Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - arm64 perf: DDR PMU driver for Alibaba's T-Head Yitian 710 SoC, SVE
   vector granule register added to the user regs together with SVE perf
   extensions documentation.

 - SVE updates: add HWCAP for SVE EBF16, update the SVE ABI
   documentation to match the actual kernel behaviour (zeroing the
   registers on syscall rather than "zeroed or preserved" previously).

 - More conversions to automatic system registers generation.

 - vDSO: use self-synchronising virtual counter access in gettimeofday()
   if the architecture supports it.

 - arm64 stacktrace cleanups and improvements.

 - arm64 atomics improvements: always inline assembly, remove LL/SC
   trampolines.

 - Improve the reporting of EL1 exceptions: rework BTI and FPAC
   exception handling, better EL1 undefs reporting.

 - Cortex-A510 erratum 2658417: remove BF16 support due to incorrect
   result.

 - arm64 defconfig updates: build CoreSight as a module, enable options
   necessary for docker, memory hotplug/hotremove, enable all PMUs
   provided by Arm.

 - arm64 ptrace() support for TPIDR2_EL0 (register provided with the SME
   extensions).

 - arm64 ftraces updates/fixes: fix module PLTs with mcount, remove
   unused function.

 - kselftest updates for arm64: simple HWCAP validation, FP stress test
   improvements, validation of ZA regs in signal handlers, include
   larger SVE and SME vector lengths in signal tests, various cleanups.

 - arm64 alternatives (code patching) improvements to robustness and
   consistency: replace cpucap static branches with equivalent
   alternatives, associate callback alternatives with a cpucap.

 - Miscellaneous updates: optimise kprobe performance of patching
   single-step slots, simplify uaccess_mask_ptr(), move MTE registers
   initialisation to C, support huge vmalloc() mappings, run softirqs on
   the per-CPU IRQ stack, compat (arm32) misalignment fixups for
   multiword accesses.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (126 commits)
  arm64: alternatives: Use vdso/bits.h instead of linux/bits.h
  arm64/kprobe: Optimize the performance of patching single-step slot
  arm64: defconfig: Add Coresight as module
  kselftest/arm64: Handle EINTR while reading data from children
  kselftest/arm64: Flag fp-stress as exiting when we begin finishing up
  kselftest/arm64: Don't repeat termination handler for fp-stress
  ARM64: reloc_test: add __init/__exit annotations to module init/exit funcs
  arm64/mm: fold check for KFENCE into can_set_direct_map()
  arm64: ftrace: fix module PLTs with mcount
  arm64: module: Remove unused plt_entry_is_initialized()
  arm64: module: Make plt_equals_entry() static
  arm64: fix the build with binutils 2.27
  kselftest/arm64: Don't enable v8.5 for MTE selftest builds
  arm64: uaccess: simplify uaccess_mask_ptr()
  arm64: asm/perf_regs.h: Avoid C++-style comment in UAPI header
  kselftest/arm64: Fix typo in hwcap check
  arm64: mte: move register initialization to C
  arm64: mm: handle ARM64_KERNEL_USES_PMD_MAPS in vmemmap_populate()
  arm64: dma: Drop cache invalidation from arch_dma_prep_coherent()
  arm64/sve: Add Perf extensions documentation
  ...

1 files changed, 170 insertions, 155 deletions

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d8361691efeb..6062454a9067 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -108,8 +108,7 @@ DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcaps);
 static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM64_NCAPS];
 
-/* Need also bit for ARM64_CB_PATCH */
-DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
+DECLARE_BITMAP(boot_capabilities, ARM64_NCAPS);
 
 bool arm64_use_ng_mappings = false;
 EXPORT_SYMBOL(arm64_use_ng_mappings);
@@ -134,31 +133,12 @@ DEFINE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
  */
 static cpumask_var_t cpu_32bit_el0_mask __cpumask_var_read_mostly;
 
