Merge branch 'for-next/sme' into for-next/sysreg-gen

* for-next/sme: (29 commits)
  : Scalable Matrix Extensions support.
  arm64/sve: Make kernel FPU protection RT friendly
  arm64/sve: Delay freeing memory in fpsimd_flush_thread()
  arm64/sme: More sensibly define the size for the ZA register set
  arm64/sme: Fix NULL check after kzalloc
  arm64/sme: Add ID_AA64SMFR0_EL1 to __read_sysreg_by_encoding()
  arm64/sme: Provide Kconfig for SME
  KVM: arm64: Handle SME host state when running guests
  KVM: arm64: Trap SME usage in guest
  KVM: arm64: Hide SME system registers from guests
  arm64/sme: Save and restore streaming mode over EFI runtime calls
  arm64/sme: Disable streaming mode and ZA when flushing CPU state
  arm64/sme: Add ptrace support for ZA
  arm64/sme: Implement ptrace support for streaming mode SVE registers
  arm64/sme: Implement ZA signal handling
  arm64/sme: Implement streaming SVE signal handling
  arm64/sme: Disable ZA and streaming mode when handling signals
  arm64/sme: Implement traps and syscall handling for SME
  arm64/sme: Implement ZA context switching
  arm64/sme: Implement streaming SVE context switching
  arm64/sme: Implement SVCR context switching
  ...

10 files changed, 1299 insertions, 112 deletions

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 01e7ae167f9f..08689362cd89 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -261,6 +261,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 };
 
 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),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE),
@@ -293,6 +295,24 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 	ARM64_FTR_END,
 };
 
+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_FA64_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I16I64_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F64F64_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I8I32_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F16F32_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_B16F32_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F32F32_SHIFT, 1, 0),
+	ARM64_FTR_END,
+};
+
 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),
@@ -561,6 +581,12 @@ static const struct arm64_ftr_bits ftr_zcr[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_smcr[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
+		SMCR_ELx_LEN_SHIFT, SMCR_ELx_LEN_SIZE, 0),	/* LEN */
+	ARM64_FTR_END,
+};
+
 /*
  * Common ftr bits for a 32bit register with all hidden, strict
  * attributes, with 4bit feature fields and a default safe value of
@@ -645,6 +671,7 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1,
 			       &id_aa64pfr1_override),
 	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
+	ARM64_FTR_REG(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
 	ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -666,6 +693,7 @@ static const struct __ftr_reg_entry {
 
 	/* Op1 = 0, CRn = 1, CRm = 2 */
 	ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
+	ARM64_FTR_REG(SYS_SMCR_EL1, ftr_smcr),
 
 	/* Op1 = 1, CRn = 0, CRm = 0 */
 	ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid),
@@ -960,6 +988,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
 	init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
+	init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0);
 
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
 		init_32bit_cpu_features(&info->aarch32);
@@ -969,6 +998,12 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		vec_init_vq_map(ARM64_VEC_SVE);
 	}
 
+	if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) {
+		init_cpu_ftr_reg(SYS_SMCR_EL1, info->reg_smcr);
+		if (IS_ENABLED(CONFIG_ARM64_SME))
+			vec_init_vq_map(ARM64_VEC_SME);
+	}
+
 	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
 		init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid);
 
@@ -1195,6 +1230,9 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu,
 				      info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0);
 
+	taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu,
+				      info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0);
+
 	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
 		taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu,
 					info->reg_zcr, boot->reg_zcr);
@@ -1205,6 +1243,16 @@ void update_cpu_features(int cpu,
 			vec_update_vq_map(ARM64_VEC_SVE);
 	}
 
+	if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) {
+		taint |= check_update_ftr_reg(SYS_SMCR_EL1, cpu,
+					info->reg_smcr, boot->reg_smcr);
+
+		/* Probe vector lengths, unless we already gave up on SME */
+		if (id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1)) &&
+		    !system_capabilities_finalized())
+			vec_update_vq_map(ARM64_VEC_SME);
+	}
+
 	/*
 	 * The kernel uses the LDGM/STGM instructions and the number of tags
 	 * they read/write depends on the GMID_EL1.BS field. Check that the
@@ -1288,6 +1336,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id)
 	read_sysreg_case(SYS_ID_AA64PFR0_EL1);
 	read_sysreg_case(SYS_ID_AA64PFR1_EL1);
 	read_sysreg_case(SYS_ID_AA64ZFR0_EL1);
+	read_sysreg_case(SYS_ID_AA64SMFR0_EL1);
 	read_sysreg_case(SYS_ID_AA64DFR0_EL1);
 	read_sysreg_case(SYS_ID_AA64DFR1_EL1);
 	read_sysreg_case(SYS_ID_AA64MMFR0_EL1);
@@ -2442,6 +2491,33 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.min_field_value = 1,
 	},
+#ifdef CONFIG_ARM64_SME
+	{
+		.desc = "Scalable Matrix Extension",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_SME,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR1_SME_SHIFT,
+		.field_width = 4,
+		.min_field_value = ID_AA64PFR1_SME,
+		.matches = has_cpuid_feature,
+		.cpu_enable = sme_kernel_enable,
+	},
+	/* FA64 should be sorted after the base SME capability */
+	{
+		.desc = "FA64",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_SME_FA64,
+		.sys_reg = SYS_ID_AA64SMFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64SMFR0_FA64_SHIFT,
+		.field_width = 1,
+		.min_field_value = ID_AA64SMFR0_FA64,
+		.matches = has_cpuid_feature,
+		.cpu_enable = fa64_kernel_enable,
+	},
+#endif /* CONFIG_ARM64_SME */
 	{},
 };
 
@@ -2575,6 +2651,16 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	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_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
+#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_AA64SMFR0_EL1, ID_AA64SMFR0_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_FA64, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I16I64, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F64F64, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I8I32, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F16F32, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_B16F32, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F32F32, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+#endif /* CONFIG_ARM64_SME */
 	{},
 };
 
@@ -2872,6 +2958,23 @@ static void verify_sve_features(void)
 	/* Add checks on other ZCR bits here if necessary */
 }
 
+static void verify_sme_features(void)
+{
+	u64 safe_smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1);
+	u64 smcr = read_smcr_features();
+
+	unsigned int safe_len = safe_smcr & SMCR_ELx_LEN_MASK;
+	unsigned int len = smcr & SMCR_ELx_LEN_MASK;
+
+	if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SME)) {
+		pr_crit("CPU%d: SME: vector length support mismatch\n",
+			smp_processor_id());
+		cpu_die_early();
+	}
+
+	/* Add checks on other SMCR bits here if necessary */
+}
+
 static void verify_hyp_capabilities(void)
 {
 	u64 safe_mmfr1, mmfr0, mmfr1;
@@ -2924,6 +3027,9 @@ static void verify_local_cpu_capabilities(void)
 	if (system_supports_sve())
 		verify_sve_features();
 
+	if (system_supports_sme())
+		verify_sme_features();
+
 	if (is_hyp_mode_available())
 		verify_hyp_capabilities();
 }
@@ -3041,6 +3147,7 @@ void __init setup_cpu_features(void)
 		pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n");
 
 	sve_setup();
+	sme_setup();
 	minsigstksz_setup();
 
 	/* Advertise that we have computed the system capabilities */
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 330b92ea863a..8a8136a096ac 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -98,6 +98,14 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_AFP]		= "afp",
 	[KERNEL_HWCAP_RPRES]		= "rpres",
 	[KERNEL_HWCAP_MTE3]		= "mte3",
+	[KERNEL_HWCAP_SME]		= "sme",
+	[KERNEL_HWCAP_SME_I16I64]	= "smei16i64",
+	[KERNEL_HWCAP_SME_F64F64]	= "smef64f64",
+	[KERNEL_HWCAP_SME_I8I32]	= "smei8i32",
+	[KERNEL_HWCAP_SME_F16F32]	= "smef16f32",
+	[KERNEL_HWCAP_SME_B16F32]	= "smeb16f32",
+	[KERNEL_HWCAP_SME_F32F32]	= "smef32f32",
+	[KERNEL_HWCAP_SME_FA64]		= "smefa64",
 };
 
 #ifdef CONFIG_COMPAT
@@ -401,6 +409,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
 	info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1);
+	info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1);
 
