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
  ...

16 files changed, 553 insertions, 15 deletions

diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index a58e366f0b07..115cdec1ae87 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -58,11 +58,15 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
 	u64		reg_id_aa64zfr0;
+	u64		reg_id_aa64smfr0;
 
 	struct cpuinfo_32bit	aarch32;
 
 	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
 	u64		reg_zcr;
+
+	/* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */
+	u64		reg_smcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index c62e7e5e2f0c..14a8f3d93add 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -622,6 +622,13 @@ static inline bool id_aa64pfr0_sve(u64 pfr0)
 	return val > 0;
 }
 
+static inline bool id_aa64pfr1_sme(u64 pfr1)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_SME_SHIFT);
+
+	return val > 0;
+}
+
 static inline bool id_aa64pfr1_mte(u64 pfr1)
 {
 	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT);
@@ -759,6 +766,23 @@ static __always_inline bool system_supports_sve(void)
 		cpus_have_const_cap(ARM64_SVE);
 }
 
+static __always_inline bool system_supports_sme(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME);
+}
+
+static __always_inline bool system_supports_fa64(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME_FA64);
+}
+
+static __always_inline bool system_supports_tpidr2(void)
+{
+	return system_supports_sme();
+}
+
 static __always_inline bool system_supports_cnp(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_CNP) &&
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index c31be7eda9df..fabdbde0fe02 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -143,6 +143,50 @@
 .Lskip_sve_\@:
 .endm
 
+/* SME register access and priority mapping */
+.macro __init_el2_nvhe_sme
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_SME_SHIFT, #4
+	cbz	x1, .Lskip_sme_\@
+
+	bic	x0, x0, #CPTR_EL2_TSM		// Also disable SME traps
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+	isb
+
+	mrs	x1, sctlr_el2
+	orr	x1, x1, #SCTLR_ELx_ENTP2	// Disable TPIDR2 traps
+	msr	sctlr_el2, x1
+	isb
+
+	mov	x1, #0				// SMCR controls
+
+	mrs_s	x2, SYS_ID_AA64SMFR0_EL1
+	ubfx	x2, x2, #ID_AA64SMFR0_FA64_SHIFT, #1 // Full FP in SM?
+	cbz	x2, .Lskip_sme_fa64_\@
+
+	orr	x1, x1, SMCR_ELx_FA64_MASK
+.Lskip_sme_fa64_\@:
+
+	orr	x1, x1, #SMCR_ELx_LEN_MASK	// Enable full SME vector
+	msr_s	SYS_SMCR_EL2, x1		// length for EL1.
+
+	mrs_s	x1, SYS_SMIDR_EL1		// Priority mapping supported?
+	ubfx    x1, x1, #SYS_SMIDR_EL1_SMPS_SHIFT, #1
+	cbz     x1, .Lskip_sme_\@
+
+	msr_s	SYS_SMPRIMAP_EL2, xzr		// Make all priorities equal
+
+	mrs	x1, id_aa64mmfr1_el1		// HCRX_EL2 present?
+	ubfx	x1, x1, #ID_AA64MMFR1_HCX_SHIFT, #4
+	cbz	x1, .Lskip_sme_\@
+
+	mrs_s	x1, SYS_HCRX_EL2
+	orr	x1, x1, #HCRX_EL2_SMPME_MASK	// Enable priority mapping
+	msr_s	SYS_HCRX_EL2, x1
+
+.Lskip_sme_\@:
+.endm
+
 /* Disable any fine grained traps */
 .macro __init_el2_fgt
 	mrs	x1, id_aa64mmfr0_el1
@@ -153,15 +197,26 @@
 	mrs	x1, id_aa64dfr0_el1
 	ubfx	x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
 	cmp	x1, #3
-	b.lt	.Lset_fgt_\@
+	b.lt	.Lset_debug_fgt_\@
 	/* Disable PMSNEVFR_EL1 read and write traps */
 	orr	x0, x0, #(1 << 62)
 
-.Lset_fgt_\@:
+.Lset_debug_fgt_\@:
 	msr_s	SYS_HDFGRTR_EL2, x0
 	msr_s	SYS_HDFGWTR_EL2, x0
-	msr_s	SYS_HFGRTR_EL2, xzr
-	msr_s	SYS_HFGWTR_EL2, xzr
+
+	mov	x0, xzr
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_SME_SHIFT, #4
+	cbz	x1, .Lset_fgt_\@
+
+	/* Disable nVHE traps of TPIDR2 and SMPRI */
+	orr	x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK
+	orr	x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK
+
+.Lset_fgt_\@:
+	msr_s	SYS_HFGRTR_EL2, x0
+	msr_s	SYS_HFGWTR_EL2, x0
 	msr_s	SYS_HFGITR_EL2, xzr
 