-/*
- * Flag to indicate if we have computed the system wide
- * capabilities based on the boot time active CPUs. This
- * will be used to determine if a new booting CPU should
- * go through the verification process to make sure that it
- * supports the system capabilities, without using a hotplug
- * notifier. This is also used to decide if we could use
- * the fast path for checking constant CPU caps.
- */
-DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready);
-EXPORT_SYMBOL(arm64_const_caps_ready);
-static inline void finalize_system_capabilities(void)
-{
-	static_branch_enable(&arm64_const_caps_ready);
-}
-
 void dump_cpu_features(void)
 {
 	/* file-wide pr_fmt adds "CPU features: " prefix */
 	pr_emerg("0x%*pb\n", ARM64_NCAPS, &cpu_hwcaps);
 }
 
-DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
-EXPORT_SYMBOL(cpu_hwcap_keys);
-
 #define __ARM64_FTR_BITS(SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
 	{						\
 		.sign = SIGNED,				\
@@ -243,35 +223,35 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_DIT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_AMU_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_MPAM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SEL2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_DIT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_AMU_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_MPAM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SEL2_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
-				   FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
-	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
-	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_ELx_64BIT_ONLY),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_ELx_64BIT_ONLY),
+				   FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SVE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_RAS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_GIC_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, ID_AA64PFR0_EL1_AdvSIMD_NI),
+	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_FP_SHIFT, 4, ID_AA64PFR0_EL1_FP_NI),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL1_SHIFT, 4, ID_AA64PFR0_EL1_ELx_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL0_SHIFT, 4, ID_AA64PFR0_EL1_ELx_64BIT_ONLY),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
-		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SME_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_SME_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MPAM_frac_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_RAS_frac_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE),
-		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MTE_SHIFT, 4, ID_AA64PFR1_MTE_NI),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MTE_SHIFT, 4, ID_AA64PFR1_EL1_MTE_NI),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_SSBS_SHIFT, 4, ID_AA64PFR1_EL1_SSBS_NI),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_BTI),
-				    FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_BT_SHIFT, 4, 0),
+				    FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_BT_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -316,9 +296,9 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EXS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_FGT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_EXS_SHIFT, 4, 0),
 	/*
 	 * 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
@@ -334,9 +314,9 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	 * 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),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT, 4, 1),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_TGRAN64_2_SHIFT, 4, 1),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_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
@@ -344,55 +324,55 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	 * exist in the wild so, even though we don't like it, we'll have to go
 	 * along with it and treat them as non-strict.
 	 */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN4_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN4_NI),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN64_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN64_NI),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN16_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN16_NI),
 
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT, 4, 0),
 	/* Linux shouldn't care about secure memory */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ASID_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_SNSMEM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_BIGEND_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_ASIDBITS_SHIFT, 4, 0),
 	/*
 	 * Differing PARange is fine as long as all peripherals and memory are mapped
 	 * within the minimum PARange of all CPUs
 	 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_PARANGE_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TIDCP1_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_AFP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_ETS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TWED_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_XNX_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64MMFR1_SPECSEI_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HPD_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VHE_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HADBS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_TIDCP1_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_ETS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_TWED_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_XNX_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64MMFR1_EL1_SpecSEI_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_PAN_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_LO_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_HPDS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_VH_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_VMIDBits_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_HAFDBS_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_E0PD_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EVT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_BBM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_TTL_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IDS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_ST_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_NV_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CCIDX_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_UAO_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CNP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_E0PD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_EVT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_BBM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_TTL_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_FWB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_IDS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_AT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_ST_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_NV_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_CCIDX_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_VARange_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_IESB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_LSM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_UAO_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_CnP_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -434,17 +414,17 @@ static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_DOUBLELOCK_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_PMSVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_DoubleLock_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_PMSVer_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_CTX_CMPs_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_WRPs_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_BRPs_SHIFT, 4, 0),
 	/*
 	 * We can instantiate multiple PMU instances with different levels
 	 * of support.
 	 */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_EL1_PMUVer_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_EL1_DebugVer_SHIFT, 4, 0x6),
 	ARM64_FTR_END,
 };
 
