Merge branches 'for-next/tpidr2' and 'for-next/sme2' into for-next/signal

Patches on this branch depend on the branches merged above.

Documentation/arm64/booting.rst

@@ -369,6 +369,16 @@ Before jumping into the kernel, the following conditions must be met:
 
     - HCR_EL2.ATA (bit 56) must be initialised to 0b1.
 
+  For CPUs with the Scalable Matrix Extension version 2 (FEAT_SME2):
+
+  - If EL3 is present:
+
+    - SMCR_EL3.EZT0 (bit 30) must be initialised to 0b1.
+
+ - If the kernel is entered at EL1 and EL2 is present:
+
+    - SMCR_EL2.EZT0 (bit 30) must be initialised to 0b1.
+
 The requirements described above for CPU mode, caches, MMUs, architected
 timers, coherency and system registers apply to all CPUs.  All CPUs must
 enter the kernel in the same exception level.  Where the values documented

Documentation/arm64/elf_hwcaps.rst

@@ -284,6 +284,24 @@ HWCAP2_RPRFM
 HWCAP2_SVE2P1
     Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0010.
 
+HWCAP2_SME2
+    Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0001.
+
+HWCAP2_SME2P1
+    Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0010.
+
+HWCAP2_SMEI16I32
+    Functionality implied by ID_AA64SMFR0_EL1.I16I32 == 0b0101
+
+HWCAP2_SMEBI32I32
+    Functionality implied by ID_AA64SMFR0_EL1.BI32I32 == 0b1
+
+HWCAP2_SMEB16B16
+    Functionality implied by ID_AA64SMFR0_EL1.B16B16 == 0b1
+
+HWCAP2_SMEF16F16
+    Functionality implied by ID_AA64SMFR0_EL1.F16F16 == 0b1
+
 4. Unused AT_HWCAP bits
 -----------------------
 

Documentation/arm64/sme.rst

@@ -18,14 +18,19 @@ model features for SME is included in Appendix A.
 1.  General
 -----------
 
-* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA
-  register state and TPIDR2_EL0 are tracked per thread.
+* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA and (when
+  present) ZTn register state and TPIDR2_EL0 are tracked per thread.
 
 * The presence of SME is reported to userspace via HWCAP2_SME in the aux vector
   AT_HWCAP2 entry.  Presence of this flag implies the presence of the SME
   instructions and registers, and the Linux-specific system interfaces
   described in this document.  SME is reported in /proc/cpuinfo as "sme".
 
+* The presence of SME2 is reported to userspace via HWCAP2_SME2 in the
+  aux vector AT_HWCAP2 entry.  Presence of this flag implies the presence of
+  the SME2 instructions and ZT0, and the Linux-specific system interfaces
+  described in this document.  SME2 is reported in /proc/cpuinfo as "sme2".
+
 * Support for the execution of SME instructions in userspace can also be
   detected by reading the CPU ID register ID_AA64PFR1_EL1 using an MRS
   instruction, and checking that the value of the SME field is nonzero. [3]
@@ -44,6 +49,7 @@ model features for SME is included in Appendix A.
 	HWCAP2_SME_B16F32
 	HWCAP2_SME_F32F32
 	HWCAP2_SME_FA64
+        HWCAP2_SME2
 
   This list may be extended over time as the SME architecture evolves.
 
@@ -52,8 +58,8 @@ model features for SME is included in Appendix A.
   cpu-feature-registers.txt for details.
 
 * Debuggers should restrict themselves to interacting with the target via the
-  NT_ARM_SVE, NT_ARM_SSVE and NT_ARM_ZA regsets.  The recommended way
-  of detecting support for these regsets is to connect to a target process
+  NT_ARM_SVE, NT_ARM_SSVE, NT_ARM_ZA and NT_ARM_ZT regsets.  The recommended
+  way of detecting support for these regsets is to connect to a target process
   first and then attempt a
 
 	ptrace(PTRACE_GETREGSET, pid, NT_ARM_<regset>, &iov).
@@ -89,13 +95,13 @@ be zeroed.
 -------------------------
 
 * On syscall PSTATE.ZA is preserved, if PSTATE.ZA==1 then the contents of the
-  ZA matrix are preserved.
+  ZA matrix and ZTn (if present) are preserved.
 
 * On syscall PSTATE.SM will be cleared and the SVE registers will be handled
   as per the standard SVE ABI.
 
-* Neither the SVE registers nor ZA are used to pass arguments to or receive
-  results from any syscall.
+* None of the SVE registers, ZA or ZTn are used to pass arguments to
+  or receive results from any syscall.
 
 * On process creation (eg, clone()) the newly created process will have
   PSTATE.SM cleared.
@@ -137,6 +143,14 @@ be zeroed.
   __reserved[] referencing this space.  za_context is then written in the
   extra space.  Refer to [1] for further details about this mechanism.
 
+* If ZTn is supported and PSTATE.ZA==1 then a signal frame record for ZTn will
+  be generated.
+
+* The signal record for ZTn has magic ZT_MAGIC (0x5a544e01) and consists of a
+  standard signal frame header followed by a struct zt_context specifying
+  the number of ZTn registers supported by the system, then zt_context.nregs
+  blocks of 64 bytes of data per register.
+
 
 5.  Signal return
 -----------------
@@ -154,6 +168,9 @@ 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.
 
+* If ZTn is not supported or PSTATE.ZA==0 then it is illegal to have a
+  signal frame record for ZTn, resulting in a forced SIGSEGV.
+
 
 6.  prctl extensions
 --------------------
@@ -217,8 +234,8 @@ prctl(PR_SME_SET_VL, unsigned long arg)
       vector length that will be applied at the next execve() by the calling
       thread.
 
-    * Changing the vector length causes all of ZA, P0..P15, FFR and all bits of
-      Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become
+    * Changing the vector length causes all of ZA, ZTn, P0..P15, FFR and all
+      bits of Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become
       unspecified, including both streaming and non-streaming SVE state.
       Calling PR_SME_SET_VL with vl equal to the thread's current vector
       length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag,
@@ -320,6 +337,15 @@ The regset data starts with struct user_za_header, containing:
 
 * The effect of writing a partial, incomplete payload is unspecified.
 
+* A new regset NT_ARM_ZT is defined for access to ZTn state via
+  PTRACE_GETREGSET and PTRACE_SETREGSET.
+
+* The NT_ARM_ZT regset consists of a single 512 bit register.
+
+* When PSTATE.ZA==0 reads of NT_ARM_ZT will report all bits of ZTn as 0.
+
+* Writes to NT_ARM_ZT will set PSTATE.ZA to 1.
+
 
 8.  ELF coredump extensions
 ---------------------------
@@ -334,6 +360,11 @@ The regset data starts with struct user_za_header, containing:
   been read if a PTRACE_GETREGSET of NT_ARM_ZA were executed for each thread
   when the coredump was generated.
 
