Merge branch 'for-next/cpus_have_const_cap' into for-next/core

* for-next/cpus_have_const_cap: (38 commits)
  : cpus_have_const_cap() removal
  arm64: Remove cpus_have_const_cap()
  arm64: Avoid cpus_have_const_cap() for ARM64_WORKAROUND_REPEAT_TLBI
  arm64: Avoid cpus_have_const_cap() for ARM64_WORKAROUND_NVIDIA_CARMEL_CNP
  arm64: Avoid cpus_have_const_cap() for ARM64_WORKAROUND_CAVIUM_23154
  arm64: Avoid cpus_have_const_cap() for ARM64_WORKAROUND_2645198
  arm64: Avoid cpus_have_const_cap() for ARM64_WORKAROUND_1742098
  arm64: Avoid cpus_have_const_cap() for ARM64_WORKAROUND_1542419
  arm64: Avoid cpus_have_const_cap() for ARM64_WORKAROUND_843419
  arm64: Avoid cpus_have_const_cap() for ARM64_UNMAP_KERNEL_AT_EL0
  arm64: Avoid cpus_have_const_cap() for ARM64_{SVE,SME,SME2,FA64}
  arm64: Avoid cpus_have_const_cap() for ARM64_SPECTRE_V2
  arm64: Avoid cpus_have_const_cap() for ARM64_SSBS
  arm64: Avoid cpus_have_const_cap() for ARM64_MTE
  arm64: Avoid cpus_have_const_cap() for ARM64_HAS_TLB_RANGE
  arm64: Avoid cpus_have_const_cap() for ARM64_HAS_WFXT
  arm64: Avoid cpus_have_const_cap() for ARM64_HAS_RNG
  arm64: Avoid cpus_have_const_cap() for ARM64_HAS_EPAN
  arm64: Avoid cpus_have_const_cap() for ARM64_HAS_PAN
  arm64: Avoid cpus_have_const_cap() for ARM64_HAS_GIC_PRIO_MASKING
  arm64: Avoid cpus_have_const_cap() for ARM64_HAS_DIT
  ...

arch/arm/xen/enlighten.c

@@ -164,9 +164,6 @@ static int xen_starting_cpu(unsigned int cpu)
 	BUG_ON(err);
 	per_cpu(xen_vcpu, cpu) = vcpup;
 
-	if (!xen_kernel_unmapped_at_usr())
-		xen_setup_runstate_info(cpu);
-
 after_register_vcpu_info:
 	enable_percpu_irq(xen_events_irq, 0);
 	return 0;
@@ -523,9 +520,6 @@ static int __init xen_guest_init(void)
 		return -EINVAL;
 	}
 
-	if (!xen_kernel_unmapped_at_usr())
-		xen_time_setup_guest();
-
 	if (xen_initial_domain())
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 
@@ -535,7 +529,13 @@ static int __init xen_guest_init(void)
 }
 early_initcall(xen_guest_init);
 
-static int __init xen_pm_init(void)
+static int xen_starting_runstate_cpu(unsigned int cpu)
+{
+	xen_setup_runstate_info(cpu);
+	return 0;
+}
+
+static int __init xen_late_init(void)
 {
 	if (!xen_domain())
 		return -ENODEV;
@@ -548,9 +548,16 @@ static int __init xen_pm_init(void)
 		do_settimeofday64(&ts);
 	}
 
+	if (xen_kernel_unmapped_at_usr())
 		return 0;
+
+	xen_time_setup_guest();
+
+	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_RUNSTATE_STARTING,
+				 "arm/xen_runstate:starting",
+				 xen_starting_runstate_cpu, NULL);
 }
-late_initcall(xen_pm_init);
+late_initcall(xen_late_init);
 
 
 /* empty stubs */

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

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 @@ alternative_has_cap_likely(const unsigned long cpucap)
 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])

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);

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)

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");

arch/arm64/include/asm/cpucaps.h

+/* 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 */

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;
+	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);

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);
 

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);

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/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);