@@ -750,7 +730,7 @@ static struct arm64_ftr_reg *get_arm64_ftr_reg_nowarn(u32 sys_id)
  * returns - Upon success,  matching ftr_reg entry for id.
  *         - NULL on failure but with an WARN_ON().
  */
-static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
+struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
 {
 	struct arm64_ftr_reg *reg;
 
@@ -1392,6 +1372,12 @@ u64 __read_sysreg_by_encoding(u32 sys_id)
 #include <linux/irqchip/arm-gic-v3.h>
 
 static bool
+has_always(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	return true;
+}
+
+static bool
 feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
 {
 	int val = cpuid_feature_extract_field_width(reg, entry->field_pos,
@@ -1401,17 +1387,40 @@ feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
 	return val >= entry->min_field_value;
 }
 
-static bool
-has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope)
+static u64
+read_scoped_sysreg(const struct arm64_cpu_capabilities *entry, int scope)
 {
-	u64 val;
-
 	WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible());
 	if (scope == SCOPE_SYSTEM)
-		val = read_sanitised_ftr_reg(entry->sys_reg);
+		return read_sanitised_ftr_reg(entry->sys_reg);
 	else
-		val = __read_sysreg_by_encoding(entry->sys_reg);
+		return __read_sysreg_by_encoding(entry->sys_reg);
+}
 
+static bool
+has_user_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	int mask;
+	struct arm64_ftr_reg *regp;
+	u64 val = read_scoped_sysreg(entry, scope);
+
+	regp = get_arm64_ftr_reg(entry->sys_reg);
+	if (!regp)
+		return false;
+
+	mask = cpuid_feature_extract_unsigned_field_width(regp->user_mask,
+							  entry->field_pos,
+							  entry->field_width);
+	if (!mask)
+		return false;
+
+	return feature_matches(val, entry);
+}
+
+static bool
+has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	u64 val = read_scoped_sysreg(entry, scope);
 	return feature_matches(val, entry);
 }
 
@@ -1492,7 +1501,7 @@ static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unus
 	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
 
 	return cpuid_feature_extract_signed_field(pfr0,
-					ID_AA64PFR0_FP_SHIFT) < 0;
+					ID_AA64PFR0_EL1_FP_SHIFT) < 0;
 }
 
 static bool has_cache_idc(const struct arm64_cpu_capabilities *entry,
@@ -1571,7 +1580,7 @@ bool kaslr_requires_kpti(void)
 	if (IS_ENABLED(CONFIG_ARM64_E0PD)) {
 		u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1);
 		if (cpuid_feature_extract_unsigned_field(mmfr2,
-						ID_AA64MMFR2_E0PD_SHIFT))
+						ID_AA64MMFR2_EL1_E0PD_SHIFT))
 			return false;
 	}
 
@@ -2034,7 +2043,8 @@ static void bti_enable(const struct arm64_cpu_capabilities *__unused)
 static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
 {
 	sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ATA | SCTLR_EL1_ATA0);
-	isb();
+
+	mte_cpu_setup();
 
 	/*
 	 * Clear the tags in the zero page. This needs to be done via the
@@ -2088,12 +2098,22 @@ cpucap_panic_on_conflict(const struct arm64_cpu_capabilities *cap)
 