+* A NT_ARM_ZT 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_ZT were executed for each thread
+  when the coredump was generated.
+
 * The NT_ARM_TLS note will be extended to two registers, the second register
   will contain TPIDR2_EL0 on systems that support SME and will be read as
   zero with writes ignored otherwise.
@@ -409,6 +440,9 @@ In A64 state, SME adds the following:
   For best system performance it is strongly encouraged for software to enable
   ZA only when it is actively being used.
 
+* A new ZT0 register is introduced when SME2 is present. This is a 512 bit
+  register which is accessible when PSTATE.ZA is set, as ZA itself is.
+
 * Two new 1 bit fields in PSTATE which may be controlled via the SMSTART and
   SMSTOP instructions or by access to the SVCR system register:
 

arch/arm64/include/asm/cpufeature.h

@@ -769,6 +769,12 @@ static __always_inline bool system_supports_sme(void)
 		cpus_have_const_cap(ARM64_SME);
 }
 
+static __always_inline bool system_supports_sme2(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME2);
+}
+
 static __always_inline bool system_supports_fa64(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_SME) &&

arch/arm64/include/asm/esr.h

@@ -341,6 +341,7 @@
 #define ESR_ELx_SME_ISS_ILL		1
 #define ESR_ELx_SME_ISS_SM_DISABLED	2
 #define ESR_ELx_SME_ISS_ZA_DISABLED	3
+#define ESR_ELx_SME_ISS_ZT_DISABLED	4
 
 #ifndef __ASSEMBLY__
 #include <asm/types.h>

arch/arm64/include/asm/fpsimd.h

@@ -61,7 +61,7 @@ extern void fpsimd_kvm_prepare(void);
 struct cpu_fp_state {
 	struct user_fpsimd_state *st;
 	void *sve_state;
-	void *za_state;
+	void *sme_state;
 	u64 *svcr;
 	unsigned int sve_vl;
 	unsigned int sme_vl;
@@ -105,6 +105,13 @@ static inline void *sve_pffr(struct thread_struct *thread)
 	return (char *)thread->sve_state + sve_ffr_offset(vl);
 }
 
+static inline void *thread_zt_state(struct thread_struct *thread)
+{
+	/* The ZT register state is stored immediately after the ZA state */
+	unsigned int sme_vq = sve_vq_from_vl(thread_get_sme_vl(thread));
+	return thread->sme_state + ZA_SIG_REGS_SIZE(sme_vq);
+}
+
 extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
 extern void sve_load_state(void const *state, u32 const *pfpsr,
 			   int restore_ffr);
@@ -112,12 +119,13 @@ 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);
+extern void sme_save_state(void *state, int zt);
+extern void sme_load_state(void const *state, int zt);
 
 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 sme2_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);
@@ -355,14 +363,20 @@ 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.
+ * specific state for task, given task's currently configured vector
+ * length.
  */
-static inline size_t za_state_size(struct task_struct const *task)
+static inline size_t sme_state_size(struct task_struct const *task)
 {
 	unsigned int vl = task_get_sme_vl(task);
+	size_t size;
+
+	size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+
+	if (system_supports_sme2())
+		size += ZT_SIG_REG_SIZE;
 
-	return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+	return size;
 }
 
 #else
@@ -382,7 +396,7 @@ 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)
+static inline size_t sme_state_size(struct task_struct const *task)
 {
 	return 0;
 }

arch/arm64/include/asm/fpsimdmacros.h

@@ -220,6 +220,28 @@
 		| ((\offset) & 7)
 .endm
 
+/*
+ * LDR (ZT0)
+ *
+ *	LDR ZT0, nx
+ */
+.macro _ldr_zt nx
+	_check_general_reg \nx
+	.inst	0xe11f8000	\
+		 | (\nx << 5)
+.endm
+
+/*
+ * STR (ZT0)
+ *
+ *	STR ZT0, nx
+ */
+.macro _str_zt nx
+	_check_general_reg \nx
+	.inst	0xe13f8000		\
+		| (\nx << 5)
+.endm
+
 /*
  * Zero the entire ZA array
  *	ZERO ZA

arch/arm64/include/asm/hwcap.h

@@ -123,6 +123,12 @@
 #define KERNEL_HWCAP_CSSC		__khwcap2_feature(CSSC)
 #define KERNEL_HWCAP_RPRFM		__khwcap2_feature(RPRFM)
 #define KERNEL_HWCAP_SVE2P1		__khwcap2_feature(SVE2P1)
+#define KERNEL_HWCAP_SME2		__khwcap2_feature(SME2)
+#define KERNEL_HWCAP_SME2P1		__khwcap2_feature(SME2P1)
+#define KERNEL_HWCAP_SME_I16I32		__khwcap2_feature(SME_I16I32)
+#define KERNEL_HWCAP_SME_BI32I32	__khwcap2_feature(SME_BI32I32)
+#define KERNEL_HWCAP_SME_B16B16		__khwcap2_feature(SME_B16B16)
+#define KERNEL_HWCAP_SME_F16F16		__khwcap2_feature(SME_F16F16)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/processor.h

@@ -161,7 +161,7 @@ struct thread_struct {
 	enum fp_type		fp_type;	/* registers FPSIMD or SVE? */
 	unsigned int		fpsimd_cpu;
 	void			*sve_state;	/* SVE registers, if any */
-	void			*za_state;	/* ZA register, if any */
+	void			*sme_state;	/* ZA and ZT state, 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 */

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

@@ -96,5 +96,11 @@
 #define HWCAP2_CSSC		(1UL << 34)
 #define HWCAP2_RPRFM		(1UL << 35)
 #define HWCAP2_SVE2P1		(1UL << 36)
+#define HWCAP2_SME2		(1UL << 37)
+#define HWCAP2_SME2P1		(1UL << 38)
+#define HWCAP2_SME_I16I32	(1UL << 39)
+#define HWCAP2_SME_BI32I32	(1UL << 40)
+#define HWCAP2_SME_B16B16	(1UL << 41)
+#define HWCAP2_SME_F16F16	(1UL << 42)
 
 #endif /* _UAPI__ASM_HWCAP_H */

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

@@ -160,6 +160,14 @@ struct za_context {
 	__u16 __reserved[3];
 };
 
+#define ZT_MAGIC	0x5a544e01
+
+struct zt_context {
+	struct _aarch64_ctx head;
+	__u16 nregs;
+	__u16 __reserved[3];
+};
+
 #endif /* !__ASSEMBLY__ */
 
 #include <asm/sve_context.h>
@@ -312,4 +320,15 @@ struct za_context {
 #define ZA_SIG_CONTEXT_SIZE(vq) \
 		(ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq))
 