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

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;
 }
 

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)

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);

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;
 }
 

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);

arch/arm64/kernel/cpu_errata.c

@@ -121,22 +121,6 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
 	sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
 }
 
-static DEFINE_RAW_SPINLOCK(reg_user_mask_modification);
-static void __maybe_unused
-cpu_clear_bf16_from_user_emulation(const struct arm64_cpu_capabilities *__unused)
-{
-	struct arm64_ftr_reg *regp;
-
-	regp = get_arm64_ftr_reg(SYS_ID_AA64ISAR1_EL1);
-	if (!regp)
-		return;
-
-	raw_spin_lock(&reg_user_mask_modification);
-	if (regp->user_mask & ID_AA64ISAR1_EL1_BF16_MASK)
-		regp->user_mask &= ~ID_AA64ISAR1_EL1_BF16_MASK;
-	raw_spin_unlock(&reg_user_mask_modification);
-}
-
 #define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max)	\
 	.matches = is_affected_midr_range,			\
 	.midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max)
@@ -727,7 +711,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		/* Cortex-A510 r0p0 - r1p1 */
 		ERRATA_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1),
 		MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)),
-		.cpu_enable = cpu_clear_bf16_from_user_emulation,
 	},
 #endif
 #ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38

arch/arm64/kernel/efi.c

@@ -113,8 +113,7 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 		pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
 	if (md->attribute & EFI_MEMORY_XP)
 		pte = set_pte_bit(pte, __pgprot(PTE_PXN));
-	else if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) &&
-		 system_supports_bti() && spd->has_bti)
+	else if (system_supports_bti_kernel() && spd->has_bti)
 		pte = set_pte_bit(pte, __pgprot(PTE_GP));
 	set_pte(ptep, pte);
 	return 0;

arch/arm64/kernel/fpsimd.c

@@ -1160,11 +1160,7 @@ static void __init sve_efi_setup(void)
 	panic("Cannot allocate percpu memory for EFI SVE save/restore");
 }
 
-/*
- * Enable SVE for EL1.
- * Intended for use by the cpufeatures code during CPU boot.
- */
-void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p)
 {
 	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1);
 	isb();
@@ -1177,7 +1173,7 @@ void __init sve_setup(void)
 	unsigned long b;
 	int max_bit;
 
-	if (!system_supports_sve())
+	if (!cpus_have_cap(ARM64_SVE))
 		return;
 
 	/*
@@ -1267,7 +1263,7 @@ static void sme_free(struct task_struct *task)
 	task->thread.sme_state = NULL;
 }
 
-void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+void cpu_enable_sme(const struct arm64_cpu_capabilities *__always_unused p)
 {
 	/* Set priority for all PEs to architecturally defined minimum */
 	write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK,
@@ -1282,23 +1278,21 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
 	isb();
 }
 
-/*
- * This must be called after sme_kernel_enable(), we rely on the
- * feature table being sorted to ensure this.
- */
-void sme2_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+void cpu_enable_sme2(const struct arm64_cpu_capabilities *__always_unused p)
 {
+	/* This must be enabled after SME */
+	BUILD_BUG_ON(ARM64_SME2 <= ARM64_SME);
+
 	/* Allow use of ZT0 */
 	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK,
 		       SYS_SMCR_EL1);
 }
 
-/*
- * This must be called after sme_kernel_enable(), we rely on the
- * feature table being sorted to ensure this.
- */
-void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+void cpu_enable_fa64(const struct arm64_cpu_capabilities *__always_unused p)
 {
+	/* This must be enabled after SME */
+	BUILD_BUG_ON(ARM64_SME_FA64 <= ARM64_SME);
+
 	/* Allow use of FA64 */
 	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK,
 		       SYS_SMCR_EL1);
@@ -1309,7 +1303,7 @@ void __init sme_setup(void)
 	struct vl_info *info = &vl_info[ARM64_VEC_SME];
 	int min_bit, max_bit;
 