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
+		.capability = ARM64_ALWAYS_BOOT,
+		.type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
+		.matches = has_always,
+	},
+	{
+		.capability = ARM64_ALWAYS_SYSTEM,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_always,
+	},
+	{
 		.desc = "GIC system register CPU interface",
 		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
 		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
 		.matches = has_useable_gicv3_cpuif,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
-		.field_pos = ID_AA64PFR0_GIC_SHIFT,
+		.field_pos = ID_AA64PFR0_EL1_GIC_SHIFT,
 		.field_width = 4,
 		.sign = FTR_UNSIGNED,
 		.min_field_value = 1,
@@ -2104,7 +2124,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64MMFR0_EL1,
-		.field_pos = ID_AA64MMFR0_ECV_SHIFT,
+		.field_pos = ID_AA64MMFR0_EL1_ECV_SHIFT,
 		.field_width = 4,
 		.sign = FTR_UNSIGNED,
 		.min_field_value = 1,
@@ -2116,7 +2136,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64MMFR1_EL1,
-		.field_pos = ID_AA64MMFR1_PAN_SHIFT,
+		.field_pos = ID_AA64MMFR1_EL1_PAN_SHIFT,
 		.field_width = 4,
 		.sign = FTR_UNSIGNED,
 		.min_field_value = 1,
@@ -2130,7 +2150,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64MMFR1_EL1,
-		.field_pos = ID_AA64MMFR1_PAN_SHIFT,
+		.field_pos = ID_AA64MMFR1_EL1_PAN_SHIFT,
 		.field_width = 4,
 		.sign = FTR_UNSIGNED,
 		.min_field_value = 3,
@@ -2168,9 +2188,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_32bit_el0,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64PFR0_EL0_SHIFT,
+		.field_pos = ID_AA64PFR0_EL1_EL0_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR0_ELx_32BIT_64BIT,
+		.min_field_value = ID_AA64PFR0_EL1_ELx_32BIT_64BIT,
 	},
 #ifdef CONFIG_KVM
 	{
@@ -2180,9 +2200,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64PFR0_EL1_SHIFT,
+		.field_pos = ID_AA64PFR0_EL1_EL1_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR0_ELx_32BIT_64BIT,
+		.min_field_value = ID_AA64PFR0_EL1_ELx_32BIT_64BIT,
 	},
 	{
 		.desc = "Protected KVM",
@@ -2201,7 +2221,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		 * more details.
 		 */
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
-		.field_pos = ID_AA64PFR0_CSV3_SHIFT,
+		.field_pos = ID_AA64PFR0_EL1_CSV3_SHIFT,
 		.field_width = 4,
 		.min_field_value = 1,
 		.matches = unmap_kernel_at_el0,
@@ -2244,9 +2264,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_SVE,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64PFR0_SVE_SHIFT,
+		.field_pos = ID_AA64PFR0_EL1_SVE_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR0_SVE,
+		.min_field_value = ID_AA64PFR0_EL1_SVE_IMP,
 		.matches = has_cpuid_feature,
 		.cpu_enable = sve_kernel_enable,
 	},
@@ -2259,9 +2279,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64PFR0_RAS_SHIFT,
+		.field_pos = ID_AA64PFR0_EL1_RAS_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR0_RAS_V1,
+		.min_field_value = ID_AA64PFR0_EL1_RAS_IMP,
 		.cpu_enable = cpu_clear_disr,
 	},
 #endif /* CONFIG_ARM64_RAS_EXTN */
@@ -2278,9 +2298,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_amu,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64PFR0_AMU_SHIFT,
+		.field_pos = ID_AA64PFR0_EL1_AMU_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR0_AMU,
+		.min_field_value = ID_AA64PFR0_EL1_AMU_IMP,
 		.cpu_enable = cpu_amu_enable,
 	},
 #endif /* CONFIG_ARM64_AMU_EXTN */
@@ -2303,7 +2323,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HAS_STAGE2_FWB,
 		.sys_reg = SYS_ID_AA64MMFR2_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64MMFR2_FWB_SHIFT,
+		.field_pos = ID_AA64MMFR2_EL1_FWB_SHIFT,
 		.field_width = 4,
 		.min_field_value = 1,
 		.matches = has_cpuid_feature,
@@ -2314,7 +2334,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HAS_ARMv8_4_TTL,