+#define ZT_SIG_REG_SIZE 512
+
+#define ZT_SIG_REG_BYTES (ZT_SIG_REG_SIZE / 8)
+
+#define ZT_SIG_REGS_OFFSET sizeof(struct zt_context)
+
+#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * n)
+
+#define ZT_SIG_CONTEXT_SIZE(n) \
+	(sizeof(struct zt_context) + ZT_SIG_REGS_SIZE(n))
+
 #endif /* _UAPI__ASM_SIGCONTEXT_H */

arch/arm64/kernel/cpufeature.c

@@ -282,16 +282,26 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I32_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0),
 	ARM64_FTR_END,
@@ -2649,6 +2659,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.cpu_enable = fa64_kernel_enable,
 	},
+	{
+		.desc = "SME2",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_SME2,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR1_EL1_SME_SHIFT,
+		.field_width = ID_AA64PFR1_EL1_SME_WIDTH,
+		.min_field_value = ID_AA64PFR1_EL1_SME_SME2,
+		.matches = has_cpuid_feature,
+		.cpu_enable = sme2_kernel_enable,
+	},
 #endif /* CONFIG_ARM64_SME */
 	{
 		.desc = "WFx with timeout",
@@ -2827,11 +2849,17 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 #ifdef CONFIG_ARM64_SME
 	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SME_IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_FA64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_SMEver_SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_SMEver_SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F64F64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_B16B16_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F16F16_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I8I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_B16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_BI32I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F32F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
 #endif /* CONFIG_ARM64_SME */
 	{},

arch/arm64/kernel/cpuinfo.c

@@ -119,6 +119,12 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_CSSC]		= "cssc",
 	[KERNEL_HWCAP_RPRFM]		= "rprfm",
 	[KERNEL_HWCAP_SVE2P1]		= "sve2p1",
+	[KERNEL_HWCAP_SME2]		= "sme2",
+	[KERNEL_HWCAP_SME2P1]		= "sme2p1",
+	[KERNEL_HWCAP_SME_I16I32]	= "smei16i32",
+	[KERNEL_HWCAP_SME_BI32I32]	= "smebi32i32",
+	[KERNEL_HWCAP_SME_B16B16]	= "smeb16b16",
+	[KERNEL_HWCAP_SME_F16F16]	= "smef16f16",
 };
 
 #ifdef CONFIG_COMPAT

arch/arm64/kernel/entry-fpsimd.S

@@ -100,25 +100,35 @@ SYM_FUNC_START(sme_set_vq)
 SYM_FUNC_END(sme_set_vq)
 
 /*
- * Save the SME state
+ * Save the ZA and ZT state
  *
  * x0 - pointer to buffer for state
+ * x1 - number of ZT registers to save
  */
-SYM_FUNC_START(za_save_state)
-	_sme_rdsvl	1, 1		// x1 = VL/8
-	sme_save_za 0, x1, 12
+SYM_FUNC_START(sme_save_state)
+	_sme_rdsvl	2, 1		// x2 = VL/8
+	sme_save_za 0, x2, 12		// Leaves x0 pointing to the end of ZA
+
+	cbz	x1, 1f
+	_str_zt 0
+1:
 	ret
-SYM_FUNC_END(za_save_state)
+SYM_FUNC_END(sme_save_state)
 
 /*
- * Load the SME state
+ * Load the ZA and ZT state
  *
  * x0 - pointer to buffer for state
+ * x1 - number of ZT registers to save
  */
-SYM_FUNC_START(za_load_state)
-	_sme_rdsvl	1, 1		// x1 = VL/8
-	sme_load_za 0, x1, 12
+SYM_FUNC_START(sme_load_state)
+	_sme_rdsvl	2, 1		// x2 = VL/8
+	sme_load_za 0, x2, 12		// Leaves x0 pointing to the end of ZA
+
+	cbz	x1, 1f
+	_ldr_zt 0
+1:
 	ret
-SYM_FUNC_END(za_load_state)
+SYM_FUNC_END(sme_load_state)
 
 #endif /* CONFIG_ARM64_SME */

arch/arm64/kernel/fpsimd.c

@@ -299,7 +299,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
 /*
  * TIF_SME controls whether a task can use SME without trapping while
  * in userspace, when TIF_SME is set then we must have storage
- * alocated in sve_state and za_state to store the contents of both ZA
+ * alocated in sve_state and sme_state to store the contents of both ZA
  * and the SVE registers for both streaming and non-streaming modes.
  *
  * If both SVCR.ZA and SVCR.SM are disabled then at any point we
@@ -429,7 +429,8 @@ static void task_fpsimd_load(void)
 		write_sysreg_s(current->thread.svcr, SYS_SVCR);
 
 		if (thread_za_enabled(&current->thread))
-			za_load_state(current->thread.za_state);
+			sme_load_state(current->thread.sme_state,
+				       system_supports_sme2());
 
 		if (thread_sm_enabled(&current->thread))
 			restore_ffr = system_supports_fa64();
@@ -490,7 +491,8 @@ static void fpsimd_save(void)
 		*svcr = read_sysreg_s(SYS_SVCR);
 
 		if (*svcr & SVCR_ZA_MASK)
-			za_save_state(last->za_state);
+			sme_save_state(last->sme_state,
+				       system_supports_sme2());
 
 		/* If we are in streaming mode override regular SVE. */
 		if (*svcr & SVCR_SM_MASK) {
@@ -1257,30 +1259,30 @@ void fpsimd_release_task(struct task_struct *dead_task)
 #ifdef CONFIG_ARM64_SME
 
 /*
- * Ensure that task->thread.za_state is allocated and sufficiently large.
+ * Ensure that task->thread.sme_state is allocated and sufficiently large.
  *
  * This function should be used only in preparation for replacing
- * task->thread.za_state with new data.  The memory is always zeroed
+ * task->thread.sme_state with new data.  The memory is always zeroed
  * here to prevent stale data from showing through: this is done in
  * the interest of testability and predictability, the architecture
  * guarantees that when ZA is enabled it will be zeroed.
  */
 void sme_alloc(struct task_struct *task)
 {
-	if (task->thread.za_state) {
-		memset(task->thread.za_state, 0, za_state_size(task));
+	if (task->thread.sme_state) {
+		memset(task->thread.sme_state, 0, sme_state_size(task));
 		return;
 	}
 
 	/* This could potentially be up to 64K. */
-	task->thread.za_state =
-		kzalloc(za_state_size(task), GFP_KERNEL);
+	task->thread.sme_state =
+		kzalloc(sme_state_size(task), GFP_KERNEL);
 }
 
 static void sme_free(struct task_struct *task)
 {
-	kfree(task->thread.za_state);
-	task->thread.za_state = NULL;
+	kfree(task->thread.sme_state);
+	task->thread.sme_state = NULL;
 }
 
 void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
@@ -1298,6 +1300,17 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
 	isb();
 }
 
