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

Pull arm64 updates from Catalin Marinas: - Support for arm64 SME 2 and 2.1. SME2 introduces a new 512-bit architectural register (ZT0, for the look-up table feature) that Linux needs to save/restore - Include TPIDR2 in the signal context and add the corresponding kselftests - Perf updates: Arm SPEv1.2 support, HiSilicon uncore PMU updates, ACPI support to the Marvell DDR and TAD PMU drivers, reset DTM_PMU_CONFIG (ARM CMN) at probe time - Support for DYNAMIC_FTRACE_WITH_CALL_OPS on arm64 - Permit EFI boot with MMU and caches on. Instead of cleaning the entire loaded kernel image to the PoC and disabling the MMU and caches before branching to the kernel bare metal entry point, leave the MMU and caches enabled and rely on EFI's cacheable 1:1 mapping of all of system RAM to populate the initial page tables - Expose the AArch32 (compat) ELF_HWCAP features to user in an arm64 kernel (the arm32 kernel only defines the values) - Harden the arm64 shadow call stack pointer handling: stash the shadow stack pointer in the task struct on interrupt, load it directly from this structure - Signal handling cleanups to remove redundant validation of size information and avoid reading the same data from userspace twice - Refactor the hwcap macros to make use of the automatically generated ID registers. It should make new hwcaps writing less error prone - Further arm64 sysreg conversion and some fixes - arm64 kselftest fixes and improvements - Pointer authentication cleanups: don't sign leaf functions, unify asm-arch manipulation - Pseudo-NMI code generation optimisations - Minor fixes for SME and TPIDR2 handling - Miscellaneous updates: ARCH_FORCE_MAX_ORDER is now selectable, replace strtobool() to kstrtobool() in the cpufeature.c code, apply dynamic shadow call stack in two passes, intercept pfn changes in set_pte_at() without the required break-before-make sequence, attempt to dump all instructions on unhandled kernel faults * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (130 commits) arm64: fix .idmap.text assertion for large kernels kselftest/arm64: Don't require FA64 for streaming SVE+ZA tests kselftest/arm64: Copy whole EXTRA context arm64: kprobes: Drop ID map text from kprobes blacklist perf: arm_spe: Print the version of SPE detected perf: arm_spe: Add support for SPEv1.2 inverted event filtering perf: Add perf_event_attr::config3 arm64/sme: Fix __finalise_el2 SMEver check drivers/perf: fsl_imx8_ddr_perf: Remove set-but-not-used variable arm64/signal: Only read new data when parsing the ZT context arm64/signal: Only read new data when parsing the ZA context arm64/signal: Only read new data when parsing the SVE context arm64/signal: Avoid rereading context frame sizes arm64/signal: Make interface for restore_fpsimd_context() consistent arm64/signal: Remove redundant size validation from parse_user_sigframe() arm64/signal: Don't redundantly verify FPSIMD magic arm64/cpufeature: Use helper macros to specify hwcaps arm64/cpufeature: Always use symbolic name for feature value in hwcaps arm64/sysreg: Initial unsigned annotations for ID registers arm64/sysreg: Initial annotation of signed ID registers ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2023-02-21 15:27:48 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2023-02-21 15:27:48 -0800
commit: 8bf1a529cd664c8e5268381f1e24fe67aa611dd3 (patch)
tree: c5cec84941923778e4e2ec5a5d65e2fc8ea71b58 /arch/arm64/kernel
parent: b327dfe05258e09c8db6e1e091c2e6d84dd426a6 (diff)
parent: d54170812ef1c80e0fa3ed3e554a0bbfc2920d9d (diff)
23 files changed, 900 insertions, 276 deletions
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 2234624536d9..ae345b06e9f7 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -9,6 +9,7 @@
 
 #include <linux/arm_sdei.h>
 #include <linux/sched.h>
+#include <linux/ftrace.h>
 #include <linux/kexec.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
@@ -194,5 +195,8 @@ int main(void)
   DEFINE(KIMAGE_START,			offsetof(struct kimage, start));
   BLANK();
 #endif
+#ifdef CONFIG_FUNCTION_TRACER
+  DEFINE(FTRACE_OPS_FUNC,		offsetof(struct ftrace_ops, func));
+#endif
   return 0;
 }
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index a77315b338e6..45a42cf2191c 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -65,6 +65,7 @@
 #include <linux/bsearch.h>
 #include <linux/cpumask.h>
 #include <linux/crash_dump.h>
+#include <linux/kstrtox.h>
 #include <linux/sort.h>
 #include <linux/stop_machine.h>
 #include <linux/sysfs.h>
@@ -283,16 +284,26 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I32_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0),
 	ARM64_FTR_END,
 };
@@ -444,8 +455,8 @@ static const struct arm64_ftr_bits ftr_mvfr0[] = {
 
 static const struct arm64_ftr_bits ftr_mvfr1[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDFMAC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDSP_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDInt_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDLS_SHIFT, 4, 0),
@@ -529,12 +540,12 @@ static const struct arm64_ftr_bits ftr_id_mmfr5[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_isar6[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SPECRES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_JSCVT_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
@@ -562,7 +573,7 @@ static const struct arm64_ftr_bits ftr_id_pfr1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_pfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_CSV3_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
@@ -1795,7 +1806,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 static int __init parse_kpti(char *str)
 {
 	bool enabled;
-	int ret = strtobool(str, &enabled);
+	int ret = kstrtobool(str, &enabled);
 
 	if (ret)
 		return ret;
@@ -2039,14 +2050,50 @@ static bool enable_pseudo_nmi;
 
 static int __init early_enable_pseudo_nmi(char *p)
 {
-	return strtobool(p, &enable_pseudo_nmi);
+	return kstrtobool(p, &enable_pseudo_nmi);
 }
 early_param("irqchip.gicv3_pseudo_nmi", early_enable_pseudo_nmi);
 
 static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
 				   int scope)
 {
-	return enable_pseudo_nmi && has_useable_gicv3_cpuif(entry, scope);
+	/*
+	 * ARM64_HAS_GIC_CPUIF_SYSREGS has a lower index, and is a boot CPU
+	 * feature, so will be detected earlier.
+	 */
+	BUILD_BUG_ON(ARM64_HAS_GIC_PRIO_MASKING <= ARM64_HAS_GIC_CPUIF_SYSREGS);
+	if (!cpus_have_cap(ARM64_HAS_GIC_CPUIF_SYSREGS))
+		return false;
+
+	return enable_pseudo_nmi;
+}
+
+static bool has_gic_prio_relaxed_sync(const struct arm64_cpu_capabilities *entry,
+				      int scope)
+{
+	/*
+	 * If we're not using priority masking then we won't be poking PMR_EL1,
+	 * and there's no need to relax synchronization of writes to it, and
+	 * ICC_CTLR_EL1 might not be accessible and we must avoid reads from
+	 * that.
+	 *
+	 * ARM64_HAS_GIC_PRIO_MASKING has a lower index, and is a boot CPU
+	 * feature, so will be detected earlier.
+	 */
+	BUILD_BUG_ON(ARM64_HAS_GIC_PRIO_RELAXED_SYNC <= ARM64_HAS_GIC_PRIO_MASKING);
+	if (!cpus_have_cap(ARM64_HAS_GIC_PRIO_MASKING))
+		return false;
+
+	/*
+	 * When Priority Mask Hint Enable (PMHE) == 0b0, PMR is not used as a
+	 * hint for interrupt distribution, a DSB is not necessary when
+	 * unmasking IRQs via PMR, and we can relax the barrier to a NOP.
+	 *
+	 * Linux itself doesn't use 1:N distribution, so has no need to
+	 * set PMHE. The only reason to have it set is if EL3 requires it
+	 * (and we can't change it).
+	 */
+	return (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) == 0;
 }
 #endif
 
@@ -2142,7 +2189,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	},
 	{
 		.desc = "GIC system register CPU interface",
-		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
+		.capability = ARM64_HAS_GIC_CPUIF_SYSREGS,
 		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
 		.matches = has_useable_gicv3_cpuif,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
@@ -2534,14 +2581,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		 * Depends on having GICv3
 		 */
 		.desc = "IRQ priority masking",
-		.capability = ARM64_HAS_IRQ_PRIO_MASKING,
+		.capability = ARM64_HAS_GIC_PRIO_MASKING,
 		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
 		.matches = can_use_gic_priorities,
-		.sys_reg = SYS_ID_AA64PFR0_EL1,
-		.field_pos = ID_AA64PFR0_EL1_GIC_SHIFT,
-		.field_width = 4,
-		.sign = FTR_UNSIGNED,
-		.min_field_value = 1,
+	},
+	{
+		/*
+		 * Depends on ARM64_HAS_GIC_PRIO_MASKING
+		 */
+		.capability = ARM64_HAS_GIC_PRIO_RELAXED_SYNC,
+		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
+		.matches = has_gic_prio_relaxed_sync,
 	},
 #endif
 #ifdef CONFIG_ARM64_E0PD
@@ -2649,6 +2699,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.cpu_enable = fa64_kernel_enable,
 	},
+	{
+		.desc = "SME2",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_SME2,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR1_EL1_SME_SHIFT,
+		.field_width = ID_AA64PFR1_EL1_SME_WIDTH,
+		.min_field_value = ID_AA64PFR1_EL1_SME_SME2,
+		.matches = has_cpuid_feature,
+		.cpu_enable = sme2_kernel_enable,
+	},
 #endif /* CONFIG_ARM64_SME */
 	{
 		.desc = "WFx with timeout",
@@ -2688,13 +2750,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{},
 };
 
-#define HWCAP_CPUID_MATCH(reg, field, width, s, min_value)			\
+#define HWCAP_CPUID_MATCH(reg, field, min_value)			\
 		.matches = has_user_cpuid_feature,					\
-		.sys_reg = reg,							\
-		.field_pos = field,						\
-		.field_width = width,						\
-		.sign = s,							\
-		.min_field_value = min_value,
+		.sys_reg = SYS_##reg,							\
+		.field_pos = reg##_##field##_SHIFT,						\
+		.field_width = reg##_##field##_WIDTH,						\
+		.sign = reg##_##field##_SIGNED,							\
+		.min_field_value = reg##_##field##_##min_value,
 
