Merge remote-tracking branch 'arm64/for-next/sme' into kvmarm-master/next

Merge arm64's SME branch to resolve conflicts with the WFxT branch.
Signed-off-by: Marc Zyngier <maz@kernel.org>

Documentation/arm64/elf_hwcaps.rst

@@ -264,6 +264,39 @@ HWCAP2_MTE3
     Functionality implied by ID_AA64PFR1_EL1.MTE == 0b0011, as described
     by Documentation/arm64/memory-tagging-extension.rst.
 
+HWCAP2_SME
+
+    Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described
+    by Documentation/arm64/sme.rst.
+
+HWCAP2_SME_I16I64
+
+    Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111.
+
+HWCAP2_SME_F64F64
+
+    Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1.
+
+HWCAP2_SME_I8I32
+
+    Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111.
+
+HWCAP2_SME_F16F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1.
+
+HWCAP2_SME_B16F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1.
+
+HWCAP2_SME_F32F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1.
+
+HWCAP2_SME_FA64
+
+    Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1.
+
 4. Unused AT_HWCAP bits
 -----------------------
 

Documentation/arm64/index.rst

@@ -21,6 +21,7 @@ ARM64 Architecture
     perf
     pointer-authentication
     silicon-errata
+    sme
     sve
     tagged-address-abi
     tagged-pointers

Documentation/arm64/sve.rst

@@ -7,7 +7,9 @@ Author: Dave Martin <Dave.Martin@arm.com>
 Date:   4 August 2017
 
 This document outlines briefly the interface provided to userspace by Linux in
-order to support use of the ARM Scalable Vector Extension (SVE).
+order to support use of the ARM Scalable Vector Extension (SVE), including
+interactions with Streaming SVE mode added by the Scalable Matrix Extension
+(SME).
 
 This is an outline of the most important features and issues only and not
 intended to be exhaustive.
@@ -23,6 +25,10 @@ model features for SVE is included in Appendix A.
 * SVE registers Z0..Z31, P0..P15 and FFR and the current vector length VL, are
   tracked per-thread.
 
+* In streaming mode FFR is not accessible unless HWCAP2_SME_FA64 is present
+  in the system, when it is not supported and these interfaces are used to
+  access streaming mode FFR is read and written as zero.
+
 * The presence of SVE is reported to userspace via HWCAP_SVE in the aux vector
   AT_HWCAP entry.  Presence of this flag implies the presence of the SVE
   instructions and registers, and the Linux-specific system interfaces
@@ -53,10 +59,19 @@ model features for SVE is included in Appendix A.
   which userspace can read using an MRS instruction.  See elf_hwcaps.txt and
   cpu-feature-registers.txt for details.
 
+* On hardware that supports the SME extensions, HWCAP2_SME will also be
+  reported in the AT_HWCAP2 aux vector entry.  Among other things SME adds
+  streaming mode which provides a subset of the SVE feature set using a
+  separate SME vector length and the same Z/V registers.  See sme.rst
+  for more details.
+
 * Debuggers should restrict themselves to interacting with the target via the
   NT_ARM_SVE regset.  The recommended way of detecting support for this regset
   is to connect to a target process first and then attempt a
-  ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov).
+  ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov).  Note that when SME is
+  present and streaming SVE mode is in use the FPSIMD subset of registers
+  will be read via NT_ARM_SVE and NT_ARM_SVE writes will exit streaming mode
+  in the target.
 
 * Whenever SVE scalable register values (Zn, Pn, FFR) are exchanged in memory
   between userspace and the kernel, the register value is encoded in memory in
@@ -126,6 +141,11 @@ the SVE instruction set architecture.
   are only present in fpsimd_context.  For convenience, the content of V0..V31
   is duplicated between sve_context and fpsimd_context.
 
+* The record contains a flag field which includes a flag SVE_SIG_FLAG_SM which
+  if set indicates that the thread is in streaming mode and the vector length
+  and register data (if present) describe the streaming SVE data and vector
+  length.
+
 * The signal frame record for SVE always contains basic metadata, in particular
   the thread's vector length (in sve_context.vl).
 