+/*
+ * This must be called after sme_kernel_enable(), we rely on the
+ * feature table being sorted to ensure this.
+ */
+void sme2_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+	/* Allow use of ZT0 */
+	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK,
+		       SYS_SMCR_EL1);
+}
+
 /*
  * This must be called after sme_kernel_enable(), we rely on the
  * feature table being sorted to ensure this.
@@ -1488,7 +1501,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 
 	sve_alloc(current, false);
 	sme_alloc(current);
-	if (!current->thread.sve_state || !current->thread.za_state) {
+	if (!current->thread.sve_state || !current->thread.sme_state) {
 		force_sig(SIGKILL);
 		return;
 	}
@@ -1609,7 +1622,7 @@ static void fpsimd_flush_thread_vl(enum vec_type type)
 void fpsimd_flush_thread(void)
 {
 	void *sve_state = NULL;
-	void *za_state = NULL;
+	void *sme_state = NULL;
 
 	if (!system_supports_fpsimd())
 		return;
@@ -1634,8 +1647,8 @@ void fpsimd_flush_thread(void)
 		clear_thread_flag(TIF_SME);
 
 		/* Defer kfree() while in atomic context */
-		za_state = current->thread.za_state;
-		current->thread.za_state = NULL;
+		sme_state = current->thread.sme_state;
+		current->thread.sme_state = NULL;
 
 		fpsimd_flush_thread_vl(ARM64_VEC_SME);
 		current->thread.svcr = 0;
@@ -1645,7 +1658,7 @@ void fpsimd_flush_thread(void)
 
 	put_cpu_fpsimd_context();
 	kfree(sve_state);
-	kfree(za_state);
+	kfree(sme_state);
 }
 
 /*
@@ -1711,7 +1724,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
-	last->za_state = current->thread.za_state;
+	last->sme_state = current->thread.sme_state;
 	last->sve_vl = task_get_sve_vl(current);
 	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;

arch/arm64/kernel/hyp-stub.S

@@ -132,6 +132,12 @@ SYM_CODE_START_LOCAL(__finalise_el2)
 	orr	x0, x0, SMCR_ELx_FA64_MASK
 .Lskip_sme_fa64:
 
+	// ZT0 available?
+	__check_override id_aa64smfr0 ID_AA64SMFR0_EL1_SMEver_SHIFT 4 .Linit_sme_zt0 .Lskip_sme_zt0
+.Linit_sme_zt0:
+	orr	x0, x0, SMCR_ELx_EZT0_MASK
+.Lskip_sme_zt0:
+
 	orr	x0, x0, #SMCR_ELx_LEN_MASK	// Enable full SME vector
 	msr_s	SYS_SMCR_EL2, x0		// length for EL1.
 

arch/arm64/kernel/idreg-override.c

@@ -131,6 +131,7 @@ static const struct ftr_set_desc smfr0 __initconst = {
 	.name		= "id_aa64smfr0",
 	.override	= &id_aa64smfr0_override,
 	.fields		= {
+		FIELD("smever", ID_AA64SMFR0_EL1_SMEver_SHIFT, NULL),
 		/* FA64 is a one bit field... :-/ */
 		{ "fa64", ID_AA64SMFR0_EL1_FA64_SHIFT, 1, },
 		{}

arch/arm64/kernel/process.c

@@ -307,27 +307,28 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	/*
 	 * In the unlikely event that we create a new thread with ZA
-	 * enabled we should retain the ZA state so duplicate it here.
-	 * This may be shortly freed if we exec() or if CLONE_SETTLS
-	 * but it's simpler to do it here. To avoid confusing the rest
-	 * of the code ensure that we have a sve_state allocated
-	 * whenever za_state is allocated.
+	 * enabled we should retain the ZA and ZT state so duplicate
+	 * it here.  This may be shortly freed if we exec() or if
+	 * CLONE_SETTLS but it's simpler to do it here. To avoid
+	 * confusing the rest of the code ensure that we have a
+	 * sve_state allocated whenever sme_state is allocated.
 	 */
 	if (thread_za_enabled(&src->thread)) {
 		dst->thread.sve_state = kzalloc(sve_state_size(src),
 						GFP_KERNEL);
 		if (!dst->thread.sve_state)
 			return -ENOMEM;
-		dst->thread.za_state = kmemdup(src->thread.za_state,
-					       za_state_size(src),
-					       GFP_KERNEL);
-		if (!dst->thread.za_state) {
+
+		dst->thread.sme_state = kmemdup(src->thread.sme_state,
+						sme_state_size(src),
+						GFP_KERNEL);
+		if (!dst->thread.sme_state) {
 			kfree(dst->thread.sve_state);
 			dst->thread.sve_state = NULL;
 			return -ENOMEM;
 		}
 	} else {
-		dst->thread.za_state = NULL;
+		dst->thread.sme_state = NULL;
 		clear_tsk_thread_flag(dst, TIF_SME);
 	}
 

arch/arm64/kernel/ptrace.c

@@ -1045,7 +1045,7 @@ static int za_get(struct task_struct *target,
 	if (thread_za_enabled(&target->thread)) {
 		start = end;
 		end = ZA_PT_SIZE(vq);
-		membuf_write(&to, target->thread.za_state, end - start);
+		membuf_write(&to, target->thread.sme_state, end - start);
 	}
 
 	/* Zero any trailing padding */
@@ -1099,7 +1099,7 @@ static int za_set(struct task_struct *target,
 
 	/* Allocate/reinit ZA storage */
 	sme_alloc(target);
-	if (!target->thread.za_state) {
+	if (!target->thread.sme_state) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1124,7 +1124,7 @@ static int za_set(struct task_struct *target,
 	start = ZA_PT_ZA_OFFSET;
 	end = ZA_PT_SIZE(vq);
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 target->thread.za_state,
+				 target->thread.sme_state,
 				 start, end);
 	if (ret)
 		goto out;
@@ -1138,6 +1138,51 @@ static int za_set(struct task_struct *target,
 	return ret;
 }
 