 #define __HWCAP_CAP(name, cap_type, cap)					\
 		.desc = name,							\
@@ -2702,10 +2764,10 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.hwcap_type = cap_type,						\
 		.hwcap = cap,							\
 
-#define HWCAP_CAP(reg, field, width, s, min_value, cap_type, cap)		\
+#define HWCAP_CAP(reg, field, min_value, cap_type, cap)		\
 	{									\
 		__HWCAP_CAP(#cap, cap_type, cap)				\
-		HWCAP_CPUID_MATCH(reg, field, width, s, min_value) 		\
+		HWCAP_CPUID_MATCH(reg, field, min_value) 		\
 	}
 
 #define HWCAP_MULTI_CAP(list, cap_type, cap)					\
@@ -2724,115 +2786,114 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 #ifdef CONFIG_ARM64_PTR_AUTH
 static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = {
 	{
-		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_APA_SHIFT,
-				  4, FTR_UNSIGNED,
-				  ID_AA64ISAR1_EL1_APA_PAuth)
+		HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, APA, PAuth)
 	},
 	{
-		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_APA3_SHIFT,
-				  4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_APA3_PAuth)
+		HWCAP_CPUID_MATCH(ID_AA64ISAR2_EL1, APA3, PAuth)
 	},
 	{
-		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_API_SHIFT,
-				  4, FTR_UNSIGNED, ID_AA64ISAR1_EL1_API_PAuth)
+		HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, API, PAuth)
 	},
 	{},
 };
 
 static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = {
 	{
-		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_GPA_SHIFT,
-				  4, FTR_UNSIGNED, ID_AA64ISAR1_EL1_GPA_IMP)
+		HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, GPA, IMP)
 	},
 	{
-		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_GPA3_SHIFT,
-				  4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_GPA3_IMP)
+		HWCAP_CPUID_MATCH(ID_AA64ISAR2_EL1, GPA3, IMP)
 	},
 	{
-		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_GPI_SHIFT,
-				  4, FTR_UNSIGNED, ID_AA64ISAR1_EL1_GPI_IMP)
+		HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, GPI, IMP)
 	},
 	{},
 };
 #endif
 
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_ATOMIC_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RDM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SM3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SM4_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_DP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_FHM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
-	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_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),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_FCMA_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_LRCPC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_LRCPC_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_FRINTTS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_SB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16),
-	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_EL1_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, SHA1, IMP, CAP_HWCAP, KERNEL_HWCAP_SHA1),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, SHA2, SHA256, CAP_HWCAP, KERNEL_HWCAP_SHA2),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, SHA2, SHA512, CAP_HWCAP, KERNEL_HWCAP_SHA512),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, CRC32, IMP, CAP_HWCAP, KERNEL_HWCAP_CRC32),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, ATOMIC, IMP, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, RDM, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SHA3),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, SM3, IMP, CAP_HWCAP, KERNEL_HWCAP_SM3),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SM4),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, DP, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, FHM, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
+	HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG),
+	HWCAP_CAP(ID_AA64PFR0_EL1, FP, IMP, CAP_HWCAP, KERNEL_HWCAP_FP),
+	HWCAP_CAP(ID_AA64PFR0_EL1, FP, FP16, CAP_HWCAP, KERNEL_HWCAP_FPHP),
+	HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
+	HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, FP16, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
+	HWCAP_CAP(ID_AA64PFR0_EL1, DIT, IMP, CAP_HWCAP, KERNEL_HWCAP_DIT),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, IMP, CAP_HWCAP, KERNEL_HWCAP_DCPOP),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, DPB2, CAP_HWCAP, KERNEL_HWCAP_DCPODP),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, JSCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_JSCVT),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, FCMA, IMP, CAP_HWCAP, KERNEL_HWCAP_FCMA),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, IMP, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, LRCPC2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, FRINTTS, IMP, CAP_HWCAP, KERNEL_HWCAP_FRINT),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, SB, IMP, CAP_HWCAP, KERNEL_HWCAP_SB),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_BF16),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_EBF16),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, DGH, IMP, CAP_HWCAP, KERNEL_HWCAP_DGH),
+	HWCAP_CAP(ID_AA64ISAR1_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_I8MM),
+	HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_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_SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
-	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),
+	HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
+	HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
 #endif
-	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SSBS_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SSBS_SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS),
+	HWCAP_CAP(ID_AA64PFR1_EL1, SSBS, SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS),
 #ifdef CONFIG_ARM64_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),
+	HWCAP_CAP(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_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),
+	HWCAP_CAP(ID_AA64PFR1_EL1, MTE, MTE2, CAP_HWCAP, KERNEL_HWCAP_MTE),
+	HWCAP_CAP(ID_AA64PFR1_EL1, MTE, MTE3, CAP_HWCAP, KERNEL_HWCAP_MTE3),
 #endif /* CONFIG_ARM64_MTE */
-	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_CSSC_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_CSSC_IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC),
-	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_RPRFM_IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM),
-	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),
+	HWCAP_CAP(ID_AA64MMFR0_EL1, ECV, IMP, CAP_HWCAP, KERNEL_HWCAP_ECV),
+	HWCAP_CAP(ID_AA64MMFR1_EL1, AFP, IMP, CAP_HWCAP, KERNEL_HWCAP_AFP),
+	HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC),
+	HWCAP_CAP(ID_AA64ISAR2_EL1, RPRFM, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM),
+	HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES),
+	HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
 #ifdef CONFIG_ARM64_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),
-	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I8I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
-	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
-	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_B16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
-	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F32F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+	HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
 #endif /* CONFIG_ARM64_SME */
 	{},
 };
@@ -2862,15 +2923,23 @@ static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope)
 static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = {
 #ifdef CONFIG_COMPAT
 	HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON),
-	HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_EL1_SIMDFMAC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
+	HWCAP_CAP(MVFR1_EL1, SIMDFMAC, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
 	/* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */
-	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
-	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
+	HWCAP_CAP(MVFR0_EL1, FPDP, VFPv3, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
+	HWCAP_CAP(MVFR0_EL1, FPDP, VFPv3, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
+	HWCAP_CAP(MVFR1_EL1, FPHP, FP16, CAP_COMPAT_HWCAP, COMPAT_HWCAP_FPHP),
+	HWCAP_CAP(MVFR1_EL1, SIMDHP, SIMDHP_FLOAT, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDHP),
+	HWCAP_CAP(ID_ISAR5_EL1, AES, VMULL, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
+	HWCAP_CAP(ID_ISAR5_EL1, AES, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
+	HWCAP_CAP(ID_ISAR5_EL1, SHA1, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
+	HWCAP_CAP(ID_ISAR5_EL1, SHA2, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
+	HWCAP_CAP(ID_ISAR5_EL1, CRC32, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
+	HWCAP_CAP(ID_ISAR6_EL1, DP, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDDP),
+	HWCAP_CAP(ID_ISAR6_EL1, FHM, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDFHM),
+	HWCAP_CAP(ID_ISAR6_EL1, SB, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SB),
+	HWCAP_CAP(ID_ISAR6_EL1, BF16, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDBF16),
+	HWCAP_CAP(ID_ISAR6_EL1, I8MM, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_I8MM),
+	HWCAP_CAP(ID_PFR2_EL1, SSBS, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SSBS),
 #endif
 	{},
 };
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 379695262b77..eb4378c23b3c 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -119,6 +119,12 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_CSSC]		= "cssc",
 	[KERNEL_HWCAP_RPRFM]		= "rprfm",
 	[KERNEL_HWCAP_SVE2P1]		= "sve2p1",
+	[KERNEL_HWCAP_SME2]		= "sme2",
+	[KERNEL_HWCAP_SME2P1]		= "sme2p1",
+	[KERNEL_HWCAP_SME_I16I32]	= "smei16i32",
+	[KERNEL_HWCAP_SME_BI32I32]	= "smebi32i32",
+	[KERNEL_HWCAP_SME_B16B16]	= "smeb16b16",
+	[KERNEL_HWCAP_SME_F16F16]	= "smef16f16",
 };
 
 #ifdef CONFIG_COMPAT
@@ -146,6 +152,12 @@ static const char *const compat_hwcap_str[] = {
 	[COMPAT_KERNEL_HWCAP(VFPD32)]	= NULL,	/* Not possible on arm64 */
 	[COMPAT_KERNEL_HWCAP(LPAE)]	= "lpae",
 	[COMPAT_KERNEL_HWCAP(EVTSTRM)]	= "evtstrm",
+	[COMPAT_KERNEL_HWCAP(FPHP)]	= "fphp",
+	[COMPAT_KERNEL_HWCAP(ASIMDHP)]	= "asimdhp",
+	[COMPAT_KERNEL_HWCAP(ASIMDDP)]	= "asimddp",
+	[COMPAT_KERNEL_HWCAP(ASIMDFHM)]	= "asimdfhm",
+	[COMPAT_KERNEL_HWCAP(ASIMDBF16)] = "asimdbf16",
+	[COMPAT_KERNEL_HWCAP(I8MM)]	= "i8mm",
 };
 
 #define COMPAT_KERNEL_HWCAP2(x)	const_ilog2(COMPAT_HWCAP2_ ## x)
@@ -155,6 +167,8 @@ static const char *const compat_hwcap2_str[] = {
 	[COMPAT_KERNEL_HWCAP2(SHA1)]	= "sha1",
 	[COMPAT_KERNEL_HWCAP2(SHA2)]	= "sha2",
 	[COMPAT_KERNEL_HWCAP2(CRC32)]	= "crc32",
+	[COMPAT_KERNEL_HWCAP2(SB)]	= "sb",
+	[COMPAT_KERNEL_HWCAP2(SSBS)]	= "ssbs",
 };
 #endif /* CONFIG_COMPAT */
 
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 229436f33df5..6325db1a2179 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -100,25 +100,35 @@ SYM_FUNC_START(sme_set_vq)
 SYM_FUNC_END(sme_set_vq)
 