 	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
 		info->reg_gmid = read_cpuid(GMID_EL1);
@@ -412,6 +421,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	    id_aa64pfr0_sve(info->reg_id_aa64pfr0))
 		info->reg_zcr = read_zcr_features();
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) &&
+	    id_aa64pfr1_sme(info->reg_id_aa64pfr1))
+		info->reg_smcr = read_smcr_features();
+
 	cpuinfo_detect_icache_policy(info);
 }
 
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 878c65aa7206..29139e9a1517 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -537,6 +537,14 @@ static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr)
 	exit_to_user_mode(regs);
 }
 
+static void noinstr el0_sme_acc(struct pt_regs *regs, unsigned long esr)
+{
+	enter_from_user_mode(regs);
+	local_daif_restore(DAIF_PROCCTX);
+	do_sme_acc(esr, regs);
+	exit_to_user_mode(regs);
+}
+
 static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
 {
 	enter_from_user_mode(regs);
@@ -645,6 +653,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs)
 	case ESR_ELx_EC_SVE:
 		el0_sve_acc(regs, esr);
 		break;
+	case ESR_ELx_EC_SME:
+		el0_sme_acc(regs, esr);
+		break;
 	case ESR_ELx_EC_FP_EXC64:
 		el0_fpsimd_exc(regs, esr);
 		break;
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index dc242e269f9a..229436f33df5 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -86,3 +86,39 @@ SYM_FUNC_START(sve_flush_live)
 SYM_FUNC_END(sve_flush_live)
 
 #endif /* CONFIG_ARM64_SVE */
+
+#ifdef CONFIG_ARM64_SME
+
+SYM_FUNC_START(sme_get_vl)
+	_sme_rdsvl	0, 1
+	ret
+SYM_FUNC_END(sme_get_vl)
+
+SYM_FUNC_START(sme_set_vq)
+	sme_load_vq x0, x1, x2
+	ret
+SYM_FUNC_END(sme_set_vq)
+
+/*
+ * Save the SME state
+ *
+ * x0 - pointer to buffer for state
+ */
+SYM_FUNC_START(za_save_state)
+	_sme_rdsvl	1, 1		// x1 = VL/8
+	sme_save_za 0, x1, 12
+	ret
+SYM_FUNC_END(za_save_state)
+
+/*
+ * Load the SME state
+ *
+ * x0 - pointer to buffer for state
+ */
+SYM_FUNC_START(za_load_state)
+	_sme_rdsvl	1, 1		// x1 = VL/8
+	sme_load_za 0, x1, 12
+	ret
+SYM_FUNC_END(za_load_state)
+
+#endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 47af76e53221..a568735b7c2e 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -121,7 +121,10 @@
 struct fpsimd_last_state_struct {
 	struct user_fpsimd_state *st;
 	void *sve_state;
+	void *za_state;
+	u64 *svcr;
 	unsigned int sve_vl;
+	unsigned int sme_vl;
 };
 
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -136,6 +139,12 @@ __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
 		.max_virtualisable_vl	= SVE_VL_MIN,
 	},
 #endif
+#ifdef CONFIG_ARM64_SME
+	[ARM64_VEC_SME] = {
+		.type			= ARM64_VEC_SME,
+		.name			= "SME",
+	},
+#endif
 };
 
 static unsigned int vec_vl_inherit_flag(enum vec_type type)
@@ -143,6 +152,8 @@ static unsigned int vec_vl_inherit_flag(enum vec_type type)
 	switch (type) {
 	case ARM64_VEC_SVE:
 		return TIF_SVE_VL_INHERIT;
+	case ARM64_VEC_SME:
+		return TIF_SME_VL_INHERIT;
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -186,6 +197,26 @@ extern void __percpu *efi_sve_state;
 
 #endif /* ! CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static int get_sme_default_vl(void)
+{
+	return get_default_vl(ARM64_VEC_SME);
+}
+
+static void set_sme_default_vl(int val)
+{
+	set_default_vl(ARM64_VEC_SME, val);
+}
+
+static void sme_free(struct task_struct *);
+
+#else
+
+static inline void sme_free(struct task_struct *t) { }
+
+#endif
+
 DEFINE_PER_CPU(bool, fpsimd_context_busy);
 EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);
 
@@ -206,10 +237,19 @@ static void __get_cpu_fpsimd_context(void)
  *
  * The double-underscore version must only be called if you know the task
  * can't be preempted.
+ *
+ * On RT kernels local_bh_disable() is not sufficient because it only
+ * serializes soft interrupt related sections via a local lock, but stays
+ * preemptible. Disabling preemption is the right choice here as bottom
+ * half processing is always in thread context on RT kernels so it
+ * implicitly prevents bottom half processing as well.
  */
 static void get_cpu_fpsimd_context(void)
 {
-	local_bh_disable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_disable();
+	else
+		preempt_disable();
 	__get_cpu_fpsimd_context();
 }
 
@@ -230,7 +270,10 @@ static void __put_cpu_fpsimd_context(void)
 static void put_cpu_fpsimd_context(void)
 {
 	__put_cpu_fpsimd_context();
-	local_bh_enable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_enable();
+	else
+		preempt_enable();
 }
 
 static bool have_cpu_fpsimd_context(void)
@@ -279,16 +322,27 @@ 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
+ * 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
+ * may disable TIF_SME and reenable traps.
+ */
+
+
+/*
  * TIF_SVE controls whether a task can use SVE without trapping while
- * in userspace, and also the way a task's FPSIMD/SVE state is stored
- * in thread_struct.
+ * in userspace, and also (together with TIF_SME) the way a task's
+ * FPSIMD/SVE state is stored in thread_struct.
  *
  * The kernel uses this flag to track whether a user task is actively
  * using SVE, and therefore whether full SVE register state needs to
  * be tracked.  If not, the cheaper FPSIMD context handling code can
  * be used instead of the more costly SVE equivalents.
  *
- *  * TIF_SVE set:
+ *  * TIF_SVE or SVCR.SM set:
  *
  *    The task can execute SVE instructions while in userspace without
  *    trapping to the kernel.
@@ -296,7 +350,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
  *    corresponding Zn), P0-P15 and FFR are encoded in in
  *    task->thread.sve_state, formatted appropriately for vector
- *    length task->thread.sve_vl.
+ *    length task->thread.sve_vl or, if SVCR.SM is set,
+ *    task->thread.sme_vl.
  *
  *    task->thread.sve_state must point to a valid buffer at least
  *    sve_state_size(task) bytes in size.
@@ -334,16 +389,44 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  */
 static void task_fpsimd_load(void)
 {
+	bool restore_sve_regs = false;
+	bool restore_ffr;
+
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
 
+	/* Check if we should restore SVE first */
 	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
 		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
+		restore_sve_regs = true;
+		restore_ffr = true;
+	}
+
+	/* Restore SME, override SVE register configuration if needed */
+	if (system_supports_sme()) {
+		unsigned long sme_vl = task_get_sme_vl(current);
+
+		/* Ensure VL is set up for restoring data */
+		if (test_thread_flag(TIF_SME))
+			sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
+
+		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
+
+		if (thread_za_enabled(&current->thread))
+			za_load_state(current->thread.za_state);
+
+		if (thread_sm_enabled(&current->thread)) {
+			restore_sve_regs = true;
+			restore_ffr = system_supports_fa64();
+		}
+	}
+
+	if (restore_sve_regs)
 		sve_load_state(sve_pffr(&current->thread),
-			       &current->thread.uw.fpsimd_state.fpsr, true);
-	} else {
+			       &current->thread.uw.fpsimd_state.fpsr,
+			       restore_ffr);
+	else
 		fpsimd_load_state(&current->thread.uw.fpsimd_state);
-	}
 }
 
 /*
@@ -361,6 +444,9 @@ static void fpsimd_save(void)
 	struct fpsimd_last_state_struct const *last =
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
+	bool save_sve_regs = false;
+	bool save_ffr;
+	unsigned int vl;
 