 	mrs	x1, id_aa64pfr0_el1		// AMU traps UNDEF without AMU
@@ -196,6 +251,7 @@
 	__init_el2_nvhe_idregs
 	__init_el2_nvhe_cptr
 	__init_el2_nvhe_sve
+	__init_el2_nvhe_sme
 	__init_el2_fgt
 	__init_el2_nvhe_prepare_eret
 .endm
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index d52a0b269ee8..0467837fd66b 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -37,7 +37,8 @@
 #define ESR_ELx_EC_ERET		(0x1a)	/* EL2 only */
 /* Unallocated EC: 0x1B */
 #define ESR_ELx_EC_FPAC		(0x1C)	/* EL1 and above */
-/* Unallocated EC: 0x1D - 0x1E */
+#define ESR_ELx_EC_SME		(0x1D)
+/* Unallocated EC: 0x1E */
 #define ESR_ELx_EC_IMP_DEF	(0x1f)	/* EL3 only */
 #define ESR_ELx_EC_IABT_LOW	(0x20)
 #define ESR_ELx_EC_IABT_CUR	(0x21)
@@ -75,6 +76,7 @@
 #define ESR_ELx_IL_SHIFT	(25)
 #define ESR_ELx_IL		(UL(1) << ESR_ELx_IL_SHIFT)
 #define ESR_ELx_ISS_MASK	(ESR_ELx_IL - 1)
+#define ESR_ELx_ISS(esr)	((esr) & ESR_ELx_ISS_MASK)
 
 /* ISS field definitions shared by different classes */
 #define ESR_ELx_WNR_SHIFT	(6)
@@ -327,6 +329,15 @@
 #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ	(ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\
 					 ESR_ELx_CP15_32_ISS_DIR_READ)
 
+/*
+ * ISS values for SME traps
+ */
+
+#define ESR_ELx_SME_ISS_SME_DISABLED	0
+#define ESR_ELx_SME_ISS_ILL		1
+#define ESR_ELx_SME_ISS_SM_DISABLED	2
+#define ESR_ELx_SME_ISS_ZA_DISABLED	3
+
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 339477dca551..2add7f33b7c2 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -64,6 +64,7 @@ void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 			struct pt_regs *regs);
 void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs);
 void do_sve_acc(unsigned int esr, struct pt_regs *regs);
+void do_sme_acc(unsigned int esr, struct pt_regs *regs);
 void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs);
 void do_sysinstr(unsigned int esr, struct pt_regs *regs);
 void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index cb24385e3632..75caa2098d5b 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -32,6 +32,18 @@
 #define VFP_STATE_SIZE		((32 * 8) + 4)
 #endif
 
+/*
+ * When we defined the maximum SVE vector length we defined the ABI so
+ * that the maximum vector length included all the reserved for future
+ * expansion bits in ZCR rather than those just currently defined by
+ * the architecture. While SME follows a similar pattern the fact that
+ * it includes a square matrix means that any allocations that attempt
+ * to cover the maximum potential vector length (such as happen with
+ * the regset used for ptrace) end up being extremely large. Define
+ * the much lower actual limit for use in such situations.
+ */
+#define SME_VQ_MAX	16
+
 struct task_struct;
 
 extern void fpsimd_save_state(struct user_fpsimd_state *state);
@@ -46,11 +58,23 @@ extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
-				     void *sve_state, unsigned int sve_vl);
+				     void *sve_state, unsigned int sve_vl,
+				     void *za_state, unsigned int sme_vl,
+				     u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK);
+}
+
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
 #define VL_ARCH_MAX 0x100
 
@@ -62,7 +86,14 @@ static inline size_t sve_ffr_offset(int vl)
 
 static inline void *sve_pffr(struct thread_struct *thread)
 {
-	return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread));
+	unsigned int vl;
+
+	if (system_supports_sme() && thread_sm_enabled(thread))
+		vl = thread_get_sme_vl(thread);
+	else
+		vl = thread_get_sve_vl(thread);
+
+	return (char *)thread->sve_state + sve_ffr_offset(vl);
 }
 
 extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
@@ -71,11 +102,17 @@ extern void sve_load_state(void const *state, u32 const *pfpsr,
 extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
 extern unsigned int sve_get_vl(void);
 extern void sve_set_vq(unsigned long vq_minus_1);
+extern void sme_set_vq(unsigned long vq_minus_1);
+extern void za_save_state(void *state);
+extern void za_load_state(void const *state);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 
 extern u64 read_zcr_features(void);
+extern u64 read_smcr_features(void);
 
 /*
  * Helpers to translate bit indices in sve_vq_map to VQ values (and
@@ -119,6 +156,7 @@ struct vl_info {
 extern void sve_alloc(struct task_struct *task);
 extern void fpsimd_release_task(struct task_struct *task);
 extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void fpsimd_force_sync_to_sve(struct task_struct *task);
 extern void sve_sync_to_fpsimd(struct task_struct *task);
 extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
 