 /*
- * Save the SME state
+ * Save the ZA and ZT state
  *
  * x0 - pointer to buffer for state
+ * x1 - number of ZT registers to save
  */
-SYM_FUNC_START(za_save_state)
-	_sme_rdsvl	1, 1		// x1 = VL/8
-	sme_save_za 0, x1, 12
+SYM_FUNC_START(sme_save_state)
+	_sme_rdsvl	2, 1		// x2 = VL/8
+	sme_save_za 0, x2, 12		// Leaves x0 pointing to the end of ZA
+
+	cbz	x1, 1f
+	_str_zt 0
+1:
 	ret
-SYM_FUNC_END(za_save_state)
+SYM_FUNC_END(sme_save_state)
 
 /*
- * Load the SME state
+ * Load the ZA and ZT state
  *
  * x0 - pointer to buffer for state
+ * x1 - number of ZT registers to save
  */
-SYM_FUNC_START(za_load_state)
-	_sme_rdsvl	1, 1		// x1 = VL/8
-	sme_load_za 0, x1, 12
+SYM_FUNC_START(sme_load_state)
+	_sme_rdsvl	2, 1		// x2 = VL/8
+	sme_load_za 0, x2, 12		// Leaves x0 pointing to the end of ZA
+
+	cbz	x1, 1f
+	_ldr_zt 0
+1:
 	ret
-SYM_FUNC_END(za_load_state)
+SYM_FUNC_END(sme_load_state)
 
 #endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 3b625f76ffba..350ed81324ac 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -65,13 +65,35 @@ SYM_CODE_START(ftrace_caller)
 	stp	x29, x30, [sp, #FREGS_SIZE]
 	add	x29, sp, #FREGS_SIZE
 
-	sub	x0, x30, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
-	mov	x1, x9				// parent_ip (callsite's LR)
-	ldr_l	x2, function_trace_op		// op
-	mov	x3, sp				// regs
+	/* Prepare arguments for the the tracer func */
+	sub	x0, x30, #AARCH64_INSN_SIZE		// ip (callsite's BL insn)
+	mov	x1, x9					// parent_ip (callsite's LR)
+	mov	x3, sp					// regs
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	/*
+	 * The literal pointer to the ops is at an 8-byte aligned boundary
+	 * which is either 12 or 16 bytes before the BL instruction in the call
+	 * site. See ftrace_call_adjust() for details.
+	 *
+	 * Therefore here the LR points at `literal + 16` or `literal + 20`,
+	 * and we can find the address of the literal in either case by
+	 * aligning to an 8-byte boundary and subtracting 16. We do the
+	 * alignment first as this allows us to fold the subtraction into the
+	 * LDR.
+	 */
+	bic	x2, x30, 0x7
+	ldr	x2, [x2, #-16]				// op
+
+	ldr	x4, [x2, #FTRACE_OPS_FUNC]		// op->func
+	blr	x4					// op->func(ip, parent_ip, op, regs)
+
+#else
+	ldr_l   x2, function_trace_op			// op
 
 SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
-	bl	ftrace_stub
+	bl      ftrace_stub				// func(ip, parent_ip, op, regs)
+#endif
 
 /*
  * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 11cb99c4d298..ab2a6e33c052 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -275,7 +275,7 @@ alternative_if ARM64_HAS_ADDRESS_AUTH
 alternative_else_nop_endif
 1:
 
-	scs_load tsk
+	scs_load_current
 	.else
 	add	x21, sp, #PT_REGS_SIZE
 	get_current_task tsk
@@ -311,13 +311,16 @@ alternative_else_nop_endif
 	.endif
 
 #ifdef CONFIG_ARM64_PSEUDO_NMI
-	/* Save pmr */
-alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+alternative_if_not ARM64_HAS_GIC_PRIO_MASKING
+	b	.Lskip_pmr_save\@
+alternative_else_nop_endif
+
 	mrs_s	x20, SYS_ICC_PMR_EL1
 	str	x20, [sp, #S_PMR_SAVE]
 	mov	x20, #GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET
 	msr_s	SYS_ICC_PMR_EL1, x20
-alternative_else_nop_endif
+
+.Lskip_pmr_save\@:
 #endif
 
 	/*
@@ -336,15 +339,19 @@ alternative_else_nop_endif
 	.endif
 
 #ifdef CONFIG_ARM64_PSEUDO_NMI
-	/* Restore pmr */
-alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+alternative_if_not ARM64_HAS_GIC_PRIO_MASKING
+	b	.Lskip_pmr_restore\@
+alternative_else_nop_endif
+
 	ldr	x20, [sp, #S_PMR_SAVE]
 	msr_s	SYS_ICC_PMR_EL1, x20
-	mrs_s	x21, SYS_ICC_CTLR_EL1
-	tbz	x21, #6, .L__skip_pmr_sync\@	// Check for ICC_CTLR_EL1.PMHE
-	dsb	sy				// Ensure priority change is seen by redistributor
-.L__skip_pmr_sync\@:
+
+	/* Ensure priority change is seen by redistributor */
+alternative_if_not ARM64_HAS_GIC_PRIO_RELAXED_SYNC
+	dsb	sy
 alternative_else_nop_endif
+
+.Lskip_pmr_restore\@:
 #endif
 
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
@@ -848,7 +855,7 @@ SYM_FUNC_START(cpu_switch_to)
 	msr	sp_el0, x1
 	ptrauth_keys_install_kernel x1, x8, x9, x10
 	scs_save x0
-	scs_load x1
+	scs_load_current
 	ret
 SYM_FUNC_END(cpu_switch_to)
 NOKPROBE(cpu_switch_to)
@@ -876,19 +883,19 @@ NOKPROBE(ret_from_fork)
  */
 SYM_FUNC_START(call_on_irq_stack)
 #ifdef CONFIG_SHADOW_CALL_STACK
-	stp	scs_sp, xzr, [sp, #-16]!
+	get_current_task x16
+	scs_save x16
 	ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x17
 #endif
+
 	/* Create a frame record to save our LR and SP (implicit in FP) */
 	stp	x29, x30, [sp, #-16]!
 	mov	x29, sp
 
 	ldr_this_cpu x16, irq_stack_ptr, x17
-	mov	x15, #IRQ_STACK_SIZE
-	add	x16, x16, x15
 
 	/* Move to the new stack and call the function there */
-	mov	sp, x16
+	add	sp, x16, #IRQ_STACK_SIZE
 	blr	x1
 
 	/*
@@ -897,9 +904,7 @@ SYM_FUNC_START(call_on_irq_stack)
 	 */
 	mov	sp, x29
 	ldp	x29, x30, [sp], #16
-#ifdef CONFIG_SHADOW_CALL_STACK
-	ldp	scs_sp, xzr, [sp], #16
-#endif
+	scs_load_current
 	ret
 SYM_FUNC_END(call_on_irq_stack)
 NOKPROBE(call_on_irq_stack)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index b6ef1af0122e..692dfefbe0ed 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -299,7 +299,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
 /*
  * TIF_SME controls whether a task can use SME without trapping while
  * in userspace, when TIF_SME is set then we must have storage
- * alocated in sve_state and za_state to store the contents of both ZA
+ * alocated in sve_state and sme_state to store the contents of both ZA
  * and the SVE registers for both streaming and non-streaming modes.
  *
  * If both SVCR.ZA and SVCR.SM are disabled then at any point we
@@ -429,7 +429,8 @@ static void task_fpsimd_load(void)
 		write_sysreg_s(current->thread.svcr, SYS_SVCR);
 
 		if (thread_za_enabled(&current->thread))
-			za_load_state(current->thread.za_state);
+			sme_load_state(current->thread.sme_state,
+				       system_supports_sme2());
 
 		if (thread_sm_enabled(&current->thread))
 			restore_ffr = system_supports_fa64();
@@ -490,7 +491,8 @@ static void fpsimd_save(void)
 		*svcr = read_sysreg_s(SYS_SVCR);
 
 		if (*svcr & SVCR_ZA_MASK)
-			za_save_state(last->za_state);
+			sme_save_state(last->sme_state,
+				       system_supports_sme2());
 
 		/* If we are in streaming mode override regular SVE. */
 		if (*svcr & SVCR_SM_MASK) {
@@ -1257,30 +1259,30 @@ void fpsimd_release_task(struct task_struct *dead_task)
 #ifdef CONFIG_ARM64_SME
 
 /*
- * Ensure that task->thread.za_state is allocated and sufficiently large.
+ * Ensure that task->thread.sme_state is allocated and sufficiently large.
  *
  * This function should be used only in preparation for replacing
- * task->thread.za_state with new data.  The memory is always zeroed
+ * task->thread.sme_state with new data.  The memory is always zeroed
  * here to prevent stale data from showing through: this is done in
  * the interest of testability and predictability, the architecture
  * guarantees that when ZA is enabled it will be zeroed.
  */
 void sme_alloc(struct task_struct *task)
 {
-	if (task->thread.za_state) {
-		memset(task->thread.za_state, 0, za_state_size(task));
+	if (task->thread.sme_state) {
+		memset(task->thread.sme_state, 0, sme_state_size(task));
 		return;
 	}
 
 	/* This could potentially be up to 64K. */
-	task->thread.za_state =
-		kzalloc(za_state_size(task), GFP_KERNEL);
+	task->thread.sme_state =
+		kzalloc(sme_state_size(task), GFP_KERNEL);
 }
 
 static void sme_free(struct task_struct *task)
 {
-	kfree(task->thread.za_state);
-	task->thread.za_state = NULL;
+	kfree(task->thread.sme_state);
+	task->thread.sme_state = NULL;
 }
 
 void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
@@ -1302,6 +1304,17 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
  * 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)
+{
+	/* 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)
 {
 	/* Allow use of FA64 */
@@ -1322,7 +1335,6 @@ u64 read_smcr_features(void)
 	unsigned int vq_max;
 
 	sme_kernel_enable(NULL);
-	sme_smstart_sm();
 
 	/*
 	 * Set the maximum possible VL.
@@ -1332,11 +1344,9 @@ u64 read_smcr_features(void)
 
 	smcr = read_sysreg_s(SYS_SMCR_EL1);
 	smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */
-	vq_max = sve_vq_from_vl(sve_get_vl());
+	vq_max = sve_vq_from_vl(sme_get_vl());
 	smcr |= vq_max - 1; /* set LEN field to maximum effective value */
 