@@ -170,6 +190,11 @@ When returning from a signal handler:
   the signal frame does not match the current vector length, the signal return
   attempt is treated as illegal, resulting in a forced SIGSEGV.
 
+* It is permitted to enter or leave streaming mode by setting or clearing
+  the SVE_SIG_FLAG_SM flag but applications should take care to ensure that
+  when doing so sve_context.vl and any register data are appropriate for the
+  vector length in the new mode.
+
 
 6.  prctl extensions
 --------------------
@@ -265,8 +290,14 @@ prctl(PR_SVE_GET_VL)
 7.  ptrace extensions
 ---------------------
 
-* A new regset NT_ARM_SVE is defined for use with PTRACE_GETREGSET and
-  PTRACE_SETREGSET.
+* New regsets NT_ARM_SVE and NT_ARM_SSVE are defined for use with
+  PTRACE_GETREGSET and PTRACE_SETREGSET. NT_ARM_SSVE describes the
+  streaming mode SVE registers and NT_ARM_SVE describes the
+  non-streaming mode SVE registers.
+
+  In this description a register set is referred to as being "live" when
+  the target is in the appropriate streaming or non-streaming mode and is
+  using data beyond the subset shared with the FPSIMD Vn registers.
 
   Refer to [2] for definitions.
 
@@ -297,7 +328,7 @@ The regset data starts with struct user_sve_header, containing:
 
     flags
 
-	either
+	at most one of
 
 	    SVE_PT_REGS_FPSIMD
 
@@ -331,6 +362,10 @@ The regset data starts with struct user_sve_header, containing:
 
 	    SVE_PT_VL_ONEXEC (SETREGSET only).
 
+	If neither FPSIMD nor SVE flags are provided then no register
+	payload is available, this is only possible when SME is implemented.
+
+
 * The effects of changing the vector length and/or flags are equivalent to
   those documented for PR_SVE_SET_VL.
 
@@ -346,6 +381,13 @@ The regset data starts with struct user_sve_header, containing:
   case only the vector length and flags are changed (along with any
   consequences of those changes).
 
+* In systems supporting SME when in streaming mode a GETREGSET for
+  NT_REG_SVE will return only the user_sve_header with no register data,
+  similarly a GETREGSET for NT_REG_SSVE will not return any register data
+  when not in streaming mode.
+
+* A GETREGSET for NT_ARM_SSVE will never return SVE_PT_REGS_FPSIMD.
+
 * For SETREGSET, if an SVE_PT_REGS_SVE payload is present and the
   requested VL is not supported, the effect will be the same as if the
   payload were omitted, except that an EIO error is reported.  No
@@ -355,17 +397,25 @@ The regset data starts with struct user_sve_header, containing:
   unspecified.  It is up to the caller to translate the payload layout
   for the actual VL and retry.
 
+* Where SME is implemented it is not possible to GETREGSET the register
+  state for normal SVE when in streaming mode, nor the streaming mode
+  register state when in normal mode, regardless of the implementation defined
+  behaviour of the hardware for sharing data between the two modes.
+
+* Any SETREGSET of NT_ARM_SVE will exit streaming mode if the target was in
+  streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode
+  if the target was not in streaming mode.
+
 * The effect of writing a partial, incomplete payload is unspecified.
 
 
 8.  ELF coredump extensions
 ---------------------------
 
-* A NT_ARM_SVE note will be added to each coredump for each thread of the
-  dumped process.  The contents will be equivalent to the data that would have
-  been read if a PTRACE_GETREGSET of NT_ARM_SVE were executed for each thread
-  when the coredump was generated.
-
+* NT_ARM_SVE and NT_ARM_SSVE notes will be added to each coredump for
+  each thread of the dumped process.  The contents will be equivalent to the
+  data that would have been read if a PTRACE_GETREGSET of the corresponding
+  type were executed for each thread when the coredump was generated.
 
 9.  System runtime configuration
 --------------------------------

arch/arm64/Kconfig

@@ -1948,6 +1948,17 @@ config ARM64_SVE
 	  booting the kernel.  If unsure and you are not observing these
 	  symptoms, you should assume that it is safe to say Y.
 
