if (num >= ARM64_NCAPS)
-		return false;
-	return alternative_has_cap_unlikely(num);
+	if (boot_capabilities_finalized())
+		return alternative_has_cap_unlikely(num);
+	else
+		BUG();
 }
 
 /*
  * Test for a capability without a runtime check.
  *
- * Before capabilities are finalized, this will BUG().
- * After capabilities are finalized, this is patched to avoid a runtime check.
+ * Before system capabilities are finalized, this will BUG().
+ * After system capabilities are finalized, this is patched to avoid a runtime
+ * check.
  *
  * @num must be a compile-time constant.
  */
 static __always_inline bool cpus_have_final_cap(int num)
 {
 	if (system_capabilities_finalized())
-		return __cpus_have_const_cap(num);
+		return alternative_has_cap_unlikely(num);
 	else
 		BUG();
 }
 
-/*
- * Test for a capability, possibly with a runtime check for non-hyp code.
- *
- * For hyp code, this behaves the same as cpus_have_final_cap().
- *
- * For non-hyp code:
- * Before capabilities are finalized, this behaves as cpus_have_cap().
- * After capabilities are finalized, this is patched to avoid a runtime check.
- *
- * @num must be a compile-time constant.
- */
-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);
-}
-
 static inline int __attribute_const__
 cpuid_feature_extract_signed_field_width(u64 features, int field, int width)
 {
@@ -628,7 +617,9 @@ static inline bool id_aa64pfr1_mte(u64 pfr1)
 	return val >= ID_AA64PFR1_EL1_MTE_MTE2;
 }
 
-void __init setup_cpu_features(void);
+void __init setup_system_features(void);
+void __init setup_user_features(void);
+
 void check_local_cpu_capabilities(void);
 
 u64 read_sanitised_ftr_reg(u32 id);
@@ -737,13 +728,12 @@ static inline bool system_supports_mixed_endian(void)
 
 static __always_inline bool system_supports_fpsimd(void)
 {
-	return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD);
+	return alternative_has_cap_likely(ARM64_HAS_FPSIMD);
 }
 
 static inline bool system_uses_hw_pan(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_PAN) &&
-		cpus_have_const_cap(ARM64_HAS_PAN);
+	return alternative_has_cap_unlikely(ARM64_HAS_PAN);
 }
 
 static inline bool system_uses_ttbr0_pan(void)
@@ -754,26 +744,22 @@ static inline bool system_uses_ttbr0_pan(void)
 
 static __always_inline bool system_supports_sve(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_SVE) &&
-		cpus_have_const_cap(ARM64_SVE);
+	return alternative_has_cap_unlikely(ARM64_SVE);
 }
 
 static __always_inline bool system_supports_sme(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_SME) &&
-		cpus_have_const_cap(ARM64_SME);
+	return alternative_has_cap_unlikely(ARM64_SME);
 }
 
 static __always_inline bool system_supports_sme2(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_SME) &&
-		cpus_have_const_cap(ARM64_SME2);
+	return alternative_has_cap_unlikely(ARM64_SME2);
 }
 
 static __always_inline bool system_supports_fa64(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_SME) &&
-		cpus_have_const_cap(ARM64_SME_FA64);
+	return alternative_has_cap_unlikely(ARM64_SME_FA64);
 }
 
 static __always_inline bool system_supports_tpidr2(void)
@@ -783,20 +769,17 @@ static __always_inline bool system_supports_tpidr2(void)
 
 static __always_inline bool system_supports_cnp(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_CNP) &&
-		cpus_have_const_cap(ARM64_HAS_CNP);
+	return alternative_has_cap_unlikely(ARM64_HAS_CNP);
 }
 
 static inline bool system_supports_address_auth(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
-		cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH);
+	return cpus_have_final_boot_cap(ARM64_HAS_ADDRESS_AUTH);
 }
 
 static inline bool system_supports_generic_auth(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
-		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
+	return alternative_has_cap_unlikely(ARM64_HAS_GENERIC_AUTH);
 }
 
 static inline bool system_has_full_ptr_auth(void)
@@ -806,14 +789,12 @@ static inline bool system_has_full_ptr_auth(void)
 
 static __always_inline bool system_uses_irq_prio_masking(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
-	       cpus_have_const_cap(ARM64_HAS_GIC_PRIO_MASKING);
+	return alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING);
 }
 
 static inline bool system_supports_mte(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_MTE) &&
-		cpus_have_const_cap(ARM64_MTE);
+	return alternative_has_cap_unlikely(ARM64_MTE);
 }
 