-	sme_smstop_sm();
-
 	return smcr;
 }
 
@@ -1488,7 +1498,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 
 	sve_alloc(current, false);
 	sme_alloc(current);
-	if (!current->thread.sve_state || !current->thread.za_state) {
+	if (!current->thread.sve_state || !current->thread.sme_state) {
 		force_sig(SIGKILL);
 		return;
 	}
@@ -1609,7 +1619,7 @@ static void fpsimd_flush_thread_vl(enum vec_type type)
 void fpsimd_flush_thread(void)
 {
 	void *sve_state = NULL;
-	void *za_state = NULL;
+	void *sme_state = NULL;
 
 	if (!system_supports_fpsimd())
 		return;
@@ -1634,8 +1644,8 @@ void fpsimd_flush_thread(void)
 		clear_thread_flag(TIF_SME);
 
 		/* Defer kfree() while in atomic context */
-		za_state = current->thread.za_state;
-		current->thread.za_state = NULL;
+		sme_state = current->thread.sme_state;
+		current->thread.sme_state = NULL;
 
 		fpsimd_flush_thread_vl(ARM64_VEC_SME);
 		current->thread.svcr = 0;
@@ -1645,7 +1655,7 @@ void fpsimd_flush_thread(void)
 
 	put_cpu_fpsimd_context();
 	kfree(sve_state);
-	kfree(za_state);
+	kfree(sme_state);
 }
 
 /*
@@ -1711,7 +1721,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
-	last->za_state = current->thread.za_state;
+	last->sme_state = current->thread.sme_state;
 	last->sve_vl = task_get_sve_vl(current);
 	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index b30b955a8921..5545fe1a9012 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -60,6 +60,89 @@ int ftrace_regs_query_register_offset(const char *name)
 }
 #endif
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/*
+	 * When using mcount, addr is the address of the mcount call
+	 * instruction, and no adjustment is necessary.
+	 */
+	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
+		return addr;
+
+	/*
+	 * When using patchable-function-entry without pre-function NOPS, addr
+	 * is the address of the first NOP after the function entry point.
+	 *
+	 * The compiler has either generated:
+	 *
+	 * addr+00:	func:	NOP		// To be patched to MOV X9, LR
+	 * addr+04:		NOP		// To be patched to BL <caller>
+	 *
+	 * Or:
+	 *
+	 * addr-04:		BTI	C
+	 * addr+00:	func:	NOP		// To be patched to MOV X9, LR
+	 * addr+04:		NOP		// To be patched to BL <caller>
+	 *
+	 * We must adjust addr to the address of the NOP which will be patched
+	 * to `BL <caller>`, which is at `addr + 4` bytes in either case.
+	 *
+	 */
+	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+		return addr + AARCH64_INSN_SIZE;
+
+	/*
+	 * When using patchable-function-entry with pre-function NOPs, addr is
+	 * the address of the first pre-function NOP.
+	 *
+	 * Starting from an 8-byte aligned base, the compiler has either
+	 * generated:
+	 *
+	 * addr+00:		NOP		// Literal (first 32 bits)
+	 * addr+04:		NOP		// Literal (last 32 bits)
+	 * addr+08:	func:	NOP		// To be patched to MOV X9, LR
+	 * addr+12:		NOP		// To be patched to BL <caller>
+	 *
+	 * Or:
+	 *
+	 * addr+00:		NOP		// Literal (first 32 bits)
+	 * addr+04:		NOP		// Literal (last 32 bits)
+	 * addr+08:	func:	BTI	C
+	 * addr+12:		NOP		// To be patched to MOV X9, LR
+	 * addr+16:		NOP		// To be patched to BL <caller>
+	 *
+	 * We must adjust addr to the address of the NOP which will be patched
+	 * to `BL <caller>`, which is at either addr+12 or addr+16 depending on
+	 * whether there is a BTI.
+	 */
+
+	if (!IS_ALIGNED(addr, sizeof(unsigned long))) {
+		WARN_RATELIMIT(1, "Misaligned patch-site %pS\n",
+			       (void *)(addr + 8));
+		return 0;
+	}
+
+	/* Skip the NOPs placed before the function entry point */
+	addr += 2 * AARCH64_INSN_SIZE;
+
+	/* Skip any BTI */
+	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) {
+		u32 insn = le32_to_cpu(*(__le32 *)addr);
+
+		if (aarch64_insn_is_bti(insn)) {
+			addr += AARCH64_INSN_SIZE;
+		} else if (insn != aarch64_insn_gen_nop()) {
+			WARN_RATELIMIT(1, "unexpected insn in patch-site %pS: 0x%08x\n",
+				       (void *)addr, insn);
+		}
+	}
+
+	/* Skip the first NOP after function entry */
+	addr += AARCH64_INSN_SIZE;
+
+	return addr;
+}
+
 /*
  * Replace a single instruction, which may be a branch or NOP.
  * If @validate == true, a replaced instruction is checked against 'old'.
@@ -98,6 +181,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	unsigned long pc;
 	u32 new;
 
+	/*
+	 * When using CALL_OPS, the function to call is associated with the
+	 * call site, and we don't have a global function pointer to update.
+	 */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+		return 0;
+
 	pc = (unsigned long)ftrace_call;
 	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func,
 					  AARCH64_INSN_BRANCH_LINK);
@@ -176,6 +266,44 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 	return true;
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+static const struct ftrace_ops *arm64_rec_get_ops(struct dyn_ftrace *rec)
+{
+	const struct ftrace_ops *ops = NULL;
+
+	if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
+		ops = ftrace_find_unique_ops(rec);
+		WARN_ON_ONCE(!ops);
+	}
+
+	if (!ops)
+		ops = &ftrace_list_ops;
+
+	return ops;
+}
+
+static int ftrace_rec_set_ops(const struct dyn_ftrace *rec,
+			      const struct ftrace_ops *ops)
+{
+	unsigned long literal = ALIGN_DOWN(rec->ip - 12, 8);
+	return aarch64_insn_write_literal_u64((void *)literal,
+					      (unsigned long)ops);
+}
+
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec)
+{
+	return ftrace_rec_set_ops(rec, &ftrace_nop_ops);
+}
+
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec)
+{
+	return ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec));
+}
+#else
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; }
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; }
+#endif
+
 /*
  * Turn on the call to ftrace_caller() in instrumented function
  */
@@ -183,6 +311,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
 	unsigned long pc = rec->ip;
 	u32 old, new;
+	int ret;
+
+	ret = ftrace_rec_update_ops(rec);
+	if (ret)
+		return ret;
 
 	if (!ftrace_find_callable_addr(rec, NULL, &addr))
 		return -EINVAL;
@@ -193,6 +326,19 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ftrace_modify_code(pc, old, new, true);
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+		       unsigned long addr)
+{
+	if (WARN_ON_ONCE(old_addr != (unsigned long)ftrace_caller))
+		return -EINVAL;
+	if (WARN_ON_ONCE(addr != (unsigned long)ftrace_caller))
+		return -EINVAL;
+
+	return ftrace_rec_update_ops(rec);
+}
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 /*
  * The compiler has inserted two NOPs before the regular function prologue.
@@ -209,7 +355,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
  * | NOP      | MOV X9, LR | MOV X9, LR |
  * | NOP      | NOP        | BL <entry> |
  *
- * The LR value will be recovered by ftrace_regs_entry, and restored into LR
+ * The LR value will be recovered by ftrace_caller, and restored into LR
  * before returning to the regular function prologue. When a function is not
  * being traced, the MOV is not harmful given x9 is not live per the AAPCS.
  *
@@ -220,6 +366,11 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 {
 	unsigned long pc = rec->ip - AARCH64_INSN_SIZE;
 	u32 old, new;
+	int ret;
+
+	ret = ftrace_rec_set_nop_ops(rec);
+	if (ret)
+		return ret;
 
 	old = aarch64_insn_gen_nop();
 	new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9,
@@ -237,9 +388,14 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 {
 	unsigned long pc = rec->ip;
 	u32 old = 0, new;
+	int ret;
 
 	new = aarch64_insn_gen_nop();
 
+	ret = ftrace_rec_set_nop_ops(rec);
+	if (ret)
+		return ret;
+
 	/*
 	 * When using mcount, callsites in modules may have been initalized to
 	 * call an arbitrary module PLT (which redirects to the _mcount stub)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 952e17bd1c0b..b98970907226 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -70,13 +70,14 @@
 
 	__EFI_PE_HEADER
 
-	__INIT
+	.section ".idmap.text","a"
 
 	/*
 	 * The following callee saved general purpose registers are used on the
 	 * primary lowlevel boot path:
 	 *
 	 *  Register   Scope                      Purpose
+	 *  x19        primary_entry() .. start_kernel()        whether we entered with the MMU on
 	 *  x20        primary_entry() .. __primary_switch()    CPU boot mode
 	 *  x21        primary_entry() .. start_kernel()        FDT pointer passed at boot in x0
 	 *  x22        create_idmap() .. start_kernel()         ID map VA of the DT blob
@@ -86,10 +87,23 @@
 	 *  x28        create_idmap()                           callee preserved temp register
 	 */
 SYM_CODE_START(primary_entry)
+	bl	record_mmu_state
 	bl	preserve_boot_args
+	bl	create_idmap
+
+	/*
+	 * If we entered with the MMU and caches on, clean the ID mapped part
+	 * of the primary boot code to the PoC so we can safely execute it with
+	 * the MMU off.
+	 */
+	cbz	x19, 0f
+	adrp	x0, __idmap_text_start
+	adr_l	x1, __idmap_text_end
+	adr_l	x2, dcache_clean_poc
+	blr	x2
+0:	mov	x0, x19
 	bl	init_kernel_el			// w0=cpu_boot_mode
 	mov	x20, x0
-	bl	create_idmap
 
 	/*
 	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
@@ -109,6 +123,40 @@ SYM_CODE_START(primary_entry)
 	b	__primary_switch
 SYM_CODE_END(primary_entry)
 