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
@@ -368,9 +454,32 @@ static void fpsimd_save(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
-	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
-	    test_thread_flag(TIF_SVE)) {
-		if (WARN_ON(sve_get_vl() != last->sve_vl)) {
+	if (test_thread_flag(TIF_SVE)) {
+		save_sve_regs = true;
+		save_ffr = true;
+		vl = last->sve_vl;
+	}
+
+	if (system_supports_sme()) {
+		u64 *svcr = last->svcr;
+		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+		if (*svcr & SYS_SVCR_EL0_ZA_MASK)
+			za_save_state(last->za_state);
+
+		/* If we are in streaming mode override regular SVE. */
+		if (*svcr & SYS_SVCR_EL0_SM_MASK) {
+			save_sve_regs = true;
+			save_ffr = system_supports_fa64();
+			vl = last->sme_vl;
+		}
+	}
+
+	if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) {
+		/* Get the configured VL from RDVL, will account for SM */
+		if (WARN_ON(sve_get_vl() != vl)) {
 			/*
 			 * Can't save the user regs, so current would
 			 * re-enter user with corrupt state.
@@ -381,8 +490,8 @@ static void fpsimd_save(void)
 		}
 
 		sve_save_state((char *)last->sve_state +
-					sve_ffr_offset(last->sve_vl),
-			       &last->st->fpsr, true);
+					sve_ffr_offset(vl),
+			       &last->st->fpsr, save_ffr);
 	} else {
 		fpsimd_save_state(last->st);
 	}
@@ -409,6 +518,8 @@ static unsigned int find_supported_vector_length(enum vec_type type,
 
 	if (vl > max_vl)
 		vl = max_vl;
+	if (vl < info->min_vl)
+		vl = info->min_vl;
 
 	bit = find_next_bit(info->vq_map, SVE_VQ_MAX,
 			    __vq_to_bit(sve_vq_from_vl(vl)));
@@ -467,6 +578,30 @@ static int __init sve_sysctl_init(void)
 static int __init sve_sysctl_init(void) { return 0; }
 #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
+#if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL)
+static struct ctl_table sme_default_vl_table[] = {
+	{
+		.procname	= "sme_default_vector_length",
+		.mode		= 0644,
+		.proc_handler	= vec_proc_do_default_vl,
+		.extra1		= &vl_info[ARM64_VEC_SME],
+	},
+	{ }
+};
+
+static int __init sme_sysctl_init(void)
+{
+	if (system_supports_sme())
+		if (!register_sysctl("abi", sme_default_vl_table))
+			return -EINVAL;
+
+	return 0;
+}
+
+#else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */
+static int __init sme_sysctl_init(void) { return 0; }
+#endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */
+
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
 
@@ -520,7 +655,7 @@ static void fpsimd_to_sve(struct task_struct *task)
 	if (!system_supports_sve())
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
 	__fpsimd_to_sve(sst, fst, vq);
 }
 
@@ -537,7 +672,7 @@ static void fpsimd_to_sve(struct task_struct *task)
  */
 static void sve_to_fpsimd(struct task_struct *task)
 {
-	unsigned int vq;
+	unsigned int vq, vl;
 	void const *sst = task->thread.sve_state;
 	struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
 	unsigned int i;
@@ -546,7 +681,8 @@ static void sve_to_fpsimd(struct task_struct *task)
 	if (!system_supports_sve())
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vl = thread_get_cur_vl(&task->thread);
+	vq = sve_vq_from_vl(vl);
 	for (i = 0; i < SVE_NUM_ZREGS; ++i) {
 		p = (__uint128_t const *)ZREG(sst, vq, i);
 		fst->vregs[i] = arm64_le128_to_cpu(*p);
@@ -559,9 +695,16 @@ static void sve_to_fpsimd(struct task_struct *task)
  * Return how many bytes of memory are required to store the full SVE
  * state for task, given task's currently configured vector length.
  */
-static size_t sve_state_size(struct task_struct const *task)
+size_t sve_state_size(struct task_struct const *task)
 {
-	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task)));
+	unsigned int vl = 0;
+
+	if (system_supports_sve())
+		vl = task_get_sve_vl(task);
+	if (system_supports_sme())
+		vl = max(vl, task_get_sme_vl(task));
+
+	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
 }
 
 /*
@@ -588,6 +731,19 @@ void sve_alloc(struct task_struct *task)
 
 
 /*
+ * Force the FPSIMD state shared with SVE to be updated in the SVE state
+ * even if the SVE state is the current active state.
+ *
+ * This should only be called by ptrace.  task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ */
+void fpsimd_force_sync_to_sve(struct task_struct *task)
+{
+	fpsimd_to_sve(task);
+}
+
+/*
  * Ensure that task->thread.sve_state is up to date with respect to
  * the user task, irrespective of when SVE is in use or not.
  *
@@ -597,7 +753,8 @@ void sve_alloc(struct task_struct *task)
  */
 void fpsimd_sync_to_sve(struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SVE))
+	if (!test_tsk_thread_flag(task, TIF_SVE) &&
+	    !thread_sm_enabled(&task->thread))
 		fpsimd_to_sve(task);
 }
 
@@ -611,7 +768,8 @@ void fpsimd_sync_to_sve(struct task_struct *task)
  */
 void sve_sync_to_fpsimd(struct task_struct *task)
 {
-	if (test_tsk_thread_flag(task, TIF_SVE))
+	if (test_tsk_thread_flag(task, TIF_SVE) ||
+	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 }
 
@@ -636,7 +794,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 	if (!test_tsk_thread_flag(task, TIF_SVE))
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
 
 	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
 	__fpsimd_to_sve(sst, fst, vq);
@@ -680,8 +838,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	/*
 	 * To ensure the FPSIMD bits of the SVE vector registers are preserved,
 	 * write any live register state back to task_struct, and convert to a
-	 * regular FPSIMD thread.  Since the vector length can only be changed
-	 * with a syscall we can't be in streaming mode while reconfiguring.
+	 * regular FPSIMD thread.
 	 */
 	if (task == current) {
 		get_cpu_fpsimd_context();
@@ -690,17 +847,26 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	}
 
 	fpsimd_flush_task_state(task);
-	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
+	if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
+	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 
+	if (system_supports_sme() && type == ARM64_VEC_SME) {
+		task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK |
+				       SYS_SVCR_EL0_ZA_MASK);
+		clear_thread_flag(TIF_SME);
+	}
+
 	if (task == current)
 		put_cpu_fpsimd_context();
 
 	/*
-	 * Force reallocation of task SVE state to the correct size
-	 * on next use:
+	 * Force reallocation of task SVE and SME state to the correct
+	 * size on next use:
 	 */
 	sve_free(task);
+	if (system_supports_sme() && type == ARM64_VEC_SME)
+		sme_free(task);
 
 	task_set_vl(task, type, vl);
 
@@ -761,6 +927,36 @@ int sve_get_current_vl(void)
 	return vec_prctl_status(ARM64_VEC_SVE, 0);
 }
 
+#ifdef CONFIG_ARM64_SME
+/* PR_SME_SET_VL */
+int sme_set_current_vl(unsigned long arg)
+{
+	unsigned long vl, flags;
+	int ret;
+
+	vl = arg & PR_SME_VL_LEN_MASK;
+	flags = arg & ~vl;
+
+	if (!system_supports_sme() || is_compat_task())
+		return -EINVAL;
+
+	ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags);
+	if (ret)
+		return ret;
+
+	return vec_prctl_status(ARM64_VEC_SME, flags);
+}
+
+/* PR_SME_GET_VL */
+int sme_get_current_vl(void)
+{
+	if (!system_supports_sme() || is_compat_task())
+		return -EINVAL;
+
+	return vec_prctl_status(ARM64_VEC_SME, 0);
+}
+#endif /* CONFIG_ARM64_SME */
+
 static void vec_probe_vqs(struct vl_info *info,
 			  DECLARE_BITMAP(map, SVE_VQ_MAX))
 {
@@ -770,7 +966,23 @@ static void vec_probe_vqs(struct vl_info *info,
 
 	for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) {
 		write_vl(info->type, vq - 1); /* self-syncing */
-		vl = sve_get_vl();
+
+		switch (info->type) {
+		case ARM64_VEC_SVE:
+			vl = sve_get_vl();
+			break;
+		case ARM64_VEC_SME:
+			vl = sme_get_vl();
+			break;
+		default:
+			vl = 0;
+			break;
+		}
+
+		/* Minimum VL identified? */
+		if (sve_vq_from_vl(vl) > vq)
+			break;
+
 		vq = sve_vq_from_vl(vl); /* skip intervening lengths */
 		set_bit(__vq_to_bit(vq), map);
 	}
@@ -856,21 +1068,25 @@ int vec_verify_vq_map(enum vec_type type)
 
 static void __init sve_efi_setup(void)
 {
-	struct vl_info *info = &vl_info[ARM64_VEC_SVE];
+	int max_vl = 0;
+	int i;
 
 	if (!IS_ENABLED(CONFIG_EFI))
 		return;
 