-	if (!system_supports_sme())
+	if (!cpus_have_cap(ARM64_SME))
 		return;
 
 	/*
@@ -1470,8 +1464,17 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
  */
 void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs)
 {
-	/* TODO: implement lazy context saving/restoring */
-	WARN_ON(1);
+	/* Even if we chose not to use FPSIMD, the hardware could still trap: */
+	if (!system_supports_fpsimd()) {
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+		return;
+	}
+
+	/*
+	 * When FPSIMD is enabled, we should never take a trap unless something
+	 * has gone very wrong.
+	 */
+	BUG();
 }
 
 /*
@@ -1712,13 +1715,23 @@ void fpsimd_bind_state_to_cpu(struct cpu_fp_state *state)
 void fpsimd_restore_current_state(void)
 {
 	/*
-	 * For the tasks that were created before we detected the absence of
-	 * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(),
-	 * e.g, init. This could be then inherited by the children processes.
-	 * If we later detect that the system doesn't support FP/SIMD,
-	 * we must clear the flag for  all the tasks to indicate that the
-	 * FPSTATE is clean (as we can't have one) to avoid looping for ever in
-	 * do_notify_resume().
+	 * TIF_FOREIGN_FPSTATE is set on the init task and copied by
+	 * arch_dup_task_struct() regardless of whether FP/SIMD is detected.
+	 * Thus user threads can have this set even when FP/SIMD hasn't been
+	 * detected.
+	 *
+	 * When FP/SIMD is detected, begin_new_exec() will set
+	 * TIF_FOREIGN_FPSTATE via flush_thread() -> fpsimd_flush_thread(),
+	 * and fpsimd_thread_switch() will set TIF_FOREIGN_FPSTATE when
+	 * switching tasks. We detect FP/SIMD before we exec the first user
+	 * process, ensuring this has TIF_FOREIGN_FPSTATE set and
+	 * do_notify_resume() will call fpsimd_restore_current_state() to
+	 * install the user FP/SIMD context.
+	 *
+	 * When FP/SIMD is not detected, nothing else will clear or set
+	 * TIF_FOREIGN_FPSTATE prior to the first return to userspace, and
+	 * we must clear TIF_FOREIGN_FPSTATE to avoid do_notify_resume()
+	 * looping forever calling fpsimd_restore_current_state().
 	 */
 	if (!system_supports_fpsimd()) {
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
@@ -2051,6 +2064,13 @@ static inline void fpsimd_hotplug_init(void)
 static inline void fpsimd_hotplug_init(void) { }
 #endif
 
+void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__always_unused p)
+{
+	unsigned long enable = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN;
+	write_sysreg(read_sysreg(CPACR_EL1) | enable, CPACR_EL1);
+	isb();
+}
+
 /*
  * FP/SIMD support code initialisation.
  */

arch/arm64/kernel/module-plts.c

@@ -200,8 +200,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num,
 			break;
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 		case R_AARCH64_ADR_PREL_PG_HI21:
-			if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) ||
-			    !cpus_have_const_cap(ARM64_WORKAROUND_843419))
+			if (!cpus_have_final_cap(ARM64_WORKAROUND_843419))
 				break;
 
 			/*
@@ -236,13 +235,13 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num,
 		}
 	}
 
-	if (IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) &&
-	    cpus_have_const_cap(ARM64_WORKAROUND_843419))
+	if (cpus_have_final_cap(ARM64_WORKAROUND_843419)) {
 		/*
 		 * Add some slack so we can skip PLT slots that may trigger
 		 * the erratum due to the placement of the ADRP instruction.
 		 */
 		ret += DIV_ROUND_UP(ret, (SZ_4K / sizeof(struct plt_entry)));
+	}
 
 	return ret;
 }

arch/arm64/kernel/process.c

@@ -454,7 +454,7 @@ static void ssbs_thread_switch(struct task_struct *next)
 	 * If all CPUs implement the SSBS extension, then we just need to
 	 * context-switch the PSTATE field.
 	 */
-	if (cpus_have_const_cap(ARM64_SSBS))
+	if (alternative_has_cap_unlikely(ARM64_SSBS))
 		return;
 