 static inline bool system_has_prio_mask_debugging(void)
@@ -824,13 +805,18 @@ static inline bool system_has_prio_mask_debugging(void)
 
 static inline bool system_supports_bti(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
+	return cpus_have_final_cap(ARM64_BTI);
+}
+
+static inline bool system_supports_bti_kernel(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) &&
+		cpus_have_final_boot_cap(ARM64_BTI);
 }
 
 static inline bool system_supports_tlb_range(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) &&
-		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
+	return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE);
 }
 
 int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 9e5d3a0812b6..50e5f25d3024 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -32,6 +32,32 @@
 #define VFP_STATE_SIZE		((32 * 8) + 4)
 #endif
 
+static inline unsigned long cpacr_save_enable_kernel_sve(void)
+{
+	unsigned long old = read_sysreg(cpacr_el1);
+	unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN;
+
+	write_sysreg(old | set, cpacr_el1);
+	isb();
+	return old;
+}
+
+static inline unsigned long cpacr_save_enable_kernel_sme(void)
+{
+	unsigned long old = read_sysreg(cpacr_el1);
+	unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_SMEN_EL1EN;
+
+	write_sysreg(old | set, cpacr_el1);
+	isb();
+	return old;
+}
+
+static inline void cpacr_restore(unsigned long cpacr)
+{
+	write_sysreg(cpacr, cpacr_el1);
+	isb();
+}
+
 /*
  * When we defined the maximum SVE vector length we defined the ABI so
  * that the maximum vector length included all the reserved for future
@@ -123,10 +149,11 @@ extern void sme_save_state(void *state, int zt);
 extern void sme_load_state(void const *state, int zt);
 
 struct arm64_cpu_capabilities;
-extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
-extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
-extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused);
-extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused);
 
 extern u64 read_smcr_features(void);
 
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 1f31ec146d16..0a7186a93882 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -21,12 +21,6 @@
  * exceptions should be unmasked.
  */
 
-static __always_inline bool __irqflags_uses_pmr(void)
-{
-	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
-	       alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING);
-}
-
 static __always_inline void __daif_local_irq_enable(void)
 {
 	barrier();
@@ -49,7 +43,7 @@ static __always_inline void __pmr_local_irq_enable(void)
 
 static inline void arch_local_irq_enable(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_enable();
 	} else {
 		__daif_local_irq_enable();
@@ -77,7 +71,7 @@ static __always_inline void __pmr_local_irq_disable(void)
 
 static inline void arch_local_irq_disable(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_disable();
 	} else {
 		__daif_local_irq_disable();
@@ -99,7 +93,7 @@ static __always_inline unsigned long __pmr_local_save_flags(void)
  */
 static inline unsigned long arch_local_save_flags(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		return __pmr_local_save_flags();
 	} else {
 		return __daif_local_save_flags();
@@ -118,7 +112,7 @@ static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags)
 
 static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		return __pmr_irqs_disabled_flags(flags);
 	} else {
 		return __daif_irqs_disabled_flags(flags);
@@ -137,7 +131,7 @@ static __always_inline bool __pmr_irqs_disabled(void)
 
 static inline bool arch_irqs_disabled(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		return __pmr_irqs_disabled();
 	} else {
 		return __daif_irqs_disabled();
@@ -169,7 +163,7 @@ static __always_inline unsigned long __pmr_local_irq_save(void)
 
 static inline unsigned long arch_local_irq_save(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		return __pmr_local_irq_save();
 	} else {
 		return __daif_local_irq_save();
@@ -196,7 +190,7 @@ static __always_inline void __pmr_local_irq_restore(unsigned long flags)
  */
 static inline void arch_local_irq_restore(unsigned long flags)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_restore(flags);
 	} else {
 		__daif_local_irq_restore(flags);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 3d6725ff0bf6..cbd2f163a67d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/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 {
 		/*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index af06ccb7ee34..e64d64e6ad44 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/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) {}
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 96a80e8f6226..27810667dec7 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/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);
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 94b68850cb9f..2fcf51231d6e 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -57,7 +57,7 @@ typedef struct {
 
 static inline bool arm64_kernel_unmapped_at_el0(void)
 {
-	return cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
+	return alternative_has_cap_unlikely(ARM64_UNMAP_KERNEL_AT_EL0);
 }
 
 extern void arm64_memblock_init(void);
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a6fb325424e7..9ce4200508b1 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -152,7 +152,7 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz)
  * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
  * avoiding the possibility of conflicting TLB entries being allocated.
  */
-static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
+static inline void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp)
 {
 	typedef void (ttbr_replace_func)(phys_addr_t);
 	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
@@ -162,17 +162,8 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 	/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
 	phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
 