+static int zt_get(struct task_struct *target,
+		  const struct user_regset *regset,
+		  struct membuf to)
+{
+	if (!system_supports_sme2())
+		return -EINVAL;
+
+	/*
+	 * If PSTATE.ZA is not set then ZT will be zeroed when it is
+	 * enabled so report the current register value as zero.
+	 */
+	if (thread_za_enabled(&target->thread))
+		membuf_write(&to, thread_zt_state(&target->thread),
+			     ZT_SIG_REG_BYTES);
+	else
+		membuf_zero(&to, ZT_SIG_REG_BYTES);
+
+	return 0;
+}
+
+static int zt_set(struct task_struct *target,
+		  const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	if (!system_supports_sme2())
+		return -EINVAL;
+
+	if (!thread_za_enabled(&target->thread)) {
+		sme_alloc(target);
+		if (!target->thread.sme_state)
+			return -ENOMEM;
+	}
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 thread_zt_state(&target->thread),
+				 0, ZT_SIG_REG_BYTES);
+	if (ret == 0)
+		target->thread.svcr |= SVCR_ZA_MASK;
+
+	return ret;
+}
+
 #endif /* CONFIG_ARM64_SME */
 
 #ifdef CONFIG_ARM64_PTR_AUTH
@@ -1360,6 +1405,7 @@ enum aarch64_regset {
 #ifdef CONFIG_ARM64_SVE
 	REGSET_SSVE,
 	REGSET_ZA,
+	REGSET_ZT,
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	REGSET_PAC_MASK,
@@ -1467,6 +1513,14 @@ static const struct user_regset aarch64_regsets[] = {
 		.regset_get = za_get,
 		.set = za_set,
 	},
+	[REGSET_ZT] = { /* SME ZT */
+		.core_note_type = NT_ARM_ZT,
+		.n = 1,
+		.size = ZT_SIG_REG_BYTES,
+		.align = sizeof(u64),
+		.regset_get = zt_get,
+		.set = zt_set,
+	},
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	[REGSET_PAC_MASK] = {

arch/arm64/kernel/signal.c

@@ -58,6 +58,7 @@ struct rt_sigframe_user_layout {
 	unsigned long sve_offset;
 	unsigned long tpidr2_offset;
 	unsigned long za_offset;
+	unsigned long zt_offset;
 	unsigned long extra_offset;
 	unsigned long end_offset;
 };
@@ -223,6 +224,7 @@ struct user_ctxs {
 	struct sve_context __user *sve;
 	struct tpidr2_context __user *tpidr2;
 	struct za_context __user *za;
+	struct zt_context __user *zt;
 };
 
 #ifdef CONFIG_ARM64_SVE
@@ -417,7 +419,7 @@ static int preserve_za_context(struct za_context __user *ctx)
 		 * fpsimd_signal_preserve_current_state().
 		 */
 		err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET,
-				      current->thread.za_state,
+				      current->thread.sme_state,
 				      ZA_SIG_REGS_SIZE(vq));
 	}
 
@@ -448,7 +450,7 @@ static int restore_za_context(struct user_ctxs *user)
 
 	/*
 	 * Careful: we are about __copy_from_user() directly into
-	 * thread.za_state with preemption enabled, so protection is
+	 * thread.sme_state with preemption enabled, so protection is
 	 * needed to prevent a racing context switch from writing stale
 	 * registers back over the new data.
 	 */
@@ -457,13 +459,13 @@ static int restore_za_context(struct user_ctxs *user)
 	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
 
 	sme_alloc(current);
-	if (!current->thread.za_state) {
+	if (!current->thread.sme_state) {
 		current->thread.svcr &= ~SVCR_ZA_MASK;
 		clear_thread_flag(TIF_SME);
 		return -ENOMEM;
 	}
 
-	err = __copy_from_user(current->thread.za_state,
+	err = __copy_from_user(current->thread.sme_state,
 			       (char __user const *)user->za +
 					ZA_SIG_REGS_OFFSET,
 			       ZA_SIG_REGS_SIZE(vq));
@@ -475,6 +477,74 @@ static int restore_za_context(struct user_ctxs *user)
 
 	return 0;
 }
+
+static int preserve_zt_context(struct zt_context __user *ctx)
+{
+	int err = 0;
+	u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+
+	if (WARN_ON(!thread_za_enabled(&current->thread)))
+		return -EINVAL;
+
+	memset(reserved, 0, sizeof(reserved));
+
+	__put_user_error(ZT_MAGIC, &ctx->head.magic, err);
+	__put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16),
+			 &ctx->head.size, err);
+	__put_user_error(1, &ctx->nregs, err);
+	BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+	err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+	/*
+	 * This assumes that the ZT state has already been saved to
+	 * the task struct by calling the function
+	 * fpsimd_signal_preserve_current_state().
+	 */
+	err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET,
+			      thread_zt_state(&current->thread),
+			      ZT_SIG_REGS_SIZE(1));
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_zt_context(struct user_ctxs *user)
+{
+	int err;
+	struct zt_context zt;
+
+	/* ZA must be restored first for this check to be valid */
+	if (!thread_za_enabled(&current->thread))
+		return -EINVAL;
+
+	if (__copy_from_user(&zt, user->zt, sizeof(zt)))
+		return -EFAULT;
+
+	if (zt.nregs != 1)
+		return -EINVAL;
+
+	if (zt.head.size != ZT_SIG_CONTEXT_SIZE(zt.nregs))
+		return -EINVAL;
+
+	/*
+	 * Careful: we are about __copy_from_user() directly into
+	 * thread.zt_state with preemption enabled, so protection is
+	 * needed to prevent a racing context switch from writing stale
+	 * registers back over the new data.
+	 */
+
+	fpsimd_flush_task_state(current);
+	/* From now, fpsimd_thread_switch() won't touch ZT in thread state */
+
+	err = __copy_from_user(thread_zt_state(&current->thread),
+			       (char __user const *)user->zt +
+					ZT_SIG_REGS_OFFSET,
+			       ZT_SIG_REGS_SIZE(1));
+	if (err)
+		return -EFAULT;
+
+	return 0;
+}
+
 #else /* ! CONFIG_ARM64_SME */
 
 /* Turn any non-optimised out attempts to use these into a link error: */
@@ -482,6 +552,8 @@ extern int preserve_tpidr2_context(void __user *ctx);
 extern int restore_tpidr2_context(struct user_ctxs *user);
 extern int preserve_za_context(void __user *ctx);
 extern int restore_za_context(struct user_ctxs *user);
+extern int preserve_zt_context(void __user *ctx);
+extern int restore_zt_context(struct user_ctxs *user);
 
 #endif /* ! CONFIG_ARM64_SME */
 
@@ -500,6 +572,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	user->sve = NULL;
 	user->tpidr2 = NULL;
 	user->za = NULL;
+	user->zt = NULL;
 
 	if (!IS_ALIGNED((unsigned long)base, 16))
 		goto invalid;
@@ -591,6 +664,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			user->za = (struct za_context __user *)head;
 			break;
 
+		case ZT_MAGIC:
+			if (!system_supports_sme2())
+				goto invalid;
+
+			if (user->zt)
+				goto invalid;
+
+			if (size < sizeof(*user->zt))
+				goto invalid;
+
+			user->zt = (struct zt_context __user *)head;
+			break;
+
 		case EXTRA_MAGIC:
 			if (have_extra_context)
 				goto invalid;
@@ -716,6 +802,9 @@ static int restore_sigframe(struct pt_regs *regs,
 	if (err == 0 && system_supports_sme() && user.za)
 		err = restore_za_context(&user);
 