 	spectre_v4_enable_task_mitigation(next);

arch/arm64/kernel/proton-pack.c

@@ -972,7 +972,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
 	 * When KPTI is in use, the vectors are switched when exiting to
 	 * user-space.
 	 */
-	if (arm64_kernel_unmapped_at_el0())
+	if (cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0))
 		return;
 
 	write_sysreg(v, vbar_el1);

arch/arm64/kernel/smp.c

@@ -439,9 +439,10 @@ static void __init hyp_mode_check(void)
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
-	setup_cpu_features();
+	setup_system_features();
 	hyp_mode_check();
 	apply_alternatives_all();
+	setup_user_features();
 	mark_linear_text_alias_ro();
 }
 

arch/arm64/kernel/suspend.c

@@ -55,13 +55,13 @@ void notrace __cpu_suspend_exit(void)
 
 	/* Restore CnP bit in TTBR1_EL1 */
 	if (system_supports_cnp())
-		cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir);
+		cpu_enable_swapper_cnp();
 
 	/*
 	 * PSTATE was not saved over suspend/resume, re-enable any detected
 	 * features that might not have been set correctly.
 	 */
-	if (cpus_have_const_cap(ARM64_HAS_DIT))
+	if (alternative_has_cap_unlikely(ARM64_HAS_DIT))
 		set_pstate_dit(1);
 	__uaccess_enable_hw_pan();
 
@@ -98,6 +98,15 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	struct sleep_stack_data state;
 	struct arm_cpuidle_irq_context context;
 
+	/*
+	 * Some portions of CPU state (e.g. PSTATE.{PAN,DIT}) are initialized
+	 * before alternatives are patched, but are only restored by
+	 * __cpu_suspend_exit() after alternatives are patched. To avoid
+	 * accidentally losing these bits we must not attempt to suspend until
+	 * after alternatives have been patched.
+	 */
+	WARN_ON(!system_capabilities_finalized());
+
 	/* Report any MTE async fault before going to suspend */
 	mte_suspend_enter();
 

arch/arm64/kernel/sys_compat.c

@@ -31,7 +31,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
-		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		if (cpus_have_final_cap(ARM64_WORKAROUND_1542419)) {
 			/*
 			 * The workaround requires an inner-shareable tlbi.
 			 * We pick the reserved-ASID to minimise the impact.

arch/arm64/kernel/traps.c

@@ -631,7 +631,7 @@ static void ctr_read_handler(unsigned long esr, struct pt_regs *regs)
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_1542419)) {
 		/* Hide DIC so that we can trap the unnecessary maintenance...*/
 		val &= ~BIT(CTR_EL0_DIC_SHIFT);
 

arch/arm64/kernel/vdso.c

@@ -212,7 +212,7 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	if (IS_ERR(ret))
 		goto up_fail;
 
-	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
+	if (system_supports_bti_kernel())
 		gp_flags = VM_ARM64_BTI;
 
 	vdso_base += VVAR_NR_PAGES * PAGE_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

@@ -401,7 +401,7 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
 		if (device)
 			return -EINVAL;
 
-		if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
+		if (system_supports_bti_kernel())
 			attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP;
 	} else {
 		attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN;
@@ -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;
 	}

arch/arm64/lib/delay.c

@@ -27,7 +27,7 @@ void __delay(unsigned long cycles)
 {
 	cycles_t start = get_cycles();
 
-	if (cpus_have_const_cap(ARM64_HAS_WFXT)) {
+	if (alternative_has_cap_unlikely(ARM64_HAS_WFXT)) {
 		u64 end = start + cycles;
 