+	for (i = 0; i < ARRAY_SIZE(vl_info); i++)
+		max_vl = max(vl_info[i].max_vl, max_vl);
+
 	/*
 	 * alloc_percpu() warns and prints a backtrace if this goes wrong.
 	 * This is evidence of a crippled system and we are returning void,
 	 * so no attempt is made to handle this situation here.
 	 */
-	if (!sve_vl_valid(info->max_vl))
+	if (!sve_vl_valid(max_vl))
 		goto fail;
 
 	efi_sve_state = __alloc_percpu(
-		SVE_SIG_REGS_SIZE(sve_vq_from_vl(info->max_vl)), SVE_VQ_BYTES);
+		SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES);
 	if (!efi_sve_state)
 		goto fail;
 
@@ -989,10 +1205,172 @@ void __init sve_setup(void)
 void fpsimd_release_task(struct task_struct *dead_task)
 {
 	__sve_free(dead_task);
+	sme_free(dead_task);
 }
 
 #endif /* CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+/*
+ * Ensure that task->thread.za_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
+ * 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));
+		return;
+	}
+
+	/* This could potentially be up to 64K. */
+	task->thread.za_state =
+		kzalloc(za_state_size(task), GFP_KERNEL);
+}
+
+static void sme_free(struct task_struct *task)
+{
+	kfree(task->thread.za_state);
+	task->thread.za_state = NULL;
+}
+
+void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+	/* Set priority for all PEs to architecturally defined minimum */
+	write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK,
+		       SYS_SMPRI_EL1);
+
+	/* Allow SME in kernel */
+	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1);
+	isb();
+
+	/* Allow EL0 to access TPIDR2 */
+	write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1);
+	isb();
+}
+
+/*
+ * 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 */
+	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK,
+		       SYS_SMCR_EL1);
+}
+
+/*
+ * Read the pseudo-SMCR used by cpufeatures to identify the supported
+ * vector length.
+ *
+ * Use only if SME is present.
+ * This function clobbers the SME vector length.
+ */
+u64 read_smcr_features(void)
+{
+	u64 smcr;
+	unsigned int vq_max;
+
+	sme_kernel_enable(NULL);
+	sme_smstart_sm();
+
+	/*
+	 * Set the maximum possible VL.
+	 */
+	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK,
+		       SYS_SMCR_EL1);
+
+	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());
+	smcr |= vq_max - 1; /* set LEN field to maximum effective value */
+
+	sme_smstop_sm();
+
+	return smcr;
+}
+
+void __init sme_setup(void)
+{
+	struct vl_info *info = &vl_info[ARM64_VEC_SME];
+	u64 smcr;
+	int min_bit;
+
+	if (!system_supports_sme())
+		return;
+
+	/*
+	 * SME doesn't require any particular vector length be
+	 * supported but it does require at least one.  We should have
+	 * disabled the feature entirely while bringing up CPUs but
+	 * let's double check here.
+	 */
+	WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX));
+
+	min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX);
+	info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit));
+
+	smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1);
+	info->max_vl = sve_vl_from_vq((smcr & SMCR_ELx_LEN_MASK) + 1);
+
+	/*
+	 * Sanity-check that the max VL we determined through CPU features
+	 * corresponds properly to sme_vq_map.  If not, do our best:
+	 */
+	if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SME,
+								 info->max_vl)))
+		info->max_vl = find_supported_vector_length(ARM64_VEC_SME,
+							    info->max_vl);
+
+	WARN_ON(info->min_vl > info->max_vl);
+
+	/*
+	 * For the default VL, pick the maximum supported value <= 32
+	 * (256 bits) if there is one since this is guaranteed not to
+	 * grow the signal frame when in streaming mode, otherwise the
+	 * minimum available VL will be used.
+	 */
+	set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32));
+
+	pr_info("SME: minimum available vector length %u bytes per vector\n",
+		info->min_vl);
+	pr_info("SME: maximum available vector length %u bytes per vector\n",
+		info->max_vl);
+	pr_info("SME: default vector length %u bytes per vector\n",
+		get_sme_default_vl());
+}
+
+#endif /* CONFIG_ARM64_SME */
+
+static void sve_init_regs(void)
+{
+	/*
+	 * Convert the FPSIMD state to SVE, zeroing all the state that
+	 * is not shared with FPSIMD. If (as is likely) the current
+	 * state is live in the registers then do this there and
+	 * update our metadata for the current task including
+	 * disabling the trap, otherwise update our in-memory copy.
+	 * We are guaranteed to not be in streaming mode, we can only
+	 * take a SVE trap when not in streaming mode and we can't be
+	 * in streaming mode when taking a SME trap.
+	 */
+	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		unsigned long vq_minus_one =
+			sve_vq_from_vl(task_get_sve_vl(current)) - 1;
+		sve_set_vq(vq_minus_one);
+		sve_flush_live(true, vq_minus_one);
+		fpsimd_bind_task_to_cpu();
+	} else {
+		fpsimd_to_sve(current);
+	}
+}
+
 /*
  * Trapped SVE access
  *
@@ -1024,22 +1402,77 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 		WARN_ON(1); /* SVE access shouldn't have trapped */
 
 	/*
-	 * Convert the FPSIMD state to SVE, zeroing all the state that
-	 * is not shared with FPSIMD. If (as is likely) the current
-	 * state is live in the registers then do this there and
-	 * update our metadata for the current task including
-	 * disabling the trap, otherwise update our in-memory copy.
+	 * Even if the task can have used streaming mode we can only
+	 * generate SVE access traps in normal SVE mode and
+	 * transitioning out of streaming mode may discard any
+	 * streaming mode state.  Always clear the high bits to avoid
+	 * any potential errors tracking what is properly initialised.
 	 */
+	sve_init_regs();
+
+	put_cpu_fpsimd_context();
+}
+
+/*
+ * Trapped SME access
+ *
+ * Storage is allocated for the full SVE and SME state, the current
+ * FPSIMD register contents are migrated to SVE if SVE is not already
+ * active, and the access trap is disabled.
+ *
+ * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state()
+ * would have disabled the SME access trap for userspace during
+ * ret_to_user, making an SVE access trap impossible in that case.
+ */
+void do_sme_acc(unsigned int esr, struct pt_regs *regs)
+{
+	/* Even if we chose not to use SME, the hardware could still trap: */
+	if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) {
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+		return;
+	}
+
+	/*
+	 * If this not a trap due to SME being disabled then something
+	 * is being used in the wrong mode, report as SIGILL.
+	 */
+	if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) {
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+		return;
+	}
+
+	sve_alloc(current);
+	sme_alloc(current);
+	if (!current->thread.sve_state || !current->thread.za_state) {
+		force_sig(SIGKILL);
+		return;
+	}
+
+	get_cpu_fpsimd_context();
+
+	/* With TIF_SME userspace shouldn't generate any traps */
+	if (test_and_set_thread_flag(TIF_SME))
+		WARN_ON(1);
+
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		unsigned long vq_minus_one =
-			sve_vq_from_vl(task_get_sve_vl(current)) - 1;
-		sve_set_vq(vq_minus_one);
-		sve_flush_live(true, vq_minus_one);
+			sve_vq_from_vl(task_get_sme_vl(current)) - 1;
+		sme_set_vq(vq_minus_one);
+
 		fpsimd_bind_task_to_cpu();
-	} else {
-		fpsimd_to_sve(current);
 	}
 
+	/*
+	 * If SVE was not already active initialise the SVE registers,
+	 * any non-shared state between the streaming and regular SVE
+	 * registers is architecturally guaranteed to be zeroed when
+	 * we enter streaming mode.  We do not need to initialize ZA
+	 * since ZA must be disabled at this point and enabling ZA is
+	 * architecturally defined to zero ZA.
+	 */
+	if (system_supports_sve() && !test_thread_flag(TIF_SVE))
+		sve_init_regs();
+
 	put_cpu_fpsimd_context();
 }
 