+	__INIT
+SYM_CODE_START_LOCAL(record_mmu_state)
+	mrs	x19, CurrentEL
+	cmp	x19, #CurrentEL_EL2
+	mrs	x19, sctlr_el1
+	b.ne	0f
+	mrs	x19, sctlr_el2
+0:
+CPU_LE( tbnz	x19, #SCTLR_ELx_EE_SHIFT, 1f	)
+CPU_BE( tbz	x19, #SCTLR_ELx_EE_SHIFT, 1f	)
+	tst	x19, #SCTLR_ELx_C		// Z := (C == 0)
+	and	x19, x19, #SCTLR_ELx_M		// isolate M bit
+	csel	x19, xzr, x19, eq		// clear x19 if Z
+	ret
+
+	/*
+	 * Set the correct endianness early so all memory accesses issued
+	 * before init_kernel_el() occur in the correct byte order. Note that
+	 * this means the MMU must be disabled, or the active ID map will end
+	 * up getting interpreted with the wrong byte order.
+	 */
+1:	eor	x19, x19, #SCTLR_ELx_EE
+	bic	x19, x19, #SCTLR_ELx_M
+	b.ne	2f
+	pre_disable_mmu_workaround
+	msr	sctlr_el2, x19
+	b	3f
+	pre_disable_mmu_workaround
+2:	msr	sctlr_el1, x19
+3:	isb
+	mov	x19, xzr
+	ret
+SYM_CODE_END(record_mmu_state)
+
 /*
  * Preserve the arguments passed by the bootloader in x0 .. x3
  */
@@ -119,11 +167,14 @@ SYM_CODE_START_LOCAL(preserve_boot_args)
 	stp	x21, x1, [x0]			// x0 .. x3 at kernel entry
 	stp	x2, x3, [x0, #16]
 
+	cbnz	x19, 0f				// skip cache invalidation if MMU is on
 	dmb	sy				// needed before dc ivac with
 						// MMU off
 
 	add	x1, x0, #0x20			// 4 x 8 bytes
 	b	dcache_inval_poc		// tail call
+0:	str_l   x19, mmu_enabled_at_boot, x0
+	ret
 SYM_CODE_END(preserve_boot_args)
 
 SYM_FUNC_START_LOCAL(clear_page_tables)
@@ -360,12 +411,13 @@ SYM_FUNC_START_LOCAL(create_idmap)
 	 * accesses (MMU disabled), invalidate those tables again to
 	 * remove any speculatively loaded cache lines.
 	 */
+	cbnz	x19, 0f				// skip cache invalidation if MMU is on
 	dmb	sy
 
 	adrp	x0, init_idmap_pg_dir
 	adrp	x1, init_idmap_pg_end
 	bl	dcache_inval_poc
-	ret	x28
+0:	ret	x28
 SYM_FUNC_END(create_idmap)
 
 SYM_FUNC_START_LOCAL(create_kernel_mapping)
@@ -404,7 +456,7 @@ SYM_FUNC_END(create_kernel_mapping)
 	stp	xzr, xzr, [sp, #S_STACKFRAME]
 	add	x29, sp, #S_STACKFRAME
 
-	scs_load \tsk
+	scs_load_current
 
 	adr_l	\tmp1, __per_cpu_offset
 	ldr	w\tmp2, [\tsk, #TSK_TI_CPU]
@@ -476,7 +528,7 @@ SYM_FUNC_END(__primary_switched)
  * end early head section, begin head code that is also used for
  * hotplug and needs to have the same protections as the text region
  */
-	.section ".idmap.text","awx"
+	.section ".idmap.text","a"
 
 /*
  * Starting from EL2 or EL1, configure the CPU to execute at the highest
@@ -489,14 +541,17 @@ SYM_FUNC_END(__primary_switched)
  * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x0 if
  * booted in EL1 or EL2 respectively, with the top 32 bits containing
  * potential context flags. These flags are *not* stored in __boot_cpu_mode.
+ *
+ * x0: whether we are being called from the primary boot path with the MMU on
  */
 SYM_FUNC_START(init_kernel_el)
-	mrs	x0, CurrentEL
-	cmp	x0, #CurrentEL_EL2
+	mrs	x1, CurrentEL
+	cmp	x1, #CurrentEL_EL2
 	b.eq	init_el2
 
 SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
 	mov_q	x0, INIT_SCTLR_EL1_MMU_OFF
+	pre_disable_mmu_workaround
 	msr	sctlr_el1, x0
 	isb
 	mov_q	x0, INIT_PSTATE_EL1
@@ -506,6 +561,15 @@ SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
 	eret
 
 SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
+	msr	elr_el2, lr
+
+	// clean all HYP code to the PoC if we booted at EL2 with the MMU on
+	cbz	x0, 0f
+	adrp	x0, __hyp_idmap_text_start
+	adr_l	x1, __hyp_text_end
+	adr_l	x2, dcache_clean_poc
+	blr	x2
+0:
 	mov_q	x0, HCR_HOST_NVHE_FLAGS
 	msr	hcr_el2, x0
 	isb
@@ -529,38 +593,27 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	cbz	x0, 1f
 
 	/* Set a sane SCTLR_EL1, the VHE way */
+	pre_disable_mmu_workaround
 	msr_s	SYS_SCTLR_EL12, x1
 	mov	x2, #BOOT_CPU_FLAG_E2H
 	b	2f
 
 1:
+	pre_disable_mmu_workaround
 	msr	sctlr_el1, x1
 	mov	x2, xzr
 2:
-	msr	elr_el2, lr
 	mov	w0, #BOOT_CPU_MODE_EL2
 	orr	x0, x0, x2
 	eret
 SYM_FUNC_END(init_kernel_el)
 
-/*
- * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
- * in w0. See arch/arm64/include/asm/virt.h for more info.
- */
-SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag)
-	adr_l	x1, __boot_cpu_mode
-	cmp	w0, #BOOT_CPU_MODE_EL2
-	b.ne	1f
-	add	x1, x1, #4
-1:	str	w0, [x1]			// Save CPU boot mode
-	ret
-SYM_FUNC_END(set_cpu_boot_mode_flag)
-
 	/*
 	 * This provides a "holding pen" for platforms to hold all secondary
 	 * cores are held until we're ready for them to initialise.
 	 */
 SYM_FUNC_START(secondary_holding_pen)
+	mov	x0, xzr
 	bl	init_kernel_el			// w0=cpu_boot_mode
 	mrs	x2, mpidr_el1
 	mov_q	x1, MPIDR_HWID_BITMASK
@@ -578,6 +631,7 @@ SYM_FUNC_END(secondary_holding_pen)
 	 * be used where CPUs are brought online dynamically by the kernel.
 	 */
 SYM_FUNC_START(secondary_entry)
+	mov	x0, xzr
 	bl	init_kernel_el			// w0=cpu_boot_mode
 	b	secondary_startup
 SYM_FUNC_END(secondary_entry)
@@ -587,7 +641,6 @@ SYM_FUNC_START_LOCAL(secondary_startup)
 	 * Common entry point for secondary CPUs.
 	 */
 	mov	x20, x0				// preserve boot mode
-	bl	finalise_el2
 	bl	__cpu_secondary_check52bitva
 #if VA_BITS > 48
 	ldr_l	x0, vabits_actual
@@ -600,9 +653,14 @@ SYM_FUNC_START_LOCAL(secondary_startup)
 	br	x8
 SYM_FUNC_END(secondary_startup)
 
+	.text
 SYM_FUNC_START_LOCAL(__secondary_switched)
 	mov	x0, x20
 	bl	set_cpu_boot_mode_flag
+
+	mov	x0, x20
+	bl	finalise_el2
+
 	str_l	xzr, __early_cpu_boot_status, x3
 	adr_l	x5, vectors
 	msr	vbar_el1, x5
@@ -629,6 +687,19 @@ SYM_FUNC_START_LOCAL(__secondary_too_slow)
 SYM_FUNC_END(__secondary_too_slow)
 
 /*
+ * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
+ * in w0. See arch/arm64/include/asm/virt.h for more info.
+ */
+SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag)
+	adr_l	x1, __boot_cpu_mode
+	cmp	w0, #BOOT_CPU_MODE_EL2
+	b.ne	1f
+	add	x1, x1, #4
+1:	str	w0, [x1]			// Save CPU boot mode
+	ret
+SYM_FUNC_END(set_cpu_boot_mode_flag)
+
+/*
  * The booting CPU updates the failed status @__early_cpu_boot_status,
  * with MMU turned off.
  *
@@ -659,6 +730,7 @@ SYM_FUNC_END(__secondary_too_slow)
  * Checks if the selected granule size is supported by the CPU.
  * If it isn't, park the CPU
  */
+	.section ".idmap.text","a"
 SYM_FUNC_START(__enable_mmu)
 	mrs	x3, ID_AA64MMFR0_EL1
 	ubfx	x3, x3, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 2ee18c860f2a..111ff33d93ee 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -132,6 +132,13 @@ SYM_CODE_START_LOCAL(__finalise_el2)
 	orr	x0, x0, SMCR_ELx_FA64_MASK
 .Lskip_sme_fa64:
 
+	// ZT0 available?
+	mrs_s	x1, SYS_ID_AA64SMFR0_EL1
+	__check_override id_aa64smfr0 ID_AA64SMFR0_EL1_SMEver_SHIFT 4 .Linit_sme_zt0 .Lskip_sme_zt0
+.Linit_sme_zt0:
+	orr	x0, x0, SMCR_ELx_EZT0_MASK
+.Lskip_sme_zt0:
+
 	orr	x0, x0, #SMCR_ELx_LEN_MASK	// Enable full SME vector
 	msr_s	SYS_SMCR_EL2, x0		// length for EL1.
 
diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index 95133765ed29..d833d78a7f31 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -131,6 +131,7 @@ static const struct ftr_set_desc smfr0 __initconst = {
 	.name		= "id_aa64smfr0",
 	.override	= &id_aa64smfr0_override,
 	.fields		= {
+		FIELD("smever", ID_AA64SMFR0_EL1_SMEver_SHIFT, NULL),
 		/* FA64 is a one bit field... :-/ */
 		{ "fa64", ID_AA64SMFR0_EL1_FA64_SHIFT, 1, },
 		{}
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index d0e9bb5c91fc..8309197c0ebd 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -10,7 +10,7 @@
 #error This file should only be included in vmlinux.lds.S
 #endif
 