@@ -171,6 +209,12 @@ static inline void write_vl(enum vec_type type, u64 val)
 		write_sysreg_s(tmp | val, SYS_ZCR_EL1);
 		break;
 #endif
+#ifdef CONFIG_ARM64_SME
+	case ARM64_VEC_SME:
+		tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK;
+		write_sysreg_s(tmp | val, SYS_SMCR_EL1);
+		break;
+#endif
 	default:
 		WARN_ON_ONCE(1);
 		break;
@@ -208,6 +252,8 @@ static inline bool sve_vq_available(unsigned int vq)
 	return vq_available(ARM64_VEC_SVE, vq);
 }
 
+size_t sve_state_size(struct task_struct const *task);
+
 #else /* ! CONFIG_ARM64_SVE */
 
 static inline void sve_alloc(struct task_struct *task) { }
@@ -247,8 +293,93 @@ static inline void vec_update_vq_map(enum vec_type t) { }
 static inline int vec_verify_vq_map(enum vec_type t) { return 0; }
 static inline void sve_setup(void) { }
 
+static inline size_t sve_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
 #endif /* ! CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static inline void sme_user_disable(void)
+{
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0);
+}
+
+static inline void sme_user_enable(void)
+{
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN);
+}
+
+static inline void sme_smstart_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr"));
+}
+
+extern void __init sme_setup(void);
+
+static inline int sme_max_vl(void)
+{
+	return vec_max_vl(ARM64_VEC_SME);
+}
+
+static inline int sme_max_virtualisable_vl(void)
+{
+	return vec_max_virtualisable_vl(ARM64_VEC_SME);
+}
+
+extern void sme_alloc(struct task_struct *task);
+extern unsigned int sme_get_vl(void);
+extern int sme_set_current_vl(unsigned long arg);
+extern int sme_get_current_vl(void);
+
+/*
+ * Return how many bytes of memory are required to store the full SME
+ * specific state (currently just ZA) for task, given task's currently
+ * configured vector length.
+ */
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	unsigned int vl = task_get_sme_vl(task);
+
+	return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+}
+
+#else
+
+static inline void sme_user_disable(void) { BUILD_BUG(); }
+static inline void sme_user_enable(void) { BUILD_BUG(); }
+
+static inline void sme_smstart_sm(void) { }
+static inline void sme_smstop_sm(void) { }
+static inline void sme_smstop(void) { }
+
+static inline void sme_alloc(struct task_struct *task) { }
+static inline void sme_setup(void) { }
+static inline unsigned int sme_get_vl(void) { return 0; }
+static inline int sme_max_vl(void) { return 0; }
+static inline int sme_max_virtualisable_vl(void) { return 0; }
+static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
+static inline int sme_get_current_vl(void) { return -EINVAL; }
+
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
+#endif /* ! CONFIG_ARM64_SME */
+
 /* For use by EFI runtime services calls only */
 extern void __efi_fpsimd_begin(void);
 extern void __efi_fpsimd_end(void);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 2509d7dde55a..5e0910cf4832 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -93,6 +93,12 @@
 	.endif
 .endm
 
+.macro _sme_check_wv v
+	.if (\v) < 12 || (\v) > 15
+		.error "Bad vector select register \v."
+	.endif
+.endm
+
 /* SVE instruction encodings for non-SVE-capable assemblers */
 /* (pre binutils 2.28, all kernel capable clang versions support SVE) */
 
@@ -174,6 +180,54 @@
 		| (\np)
 .endm
 
+/* SME instruction encodings for non-SME-capable assemblers */
+/* (pre binutils 2.38/LLVM 13) */
+
+/* RDSVL X\nx, #\imm */
+.macro _sme_rdsvl nx, imm
+	_check_general_reg \nx
+	_check_num (\imm), -0x20, 0x1f
+	.inst	0x04bf5800			\
+		| (\nx)				\
+		| (((\imm) & 0x3f) << 5)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ *	STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _sme_str_zav nw, nxbase, offset=0
+	_sme_check_wv \nw
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe1200000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * LDR (vector to ZA array):
+ *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _sme_ldr_zav nw, nxbase, offset=0
+	_sme_check_wv \nw
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe1000000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * Zero the entire ZA array
+ *	ZERO ZA
+ */
+.macro zero_za
+	.inst 0xc00800ff
+.endm
+
 .macro __for from:req, to:req
 	.if (\from) == (\to)
 		_for__body %\from
@@ -208,6 +262,17 @@
 921:
 .endm
 