@@ -1141,6 +1574,9 @@ static void fpsimd_flush_thread_vl(enum vec_type type)
 
 void fpsimd_flush_thread(void)
 {
+	void *sve_state = NULL;
+	void *za_state = NULL;
+
 	if (!system_supports_fpsimd())
 		return;
 
@@ -1152,11 +1588,28 @@ void fpsimd_flush_thread(void)
 
 	if (system_supports_sve()) {
 		clear_thread_flag(TIF_SVE);
-		sve_free(current);
+
+		/* Defer kfree() while in atomic context */
+		sve_state = current->thread.sve_state;
+		current->thread.sve_state = NULL;
+
 		fpsimd_flush_thread_vl(ARM64_VEC_SVE);
 	}
 
+	if (system_supports_sme()) {
+		clear_thread_flag(TIF_SME);
+
+		/* Defer kfree() while in atomic context */
+		za_state = current->thread.za_state;
+		current->thread.za_state = NULL;
+
+		fpsimd_flush_thread_vl(ARM64_VEC_SME);
+		current->thread.svcr = 0;
+	}
+
 	put_cpu_fpsimd_context();
+	kfree(sve_state);
+	kfree(za_state);
 }
 
 /*
@@ -1198,22 +1651,34 @@ 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->sve_vl = task_get_sve_vl(current);
+	last->sme_vl = task_get_sme_vl(current);
+	last->svcr = &current->thread.svcr;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
+	/*
+	 * Toggle SVE and SME trapping for userspace if needed, these
+	 * are serialsied by ret_to_user().
+	 */
+	if (system_supports_sme()) {
+		if (test_thread_flag(TIF_SME))
+			sme_user_enable();
+		else
+			sme_user_disable();
+	}
+
 	if (system_supports_sve()) {
-		/* Toggle SVE trapping for userspace if needed */
 		if (test_thread_flag(TIF_SVE))
 			sve_user_enable();
 		else
 			sve_user_disable();
-
-		/* Serialised by exception return to user */
 	}
 }
 
 void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
-			      unsigned int sve_vl)
+			      unsigned int sve_vl, void *za_state,
+			      unsigned int sme_vl, u64 *svcr)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1222,8 +1687,11 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
 	last->st = st;
+	last->svcr = svcr;
 	last->sve_state = sve_state;
+	last->za_state = za_state;
 	last->sve_vl = sve_vl;
+	last->sme_vl = sme_vl;
 }
 
 /*
@@ -1320,6 +1788,15 @@ static void fpsimd_flush_cpu_state(void)
 {
 	WARN_ON(!system_supports_fpsimd());
 	__this_cpu_write(fpsimd_last_state.st, NULL);
+
+	/*
+	 * Leaving streaming mode enabled will cause issues for any kernel
+	 * NEON and leaving streaming mode or ZA enabled may increase power
+	 * consumption.
+	 */
+	if (system_supports_sme())
+		sme_smstop();
+
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
 
@@ -1397,6 +1874,7 @@ EXPORT_SYMBOL(kernel_neon_end);
 static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state);
 static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
 static DEFINE_PER_CPU(bool, efi_sve_state_used);
+static DEFINE_PER_CPU(bool, efi_sm_state);
 
 /*
  * EFI runtime services support functions
@@ -1431,12 +1909,28 @@ void __efi_fpsimd_begin(void)
 		 */
 		if (system_supports_sve() && likely(efi_sve_state)) {
 			char *sve_state = this_cpu_ptr(efi_sve_state);
+			bool ffr = true;
+			u64 svcr;
 
 			__this_cpu_write(efi_sve_state_used, true);
 
+			if (system_supports_sme()) {
+				svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+				if (!system_supports_fa64())
+					ffr = svcr & SYS_SVCR_EL0_SM_MASK;
+
+				__this_cpu_write(efi_sm_state, ffr);
+			}
+
 			sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()),
 				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
-				       true);
+				       ffr);
+
+			if (system_supports_sme())
+				sysreg_clear_set_s(SYS_SVCR_EL0,
+						   SYS_SVCR_EL0_SM_MASK, 0);
+
 		} else {
 			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
 		}
@@ -1459,11 +1953,26 @@ void __efi_fpsimd_end(void)
 		if (system_supports_sve() &&
 		    likely(__this_cpu_read(efi_sve_state_used))) {
 			char const *sve_state = this_cpu_ptr(efi_sve_state);
+			bool ffr = true;
+
+			/*
+			 * Restore streaming mode; EFI calls are
+			 * normal function calls so should not return in
+			 * streaming mode.
+			 */
+			if (system_supports_sme()) {
+				if (__this_cpu_read(efi_sm_state)) {
+					sysreg_clear_set_s(SYS_SVCR_EL0,
+							   0,
+							   SYS_SVCR_EL0_SM_MASK);
+					if (!system_supports_fa64())
+						ffr = efi_sm_state;
+				}
+			}
 
-			sve_set_vq(sve_vq_from_vl(sve_get_vl()) - 1);
 			sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()),
 				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
-				       true);
+				       ffr);
 
 			__this_cpu_write(efi_sve_state_used, false);
 		} else {
@@ -1538,6 +2047,13 @@ static int __init fpsimd_init(void)
 	if (!cpu_have_named_feature(ASIMD))
 		pr_notice("Advanced SIMD is not implemented\n");
 
-	return sve_sysctl_init();
+
+	if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE))
+		pr_notice("SME is implemented but not SVE\n");
+
+	sve_sysctl_init();
+	sme_sysctl_init();
+
+	return 0;
 }
 core_initcall(fpsimd_init);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7fa97df55e3a..9734c9fb1a32 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -250,6 +250,8 @@ void show_regs(struct pt_regs *regs)
 static void tls_thread_flush(void)
 {
 	write_sysreg(0, tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(0, SYS_TPIDR2_EL0);
 
 	if (is_compat_task()) {
 		current->thread.uw.tp_value = 0;
@@ -298,16 +300,42 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	/*
 	 * Detach src's sve_state (if any) from dst so that it does not
-	 * get erroneously used or freed prematurely.  dst's sve_state
+	 * get erroneously used or freed prematurely.  dst's copies
 	 * will be allocated on demand later on if dst uses SVE.
 	 * For consistency, also clear TIF_SVE here: this could be done
 	 * later in copy_process(), but to avoid tripping up future
-	 * maintainers it is best not to leave TIF_SVE and sve_state in
+	 * maintainers it is best not to leave TIF flags and buffers in
 	 * an inconsistent state, even temporarily.
 	 */
 	dst->thread.sve_state = NULL;
 	clear_tsk_thread_flag(dst, TIF_SVE);
 
+	/*
+	 * 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.
+	 */
+	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) {
+			kfree(dst->thread.sve_state);
+			dst->thread.sve_state = NULL;
+			return -ENOMEM;
+		}
+	} else {
+		dst->thread.za_state = NULL;
+		clear_tsk_thread_flag(dst, TIF_SME);
+	}
+
 	/* clear any pending asynchronous tag fault raised by the parent */
 	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
 
@@ -343,6 +371,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		 * out-of-sync with the saved value.
 		 */
 		*task_user_tls(p) = read_sysreg(tpidr_el0);
+		if (system_supports_tpidr2())
+			p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 
 		if (stack_start) {
 			if (is_compat_thread(task_thread_info(p)))
@@ -353,10 +383,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 		/*
 		 * If a TLS pointer was passed to clone, use it for the new
-		 * thread.
+		 * thread.  We also reset TPIDR2 if it's in use.
 		 */
-		if (clone_flags & CLONE_SETTLS)
+		if (clone_flags & CLONE_SETTLS) {
 			p->thread.uw.tp_value = tls;
+			p->thread.tpidr2_el0 = 0;
+		}
 	} else {
 		/*
 		 * A kthread has no context to ERET to, so ensure any buggy
@@ -387,6 +419,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 void tls_preserve_current_state(void)
 {
 	*task_user_tls(current) = read_sysreg(tpidr_el0);
+	if (system_supports_tpidr2() && !is_compat_task())
+		current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 }
 
 static void tls_thread_switch(struct task_struct *next)
@@ -399,6 +433,8 @@ static void tls_thread_switch(struct task_struct *next)
 		write_sysreg(0, tpidrro_el0);
 
 	write_sysreg(*task_user_tls(next), tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0);
 }
 