+	if (err == 0 && system_supports_sme2() && user.zt)
+		err = restore_zt_context(&user);
+
 	return err;
 }
 
@@ -821,6 +910,15 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 			return err;
 	}
 
+	if (system_supports_sme2()) {
+		if (add_all || thread_za_enabled(&current->thread)) {
+			err = sigframe_alloc(user, &user->zt_offset,
+					     ZT_SIG_CONTEXT_SIZE(1));
+			if (err)
+				return err;
+		}
+	}
+
 	return sigframe_alloc_end(user);
 }
 
@@ -883,6 +981,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		err |= preserve_za_context(za_ctx);
 	}
 
+	/* ZT state if present */
+	if (system_supports_sme2() && err == 0 && user->zt_offset) {
+		struct zt_context __user *zt_ctx =
+			apply_user_offset(user, user->zt_offset);
+		err |= preserve_zt_context(zt_ctx);
+	}
+
 	if (err == 0 && user->extra_offset) {
 		char __user *sfp = (char __user *)user->sigframe;
 		char __user *userp =

arch/arm64/kvm/fpsimd.c

@@ -143,7 +143,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 		fp_state.st = &vcpu->arch.ctxt.fp_regs;
 		fp_state.sve_state = vcpu->arch.sve_state;
 		fp_state.sve_vl = vcpu->arch.sve_max_vl;
-		fp_state.za_state = NULL;
+		fp_state.sme_state = NULL;
 		fp_state.svcr = &vcpu->arch.svcr;
 		fp_state.fp_type = &vcpu->arch.fp_type;
 

arch/arm64/tools/cpucaps

@@ -50,6 +50,7 @@ MTE
 MTE_ASYMM
 SME
 SME_FA64
+SME2
 SPECTRE_V2
 SPECTRE_V3A
 SPECTRE_V4

arch/arm64/tools/sysreg

@@ -894,6 +894,7 @@ EndEnum
 Enum	27:24	SME
 	0b0000	NI
 	0b0001	IMP
+	0b0010	SME2
 EndEnum
 Res0	23:20
 Enum	19:16	MPAM_frac
@@ -975,7 +976,9 @@ Enum	63	FA64
 EndEnum
 Res0	62:60
 Enum	59:56	SMEver
-	0b0000	IMP
+	0b0000	SME
+	0b0001	SME2
+	0b0010	SME2p1
 EndEnum
 Enum	55:52	I16I64
 	0b0000	NI
@@ -986,7 +989,19 @@ Enum	48	F64F64
 	0b0	NI
 	0b1	IMP
 EndEnum
-Res0	47:40
+Enum	47:44	I16I32
+	0b0000	NI
+	0b0101	IMP
+EndEnum
+Enum	43	B16B16
+	0b0	NI
+	0b1	IMP
+EndEnum
+Enum	42	F16F16
+	0b0	NI
+	0b1	IMP
+EndEnum
+Res0	41:40
 Enum	39:36	I8I32
 	0b0000	NI
 	0b1111	IMP
@@ -999,7 +1014,10 @@ Enum	34	B16F32
 	0b0	NI
 	0b1	IMP
 EndEnum
-Res0	33
+Enum	33	BI32I32
+	0b0	NI
+	0b1	IMP
+EndEnum
 Enum	32	F32F32
 	0b0	NI
 	0b1	IMP
@@ -1599,7 +1617,8 @@ EndSysreg
 SysregFields	SMCR_ELx
 Res0	63:32
 Field	31	FA64
-Res0	30:9
+Field	30	EZT0
+Res0	29:9
 Raz	8:4
 Field	3:0	LEN
 EndSysregFields

include/uapi/linux/elf.h

@@ -434,6 +434,7 @@ typedef struct elf64_shdr {
 #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_ARM_ZT	0x40d		/* ARM SME ZT 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 */

tools/testing/selftests/arm64/abi/hwcap.c

@@ -50,6 +50,78 @@ static void sme_sigill(void)
 	asm volatile(".inst 0x04bf5800" : : : "x0");
 }
 
+static void sme2_sigill(void)
+{
+	/* SMSTART ZA */
+	asm volatile("msr S0_3_C4_C5_3, xzr" : : : );
+
+	/* ZERO ZT0 */
+	asm volatile(".inst 0xc0480001" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void sme2p1_sigill(void)
+{
+	/* SMSTART SM */
+	asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
+
+	/* BFCLAMP { Z0.H - Z1.H }, Z0.H, Z0.H */
+	asm volatile(".inst 0xc120C000" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smei16i32_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* SMOPA ZA0.S, P0/M, P0/M, Z0.B, Z0.B */
+	asm volatile(".inst 0xa0800000" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smebi32i32_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* BMOPA ZA0.S, P0/M, P0/M, Z0.B, Z0.B */
+	asm volatile(".inst 0x80800008" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smeb16b16_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* BFADD ZA.H[W0, 0], {Z0.H-Z1.H} */
+	asm volatile(".inst 0xC1E41C00" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smef16f16_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FADD ZA.H[W0, 0], { Z0.H-Z1.H } */
+	asm volatile(".inst 0xc1a41C00" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
 static void sve_sigill(void)
 {
 	/* RDVL x0, #0 */
@@ -158,6 +230,49 @@ static const struct hwcap_data {
 		.sigill_fn = sme_sigill,
 		.sigill_reliable = true,
 	},
+	{
+		.name = "SME2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME2,
+		.cpuinfo = "sme2",
+		.sigill_fn = sme2_sigill,
+		.sigill_reliable = true,
+	},
+	{
+		.name = "SME 2.1",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME2P1,
+		.cpuinfo = "sme2p1",
+		.sigill_fn = sme2p1_sigill,
+	},
+	{
+		.name = "SME I16I32",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_I16I32,
+		.cpuinfo = "smei16i32",
+		.sigill_fn = smei16i32_sigill,
+	},
+	{
+		.name = "SME BI32I32",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_BI32I32,
+		.cpuinfo = "smebi32i32",
+		.sigill_fn = smebi32i32_sigill,
+	},
+	{
+		.name = "SME B16B16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_B16B16,
+		.cpuinfo = "smeb16b16",
+		.sigill_fn = smeb16b16_sigill,
+	},
+	{
+		.name = "SME F16F16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_F16F16,
+		.cpuinfo = "smef16f16",
+		.sigill_fn = smef16f16_sigill,
+	},
 	{
 		.name = "SVE",
 		.at_hwcap = AT_HWCAP,

tools/testing/selftests/arm64/abi/syscall-abi-asm.S

@@ -23,6 +23,9 @@
 
 .arch_extension sve
 
+#define ID_AA64SMFR0_EL1_SMEver_SHIFT           56
+#define ID_AA64SMFR0_EL1_SMEver_WIDTH           4
+
 /*
  * LDR (vector to ZA array):
  *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
@@ -45,6 +48,26 @@
 		| ((\offset) & 7)
 .endm
 