+/* Update SMCR_EL1.LEN with the new VQ */
+.macro sme_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_SMCR_EL1
+		bic		\xtmp2, \xtmp, SMCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_SMCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
 /* Preserve the first 128-bits of Znz and zero the rest. */
 .macro _sve_flush_z nz
 	_sve_check_zreg \nz
@@ -254,3 +319,25 @@
 		ldr		w\nxtmp, [\xpfpsr, #4]
 		msr		fpcr, x\nxtmp
 .endm
+
+.macro sme_save_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_str_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
+
+.macro sme_load_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_ldr_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 8db5ec0089db..9f0ce004fdbc 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -109,6 +109,14 @@
 #define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
 #define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)
 #define KERNEL_HWCAP_MTE3		__khwcap2_feature(MTE3)
+#define KERNEL_HWCAP_SME		__khwcap2_feature(SME)
+#define KERNEL_HWCAP_SME_I16I64		__khwcap2_feature(SME_I16I64)
+#define KERNEL_HWCAP_SME_F64F64		__khwcap2_feature(SME_F64F64)
+#define KERNEL_HWCAP_SME_I8I32		__khwcap2_feature(SME_I8I32)
+#define KERNEL_HWCAP_SME_F16F32		__khwcap2_feature(SME_F16F32)
+#define KERNEL_HWCAP_SME_B16F32		__khwcap2_feature(SME_B16F32)
+#define KERNEL_HWCAP_SME_F32F32		__khwcap2_feature(SME_F32F32)
+#define KERNEL_HWCAP_SME_FA64		__khwcap2_feature(SME_FA64)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 1767ded83888..13ae232ec4a1 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -279,6 +279,7 @@
 #define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
+#define CPTR_EL2_TSM	(1 << 12)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
 #define CPTR_NVHE_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 94a27a7520f4..f8f0d30dd1a2 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -295,8 +295,11 @@ struct vcpu_reset_state {
 
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
+
+	/* Guest floating point state */
 	void *sve_state;
 	unsigned int sve_max_vl;
+	u64 svcr;
 
 	/* Stage 2 paging state used by the hardware on next switch */
 	struct kvm_s2_mmu *hw_mmu;
@@ -451,6 +454,7 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE	(1 << 13) /* Save TRBE context if active  */
 #define KVM_ARM64_FP_FOREIGN_FPSTATE	(1 << 14)
 #define KVM_ARM64_ON_UNSUPPORTED_CPU	(1 << 15) /* Physical CPU not in supported_cpus */
+#define KVM_ARM64_HOST_SME_ENABLED	(1 << 16) /* SME enabled for EL0 */
 
 #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
 				 KVM_GUESTDBG_USE_SW_BP | \
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 73e38d9a540c..1d2ca4870b84 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -118,6 +118,7 @@ struct debug_info {
 
 enum vec_type {
 	ARM64_VEC_SVE = 0,
+	ARM64_VEC_SME,
 	ARM64_VEC_MAX,
 };
 
@@ -153,6 +154,7 @@ struct thread_struct {
 
 	unsigned int		fpsimd_cpu;
 	void			*sve_state;	/* SVE registers, if any */
+	void			*za_state;	/* ZA register, if any */
 	unsigned int		vl[ARM64_VEC_MAX];	/* vector length */
 	unsigned int		vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */
 	unsigned long		fault_address;	/* fault info */
@@ -168,6 +170,8 @@ struct thread_struct {
 	u64			mte_ctrl;
 #endif
 	u64			sctlr_user;
+	u64			svcr;
+	u64			tpidr2_el0;
 };
 
 static inline unsigned int thread_get_vl(struct thread_struct *thread,
@@ -181,6 +185,19 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread)
 	return thread_get_vl(thread, ARM64_VEC_SVE);
 }
 
+static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
+{
+	return thread_get_vl(thread, ARM64_VEC_SME);
+}
+
+static inline unsigned int thread_get_cur_vl(struct thread_struct *thread)
+{
+	if (system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK))
+		return thread_get_sme_vl(thread);
+	else
+		return thread_get_sve_vl(thread);
+}
+
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type);
 void task_set_vl(struct task_struct *task, enum vec_type type,
 		 unsigned long vl);
@@ -194,6 +211,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task)
 	return task_get_vl(task, ARM64_VEC_SVE);
 }
 
+static inline unsigned int task_get_sme_vl(const struct task_struct *task)
+{
+	return task_get_vl(task, ARM64_VEC_SME);
+}
+
 static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl)
 {
 	task_set_vl(task, ARM64_VEC_SVE, vl);
@@ -354,9 +376,11 @@ extern void __init minsigstksz_setup(void);
  */
 #include <asm/fpsimd.h>
 
-/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
+/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */
 #define SVE_SET_VL(arg)	sve_set_current_vl(arg)
 #define SVE_GET_VL()	sve_get_current_vl()
+#define SME_SET_VL(arg)	sme_set_current_vl(arg)
+#define SME_GET_VL()	sme_get_current_vl()
 