 /*
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 230a47b9189e..60ebc3060cf1 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -713,21 +713,51 @@ static int system_call_set(struct task_struct *target,
 #ifdef CONFIG_ARM64_SVE
 
 static void sve_init_header_from_task(struct user_sve_header *header,
-				      struct task_struct *target)
+				      struct task_struct *target,
+				      enum vec_type type)
 {
 	unsigned int vq;
+	bool active;
+	bool fpsimd_only;
+	enum vec_type task_type;
 
 	memset(header, 0, sizeof(*header));
 
-	header->flags = test_tsk_thread_flag(target, TIF_SVE) ?
-		SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD;
-	if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
-		header->flags |= SVE_PT_VL_INHERIT;
+	/* Check if the requested registers are active for the task */
+	if (thread_sm_enabled(&target->thread))
+		task_type = ARM64_VEC_SME;
+	else
+		task_type = ARM64_VEC_SVE;
+	active = (task_type == type);
+
+	switch (type) {
+	case ARM64_VEC_SVE:
+		if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
+			header->flags |= SVE_PT_VL_INHERIT;
+		fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE);
+		break;
+	case ARM64_VEC_SME:
+		if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
+			header->flags |= SVE_PT_VL_INHERIT;
+		fpsimd_only = false;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
 
-	header->vl = task_get_sve_vl(target);
+	if (active) {
+		if (fpsimd_only) {
+			header->flags |= SVE_PT_REGS_FPSIMD;
+		} else {
+			header->flags |= SVE_PT_REGS_SVE;
+		}
+	}
+
+	header->vl = task_get_vl(target, type);
 	vq = sve_vq_from_vl(header->vl);
 
-	header->max_vl = sve_max_vl();
+	header->max_vl = vec_max_vl(type);
 	header->size = SVE_PT_SIZE(vq, header->flags);
 	header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl),
 				      SVE_PT_REGS_SVE);
@@ -738,19 +768,17 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header)
 	return ALIGN(header->size, SVE_VQ_BYTES);
 }
 
-static int sve_get(struct task_struct *target,
-		   const struct user_regset *regset,
-		   struct membuf to)
+static int sve_get_common(struct task_struct *target,
+			  const struct user_regset *regset,
+			  struct membuf to,
+			  enum vec_type type)
 {
 	struct user_sve_header header;
 	unsigned int vq;
 	unsigned long start, end;
 
-	if (!system_supports_sve())
-		return -EINVAL;
-
 	/* Header */
-	sve_init_header_from_task(&header, target);
+	sve_init_header_from_task(&header, target, type);
 	vq = sve_vq_from_vl(header.vl);
 
 	membuf_write(&to, &header, sizeof(header));
@@ -758,49 +786,61 @@ static int sve_get(struct task_struct *target,
 	if (target == current)
 		fpsimd_preserve_current_state();
 
-	/* Registers: FPSIMD-only case */
-
 	BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
-	if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD)
+	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+
+	switch ((header.flags & SVE_PT_REGS_MASK)) {
+	case SVE_PT_REGS_FPSIMD:
 		return __fpr_get(target, regset, to);
 
-	/* Otherwise: full SVE case */
+	case SVE_PT_REGS_SVE:
+		start = SVE_PT_SVE_OFFSET;
+		end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+		membuf_write(&to, target->thread.sve_state, end - start);
 
-	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
-	start = SVE_PT_SVE_OFFSET;
-	end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
-	membuf_write(&to, target->thread.sve_state, end - start);
+		start = end;
+		end = SVE_PT_SVE_FPSR_OFFSET(vq);
+		membuf_zero(&to, end - start);
 
-	start = end;
-	end = SVE_PT_SVE_FPSR_OFFSET(vq);
-	membuf_zero(&to, end - start);
+		/*
+		 * Copy fpsr, and fpcr which must follow contiguously in
+		 * struct fpsimd_state:
+		 */
+		start = end;
+		end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+		membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr,
+			     end - start);
 
-	/*
-	 * Copy fpsr, and fpcr which must follow contiguously in
-	 * struct fpsimd_state:
-	 */
-	start = end;
-	end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
-	membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start);
+		start = end;
+		end = sve_size_from_header(&header);
+		return membuf_zero(&to, end - start);
 
-	start = end;
-	end = sve_size_from_header(&header);
-	return membuf_zero(&to, end - start);
+	default:
+		return 0;
+	}
 }
 
-static int sve_set(struct task_struct *target,
+static int sve_get(struct task_struct *target,
 		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
+		   struct membuf to)
+{
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	return sve_get_common(target, regset, to, ARM64_VEC_SVE);
+}
+
+static int sve_set_common(struct task_struct *target,
+			  const struct user_regset *regset,
+			  unsigned int pos, unsigned int count,
+			  const void *kbuf, const void __user *ubuf,
+			  enum vec_type type)
 {
 	int ret;
 	struct user_sve_header header;
 	unsigned int vq;
 	unsigned long start, end;
 
-	if (!system_supports_sve())
-		return -EINVAL;
-
 	/* Header */
 	if (count < sizeof(header))
 		return -EINVAL;
@@ -813,13 +853,37 @@ static int sve_set(struct task_struct *target,
 	 * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by
 	 * vec_set_vector_length(), which will also validate them for us:
 	 */
-	ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl,
+	ret = vec_set_vector_length(target, type, header.vl,
 		((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
 	if (ret)
 		goto out;
 
 	/* Actual VL set may be less than the user asked for: */
-	vq = sve_vq_from_vl(task_get_sve_vl(target));
+	vq = sve_vq_from_vl(task_get_vl(target, type));
+
+	/* Enter/exit streaming mode */
+	if (system_supports_sme()) {
+		u64 old_svcr = target->thread.svcr;
+
+		switch (type) {
+		case ARM64_VEC_SVE:
+			target->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK;
+			break;
+		case ARM64_VEC_SME:
+			target->thread.svcr |= SYS_SVCR_EL0_SM_MASK;
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
+
+		/*
+		 * If we switched then invalidate any existing SVE
+		 * state and ensure there's storage.
+		 */
+		if (target->thread.svcr != old_svcr)
+			sve_alloc(target);
+	}
 
 	/* Registers: FPSIMD-only case */
 
@@ -828,10 +892,15 @@ static int sve_set(struct task_struct *target,
 		ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
 				SVE_PT_FPSIMD_OFFSET);
 		clear_tsk_thread_flag(target, TIF_SVE);
+		if (type == ARM64_VEC_SME)
+			fpsimd_force_sync_to_sve(target);
 		goto out;
 	}
 
-	/* Otherwise: full SVE case */
+	/*
+	 * Otherwise: no registers or full SVE case.  For backwards
+	 * compatibility reasons we treat empty flags as SVE registers.
+	 */
 
 	/*
 	 * If setting a different VL from the requested VL and there is
@@ -852,8 +921,9 @@ static int sve_set(struct task_struct *target,
 
 	/*
 	 * Ensure target->thread.sve_state is up to date with target's
-	 * FPSIMD regs, so that a short copyin leaves trailing registers
-	 * unmodified.
+	 * FPSIMD regs, so that a short copyin leaves trailing
+	 * registers unmodified.  Always enable SVE even if going into
+	 * streaming mode.
 	 */
 	fpsimd_sync_to_sve(target);
 	set_tsk_thread_flag(target, TIF_SVE);
@@ -889,8 +959,181 @@ out:
 	return ret;
 }
 