-PROVIDE(__efistub_primary_entry_offset	= primary_entry - _text);
+PROVIDE(__efistub_primary_entry		= primary_entry);
 
 /*
  * The EFI stub has its own symbol namespace prefixed by __efistub_, to
@@ -21,10 +21,11 @@ PROVIDE(__efistub_primary_entry_offset	= primary_entry - _text);
  * linked at. The routines below are all implemented in assembler in a
  * position independent manner
  */
-PROVIDE(__efistub_dcache_clean_poc	= __pi_dcache_clean_poc);
+PROVIDE(__efistub_caches_clean_inval_pou = __pi_caches_clean_inval_pou);
 
 PROVIDE(__efistub__text			= _text);
 PROVIDE(__efistub__end			= _end);
+PROVIDE(__efistub___inittext_end       	= __inittext_end);
 PROVIDE(__efistub__edata		= _edata);
 PROVIDE(__efistub_screen_info		= screen_info);
 PROVIDE(__efistub__ctype		= _ctype);
@@ -67,9 +68,7 @@ KVM_NVHE_ALIAS(__hyp_stub_vectors);
 KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
 KVM_NVHE_ALIAS(vgic_v3_cpuif_trap);
 
-/* Static key checked in pmr_sync(). */
 #ifdef CONFIG_ARM64_PSEUDO_NMI
-KVM_NVHE_ALIAS(gic_pmr_sync);
 /* Static key checked in GIC_PRIO_IRQOFF. */
 KVM_NVHE_ALIAS(gic_nonsecure_priorities);
 #endif
diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/patch-scs.c
index 1b3da02d5b74..a1fe4b4ff591 100644
--- a/arch/arm64/kernel/patch-scs.c
+++ b/arch/arm64/kernel/patch-scs.c
@@ -130,7 +130,8 @@ struct eh_frame {
 
 static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
 					bool fde_has_augmentation_data,
-					int code_alignment_factor)
+					int code_alignment_factor,
+					bool dry_run)
 {
 	int size = frame->size - offsetof(struct eh_frame, opcodes) + 4;
 	u64 loc = (u64)offset_to_ptr(&frame->initial_loc);
@@ -184,7 +185,8 @@ static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
 			break;
 
 		case DW_CFA_negate_ra_state:
-			scs_patch_loc(loc - 4);
+			if (!dry_run)
+				scs_patch_loc(loc - 4);
 			break;
 
 		case 0x40 ... 0x7f:
@@ -235,9 +237,12 @@ int noinstr scs_patch(const u8 eh_frame[], int size)
 		} else {
 			ret = scs_handle_fde_frame(frame,
 						   fde_has_augmentation_data,
-						   code_alignment_factor);
+						   code_alignment_factor,
+						   true);
 			if (ret)
 				return ret;
+			scs_handle_fde_frame(frame, fde_has_augmentation_data,
+					     code_alignment_factor, false);
 		}
 
 		p += sizeof(frame->size) + frame->size;
diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c
index 33e0fabc0b79..b4835f6d594b 100644
--- a/arch/arm64/kernel/patching.c
+++ b/arch/arm64/kernel/patching.c
@@ -88,6 +88,23 @@ int __kprobes aarch64_insn_write(void *addr, u32 insn)
 	return __aarch64_insn_write(addr, cpu_to_le32(insn));
 }
 
+noinstr int aarch64_insn_write_literal_u64(void *addr, u64 val)
+{
+	u64 *waddr;
+	unsigned long flags;
+	int ret;
+
+	raw_spin_lock_irqsave(&patch_lock, flags);
+	waddr = patch_map(addr, FIX_TEXT_POKE0);
+
+	ret = copy_to_kernel_nofault(waddr, &val, sizeof(val));
+
+	patch_unmap(FIX_TEXT_POKE0);
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
+
+	return ret;
+}
+
 int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
 {
 	u32 *tp = addr;
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index f35d059a9a36..70b91a8c6bb3 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -387,10 +387,6 @@ int __init arch_populate_kprobe_blacklist(void)
 					(unsigned long)__irqentry_text_end);
 	if (ret)
 		return ret;
-	ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start,
-					(unsigned long)__idmap_text_end);
-	if (ret)
-		return ret;
 	ret = kprobe_add_area_blacklist((unsigned long)__hyp_text_start,
 					(unsigned long)__hyp_text_end);
 	if (ret || is_kernel_in_hyp_mode())
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 269ac1c25ae2..71d59b5abede 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -307,27 +307,28 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	/*
 	 * In the unlikely event that we create a new thread with ZA
-	 * enabled we should retain the ZA state so duplicate it here.
-	 * This may be shortly freed if we exec() or if CLONE_SETTLS
-	 * but it's simpler to do it here. To avoid confusing the rest
-	 * of the code ensure that we have a sve_state allocated
-	 * whenever za_state is allocated.
+	 * enabled we should retain the ZA and ZT state so duplicate
+	 * it here.  This may be shortly freed if we exec() or if
+	 * CLONE_SETTLS but it's simpler to do it here. To avoid
+	 * confusing the rest of the code ensure that we have a
+	 * sve_state allocated whenever sme_state is allocated.
 	 */
 	if (thread_za_enabled(&src->thread)) {
 		dst->thread.sve_state = kzalloc(sve_state_size(src),
 						GFP_KERNEL);
 		if (!dst->thread.sve_state)
 			return -ENOMEM;
-		dst->thread.za_state = kmemdup(src->thread.za_state,
-					       za_state_size(src),
-					       GFP_KERNEL);
-		if (!dst->thread.za_state) {
+
+		dst->thread.sme_state = kmemdup(src->thread.sme_state,
+						sme_state_size(src),
+						GFP_KERNEL);
+		if (!dst->thread.sme_state) {
 			kfree(dst->thread.sve_state);
 			dst->thread.sve_state = NULL;
 			return -ENOMEM;
 		}
 	} else {
-		dst->thread.za_state = NULL;
+		dst->thread.sme_state = NULL;
 		clear_tsk_thread_flag(dst, TIF_SME);
 	}
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 0c321ad23cd3..d7f4f0d1ae12 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -683,7 +683,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 	unsigned long tls[2];
 
 	tls[0] = target->thread.uw.tp_value;
-	if (system_supports_sme())
+	if (system_supports_tpidr2())
 		tls[1] = target->thread.tpidr2_el0;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, tls, 0, count);
@@ -691,7 +691,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 		return ret;
 
 	target->thread.uw.tp_value = tls[0];
-	if (system_supports_sme())
+	if (system_supports_tpidr2())
 		target->thread.tpidr2_el0 = tls[1];
 
 	return ret;
@@ -1045,7 +1045,7 @@ static int za_get(struct task_struct *target,
 	if (thread_za_enabled(&target->thread)) {
 		start = end;
 		end = ZA_PT_SIZE(vq);
-		membuf_write(&to, target->thread.za_state, end - start);
+		membuf_write(&to, target->thread.sme_state, end - start);
 	}
 
 	/* Zero any trailing padding */
@@ -1099,7 +1099,7 @@ static int za_set(struct task_struct *target,
 
 	/* Allocate/reinit ZA storage */
 	sme_alloc(target);
-	if (!target->thread.za_state) {
+	if (!target->thread.sme_state) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1124,7 +1124,7 @@ static int za_set(struct task_struct *target,
 	start = ZA_PT_ZA_OFFSET;
 	end = ZA_PT_SIZE(vq);
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 target->thread.za_state,
+				 target->thread.sme_state,
 				 start, end);
 	if (ret)
 		goto out;
@@ -1138,6 +1138,51 @@ out:
 	return ret;
 }
 
+static int zt_get(struct task_struct *target,
+		  const struct user_regset *regset,
+		  struct membuf to)
+{
+	if (!system_supports_sme2())
+		return -EINVAL;
+
+	/*
+	 * If PSTATE.ZA is not set then ZT will be zeroed when it is
+	 * enabled so report the current register value as zero.
+	 */
+	if (thread_za_enabled(&target->thread))
+		membuf_write(&to, thread_zt_state(&target->thread),
+			     ZT_SIG_REG_BYTES);
+	else
+		membuf_zero(&to, ZT_SIG_REG_BYTES);
+
+	return 0;
+}
+
+static int zt_set(struct task_struct *target,
+		  const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	if (!system_supports_sme2())
+		return -EINVAL;
+
+	if (!thread_za_enabled(&target->thread)) {
+		sme_alloc(target);
+		if (!target->thread.sme_state)
+			return -ENOMEM;
+	}
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 thread_zt_state(&target->thread),
+				 0, ZT_SIG_REG_BYTES);
+	if (ret == 0)
+		target->thread.svcr |= SVCR_ZA_MASK;
+
+	return ret;
+}
+
 #endif /* CONFIG_ARM64_SME */
 
 #ifdef CONFIG_ARM64_PTR_AUTH
@@ -1360,6 +1405,7 @@ enum aarch64_regset {
 #ifdef CONFIG_ARM64_SME
 	REGSET_SSVE,
 	REGSET_ZA,
+	REGSET_ZT,
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	REGSET_PAC_MASK,
@@ -1467,6 +1513,14 @@ static const struct user_regset aarch64_regsets[] = {
 		.regset_get = za_get,
 		.set = za_set,
 	},
+	[REGSET_ZT] = { /* SME ZT */
+		.core_note_type = NT_ARM_ZT,
+		.n = 1,
+		.size = ZT_SIG_REG_BYTES,
+		.align = sizeof(u64),
+		.regset_get = zt_get,
+		.set = zt_set,
+	},
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	[REGSET_PAC_MASK] = {
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 12cfe9d0d3fa..b8ec7b3ac9cb 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -58,6 +58,7 @@ static int num_standard_resources;
 static struct resource *standard_resources;
 
 phys_addr_t __fdt_pointer __initdata;
+u64 mmu_enabled_at_boot __initdata;
 
 /*
  * Standard memory resources
@@ -332,8 +333,12 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
 	xen_early_init();
 	efi_init();
 