+config ARM64_SME
+	bool "ARM Scalable Matrix Extension support"
+	default y
+	depends on ARM64_SVE
+	help
+	  The Scalable Matrix Extension (SME) is an extension to the AArch64
+	  execution state which utilises a substantial subset of the SVE
+	  instruction set, together with the addition of new architectural
+	  register state capable of holding two dimensional matrix tiles to
+	  enable various matrix operations.
+
 config ARM64_MODULE_PLTS
 	bool "Use PLTs to allow module memory to spill over into vmalloc area"
 	depends on MODULES

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);

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) &&

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

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>
 

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);

arch/arm64/include/asm/fpsimd.h

@@ -46,11 +46,23 @@ 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 +74,14 @@ 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 +90,17 @@ 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 +144,7 @@ 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);
 
@@ -170,6 +196,12 @@ static inline void write_vl(enum vec_type type, u64 val)
 		tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK;
 		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);
@@ -208,6 +240,8 @@ 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 +281,93 @@ 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);

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

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

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) */

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 | \

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)

arch/arm64/include/asm/sysreg.h

@@ -118,6 +118,10 @@
  * 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)
@@ -181,6 +185,7 @@
 #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)
@@ -204,6 +209,8 @@
 
 #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_TTBR0_EL1			sys_reg(3, 0, 2, 0, 0)
 #define SYS_TTBR1_EL1			sys_reg(3, 0, 2, 0, 1)
@@ -396,6 +403,8 @@
 #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)
 
@@ -451,8 +460,13 @@
 #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)
@@ -461,6 +475,10 @@
 #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)
@@ -477,6 +495,7 @@
 
 #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)
 
@@ -546,6 +565,9 @@
 #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)
@@ -605,6 +627,7 @@
 #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)
@@ -628,6 +651,7 @@
 #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))
 
@@ -836,6 +860,7 @@
 #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
@@ -846,6 +871,7 @@
 #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
@@ -874,6 +900,23 @@
 #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
@@ -926,6 +969,7 @@
 
 /* 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
@@ -1119,9 +1163,24 @@
 #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 */
 
@@ -1170,6 +1229,8 @@
 #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 */
@@ -1233,6 +1294,12 @@
 #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. */

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)

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 */

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))
 
@@ -243,7 +244,9 @@ struct user_sve_header {
 #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))
+		: ((((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 */

arch/arm64/include/uapi/asm/sigcontext.h

@@ -132,6 +132,17 @@ struct extra_context {
 #define SVE_MAGIC	0x53564501
 
 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 */

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 */

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);
 }
 

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;

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 */

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);
 }
 
 /*

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;
 	}
 
@@ -301,6 +320,9 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	if (err)
 		return -EFAULT;
 
+	if (sve.flags & SVE_SIG_FLAG_SM)
+		current->thread.svcr |= SYS_SVCR_EL0_SM_MASK;
+	else
 		set_thread_flag(TIF_SVE);
 
 fpsimd_only:
@@ -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

arch/arm64/kernel/syscall.c

@@ -158,11 +158,36 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	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);
 }
 

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)",

arch/arm64/kvm/fpsimd.c

@@ -82,6 +82,26 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
 		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
+
+	/*
+	 * We don't currently support SME guests but if we leave
+	 * things in streaming mode then when the guest starts running
+	 * FPSIMD or SVE code it may generate SME traps so as a
+	 * special case if we are in streaming mode we force the host
+	 * state to be saved now and exit streaming mode so that we
+	 * don't have to handle any SME traps for valid guest
+	 * operations. Do this for ZA as well for now for simplicity.
+	 */
+	if (system_supports_sme()) {
+		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
+			vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED;
+
+		if (read_sysreg_s(SYS_SVCR_EL0) &
+		    (SYS_SVCR_EL0_SM_MASK | SYS_SVCR_EL0_ZA_MASK)) {
+			vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
+			fpsimd_save_and_flush_cpu_state();
+		}
+	}
 }
 