+static int sve_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	return sve_set_common(target, regset, pos, count, kbuf, ubuf,
+			      ARM64_VEC_SVE);
+}
+
 #endif /* CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static int ssve_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	if (!system_supports_sme())
+		return -EINVAL;
+
+	return sve_get_common(target, regset, to, ARM64_VEC_SME);
+}
+
+static int ssve_set(struct task_struct *target,
+		    const struct user_regset *regset,
+		    unsigned int pos, unsigned int count,
+		    const void *kbuf, const void __user *ubuf)
+{
+	if (!system_supports_sme())
+		return -EINVAL;
+
+	return sve_set_common(target, regset, pos, count, kbuf, ubuf,
+			      ARM64_VEC_SME);
+}
+
+static int za_get(struct task_struct *target,
+		  const struct user_regset *regset,
+		  struct membuf to)
+{
+	struct user_za_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sme())
+		return -EINVAL;
+
+	/* Header */
+	memset(&header, 0, sizeof(header));
+
+	if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
+		header.flags |= ZA_PT_VL_INHERIT;
+
+	header.vl = task_get_sme_vl(target);
+	vq = sve_vq_from_vl(header.vl);
+	header.max_vl = sme_max_vl();
+	header.max_size = ZA_PT_SIZE(vq);
+
+	/* If ZA is not active there is only the header */
+	if (thread_za_enabled(&target->thread))
+		header.size = ZA_PT_SIZE(vq);
+	else
+		header.size = ZA_PT_ZA_OFFSET;
+
+	membuf_write(&to, &header, sizeof(header));
+
+	BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header));
+	end = ZA_PT_ZA_OFFSET;
+
+	if (target == current)
+		fpsimd_preserve_current_state();
+
+	/* Any register data to include? */
+	if (thread_za_enabled(&target->thread)) {
+		start = end;
+		end = ZA_PT_SIZE(vq);
+		membuf_write(&to, target->thread.za_state, end - start);
+	}
+
+	/* Zero any trailing padding */
+	start = end;
+	end = ALIGN(header.size, SVE_VQ_BYTES);
+	return membuf_zero(&to, end - start);
+}
+
+static int za_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;
+	struct user_za_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sme())
+		return -EINVAL;
+
+	/* Header */
+	if (count < sizeof(header))
+		return -EINVAL;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header,
+				 0, sizeof(header));
+	if (ret)
+		goto out;
+
+	/*
+	 * All current ZA_PT_* flags are consumed by
+	 * vec_set_vector_length(), which will also validate them for
+	 * us:
+	 */
+	ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl,
+		((unsigned long)header.flags) << 16);
+	if (ret)
+		goto out;
+
+	/* Actual VL set may be less than the user asked for: */
+	vq = sve_vq_from_vl(task_get_sme_vl(target));
+
+	/* Ensure there is some SVE storage for streaming mode */
+	if (!target->thread.sve_state) {
+		sve_alloc(target);
+		if (!target->thread.sve_state) {
+			clear_thread_flag(TIF_SME);
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+
+	/* Allocate/reinit ZA storage */
+	sme_alloc(target);
+	if (!target->thread.za_state) {
+		ret = -ENOMEM;
+		clear_tsk_thread_flag(target, TIF_SME);
+		goto out;
+	}
+
+	/* If there is no data then disable ZA */
+	if (!count) {
+		target->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK;
+		goto out;
+	}
+
+	/*
+	 * If setting a different VL from the requested VL and there is
+	 * register data, the data layout will be wrong: don't even
+	 * try to set the registers in this case.
+	 */
+	if (vq != sve_vq_from_vl(header.vl)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header));
+	start = ZA_PT_ZA_OFFSET;
+	end = ZA_PT_SIZE(vq);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 target->thread.za_state,
+				 start, end);
+	if (ret)
+		goto out;
+
+	/* Mark ZA as active and let userspace use it */
+	set_tsk_thread_flag(target, TIF_SME);
+	target->thread.svcr |= SYS_SVCR_EL0_ZA_MASK;
+
+out:
+	fpsimd_flush_task_state(target);
+	return ret;
+}
+
+#endif /* CONFIG_ARM64_SME */
+
 #ifdef CONFIG_ARM64_PTR_AUTH
 static int pac_mask_get(struct task_struct *target,
 			const struct user_regset *regset,
@@ -1108,6 +1351,10 @@ enum aarch64_regset {
 #ifdef CONFIG_ARM64_SVE
 	REGSET_SVE,
 #endif
+#ifdef CONFIG_ARM64_SVE
+	REGSET_SSVE,
+	REGSET_ZA,
+#endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	REGSET_PAC_MASK,
 	REGSET_PAC_ENABLED_KEYS,
@@ -1188,6 +1435,33 @@ static const struct user_regset aarch64_regsets[] = {
 		.set = sve_set,
 	},
 #endif
+#ifdef CONFIG_ARM64_SME
+	[REGSET_SSVE] = { /* Streaming mode SVE */
+		.core_note_type = NT_ARM_SSVE,
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(SME_VQ_MAX, SVE_PT_REGS_SVE),
+				  SVE_VQ_BYTES),
+		.size = SVE_VQ_BYTES,
+		.align = SVE_VQ_BYTES,
+		.regset_get = ssve_get,
+		.set = ssve_set,
+	},
+	[REGSET_ZA] = { /* SME ZA */
+		.core_note_type = NT_ARM_ZA,
+		/*
+		 * ZA is a single register but it's variably sized and
+		 * the ptrace core requires that the size of any data
+		 * be an exact multiple of the configured register
+		 * size so report as though we had SVE_VQ_BYTES
+		 * registers. These values aren't exposed to
+		 * userspace.
+		 */
+		.n = DIV_ROUND_UP(ZA_PT_SIZE(SME_VQ_MAX), SVE_VQ_BYTES),
+		.size = SVE_VQ_BYTES,
+		.align = SVE_VQ_BYTES,
+		.regset_get = za_get,
+		.set = za_set,
+	},
+#endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	[REGSET_PAC_MASK] = {
 		.core_note_type = NT_ARM_PAC_MASK,
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 4a4122ef6f39..2295948d97fd 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -56,6 +56,7 @@ struct rt_sigframe_user_layout {
 	unsigned long fpsimd_offset;
 	unsigned long esr_offset;
 	unsigned long sve_offset;
+	unsigned long za_offset;
 	unsigned long extra_offset;
 	unsigned long end_offset;
 };
@@ -218,6 +219,7 @@ 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
@@ -226,11 +228,17 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 {
 	int err = 0;
 	u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+	u16 flags = 0;
 	unsigned int vl = task_get_sve_vl(current);
 	unsigned int vq = 0;
 
-	if (test_thread_flag(TIF_SVE))
+	if (thread_sm_enabled(&current->thread)) {
+		vl = task_get_sme_vl(current);
 		vq = sve_vq_from_vl(vl);
+		flags |= SVE_SIG_FLAG_SM;
+	} else if (test_thread_flag(TIF_SVE)) {
+		vq = sve_vq_from_vl(vl);
+	}
 
 	memset(reserved, 0, sizeof(reserved));
 
@@ -238,6 +246,7 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 	__put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16),
 			 &ctx->head.size, err);
 	__put_user_error(vl, &ctx->vl, err);
+	__put_user_error(flags, &ctx->flags, err);
 	BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
 	err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
 
@@ -258,18 +267,28 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 static int restore_sve_fpsimd_context(struct user_ctxs *user)
 {
 	int err;
-	unsigned int vq;
+	unsigned int vl, vq;
 	struct user_fpsimd_state fpsimd;
 	struct sve_context sve;
 
 	if (__copy_from_user(&sve, user->sve, sizeof(sve)))
 		return -EFAULT;
 
-	if (sve.vl != task_get_sve_vl(current))
+	if (sve.flags & SVE_SIG_FLAG_SM) {
+		if (!system_supports_sme())
+			return -EINVAL;
+
+		vl = task_get_sme_vl(current);
+	} else {
+		vl = task_get_sve_vl(current);
+	}
+
+	if (sve.vl != vl)
 		return -EINVAL;
 
 	if (sve.head.size <= sizeof(*user->sve)) {
 		clear_thread_flag(TIF_SVE);
+		current->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK;
 		goto fpsimd_only;
 	}
 
@@ -301,7 +320,10 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	if (err)
 		return -EFAULT;
 
-	set_thread_flag(TIF_SVE);
+	if (sve.flags & SVE_SIG_FLAG_SM)
+		current->thread.svcr |= SYS_SVCR_EL0_SM_MASK;
+	else
+		set_thread_flag(TIF_SVE);
 
 fpsimd_only:
 	/* copy the FP and status/control registers */
@@ -326,6 +348,101 @@ extern int restore_sve_fpsimd_context(struct user_ctxs *user);
 