 		/*

arch/arm64/mm/fault.c

@@ -571,7 +571,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		/* Write implies read */
 		vm_flags |= VM_WRITE;
 		/* If EPAN is absent then exec implies read */
-		if (!cpus_have_const_cap(ARM64_HAS_EPAN))
+		if (!alternative_has_cap_unlikely(ARM64_HAS_EPAN))
 			vm_flags |= VM_EXEC;
 	}
 

arch/arm64/mm/hugetlbpage.c

@@ -555,8 +555,7 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
-	if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
-	    cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
 		 * when the permission changes from executable to non-executable

arch/arm64/mm/mmap.c

@@ -68,7 +68,7 @@ static int __init adjust_protection_map(void)
 	 * With Enhanced PAN we can honour the execute-only permissions as
 	 * there is no PAN override with such mappings.
 	 */
-	if (cpus_have_const_cap(ARM64_HAS_EPAN)) {
+	if (cpus_have_cap(ARM64_HAS_EPAN)) {
 		protection_map[VM_EXEC] = PAGE_EXECONLY;
 		protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY;
 	}

arch/arm64/mm/mmu.c

@@ -1469,8 +1469,7 @@ early_initcall(prevent_bootmem_remove_init);
 
 pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
-	if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
-	    cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
 		 * when the permission changes from executable to non-executable

arch/arm64/mm/proc.S

@@ -405,8 +405,7 @@ SYM_FUNC_START(__cpu_setup)
 	tlbi	vmalle1				// Invalidate local TLB
 	dsb	nsh
 
-	mov	x1, #3 << 20
-	msr	cpacr_el1, x1			// Enable FP/ASIMD
+	msr	cpacr_el1, xzr			// Reset cpacr_el1
 	mov	x1, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x1			// access to the DCC from EL0
 	isb					// Unmask debug exceptions now,

arch/arm64/tools/Makefile

@@ -3,7 +3,7 @@
 gen := arch/$(ARCH)/include/generated
 kapi := $(gen)/asm
 
-kapi-hdrs-y := $(kapi)/cpucaps.h $(kapi)/sysreg-defs.h
+kapi-hdrs-y := $(kapi)/cpucap-defs.h $(kapi)/sysreg-defs.h
 
 targets += $(addprefix ../../../, $(kapi-hdrs-y))
 
@@ -17,7 +17,7 @@ quiet_cmd_gen_cpucaps = GEN     $@
 quiet_cmd_gen_sysreg = GEN     $@
       cmd_gen_sysreg = mkdir -p $(dir $@); $(AWK) -f $(real-prereqs) > $@
 
-$(kapi)/cpucaps.h: $(src)/gen-cpucaps.awk $(src)/cpucaps FORCE
+$(kapi)/cpucap-defs.h: $(src)/gen-cpucaps.awk $(src)/cpucaps FORCE
 	$(call if_changed,gen_cpucaps)
 
 $(kapi)/sysreg-defs.h: $(src)/gen-sysreg.awk $(src)/sysreg FORCE

arch/arm64/tools/cpucaps

@@ -27,6 +27,7 @@ HAS_ECV_CNTPOFF
 HAS_EPAN
 HAS_EVT
 HAS_FGT
+HAS_FPSIMD
 HAS_GENERIC_AUTH
 HAS_GENERIC_AUTH_ARCH_QARMA3
 HAS_GENERIC_AUTH_ARCH_QARMA5
@@ -39,7 +40,6 @@ HAS_LDAPR
 HAS_LSE_ATOMICS
 HAS_MOPS
 HAS_NESTED_VIRT
-HAS_NO_FPSIMD
 HAS_NO_HW_PREFETCH
 HAS_PAN
 HAS_S1PIE

arch/arm64/tools/gen-cpucaps.awk

@@ -15,8 +15,8 @@ function fatal(msg) {
 /^#/ { next }
 
 BEGIN {
-	print "#ifndef __ASM_CPUCAPS_H"
-	print "#define __ASM_CPUCAPS_H"
+	print "#ifndef __ASM_CPUCAP_DEFS_H"
+	print "#define __ASM_CPUCAP_DEFS_H"
 	print ""
 	print "/* Generated file - do not edit */"
 	cap_num = 0
@@ -31,7 +31,7 @@ BEGIN {
 END {
 	printf("#define ARM64_NCAPS\t\t\t\t\t%d\n", cap_num)
 	print ""
-	print "#endif /* __ASM_CPUCAPS_H */"
+	print "#endif /* __ASM_CPUCAP_DEFS_H */"
 }
 