-	if (!efi_enabled(EFI_BOOT) && ((u64)_text % MIN_KIMG_ALIGN) != 0)
-	     pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!");
+	if (!efi_enabled(EFI_BOOT)) {
+		if ((u64)_text % MIN_KIMG_ALIGN)
+			pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!");
+		WARN_TAINT(mmu_enabled_at_boot, TAINT_FIRMWARE_WORKAROUND,
+			   FW_BUG "Booted with MMU enabled!");
+	}
 
 	arm64_memblock_init();
 
@@ -442,3 +447,11 @@ static int __init register_arm64_panic_block(void)
 	return 0;
 }
 device_initcall(register_arm64_panic_block);
+
+static int __init check_mmu_enabled_at_boot(void)
+{
+	if (!efi_enabled(EFI_BOOT) && mmu_enabled_at_boot)
+		panic("Non-EFI boot detected with MMU and caches enabled");
+	return 0;
+}
+device_initcall_sync(check_mmu_enabled_at_boot);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index be279fd48248..06a02707f488 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -56,7 +56,9 @@ struct rt_sigframe_user_layout {
 	unsigned long fpsimd_offset;
 	unsigned long esr_offset;
 	unsigned long sve_offset;
+	unsigned long tpidr2_offset;
 	unsigned long za_offset;
+	unsigned long zt_offset;
 	unsigned long extra_offset;
 	unsigned long end_offset;
 };
@@ -168,6 +170,19 @@ static void __user *apply_user_offset(
 	return base + offset;
 }
 
+struct user_ctxs {
+	struct fpsimd_context __user *fpsimd;
+	u32 fpsimd_size;
+	struct sve_context __user *sve;
+	u32 sve_size;
+	struct tpidr2_context __user *tpidr2;
+	u32 tpidr2_size;
+	struct za_context __user *za;
+	u32 za_size;
+	struct zt_context __user *zt;
+	u32 zt_size;
+};
+
 static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 {
 	struct user_fpsimd_state const *fpsimd =
@@ -186,25 +201,20 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 	return err ? -EFAULT : 0;
 }
 
-static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
+static int restore_fpsimd_context(struct user_ctxs *user)
 {
 	struct user_fpsimd_state fpsimd;
-	__u32 magic, size;
 	int err = 0;
 
-	/* check the magic/size information */
-	__get_user_error(magic, &ctx->head.magic, err);
-	__get_user_error(size, &ctx->head.size, err);
-	if (err)
-		return -EFAULT;
-	if (magic != FPSIMD_MAGIC || size != sizeof(struct fpsimd_context))
+	/* check the size information */
+	if (user->fpsimd_size != sizeof(struct fpsimd_context))
 		return -EINVAL;
 
 	/* copy the FP and status/control registers */
-	err = __copy_from_user(fpsimd.vregs, ctx->vregs,
+	err = __copy_from_user(fpsimd.vregs, &(user->fpsimd->vregs),
 			       sizeof(fpsimd.vregs));
-	__get_user_error(fpsimd.fpsr, &ctx->fpsr, err);
-	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
+	__get_user_error(fpsimd.fpsr, &(user->fpsimd->fpsr), err);
+	__get_user_error(fpsimd.fpcr, &(user->fpsimd->fpcr), err);
 
 	clear_thread_flag(TIF_SVE);
 	current->thread.fp_type = FP_STATE_FPSIMD;
@@ -217,12 +227,6 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 }
 
 
-struct user_ctxs {
-	struct fpsimd_context __user *fpsimd;
-	struct sve_context __user *sve;
-	struct za_context __user *za;
-};
-
 #ifdef CONFIG_ARM64_SVE
 
 static int preserve_sve_context(struct sve_context __user *ctx)
@@ -267,15 +271,20 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 
 static int restore_sve_fpsimd_context(struct user_ctxs *user)
 {
-	int err;
+	int err = 0;
 	unsigned int vl, vq;
 	struct user_fpsimd_state fpsimd;
-	struct sve_context sve;
+	u16 user_vl, flags;
 
-	if (__copy_from_user(&sve, user->sve, sizeof(sve)))
-		return -EFAULT;
+	if (user->sve_size < sizeof(*user->sve))
+		return -EINVAL;
+
+	__get_user_error(user_vl, &(user->sve->vl), err);
+	__get_user_error(flags, &(user->sve->flags), err);
+	if (err)
+		return err;
 
-	if (sve.flags & SVE_SIG_FLAG_SM) {
+	if (flags & SVE_SIG_FLAG_SM) {
 		if (!system_supports_sme())
 			return -EINVAL;
 
@@ -292,19 +301,19 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 		vl = task_get_sve_vl(current);
 	}
 
-	if (sve.vl != vl)
+	if (user_vl != vl)
 		return -EINVAL;
 
-	if (sve.head.size <= sizeof(*user->sve)) {
+	if (user->sve_size == sizeof(*user->sve)) {
 		clear_thread_flag(TIF_SVE);
 		current->thread.svcr &= ~SVCR_SM_MASK;
 		current->thread.fp_type = FP_STATE_FPSIMD;
 		goto fpsimd_only;
 	}
 
-	vq = sve_vq_from_vl(sve.vl);
+	vq = sve_vq_from_vl(vl);
 
-	if (sve.head.size < SVE_SIG_CONTEXT_SIZE(vq))
+	if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq))
 		return -EINVAL;
 
 	/*
@@ -330,7 +339,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	if (err)
 		return -EFAULT;
 
-	if (sve.flags & SVE_SIG_FLAG_SM)
+	if (flags & SVE_SIG_FLAG_SM)
 		current->thread.svcr |= SVCR_SM_MASK;
 	else
 		set_thread_flag(TIF_SVE);
@@ -366,6 +375,34 @@ extern int preserve_sve_context(void __user *ctx);
 
 #ifdef CONFIG_ARM64_SME
 
+static int preserve_tpidr2_context(struct tpidr2_context __user *ctx)
+{
+	int err = 0;
+
+	current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
+
+	__put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err);
+	__put_user_error(sizeof(*ctx), &ctx->head.size, err);
+	__put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err);
+
+	return err;
+}
+
+static int restore_tpidr2_context(struct user_ctxs *user)
+{
+	u64 tpidr2_el0;
+	int err = 0;
+
+	if (user->tpidr2_size != sizeof(*user->tpidr2))
+		return -EINVAL;
+
+	__get_user_error(tpidr2_el0, &user->tpidr2->tpidr2, err);
+	if (!err)
+		current->thread.tpidr2_el0 = tpidr2_el0;
+
+	return err;
+}
+
 static int preserve_za_context(struct za_context __user *ctx)
 {
 	int err = 0;
@@ -394,7 +431,7 @@ static int preserve_za_context(struct za_context __user *ctx)
 		 * fpsimd_signal_preserve_current_state().
 		 */
 		err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET,
-				      current->thread.za_state,
+				      current->thread.sme_state,
 				      ZA_SIG_REGS_SIZE(vq));
 	}
 
@@ -403,29 +440,33 @@ static int preserve_za_context(struct za_context __user *ctx)
 
 static int restore_za_context(struct user_ctxs *user)
 {
-	int err;
+	int err = 0;
 	unsigned int vq;
-	struct za_context za;
+	u16 user_vl;
 
-	if (__copy_from_user(&za, user->za, sizeof(za)))
-		return -EFAULT;
+	if (user->za_size < sizeof(*user->za))
+		return -EINVAL;
+
+	__get_user_error(user_vl, &(user->za->vl), err);
+	if (err)
+		return err;
 
-	if (za.vl != task_get_sme_vl(current))
+	if (user_vl != task_get_sme_vl(current))
 		return -EINVAL;
 
-	if (za.head.size <= sizeof(*user->za)) {
+	if (user->za_size == sizeof(*user->za)) {
 		current->thread.svcr &= ~SVCR_ZA_MASK;
 		return 0;
 	}
 
-	vq = sve_vq_from_vl(za.vl);
+	vq = sve_vq_from_vl(user_vl);
 
-	if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq))
+	if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq))
 		return -EINVAL;
 
 	/*
 	 * Careful: we are about __copy_from_user() directly into
-	 * thread.za_state with preemption enabled, so protection is
+	 * thread.sme_state with preemption enabled, so protection is
 	 * needed to prevent a racing context switch from writing stale
 	 * registers back over the new data.
 	 */
@@ -434,13 +475,13 @@ static int restore_za_context(struct user_ctxs *user)
 	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
 
 	sme_alloc(current);
-	if (!current->thread.za_state) {
+	if (!current->thread.sme_state) {
 		current->thread.svcr &= ~SVCR_ZA_MASK;
 		clear_thread_flag(TIF_SME);
 		return -ENOMEM;
 	}
 
-	err = __copy_from_user(current->thread.za_state,
+	err = __copy_from_user(current->thread.sme_state,
 			       (char __user const *)user->za +
 					ZA_SIG_REGS_OFFSET,
 			       ZA_SIG_REGS_SIZE(vq));
@@ -452,11 +493,83 @@ static int restore_za_context(struct user_ctxs *user)
 
 	return 0;
 }
+
+static int preserve_zt_context(struct zt_context __user *ctx)
+{
+	int err = 0;
+	u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+
+	if (WARN_ON(!thread_za_enabled(&current->thread)))
+		return -EINVAL;
+
+	memset(reserved, 0, sizeof(reserved));
+
+	__put_user_error(ZT_MAGIC, &ctx->head.magic, err);
+	__put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16),
+			 &ctx->head.size, err);
+	__put_user_error(1, &ctx->nregs, err);
+	BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+	err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+	/*
+	 * This assumes that the ZT state has already been saved to
+	 * the task struct by calling the function
+	 * fpsimd_signal_preserve_current_state().
+	 */
+	err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET,
+			      thread_zt_state(&current->thread),
+			      ZT_SIG_REGS_SIZE(1));
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_zt_context(struct user_ctxs *user)
+{
+	int err;
+	u16 nregs;
+
+	/* ZA must be restored first for this check to be valid */
+	if (!thread_za_enabled(&current->thread))
+		return -EINVAL;
+
+	if (user->zt_size != ZT_SIG_CONTEXT_SIZE(1))
+		return -EINVAL;
+
+	if (__copy_from_user(&nregs, &(user->zt->nregs), sizeof(nregs)))
+		return -EFAULT;
+
+	if (nregs != 1)
+		return -EINVAL;
+
+	/*
+	 * Careful: we are about __copy_from_user() directly into
+	 * thread.zt_state with preemption enabled, so protection is
+	 * needed to prevent a racing context switch from writing stale
+	 * registers back over the new data.
+	 */
+
+	fpsimd_flush_task_state(current);
+	/* From now, fpsimd_thread_switch() won't touch ZT in thread state */
+
+	err = __copy_from_user(thread_zt_state(&current->thread),
+			       (char __user const *)user->zt +
+					ZT_SIG_REGS_OFFSET,
+			       ZT_SIG_REGS_SIZE(1));
+	if (err)
+		return -EFAULT;
+
+	return 0;
+}
+
 #else /* ! CONFIG_ARM64_SME */
 