 /* PR_PAC_RESET_KEYS prctl */
 #define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index a6b8b0deadfb..422741ca5631 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -126,6 +126,10 @@
  * System registers, organised loosely by encoding but grouped together
  * where the architected name contains an index. e.g. ID_MMFR<n>_EL1.
  */
+#define SYS_SVCR_SMSTOP_SM_EL0		sys_reg(0, 3, 4, 2, 3)
+#define SYS_SVCR_SMSTART_SM_EL0		sys_reg(0, 3, 4, 3, 3)
+#define SYS_SVCR_SMSTOP_SMZA_EL0	sys_reg(0, 3, 4, 6, 3)
+
 #define SYS_OSDTRRX_EL1			sys_reg(2, 0, 0, 0, 2)
 #define SYS_MDCCINT_EL1			sys_reg(2, 0, 0, 2, 0)
 #define SYS_MDSCR_EL1			sys_reg(2, 0, 0, 2, 2)
@@ -189,6 +193,7 @@
 #define SYS_ID_AA64PFR0_EL1		sys_reg(3, 0, 0, 4, 0)
 #define SYS_ID_AA64PFR1_EL1		sys_reg(3, 0, 0, 4, 1)
 #define SYS_ID_AA64ZFR0_EL1		sys_reg(3, 0, 0, 4, 4)
+#define SYS_ID_AA64SMFR0_EL1		sys_reg(3, 0, 0, 4, 5)
 
 #define SYS_ID_AA64DFR0_EL1		sys_reg(3, 0, 0, 5, 0)
 #define SYS_ID_AA64DFR1_EL1		sys_reg(3, 0, 0, 5, 1)
@@ -210,6 +215,8 @@
 
 #define SYS_ZCR_EL1			sys_reg(3, 0, 1, 2, 0)
 #define SYS_TRFCR_EL1			sys_reg(3, 0, 1, 2, 1)
+#define SYS_SMPRI_EL1			sys_reg(3, 0, 1, 2, 4)
+#define SYS_SMCR_EL1			sys_reg(3, 0, 1, 2, 6)
 
 #define SYS_TCR_EL1			sys_reg(3, 0, 2, 0, 2)
 
@@ -400,6 +407,8 @@
 #define TRBIDR_ALIGN_MASK		GENMASK(3, 0)
 #define TRBIDR_ALIGN_SHIFT		0
 
+#define SMPRI_EL1_PRIORITY_MASK		0xf
+
 #define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
 #define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
 
@@ -455,8 +464,13 @@
 #define SYS_CCSIDR_EL1			sys_reg(3, 1, 0, 0, 0)
 #define SYS_CLIDR_EL1			sys_reg(3, 1, 0, 0, 1)
 #define SYS_GMID_EL1			sys_reg(3, 1, 0, 0, 4)
+#define SYS_SMIDR_EL1			sys_reg(3, 1, 0, 0, 6)
 #define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
 
+#define SYS_SMIDR_EL1_IMPLEMENTER_SHIFT	24
+#define SYS_SMIDR_EL1_SMPS_SHIFT	15
+#define SYS_SMIDR_EL1_AFFINITY_SHIFT	0
+
 #define SYS_CSSELR_EL1			sys_reg(3, 2, 0, 0, 0)
 
 #define SYS_CTR_EL0			sys_reg(3, 3, 0, 0, 1)
@@ -465,6 +479,10 @@
 #define SYS_RNDR_EL0			sys_reg(3, 3, 2, 4, 0)
 #define SYS_RNDRRS_EL0			sys_reg(3, 3, 2, 4, 1)
 
+#define SYS_SVCR_EL0			sys_reg(3, 3, 4, 2, 2)
+#define SYS_SVCR_EL0_ZA_MASK		2
+#define SYS_SVCR_EL0_SM_MASK		1
+
 #define SYS_PMCR_EL0			sys_reg(3, 3, 9, 12, 0)
 #define SYS_PMCNTENSET_EL0		sys_reg(3, 3, 9, 12, 1)
 #define SYS_PMCNTENCLR_EL0		sys_reg(3, 3, 9, 12, 2)
@@ -481,6 +499,7 @@
 
 #define SYS_TPIDR_EL0			sys_reg(3, 3, 13, 0, 2)
 #define SYS_TPIDRRO_EL0			sys_reg(3, 3, 13, 0, 3)
+#define SYS_TPIDR2_EL0			sys_reg(3, 3, 13, 0, 5)
 
 #define SYS_SCXTNUM_EL0			sys_reg(3, 3, 13, 0, 7)
 