 #endif /* ! CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static int preserve_za_context(struct za_context __user *ctx)
+{
+	int err = 0;
+	u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+	unsigned int vl = task_get_sme_vl(current);
+	unsigned int vq;
+
+	if (thread_za_enabled(&current->thread))
+		vq = sve_vq_from_vl(vl);
+	else
+		vq = 0;
+
+	memset(reserved, 0, sizeof(reserved));
+
+	__put_user_error(ZA_MAGIC, &ctx->head.magic, err);
+	__put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16),
+			 &ctx->head.size, err);
+	__put_user_error(vl, &ctx->vl, err);
+	BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+	err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+	if (vq) {
+		/*
+		 * This assumes that the ZA 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 + ZA_SIG_REGS_OFFSET,
+				      current->thread.za_state,
+				      ZA_SIG_REGS_SIZE(vq));
+	}
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_za_context(struct user_ctxs __user *user)
+{
+	int err;
+	unsigned int vq;
+	struct za_context za;
+
+	if (__copy_from_user(&za, user->za, sizeof(za)))
+		return -EFAULT;
+
+	if (za.vl != task_get_sme_vl(current))
+		return -EINVAL;
+
+	if (za.head.size <= sizeof(*user->za)) {
+		current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK;
+		return 0;
+	}
+
+	vq = sve_vq_from_vl(za.vl);
+
+	if (za.head.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
+	 * 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 thread.sve_state */
+
+	sme_alloc(current);
+	if (!current->thread.za_state) {
+		current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK;
+		clear_thread_flag(TIF_SME);
+		return -ENOMEM;
+	}
+
+	err = __copy_from_user(current->thread.za_state,
+			       (char __user const *)user->za +
+					ZA_SIG_REGS_OFFSET,
+			       ZA_SIG_REGS_SIZE(vq));
+	if (err)
+		return -EFAULT;
+
+	set_thread_flag(TIF_SME);
+	current->thread.svcr |= SYS_SVCR_EL0_ZA_MASK;
+
+	return 0;
+}
+#else /* ! CONFIG_ARM64_SME */
+
+/* Turn any non-optimised out attempts to use these into a link error: */
+extern int preserve_za_context(void __user *ctx);
+extern int restore_za_context(struct user_ctxs *user);
+
+#endif /* ! CONFIG_ARM64_SME */
 
 static int parse_user_sigframe(struct user_ctxs *user,
 			       struct rt_sigframe __user *sf)
@@ -340,6 +457,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 
 	user->fpsimd = NULL;
 	user->sve = NULL;
+	user->za = NULL;
 
 	if (!IS_ALIGNED((unsigned long)base, 16))
 		goto invalid;
@@ -393,7 +511,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			break;
 
 		case SVE_MAGIC:
-			if (!system_supports_sve())
+			if (!system_supports_sve() && !system_supports_sme())
 				goto invalid;
 
 			if (user->sve)
@@ -405,6 +523,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			user->sve = (struct sve_context __user *)head;
 			break;
 
+		case ZA_MAGIC:
+			if (!system_supports_sme())
+				goto invalid;
+
+			if (user->za)
+				goto invalid;
+
+			if (size < sizeof(*user->za))
+				goto invalid;
+
+			user->za = (struct za_context __user *)head;
+			break;
+
 		case EXTRA_MAGIC:
 			if (have_extra_context)
 				goto invalid;
@@ -528,6 +659,9 @@ static int restore_sigframe(struct pt_regs *regs,
 		}
 	}
 
+	if (err == 0 && system_supports_sme() && user.za)
+		err = restore_za_context(&user);
+
 	return err;
 }
 
@@ -594,11 +728,12 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 	if (system_supports_sve()) {
 		unsigned int vq = 0;
 
-		if (add_all || test_thread_flag(TIF_SVE)) {
-			int vl = sve_max_vl();
+		if (add_all || test_thread_flag(TIF_SVE) ||
+		    thread_sm_enabled(&current->thread)) {
+			int vl = max(sve_max_vl(), sme_max_vl());
 
 			if (!add_all)
-				vl = task_get_sve_vl(current);
+				vl = thread_get_cur_vl(&current->thread);
 
 			vq = sve_vq_from_vl(vl);
 		}
@@ -609,6 +744,24 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 			return err;
 	}
 
+	if (system_supports_sme()) {
+		unsigned int vl;
+		unsigned int vq = 0;
+
+		if (add_all)
+			vl = sme_max_vl();
+		else
+			vl = task_get_sme_vl(current);
+
+		if (thread_za_enabled(&current->thread))
+			vq = sve_vq_from_vl(vl);
+
+		err = sigframe_alloc(user, &user->za_offset,
+				     ZA_SIG_CONTEXT_SIZE(vq));
+		if (err)
+			return err;
+	}
+
 	return sigframe_alloc_end(user);
 }
 
@@ -649,13 +802,21 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
 	}
 
-	/* Scalable Vector Extension state, if present */
-	if (system_supports_sve() && err == 0 && user->sve_offset) {
+	/* Scalable Vector Extension state (including streaming), if present */
+	if ((system_supports_sve() || system_supports_sme()) &&
+	    err == 0 && user->sve_offset) {
 		struct sve_context __user *sve_ctx =
 			apply_user_offset(user, user->sve_offset);
 		err |= preserve_sve_context(sve_ctx);
 	}
 
+	/* ZA state if present */
+	if (system_supports_sme() && err == 0 && user->za_offset) {
+		struct za_context __user *za_ctx =
+			apply_user_offset(user, user->za_offset);
+		err |= preserve_za_context(za_ctx);
+	}
+
 	if (err == 0 && user->extra_offset) {
 		char __user *sfp = (char __user *)user->sigframe;
 		char __user *userp =
@@ -759,6 +920,13 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 	/* TCO (Tag Check Override) always cleared for signal handlers */
 	regs->pstate &= ~PSR_TCO_BIT;
 
+	/* Signal handlers are invoked with ZA and streaming mode disabled */
+	if (system_supports_sme()) {
+		current->thread.svcr &= ~(SYS_SVCR_EL0_ZA_MASK |
+					  SYS_SVCR_EL0_SM_MASK);
+		sme_smstop();
+	}
+
 	if (ka->sa.sa_flags & SA_RESTORER)
 		sigtramp = ka->sa.sa_restorer;
 	else
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index c938603b3ba0..92c69e5ac269 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -158,11 +158,36 @@ trace_exit:
 	syscall_trace_exit(regs);
 }
 
-static inline void sve_user_discard(void)
+/*
+ * As per the ABI exit SME streaming mode and clear the SVE state not
+ * shared with FPSIMD on syscall entry.
+ */
+static inline void fp_user_discard(void)
 {
+	/*
+	 * If SME is active then exit streaming mode.  If ZA is active
+	 * then flush the SVE registers but leave userspace access to
+	 * both SVE and SME enabled, otherwise disable SME for the
+	 * task and fall through to disabling SVE too.  This means
+	 * that after a syscall we never have any streaming mode
+	 * 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_EL0);
+
+		if (svcr & SYS_SVCR_EL0_SM_MASK)
+			sme_smstop_sm();
+	}
+
 	if (!system_supports_sve())
 		return;
 
+	/*
+	 * If SME is not active then disable SVE, the registers will
+	 * be cleared when userspace next attempts to access them and
+	 * we do not need to track the SVE register state until then.
+	 */
 	clear_thread_flag(TIF_SVE);
 
 	/*
@@ -177,7 +202,7 @@ static inline void sve_user_discard(void)
 
 void do_el0_svc(struct pt_regs *regs)
 {
-	sve_user_discard();
+	fp_user_discard();
 	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
 }
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 0529fd57567e..6751621e5bea 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -821,6 +821,7 @@ static const char *esr_class_str[] = {
 	[ESR_ELx_EC_SVE]		= "SVE",
 	[ESR_ELx_EC_ERET]		= "ERET/ERETAA/ERETAB",
 	[ESR_ELx_EC_FPAC]		= "FPAC",
+	[ESR_ELx_EC_SME]		= "SME",
 	[ESR_ELx_EC_IMP_DEF]		= "EL3 IMP DEF",
 	[ESR_ELx_EC_IABT_LOW]		= "IABT (lower EL)",
 	[ESR_ELx_EC_IABT_CUR]		= "IABT (current EL)",