 /*
@@ -109,9 +129,14 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 	WARN_ON_ONCE(!irqs_disabled());
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
+		/*
+		 * Currently we do not support SME guests so SVCR is
+		 * always 0 and we just need a variable to point to.
+		 */
 		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
 					 vcpu->arch.sve_state,
-					 vcpu->arch.sve_max_vl);
+					 vcpu->arch.sve_max_vl,
+					 NULL, 0, &vcpu->arch.svcr);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
@@ -130,6 +155,22 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 
 	local_irq_save(flags);
 
+	/*
+	 * If we have VHE then the Hyp code will reset CPACR_EL1 to
+	 * CPACR_EL1_DEFAULT and we need to reenable SME.
+	 */
+	if (has_vhe() && system_supports_sme()) {
+		/* Also restore EL0 state seen on entry */
+		if (vcpu->arch.flags & KVM_ARM64_HOST_SME_ENABLED)
+			sysreg_clear_set(CPACR_EL1, 0,
+					 CPACR_EL1_SMEN_EL0EN |
+					 CPACR_EL1_SMEN_EL1EN);
+		else
+			sysreg_clear_set(CPACR_EL1,
+					 CPACR_EL1_SMEN_EL0EN,
+					 CPACR_EL1_SMEN_EL1EN);
+	}
+
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
 		if (vcpu_has_sve(vcpu)) {
 			__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -47,10 +47,24 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
 		__activate_traps_fpsimd32(vcpu);
 	}
+	if (cpus_have_final_cap(ARM64_SME))
+		val |= CPTR_EL2_TSM;
 
 	write_sysreg(val, cptr_el2);
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);
 
+	if (cpus_have_final_cap(ARM64_SME)) {
+		val = read_sysreg_s(SYS_HFGRTR_EL2);
+		val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK |
+			 HFGxTR_EL2_nSMPRI_EL1_MASK);
+		write_sysreg_s(val, SYS_HFGRTR_EL2);
+
+		val = read_sysreg_s(SYS_HFGWTR_EL2);
+		val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK |
+			 HFGxTR_EL2_nSMPRI_EL1_MASK);
+		write_sysreg_s(val, SYS_HFGWTR_EL2);
+	}
+
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
 
@@ -94,9 +108,25 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 
 	write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
 
+	if (cpus_have_final_cap(ARM64_SME)) {
+		u64 val;
+
+		val = read_sysreg_s(SYS_HFGRTR_EL2);
+		val |= HFGxTR_EL2_nTPIDR2_EL0_MASK |
+			HFGxTR_EL2_nSMPRI_EL1_MASK;
+		write_sysreg_s(val, SYS_HFGRTR_EL2);
+
+		val = read_sysreg_s(SYS_HFGWTR_EL2);
+		val |= HFGxTR_EL2_nTPIDR2_EL0_MASK |
+			HFGxTR_EL2_nSMPRI_EL1_MASK;
+		write_sysreg_s(val, SYS_HFGWTR_EL2);
+	}
+
 	cptr = CPTR_EL2_DEFAULT;
 	if (vcpu_has_sve(vcpu) && (vcpu->arch.flags & KVM_ARM64_FP_ENABLED))
 		cptr |= CPTR_EL2_TZ;
+	if (cpus_have_final_cap(ARM64_SME))
+		cptr &= ~CPTR_EL2_TSM;
 
 	write_sysreg(cptr, cptr_el2);
 	write_sysreg(__kvm_hyp_host_vector, vbar_el2);

arch/arm64/kvm/hyp/vhe/switch.c

@@ -41,7 +41,8 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
-	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);
+	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
+		 CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);
 
 	/*
 	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
@@ -62,6 +63,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		__activate_traps_fpsimd32(vcpu);
 	}
 
+	if (cpus_have_final_cap(ARM64_SME))
+		write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2,
+			     sctlr_el2);
+
 	write_sysreg(val, cpacr_el1);
 