@@ -550,6 +569,9 @@
 #define SYS_HFGITR_EL2			sys_reg(3, 4, 1, 1, 6)
 #define SYS_ZCR_EL2			sys_reg(3, 4, 1, 2, 0)
 #define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
+#define SYS_HCRX_EL2			sys_reg(3, 4, 1, 2, 2)
+#define SYS_SMPRIMAP_EL2		sys_reg(3, 4, 1, 2, 5)
+#define SYS_SMCR_EL2			sys_reg(3, 4, 1, 2, 6)
 #define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
 #define SYS_HDFGRTR_EL2			sys_reg(3, 4, 3, 1, 4)
 #define SYS_HDFGWTR_EL2			sys_reg(3, 4, 3, 1, 5)
@@ -609,6 +631,7 @@
 #define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
 #define SYS_CPACR_EL12			sys_reg(3, 5, 1, 0, 2)
 #define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
+#define SYS_SMCR_EL12			sys_reg(3, 5, 1, 2, 6)
 #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
 #define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
 #define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
@@ -632,6 +655,7 @@
 #define SYS_CNTV_CVAL_EL02		sys_reg(3, 5, 14, 3, 2)
 
 /* Common SCTLR_ELx flags. */
+#define SCTLR_ELx_ENTP2	(BIT(60))
 #define SCTLR_ELx_DSSBS	(BIT(44))
 #define SCTLR_ELx_ATA	(BIT(43))
 
@@ -795,6 +819,7 @@
 #define ID_AA64PFR0_ELx_32BIT_64BIT	0x2
 
 /* id_aa64pfr1 */
+#define ID_AA64PFR1_SME_SHIFT		24
 #define ID_AA64PFR1_MPAMFRAC_SHIFT	16
 #define ID_AA64PFR1_RASFRAC_SHIFT	12
 #define ID_AA64PFR1_MTE_SHIFT		8
@@ -805,6 +830,7 @@
 #define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 #define ID_AA64PFR1_BT_BTI		0x1
+#define ID_AA64PFR1_SME			1
 
 #define ID_AA64PFR1_MTE_NI		0x0
 #define ID_AA64PFR1_MTE_EL0		0x1
@@ -833,6 +859,23 @@
 #define ID_AA64ZFR0_AES_PMULL		0x2
 #define ID_AA64ZFR0_SVEVER_SVE2		0x1
 
+/* id_aa64smfr0 */
+#define ID_AA64SMFR0_FA64_SHIFT		63
+#define ID_AA64SMFR0_I16I64_SHIFT	52
+#define ID_AA64SMFR0_F64F64_SHIFT	48
+#define ID_AA64SMFR0_I8I32_SHIFT	36
+#define ID_AA64SMFR0_F16F32_SHIFT	35
+#define ID_AA64SMFR0_B16F32_SHIFT	34
+#define ID_AA64SMFR0_F32F32_SHIFT	32
+
+#define ID_AA64SMFR0_FA64		0x1
+#define ID_AA64SMFR0_I16I64		0x4
+#define ID_AA64SMFR0_F64F64		0x1
+#define ID_AA64SMFR0_I8I32		0x4
+#define ID_AA64SMFR0_F16F32		0x1
+#define ID_AA64SMFR0_B16F32		0x1
+#define ID_AA64SMFR0_F32F32		0x1
+
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_ECV_SHIFT		60
 #define ID_AA64MMFR0_FGT_SHIFT		56
@@ -885,6 +928,7 @@
 
 /* id_aa64mmfr1 */
 #define ID_AA64MMFR1_ECBHB_SHIFT	60
+#define ID_AA64MMFR1_HCX_SHIFT		40
 #define ID_AA64MMFR1_AFP_SHIFT		44
 #define ID_AA64MMFR1_ETS_SHIFT		36
 #define ID_AA64MMFR1_TWED_SHIFT		32
@@ -1078,9 +1122,24 @@
 #define ZCR_ELx_LEN_SIZE	9
 #define ZCR_ELx_LEN_MASK	0x1ff
 
+#define SMCR_ELx_FA64_SHIFT	31
+#define SMCR_ELx_FA64_MASK	(1 << SMCR_ELx_FA64_SHIFT)
+
+/*
+ * The SMCR_ELx_LEN_* definitions intentionally include bits [8:4] which
+ * are reserved by the SME architecture for future expansion of the LEN
+ * field, with compatible semantics.
+ */
+#define SMCR_ELx_LEN_SHIFT	0
+#define SMCR_ELx_LEN_SIZE	9
+#define SMCR_ELx_LEN_MASK	0x1ff
+
 #define CPACR_EL1_FPEN_EL1EN	(BIT(20)) /* enable EL1 access */
 #define CPACR_EL1_FPEN_EL0EN	(BIT(21)) /* enable EL0 access, if EL1EN set */
 