-	if (system_supports_cnp() && !WARN_ON(pgdp != lm_alias(swapper_pg_dir))) {
-		/*
-		 * cpu_replace_ttbr1() is used when there's a boot CPU
-		 * up (i.e. cpufeature framework is not up yet) and
-		 * latter only when we enable CNP via cpufeature's
-		 * enable() callback.
-		 * Also we rely on the system_cpucaps bit being set before
-		 * calling the enable() function.
-		 */
+	if (cnp)
 		ttbr1 |= TTBR_CNP_BIT;
-	}
 
 	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 
@@ -189,6 +180,21 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 	cpu_uninstall_idmap();
 }
 
+static inline void cpu_enable_swapper_cnp(void)
+{
+	__cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir, true);
+}
+
+static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
+{
+	/*
+	 * Only for early TTBR1 replacement before cpucaps are finalized and
+	 * before we've decided whether to use CNP.
+	 */
+	WARN_ON(system_capabilities_finalized());
+	__cpu_replace_ttbr1(pgdp, idmap, false);
+}
+
 /*
  * It would be nice to return ASIDs back to the allocator, but unfortunately
  * that introduces a race with a generation rollover where we could erroneously
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index bfa6638b4c93..79550b22ba19 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -44,8 +44,7 @@ struct plt_entry {
 
 static inline bool is_forbidden_offset_for_adrp(void *place)
 {
-	return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) &&
-	       cpus_have_const_cap(ARM64_WORKAROUND_843419) &&
+	return cpus_have_final_cap(ARM64_WORKAROUND_843419) &&
 	       ((u64)place & 0xfff) >= 0xff8;
 }
 
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index eed814b00a38..e9624f6326dd 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -75,11 +75,7 @@ extern bool arm64_use_ng_mappings;
  * If we have userspace only BTI we don't want to mark kernel pages
  * guarded even if the system does support BTI.
  */
-#ifdef CONFIG_ARM64_BTI_KERNEL
-#define PTE_MAYBE_GP		(system_supports_bti() ? PTE_GP : 0)
-#else
-#define PTE_MAYBE_GP		0
-#endif
+#define PTE_MAYBE_GP		(system_supports_bti_kernel() ? PTE_GP : 0)
 
 #define PAGE_KERNEL		__pgprot(_PAGE_KERNEL)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_KERNEL_RO)
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index 9cc501450486..06c357d83b13 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -73,7 +73,7 @@ static __always_inline void arm64_apply_bp_hardening(void)
 {
 	struct bp_hardening_data *d;
 
-	if (!cpus_have_const_cap(ARM64_SPECTRE_V2))
+	if (!alternative_has_cap_unlikely(ARM64_SPECTRE_V2))
 		return;
 
 	d = this_cpu_ptr(&bp_hardening_data);
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index b149cf9f91bc..7aa476a52180 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -105,7 +105,7 @@ static inline unsigned long get_trans_granule(void)
 #define __tlbi_level(op, addr, level) do {				\
 	u64 arg = addr;							\
 									\
-	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) &&		\
+	if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) &&	\
 	    level) {							\
 		u64 ttl = level & 3;					\
 		ttl |= get_trans_granule() << 2;			\
@@ -284,16 +284,15 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 
 static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 {
-#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
 	/*
 	 * TLB flush deferral is not required on systems which are affected by
 	 * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
 	 * will have two consecutive TLBI instructions with a dsb(ish) in between
 	 * defeating the purpose (i.e save overall 'dsb ish' cost).
 	 */
-	if (unlikely(cpus_have_const_cap(ARM64_WORKAROUND_REPEAT_TLBI)))
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
 		return false;
-#endif
+
 	return true;
 }
 
diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h
index bc9a2145f419..b815d8f2c0dc 100644
--- a/arch/arm64/include/asm/vectors.h
+++ b/arch/arm64/include/asm/vectors.h
@@ -62,7 +62,7 @@ DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector);
 static inline const char *
 arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot)
 {
-	if (arm64_kernel_unmapped_at_el0())
+	if (cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0))
 		return (char *)(TRAMP_VALIAS + SZ_2K * slot);
 
 	WARN_ON_ONCE(slot == EL1_VECTOR_KPTI);