 # Any lines not handled by previous rules are unexpected

drivers/clocksource/arm_arch_timer.c

@@ -918,7 +918,7 @@ static void arch_timer_evtstrm_enable(unsigned int divider)
 
 #ifdef CONFIG_ARM64
 	/* ECV is likely to require a large divider. Use the EVNTIS flag. */
-	if (cpus_have_const_cap(ARM64_HAS_ECV) && divider > 15) {
+	if (cpus_have_final_cap(ARM64_HAS_ECV) && divider > 15) {
 		cntkctl |= ARCH_TIMER_EVT_INTERVAL_SCALE;
 		divider -= 8;
 	}
@@ -956,6 +956,30 @@ static void arch_timer_configure_evtstream(void)
 	arch_timer_evtstrm_enable(max(0, lsb));
 }
 
+static int arch_timer_evtstrm_starting_cpu(unsigned int cpu)
+{
+	arch_timer_configure_evtstream();
+	return 0;
+}
+
+static int arch_timer_evtstrm_dying_cpu(unsigned int cpu)
+{
+	cpumask_clear_cpu(smp_processor_id(), &evtstrm_available);
+	return 0;
+}
+
+static int __init arch_timer_evtstrm_register(void)
+{
+	if (!arch_timer_evt || !evtstrm_enable)
+		return 0;
+
+	return cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_EVTSTRM_STARTING,
+				 "clockevents/arm/arch_timer_evtstrm:starting",
+				 arch_timer_evtstrm_starting_cpu,
+				 arch_timer_evtstrm_dying_cpu);
+}
+core_initcall(arch_timer_evtstrm_register);
+
 static void arch_counter_set_user_access(void)
 {
 	u32 cntkctl = arch_timer_get_cntkctl();
@@ -1017,8 +1041,6 @@ static int arch_timer_starting_cpu(unsigned int cpu)
 	}
 
 	arch_counter_set_user_access();
-	if (evtstrm_enable)
-		arch_timer_configure_evtstream();
 
 	return 0;
 }
@@ -1165,8 +1187,6 @@ static int arch_timer_dying_cpu(unsigned int cpu)
 {
 	struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt);
 
-	cpumask_clear_cpu(smp_processor_id(), &evtstrm_available);
-
 	arch_timer_stop(clk);
 	return 0;
 }
@@ -1280,6 +1300,7 @@ static int __init arch_timer_register(void)
 
 out_free:
 	free_percpu(arch_timer_evt);
+	arch_timer_evt = NULL;
 out:
 	return err;
 }

drivers/irqchip/irq-gic-v3.c

@@ -277,17 +277,6 @@ static void gic_redist_wait_for_rwp(void)
 	gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP);
 }
 
-#ifdef CONFIG_ARM64
-
-static u64 __maybe_unused gic_read_iar(void)
-{
-	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_23154))
-		return gic_read_iar_cavium_thunderx();
-	else
-		return gic_read_iar_common();
-}
-#endif
-
 static void gic_enable_redist(bool enable)
 {
 	void __iomem *rbase;

include/linux/cpuhotplug.h

@@ -172,6 +172,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARM_L2X0_STARTING,
 	CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
 	CPUHP_AP_ARM_ARCH_TIMER_STARTING,
+	CPUHP_AP_ARM_ARCH_TIMER_EVTSTRM_STARTING,
 	CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
 	CPUHP_AP_JCORE_TIMER_STARTING,
 	CPUHP_AP_ARM_TWD_STARTING,
@@ -189,6 +190,7 @@ enum cpuhp_state {
 	/* Must be the last timer callback */
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
+	CPUHP_AP_ARM_XEN_RUNSTATE_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_CTI_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,