+/*
+ * LDR (ZT0)
+ *
+ *	LDR ZT0, nx
+ */
+.macro _ldr_zt nx
+	.inst	0xe11f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
+/*
+ * STR (ZT0)
+ *
+ *	STR ZT0, nx
+ */
+.macro _str_zt nx
+	.inst	0xe13f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
 .globl do_syscall
 do_syscall:
 	// Store callee saved registers x19-x29 (80 bytes) plus x0 and x1
@@ -64,7 +87,7 @@ do_syscall:
 	msr	S3_3_C4_C2_2, x2
 1:
 
-	// Load ZA if it's enabled - uses x12 as scratch due to SME LDR
+	// Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR
 	tbz	x2, #SVCR_ZA_SHIFT, 1f
 	mov	w12, #0
 	ldr	x2, =za_in
@@ -73,6 +96,15 @@ do_syscall:
 	add	x12, x12, #1
 	cmp	x1, x12
 	bne	2b
+
+	// ZT0
+	mrs	x2, S3_0_C0_C4_5	// ID_AA64SMFR0_EL1
+	ubfx	x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
+			 #ID_AA64SMFR0_EL1_SMEver_WIDTH
+	cbz	x2, 1f
+	adrp	x2, zt_in
+	add	x2, x2, :lo12:zt_in
+	_ldr_zt 2
 1:
 
 	// Load GPRs x8-x28, and save our SP/FP for later comparison
@@ -235,6 +267,15 @@ do_syscall:
 	add	x12, x12, #1
 	cmp	x1, x12
 	bne	2b
+
+	// ZT0
+	mrs	x2, S3_0_C0_C4_5	// ID_AA64SMFR0_EL1
+	ubfx	x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
+			#ID_AA64SMFR0_EL1_SMEver_WIDTH
+	cbz	x2, 1f
+	adrp	x2, zt_out
+	add	x2, x2, :lo12:zt_out
+	_str_zt 2
 1:
 
 	// Save the SVE state if we have some

tools/testing/selftests/arm64/abi/syscall-abi.c

@@ -311,6 +311,35 @@ static int check_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	return errors;
 }
 
+uint8_t zt_in[ZT_SIG_REG_BYTES] __attribute__((aligned(16)));
+uint8_t zt_out[ZT_SIG_REG_BYTES] __attribute__((aligned(16)));
+
+static void setup_zt(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		     uint64_t svcr)
+{
+	fill_random(zt_in, sizeof(zt_in));
+	memset(zt_out, 0, sizeof(zt_out));
+}
+
+static int check_zt(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		    uint64_t svcr)
+{
+	int errors = 0;
+
+	if (!(getauxval(AT_HWCAP2) & HWCAP2_SME2))
+		return 0;
+
+	if (!(svcr & SVCR_ZA_MASK))
+		return 0;
+
+	if (memcmp(zt_in, zt_out, sizeof(zt_in)) != 0) {
+		ksft_print_msg("SME VL %d ZT does not match\n", sme_vl);
+		errors++;
+	}
+
+	return errors;
+}
+
 typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 			 uint64_t svcr);
 typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
@@ -334,6 +363,7 @@ static struct {
 	{ setup_ffr, check_ffr },
 	{ setup_svcr, check_svcr },
 	{ setup_za, check_za },
+	{ setup_zt, check_zt },
 };
 
 static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
@@ -474,6 +504,7 @@ int main(void)
 {
 	int i;
 	int tests = 1;  /* FPSIMD */
+	int sme_ver;
 
 	srandom(getpid());
 
@@ -482,10 +513,15 @@ int main(void)
 	tests += (sve_count_vls() * sme_count_vls()) * 3;
 	ksft_set_plan(ARRAY_SIZE(syscalls) * tests);
 
+	if (getauxval(AT_HWCAP2) & HWCAP2_SME2)
+		sme_ver = 2;
+	else
+		sme_ver = 1;
+
 	if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
-		ksft_print_msg("SME with FA64\n");
+		ksft_print_msg("SME%d with FA64\n", sme_ver);
 	else if (getauxval(AT_HWCAP2) & HWCAP2_SME)
-		ksft_print_msg("SME without FA64\n");
+		ksft_print_msg("SME%d without FA64\n", sme_ver);
 
 	for (i = 0; i < ARRAY_SIZE(syscalls); i++)
 		test_one_syscall(&syscalls[i]);

tools/testing/selftests/arm64/fp/.gitignore

@@ -12,3 +12,5 @@ vlset
 za-fork
 za-ptrace
 za-test
+zt-ptrace
+zt-test

tools/testing/selftests/arm64/fp/Makefile

@@ -14,6 +14,8 @@ TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
 	sve-test \
 	ssve-test \
 	za-test \
+	zt-ptrace \
+	zt-test \
 	vlset
 TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress
 
@@ -41,5 +43,8 @@ $(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o
 $(OUTPUT)/za-ptrace: za-ptrace.c
 $(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o
 	$(CC) -nostdlib $^ -o $@
+$(OUTPUT)/zt-ptrace: zt-ptrace.c
+$(OUTPUT)/zt-test: zt-test.S $(OUTPUT)/asm-utils.o
+	$(CC) -nostdlib $^ -o $@
 
 include ../../lib.mk

tools/testing/selftests/arm64/fp/fp-stress.c

@@ -370,6 +370,19 @@ static void start_za(struct child_data *child, int vl, int cpu)
 	ksft_print_msg("Started %s\n", child->name);
 }
 
+static void start_zt(struct child_data *child, int cpu)
+{
+	int ret;
+
+	ret = asprintf(&child->name, "ZT-%d", cpu);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	child_start(child, "./zt-test");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
 static void probe_vls(int vls[], int *vl_count, int set_vl)
 {
 	unsigned int vq;
@@ -426,6 +439,7 @@ int main(int argc, char **argv)
 	bool all_children_started = false;
 	int seen_children;
 	int sve_vls[MAX_VLS], sme_vls[MAX_VLS];
+	bool have_sme2;
 	struct sigaction sa;
 
 	while ((c = getopt_long(argc, argv, "t:", options, NULL)) != -1) {
@@ -458,6 +472,13 @@ int main(int argc, char **argv)
 		sme_vl_count = 0;
 	}
 