+#define CPACR_EL1_SMEN_EL1EN	(BIT(24)) /* enable EL1 access */
+#define CPACR_EL1_SMEN_EL0EN	(BIT(25)) /* enable EL0 access, if EL1EN set */
+
 #define CPACR_EL1_ZEN_EL1EN	(BIT(16)) /* enable EL1 access */
 #define CPACR_EL1_ZEN_EL0EN	(BIT(17)) /* enable EL0 access, if EL1EN set */
 
@@ -1129,6 +1188,8 @@
 #define TRFCR_ELx_ExTRE			BIT(1)
 #define TRFCR_ELx_E0TRE			BIT(0)
 
+/* HCRX_EL2 definitions */
+#define HCRX_EL2_SMPME_MASK		(1 << 5)
 
 /* GIC Hypervisor interface registers */
 /* ICH_MISR_EL2 bit definitions */
@@ -1192,6 +1253,12 @@
 #define ICH_VTR_TDS_SHIFT	19
 #define ICH_VTR_TDS_MASK	(1 << ICH_VTR_TDS_SHIFT)
 
+/* HFG[WR]TR_EL2 bit definitions */
+#define HFGxTR_EL2_nTPIDR2_EL0_SHIFT	55
+#define HFGxTR_EL2_nTPIDR2_EL0_MASK	BIT_MASK(HFGxTR_EL2_nTPIDR2_EL0_SHIFT)
+#define HFGxTR_EL2_nSMPRI_EL1_SHIFT	54
+#define HFGxTR_EL2_nSMPRI_EL1_MASK	BIT_MASK(HFGxTR_EL2_nSMPRI_EL1_SHIFT)
+
 #define ARM64_FEATURE_FIELD_BITS	4
 
 /* Create a mask for the feature bits of the specified feature. */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index e1317b7c4525..848739c15de8 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -82,6 +82,8 @@ int arch_dup_task_struct(struct task_struct *dst,
 #define TIF_SVE_VL_INHERIT	24	/* Inherit SVE vl_onexec across exec */
 #define TIF_SSBD		25	/* Wants SSB mitigation */
 #define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
+#define TIF_SME			27	/* SME in use */
+#define TIF_SME_VL_INHERIT	28	/* Inherit SME vl_onexec across exec */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 99cb5d383048..b0256cec63b5 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -79,5 +79,13 @@
 #define HWCAP2_AFP		(1 << 20)
 #define HWCAP2_RPRES		(1 << 21)
 #define HWCAP2_MTE3		(1 << 22)
+#define HWCAP2_SME		(1 << 23)
+#define HWCAP2_SME_I16I64	(1 << 24)
+#define HWCAP2_SME_F64F64	(1 << 25)
+#define HWCAP2_SME_I8I32	(1 << 26)
+#define HWCAP2_SME_F16F32	(1 << 27)
+#define HWCAP2_SME_B16F32	(1 << 28)
+#define HWCAP2_SME_F32F32	(1 << 29)
+#define HWCAP2_SME_FA64		(1 << 30)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 758ae984ff97..7fa2f7036aa7 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -109,7 +109,7 @@ struct user_hwdebug_state {
 	}		dbg_regs[16];
 };
 
-/* SVE/FP/SIMD state (NT_ARM_SVE) */
+/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */
 
 struct user_sve_header {
 	__u32 size; /* total meaningful regset content in bytes */
@@ -220,6 +220,7 @@ struct user_sve_header {
 	(SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \
 		SVE_PT_SVE_PREGS_OFFSET(vq))
 
+/* For streaming mode SVE (SSVE) FFR must be read and written as zero */
 #define SVE_PT_SVE_FFR_OFFSET(vq) \
 	(SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq))
 
@@ -240,10 +241,12 @@ struct user_sve_header {
 			- SVE_PT_SVE_OFFSET + (__SVE_VQ_BYTES - 1))	\
 		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
 
-#define SVE_PT_SIZE(vq, flags)						\
-	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		\
-		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	\
-		: SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags))
+#define SVE_PT_SIZE(vq, flags)						  \
+	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		  \
+		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	  \
+		: ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ?  \
+		    SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \
+		  : SVE_PT_REGS_OFFSET)))
 
 /* pointer authentication masks (NT_ARM_PAC_MASK) */
 
@@ -265,6 +268,62 @@ struct user_pac_generic_keys {
 	__uint128_t	apgakey;
 };
 