 /* Turn any non-optimised out attempts to use these into a link error: */
+extern int preserve_tpidr2_context(void __user *ctx);
+extern int restore_tpidr2_context(struct user_ctxs *user);
 extern int preserve_za_context(void __user *ctx);
 extern int restore_za_context(struct user_ctxs *user);
+extern int preserve_zt_context(void __user *ctx);
+extern int restore_zt_context(struct user_ctxs *user);
 
 #endif /* ! CONFIG_ARM64_SME */
 
@@ -473,7 +586,9 @@ static int parse_user_sigframe(struct user_ctxs *user,
 
 	user->fpsimd = NULL;
 	user->sve = NULL;
+	user->tpidr2 = NULL;
 	user->za = NULL;
+	user->zt = NULL;
 
 	if (!IS_ALIGNED((unsigned long)base, 16))
 		goto invalid;
@@ -516,10 +631,8 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			if (user->fpsimd)
 				goto invalid;
 
-			if (size < sizeof(*user->fpsimd))
-				goto invalid;
-
 			user->fpsimd = (struct fpsimd_context __user *)head;
+			user->fpsimd_size = size;
 			break;
 
 		case ESR_MAGIC:
@@ -533,10 +646,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			if (user->sve)
 				goto invalid;
 
-			if (size < sizeof(*user->sve))
+			user->sve = (struct sve_context __user *)head;
+			user->sve_size = size;
+			break;
+
+		case TPIDR2_MAGIC:
+			if (!system_supports_sme())
 				goto invalid;
 
-			user->sve = (struct sve_context __user *)head;
+			if (user->tpidr2)
+				goto invalid;
+
+			user->tpidr2 = (struct tpidr2_context __user *)head;
+			user->tpidr2_size = size;
 			break;
 
 		case ZA_MAGIC:
@@ -546,10 +668,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			if (user->za)
 				goto invalid;
 
-			if (size < sizeof(*user->za))
+			user->za = (struct za_context __user *)head;
+			user->za_size = size;
+			break;
+
+		case ZT_MAGIC:
+			if (!system_supports_sme2())
 				goto invalid;
 
-			user->za = (struct za_context __user *)head;
+			if (user->zt)
+				goto invalid;
+
+			user->zt = (struct zt_context __user *)head;
+			user->zt_size = size;
 			break;
 
 		case EXTRA_MAGIC:
@@ -668,12 +799,18 @@ static int restore_sigframe(struct pt_regs *regs,
 		if (user.sve)
 			err = restore_sve_fpsimd_context(&user);
 		else
-			err = restore_fpsimd_context(user.fpsimd);
+			err = restore_fpsimd_context(&user);
 	}
 
+	if (err == 0 && system_supports_sme() && user.tpidr2)
+		err = restore_tpidr2_context(&user);
+
 	if (err == 0 && system_supports_sme() && user.za)
 		err = restore_za_context(&user);
 
+	if (err == 0 && system_supports_sme2() && user.zt)
+		err = restore_zt_context(&user);
+
 	return err;
 }
 
@@ -765,6 +902,11 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 		else
 			vl = task_get_sme_vl(current);
 
+		err = sigframe_alloc(user, &user->tpidr2_offset,
+				     sizeof(struct tpidr2_context));
+		if (err)
+			return err;
+
 		if (thread_za_enabled(&current->thread))
 			vq = sve_vq_from_vl(vl);
 
@@ -774,6 +916,15 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 			return err;
 	}
 
+	if (system_supports_sme2()) {
+		if (add_all || thread_za_enabled(&current->thread)) {
+			err = sigframe_alloc(user, &user->zt_offset,
+					     ZT_SIG_CONTEXT_SIZE(1));
+			if (err)
+				return err;
+		}
+	}
+
 	return sigframe_alloc_end(user);
 }
 
@@ -822,6 +973,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		err |= preserve_sve_context(sve_ctx);
 	}
 
+	/* TPIDR2 if supported */
+	if (system_supports_sme() && err == 0) {
+		struct tpidr2_context __user *tpidr2_ctx =
+			apply_user_offset(user, user->tpidr2_offset);
+		err |= preserve_tpidr2_context(tpidr2_ctx);
+	}
+
 	/* ZA state if present */
 	if (system_supports_sme() && err == 0 && user->za_offset) {
 		struct za_context __user *za_ctx =
@@ -829,6 +987,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		err |= preserve_za_context(za_ctx);
 	}
 
+	/* ZT state if present */
+	if (system_supports_sme2() && err == 0 && user->zt_offset) {
+		struct zt_context __user *zt_ctx =
+			apply_user_offset(user, user->zt_offset);
+		err |= preserve_zt_context(zt_ctx);
+	}
+
 	if (err == 0 && user->extra_offset) {
 		char __user *sfp = (char __user *)user->sigframe;
 		char __user *userp =
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 97c9de57725d..2ae7cff1953a 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -99,8 +99,9 @@ SYM_FUNC_END(__cpu_suspend_enter)
 
 	.pushsection ".idmap.text", "awx"
 SYM_CODE_START(cpu_resume)
+	mov	x0, xzr
 	bl	init_kernel_el
-	bl	finalise_el2
+	mov	x19, x0			// preserve boot mode
 #if VA_BITS > 48
 	ldr_l	x0, vabits_actual
 #endif
@@ -116,6 +117,9 @@ SYM_CODE_END(cpu_resume)
 	.popsection
 
 SYM_FUNC_START(_cpu_resume)
+	mov	x0, x19
+	bl	finalise_el2
+
 	mrs	x1, mpidr_el1
 	adr_l	x8, mpidr_hash		// x8 = struct mpidr_hash virt address
 
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index a5de47e3df2b..da84cf855c44 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -173,12 +173,8 @@ static inline void fp_user_discard(void)
 	 * register state to track, if this changes the KVM code will
 	 * need updating.
 	 */
-	if (system_supports_sme() && test_thread_flag(TIF_SME)) {
-		u64 svcr = read_sysreg_s(SYS_SVCR);
-
-		if (svcr & SVCR_SM_MASK)
-			sme_smstop_sm();
-	}
+	if (system_supports_sme())
+		sme_smstop_sm();
 
 	if (!system_supports_sve())
 		return;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 87f42eb1c950..a6dd3e90755c 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -163,10 +163,8 @@ static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
 
 		if (!bad)
 			p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val);
-		else {
-			p += sprintf(p, "bad PC value");
-			break;
-		}
+		else
+			p += sprintf(p, i == 0 ? "(????????) " : "???????? ");
 	}
 
 	printk("%sCode: %s\n", lvl, str);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 2777214cbf1a..b9202c2ee18e 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -93,6 +93,7 @@ jiffies = jiffies_64;
 
 #ifdef CONFIG_HIBERNATION
 #define HIBERNATE_TEXT					\
+	ALIGN_FUNCTION();				\
 	__hibernate_exit_text_start = .;		\
 	*(.hibernate_exit.text)				\
 	__hibernate_exit_text_end = .;
@@ -102,6 +103,7 @@ jiffies = jiffies_64;
 
 #ifdef CONFIG_KEXEC_CORE
 #define KEXEC_TEXT					\
+	ALIGN_FUNCTION();				\
 	__relocate_new_kernel_start = .;		\
 	*(.kexec_relocate.text)				\
 	__relocate_new_kernel_end = .;
@@ -178,7 +180,6 @@ SECTIONS
 			LOCK_TEXT
 			KPROBES_TEXT
 			HYPERVISOR_TEXT
-			IDMAP_TEXT
 			*(.gnu.warning)
 		. = ALIGN(16);
 		*(.got)			/* Global offset table		*/
@@ -205,6 +206,7 @@ SECTIONS
 		TRAMP_TEXT
 		HIBERNATE_TEXT
 		KEXEC_TEXT
+		IDMAP_TEXT
 		. = ALIGN(PAGE_SIZE);
 	}
 
@@ -354,6 +356,8 @@ ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
 #ifdef CONFIG_HIBERNATION
 ASSERT(__hibernate_exit_text_end - __hibernate_exit_text_start <= SZ_4K,
        "Hibernate exit text is bigger than 4 KiB")
+ASSERT(__hibernate_exit_text_start == swsusp_arch_suspend_exit,
+       "Hibernate exit text does not start with swsusp_arch_suspend_exit")
 #endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE,
@@ -380,4 +384,6 @@ ASSERT(swapper_pg_dir - tramp_pg_dir == TRAMP_SWAPPER_OFFSET,
 ASSERT(__relocate_new_kernel_end - __relocate_new_kernel_start <= SZ_4K,
        "kexec relocation code is bigger than 4 KiB")
 ASSERT(KEXEC_CONTROL_PAGE_SIZE >= SZ_4K, "KEXEC_CONTROL_PAGE_SIZE is broken")
+ASSERT(__relocate_new_kernel_start == arm64_relocate_new_kernel,
+       "kexec control page does not start with arm64_relocate_new_kernel")
 #endif
author	Linus Torvalds <torvalds@linux-foundation.org>	2023-02-21 15:27:48 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2023-02-21 15:27:48 -0800
commit	8bf1a529cd664c8e5268381f1e24fe67aa611dd3 (patch)
tree	c5cec84941923778e4e2ec5a5d65e2fc8ea71b58 /arch/arm64/kernel
parent	b327dfe05258e09c8db6e1e091c2e6d84dd426a6 (diff)
parent	d54170812ef1c80e0fa3ed3e554a0bbfc2920d9d (diff)