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
@@ -83,6 +88,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	 */
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
+	if (cpus_have_final_cap(ARM64_SME))
+		write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2,
+			     sctlr_el2);
+
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 
 	if (!arm64_kernel_unmapped_at_el0())

arch/arm64/kvm/sys_regs.c

@@ -1132,6 +1132,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 	case SYS_ID_AA64PFR1_EL1:
 		if (!kvm_has_mte(vcpu->kvm))
 			val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
+
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_SME);
 		break;
 	case SYS_ID_AA64ISAR1_EL1:
 		if (!vcpu_has_ptrauth(vcpu))
@@ -1553,7 +1555,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_UNALLOCATED(4,2),
 	ID_UNALLOCATED(4,3),
 	ID_SANITISED(ID_AA64ZFR0_EL1),
-	ID_UNALLOCATED(4,5),
+	ID_HIDDEN(ID_AA64SMFR0_EL1),
 	ID_UNALLOCATED(4,6),
 	ID_UNALLOCATED(4,7),
 
@@ -1596,6 +1598,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
 	{ SYS_DESC(SYS_TRFCR_EL1), undef_access },
+	{ SYS_DESC(SYS_SMPRI_EL1), undef_access },
+	{ SYS_DESC(SYS_SMCR_EL1), undef_access },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
 	{ SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 },
 	{ SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 },
@@ -1678,8 +1682,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
 	{ SYS_DESC(SYS_CLIDR_EL1), access_clidr },
+	{ SYS_DESC(SYS_SMIDR_EL1), undef_access },
 	{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
 	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
+	{ SYS_DESC(SYS_SVCR_EL0), undef_access },
 
 	{ PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr,
 	  .reset = reset_pmcr, .reg = PMCR_EL0 },
@@ -1719,6 +1725,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
+	{ SYS_DESC(SYS_TPIDR2_EL0), undef_access },
 
 	{ SYS_DESC(SYS_SCXTNUM_EL0), undef_access },
 

arch/arm64/tools/cpucaps

@@ -43,6 +43,8 @@ KVM_PROTECTED_MODE
 MISMATCHED_CACHE_TYPE
 MTE
 MTE_ASYMM
+SME
+SME_FA64
 SPECTRE_V2
 SPECTRE_V3A
 SPECTRE_V4

include/uapi/linux/elf.h

@@ -431,6 +431,8 @@ typedef struct elf64_shdr {
 #define NT_ARM_PACG_KEYS	0x408	/* ARM pointer authentication generic key */
 #define NT_ARM_TAGGED_ADDR_CTRL	0x409	/* arm64 tagged address control (prctl()) */
 #define NT_ARM_PAC_ENABLED_KEYS	0x40a	/* arm64 ptr auth enabled keys (prctl()) */
+#define NT_ARM_SSVE	0x40b		/* ARM Streaming SVE registers */
+#define NT_ARM_ZA	0x40c		/* ARM SME ZA registers */
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
 #define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
 #define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */

include/uapi/linux/prctl.h

@@ -272,6 +272,15 @@ struct prctl_mm_map {
 # define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
 
+/* arm64 Scalable Matrix Extension controls */
+/* Flag values must be in sync with SVE versions */
+#define PR_SME_SET_VL			63	/* set task vector length */
+# define PR_SME_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SME_GET_VL			64	/* get task vector length */
+/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */
+# define PR_SME_VL_LEN_MASK		0xffff
+# define PR_SME_VL_INHERIT		(1 << 17) /* inherit across exec */
+
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 

kernel/sys.c

@@ -117,6 +117,12 @@
 #ifndef SVE_GET_VL
 # define SVE_GET_VL()		(-EINVAL)
 #endif
+#ifndef SME_SET_VL
+# define SME_SET_VL(a)		(-EINVAL)
+#endif
+#ifndef SME_GET_VL
+# define SME_GET_VL()		(-EINVAL)
+#endif
 #ifndef PAC_RESET_KEYS
 # define PAC_RESET_KEYS(a, b)	(-EINVAL)
 #endif
@@ -2541,6 +2547,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SVE_GET_VL:
 		error = SVE_GET_VL();
 		break;
+	case PR_SME_SET_VL:
+		error = SME_SET_VL(arg2);
+		break;
+	case PR_SME_GET_VL:
+		error = SME_GET_VL();
+		break;
 	case PR_GET_SPECULATION_CTRL:
 		if (arg3 || arg4 || arg5)
 			return -EINVAL;