 		.sys_reg = SYS_ID_AA64MMFR2_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64MMFR2_TTL_SHIFT,
+		.field_pos = ID_AA64MMFR2_EL1_TTL_SHIFT,
 		.field_width = 4,
 		.min_field_value = 1,
 		.matches = has_cpuid_feature,
@@ -2344,7 +2364,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HW_DBM,
 		.sys_reg = SYS_ID_AA64MMFR1_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64MMFR1_HADBS_SHIFT,
+		.field_pos = ID_AA64MMFR1_EL1_HAFDBS_SHIFT,
 		.field_width = 4,
 		.min_field_value = 2,
 		.matches = has_hw_dbm,
@@ -2367,10 +2387,10 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64PFR1_EL1,
-		.field_pos = ID_AA64PFR1_SSBS_SHIFT,
+		.field_pos = ID_AA64PFR1_EL1_SSBS_SHIFT,
 		.field_width = 4,
 		.sign = FTR_UNSIGNED,
-		.min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY,
+		.min_field_value = ID_AA64PFR1_EL1_SSBS_IMP,
 	},
 #ifdef CONFIG_ARM64_CNP
 	{
@@ -2380,7 +2400,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_useable_cnp,
 		.sys_reg = SYS_ID_AA64MMFR2_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64MMFR2_CNP_SHIFT,
+		.field_pos = ID_AA64MMFR2_EL1_CnP_SHIFT,
 		.field_width = 4,
 		.min_field_value = 1,
 		.cpu_enable = cpu_enable_cnp,
@@ -2485,7 +2505,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
 		.matches = can_use_gic_priorities,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
-		.field_pos = ID_AA64PFR0_GIC_SHIFT,
+		.field_pos = ID_AA64PFR0_EL1_GIC_SHIFT,
 		.field_width = 4,
 		.sign = FTR_UNSIGNED,
 		.min_field_value = 1,
@@ -2499,7 +2519,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.sys_reg = SYS_ID_AA64MMFR2_EL1,
 		.sign = FTR_UNSIGNED,
 		.field_width = 4,
-		.field_pos = ID_AA64MMFR2_E0PD_SHIFT,
+		.field_pos = ID_AA64MMFR2_EL1_E0PD_SHIFT,
 		.matches = has_cpuid_feature,
 		.min_field_value = 1,
 		.cpu_enable = cpu_enable_e0pd,
@@ -2528,9 +2548,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.cpu_enable = bti_enable,
 		.sys_reg = SYS_ID_AA64PFR1_EL1,
-		.field_pos = ID_AA64PFR1_BT_SHIFT,
+		.field_pos = ID_AA64PFR1_EL1_BT_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR1_BT_BTI,
+		.min_field_value = ID_AA64PFR1_EL1_BT_IMP,
 		.sign = FTR_UNSIGNED,
 	},
 #endif
@@ -2541,9 +2561,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64PFR1_EL1,
-		.field_pos = ID_AA64PFR1_MTE_SHIFT,
+		.field_pos = ID_AA64PFR1_EL1_MTE_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR1_MTE,
+		.min_field_value = ID_AA64PFR1_EL1_MTE_MTE2,
 		.sign = FTR_UNSIGNED,
 		.cpu_enable = cpu_enable_mte,
 	},
@@ -2553,9 +2573,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64PFR1_EL1,
-		.field_pos = ID_AA64PFR1_MTE_SHIFT,
+		.field_pos = ID_AA64PFR1_EL1_MTE_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR1_MTE_ASYMM,
+		.min_field_value = ID_AA64PFR1_EL1_MTE_MTE3,
 		.sign = FTR_UNSIGNED,
 	},
 #endif /* CONFIG_ARM64_MTE */
@@ -2577,9 +2597,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_SME,
 		.sys_reg = SYS_ID_AA64PFR1_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64PFR1_SME_SHIFT,
+		.field_pos = ID_AA64PFR1_EL1_SME_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64PFR1_SME,
+		.min_field_value = ID_AA64PFR1_EL1_SME_IMP,
 		.matches = has_cpuid_feature,
 		.cpu_enable = sme_kernel_enable,
 	},
@@ -2614,9 +2634,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.sys_reg = SYS_ID_AA64MMFR1_EL1,
 		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64MMFR1_TIDCP1_SHIFT,
+		.field_pos = ID_AA64MMFR1_EL1_TIDCP1_SHIFT,
 		.field_width = 4,
-		.min_field_value = ID_AA64MMFR1_TIDCP1_IMP,
+		.min_field_value = ID_AA64MMFR1_EL1_TIDCP1_IMP,
 		.matches = has_cpuid_feature,
 		.cpu_enable = cpu_trap_el0_impdef,
 	},
@@ -2624,7 +2644,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 };
 