+/* ZA state (NT_ARM_ZA) */
+
+struct user_za_header {
+	__u32 size; /* total meaningful regset content in bytes */
+	__u32 max_size; /* maxmium possible size for this thread */
+	__u16 vl; /* current vector length */
+	__u16 max_vl; /* maximum possible vector length */
+	__u16 flags;
+	__u16 __reserved;
+};
+
+/*
+ * Common ZA_PT_* flags:
+ * These must be kept in sync with prctl interface in <linux/prctl.h>
+ */
+#define ZA_PT_VL_INHERIT		((1 << 17) /* PR_SME_VL_INHERIT */ >> 16)
+#define ZA_PT_VL_ONEXEC			((1 << 18) /* PR_SME_SET_VL_ONEXEC */ >> 16)
+
+
+/*
+ * The remainder of the ZA state follows struct user_za_header.  The
+ * total size of the ZA state (including header) depends on the
+ * metadata in the header:  ZA_PT_SIZE(vq, flags) gives the total size
+ * of the state in bytes, including the header.
+ *
+ * Refer to <asm/sigcontext.h> for details of how to pass the correct
+ * "vq" argument to these macros.
+ */
+
+/* Offset from the start of struct user_za_header to the register data */
+#define ZA_PT_ZA_OFFSET						\
+	((sizeof(struct user_za_header) + (__SVE_VQ_BYTES - 1))	\
+		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
+
+/*
+ * The payload starts at offset ZA_PT_ZA_OFFSET, and is of size
+ * ZA_PT_ZA_SIZE(vq, flags).
+ *
+ * The ZA array is stored as a sequence of horizontal vectors ZAV of SVL/8
+ * bytes each, starting from vector 0.
+ *
+ * Additional data might be appended in the future.
+ *
+ * The ZA matrix is represented in memory in an endianness-invariant layout
+ * which differs from the layout used for the FPSIMD V-registers on big-endian
+ * systems: see sigcontext.h for more explanation.
+ */
+
+#define ZA_PT_ZAV_OFFSET(vq, n) \
+	(ZA_PT_ZA_OFFSET + ((vq * __SVE_VQ_BYTES) * n))
+
+#define ZA_PT_ZA_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES))
+
+#define ZA_PT_SIZE(vq)						\
+	(ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq))
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI__ASM_PTRACE_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index 0c796c795dbe..4aaf31e3bf16 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -134,6 +134,17 @@ struct extra_context {
 struct sve_context {
 	struct _aarch64_ctx head;
 	__u16 vl;
+	__u16 flags;
+	__u16 __reserved[2];
+};
+
+#define SVE_SIG_FLAG_SM	0x1	/* Context describes streaming mode */
+
+#define ZA_MAGIC	0x54366345
+
+struct za_context {
+	struct _aarch64_ctx head;
+	__u16 vl;
 	__u16 __reserved[3];
 };
 
@@ -186,9 +197,16 @@ struct sve_context {
  * sve_context.vl must equal the thread's current vector length when
  * doing a sigreturn.
  *
+ * On systems with support for SME the SVE register state may reflect either
+ * streaming or non-streaming mode.  In streaming mode the streaming mode
+ * vector length will be used and the flag SVE_SIG_FLAG_SM will be set in
+ * the flags field. It is permitted to enter or leave streaming mode in
+ * a signal return, applications should take care to ensure that any difference
+ * in vector length between the two modes is handled, including any resizing
+ * and movement of context blocks.
  *
- * Note: for all these macros, the "vq" argument denotes the SVE
- * vector length in quadwords (i.e., units of 128 bits).
+ * Note: for all these macros, the "vq" argument denotes the vector length
+ * in quadwords (i.e., units of 128 bits).
  *
  * The correct way to obtain vq is to use sve_vq_from_vl(vl).  The
  * result is valid if and only if sve_vl_valid(vl) is true.  This is
@@ -249,4 +267,37 @@ struct sve_context {
 #define SVE_SIG_CONTEXT_SIZE(vq) \
 		(SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq))
 
+/*
+ * If the ZA register is enabled for the thread at signal delivery then,
+ * za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl))
+ * and the register data may be accessed using the ZA_SIG_*() macros.
+ *
+ * If za_context.head.size < ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl))
+ * then ZA was not enabled and no register data was included in which case
+ * ZA register was not enabled for the thread and no register data
+ * the ZA_SIG_*() macros should not be used except for this check.
+ *
+ * The same convention applies when returning from a signal: a caller
+ * will need to remove or resize the za_context block if it wants to
+ * enable the ZA register when it was previously non-live or vice-versa.
+ * This may require the caller to allocate fresh memory and/or move other
+ * context blocks in the signal frame.
+ *
+ * Changing the vector length during signal return is not permitted:
+ * za_context.vl must equal the thread's current SME vector length when
+ * doing a sigreturn.
+ */
+
+#define ZA_SIG_REGS_OFFSET					\
+	((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1))	\
+		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
+
+#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES))
+
+#define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \
+				  (SVE_SIG_ZREG_SIZE(vq) * n))
+
+#define ZA_SIG_CONTEXT_SIZE(vq) \
+		(ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq))
+
 #endif /* _UAPI__ASM_SIGCONTEXT_H */