 #define HWCAP_CPUID_MATCH(reg, field, width, s, min_value)			\
-		.matches = has_cpuid_feature,					\
+		.matches = has_user_cpuid_feature,					\
 		.sys_reg = reg,							\
 		.field_pos = field,						\
 		.field_width = width,						\
@@ -2708,11 +2728,11 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RNDR_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_FP_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_DIT_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_JSCVT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT),
@@ -2725,38 +2745,39 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_EBF16),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DGH_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_I8MM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM),
-	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
+	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_EL1_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_EL1_SVE_IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BitPerm_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BF16_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BF16_EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SHA3_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SHA3_IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SM4_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SM4_IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_I8MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_I8MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_F32MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_F32MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_F64MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
 #endif
-	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS),
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SSBS_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SSBS_SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS),
 #ifdef CONFIG_ARM64_BTI
-	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_BT_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_BT_BTI, CAP_HWCAP, KERNEL_HWCAP_BTI),
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_BT_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_BT_IMP, CAP_HWCAP, KERNEL_HWCAP_BTI),
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
 #endif
 #ifdef CONFIG_ARM64_MTE
-	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_MTE, CAP_HWCAP, KERNEL_HWCAP_MTE),
-	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_MTE_ASYMM, CAP_HWCAP, KERNEL_HWCAP_MTE3),
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_MTE_MTE2, CAP_HWCAP, KERNEL_HWCAP_MTE),
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_MTE_MTE3, CAP_HWCAP, KERNEL_HWCAP_MTE3),
 #endif /* CONFIG_ARM64_MTE */
-	HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
-	HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
+	HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
+	HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
 	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
 	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_WFxT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_WFxT_IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
 #ifdef CONFIG_ARM64_SME
-	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SME, CAP_HWCAP, KERNEL_HWCAP_SME),
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SME_IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_FA64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F64F64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
@@ -2929,9 +2950,6 @@ static void __init enable_cpu_capabilities(u16 scope_mask)
 		if (!cpus_have_cap(num))
 			continue;
 
-		/* Ensure cpus_have_const_cap(num) works */
-		static_branch_enable(&cpu_hwcap_keys[num]);
-
 		if (boot_scope && caps->cpu_enable)
 			/*
 			 * Capabilities with SCOPE_BOOT_CPU scope are finalised
@@ -3102,7 +3120,7 @@ static void verify_hyp_capabilities(void)
 
 	/* Verify IPA range */
 	parange = cpuid_feature_extract_unsigned_field(mmfr0,
-				ID_AA64MMFR0_PARANGE_SHIFT);
+				ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 	ipa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
 	if (ipa_max < get_kvm_ipa_limit()) {
 		pr_crit("CPU%d: IPA range mismatch\n", smp_processor_id());
@@ -3253,9 +3271,6 @@ void __init setup_cpu_features(void)
 	sme_setup();
 	minsigstksz_setup();
 
-	/* Advertise that we have computed the system capabilities */
-	finalize_system_capabilities();
-
 	/*
 	 * Check for sane CTR_EL0.CWG value.
 	 */