+	if (getauxval(AT_HWCAP2) & HWCAP2_SME2) {
+		tests += cpus;
+		have_sme2 = true;
+	} else {
+		have_sme2 = false;
+	}
+
 	/* Force context switching if we only have FPSIMD */
 	if (!sve_vl_count && !sme_vl_count)
 		fpsimd_per_cpu = 2;
@@ -468,8 +489,9 @@ int main(int argc, char **argv)
 	ksft_print_header();
 	ksft_set_plan(tests);
 
-	ksft_print_msg("%d CPUs, %d SVE VLs, %d SME VLs\n",
-		       cpus, sve_vl_count, sme_vl_count);
+	ksft_print_msg("%d CPUs, %d SVE VLs, %d SME VLs, SME2 %s\n",
+		       cpus, sve_vl_count, sme_vl_count,
+		       have_sme2 ? "present" : "absent");
 
 	if (timeout > 0)
 		ksft_print_msg("Will run for %ds\n", timeout);
@@ -527,6 +549,9 @@ int main(int argc, char **argv)
 			start_ssve(&children[num_children++], sme_vls[j], i);
 			start_za(&children[num_children++], sme_vls[j], i);
 		}
+
+		if (have_sme2)
+			start_zt(&children[num_children++], i);
 	}
 
 	/*

tools/testing/selftests/arm64/fp/sme-inst.h

@@ -48,4 +48,24 @@
 		| ((\offset) & 7)
 .endm
 
+/*
+ * LDR (ZT0)
+ *
+ *	LDR ZT0, nx
+ */
+.macro _ldr_zt nx
+	.inst	0xe11f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
+/*
+ * STR (ZT0)
+ *
+ *	STR ZT0, nx
+ */
+.macro _str_zt nx
+	.inst	0xe13f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
 #endif

tools/testing/selftests/arm64/fp/zt-ptrace.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 ARM Limited.
+ */
+#include <errno.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+#include <asm/sigcontext.h>
+#include <asm/ptrace.h>
+
+#include "../../kselftest.h"
+
+/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
+#ifndef NT_ARM_ZA
+#define NT_ARM_ZA 0x40c
+#endif
+#ifndef NT_ARM_ZT
+#define NT_ARM_ZT 0x40d
+#endif
+
+#define EXPECTED_TESTS 3
+
+static int sme_vl;
+
+static void fill_buf(char *buf, size_t size)
+{
+	int i;
+
+	for (i = 0; i < size; i++)
+		buf[i] = random();
+}
+
+static int do_child(void)
+{
+	if (ptrace(PTRACE_TRACEME, -1, NULL, NULL))
+		ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno));
+
+	if (raise(SIGSTOP))
+		ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno));
+
+	return EXIT_SUCCESS;
+}
+
+static struct user_za_header *get_za(pid_t pid, void **buf, size_t *size)
+{
+	struct user_za_header *za;
+	void *p;
+	size_t sz = sizeof(*za);
+	struct iovec iov;
+
+	while (1) {
+		if (*size < sz) {
+			p = realloc(*buf, sz);
+			if (!p) {
+				errno = ENOMEM;
+				goto error;
+			}
+
+			*buf = p;
+			*size = sz;
+		}
+
+		iov.iov_base = *buf;
+		iov.iov_len = sz;
+		if (ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZA, &iov))
+			goto error;
+
+		za = *buf;
+		if (za->size <= sz)
+			break;
+
+		sz = za->size;
+	}
+
+	return za;
+
+error:
+	return NULL;
+}
+
+static int set_za(pid_t pid, const struct user_za_header *za)
+{
+	struct iovec iov;
+
+	iov.iov_base = (void *)za;
+	iov.iov_len = za->size;
+	return ptrace(PTRACE_SETREGSET, pid, NT_ARM_ZA, &iov);
+}
+
+static int get_zt(pid_t pid, char zt[ZT_SIG_REG_BYTES])
+{
+	struct iovec iov;
+
+	iov.iov_base = zt;
+	iov.iov_len = ZT_SIG_REG_BYTES;
+	return ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZT, &iov);
+}
+
+
+static int set_zt(pid_t pid, const char zt[ZT_SIG_REG_BYTES])
+{
+	struct iovec iov;
+
+	iov.iov_base = (void *)zt;
+	iov.iov_len = ZT_SIG_REG_BYTES;
+	return ptrace(PTRACE_SETREGSET, pid, NT_ARM_ZT, &iov);
+}
+
+/* Reading with ZA disabled returns all zeros */
+static void ptrace_za_disabled_read_zt(pid_t child)
+{
+	struct user_za_header za;
+	char zt[ZT_SIG_REG_BYTES];
+	int ret, i;
+	bool fail = false;
+
+	/* Disable PSTATE.ZA using the ZA interface */
+	memset(&za, 0, sizeof(za));
+	za.vl = sme_vl;
+	za.size = sizeof(za);
+
+	ret = set_za(child, &za);
+	if (ret != 0) {
+		ksft_print_msg("Failed to disable ZA\n");
+		fail = true;
+	}
+
+	/* Read back ZT */
+	ret = get_zt(child, zt);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read ZT\n");
+		fail = true;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(zt); i++) {
+		if (zt[i]) {
+			ksft_print_msg("zt[%d]: 0x%x != 0\n", i, zt[i]);
+			fail = true;
+		}
+	}
+
+	ksft_test_result(!fail, "ptrace_za_disabled_read_zt\n");
+}
+
+/* Writing then reading ZT should return the data written */
+static void ptrace_set_get_zt(pid_t child)
+{
+	char zt_in[ZT_SIG_REG_BYTES];
+	char zt_out[ZT_SIG_REG_BYTES];
+	int ret, i;
+	bool fail = false;
+
+	fill_buf(zt_in, sizeof(zt_in));
+
+	ret = set_zt(child, zt_in);
+	if (ret != 0) {
+		ksft_print_msg("Failed to set ZT\n");
+		fail = true;
+	}
+
+	ret = get_zt(child, zt_out);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read ZT\n");
+		fail = true;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(zt_in); i++) {
+		if (zt_in[i] != zt_out[i]) {
+			ksft_print_msg("zt[%d]: 0x%x != 0x%x\n", i, 
+				       zt_in[i], zt_out[i]);
+			fail = true;
+		}
+	}
+
+	ksft_test_result(!fail, "ptrace_set_get_zt\n");
+}
+
+/* Writing ZT should set PSTATE.ZA */
+static void ptrace_enable_za_via_zt(pid_t child)
+{
+	struct user_za_header za_in;
+	struct user_za_header *za_out;
+	char zt[ZT_SIG_REG_BYTES];
+	char *za_data;
+	size_t za_out_size;
+	int ret, i, vq;
+	bool fail = false;
+
+	/* Disable PSTATE.ZA using the ZA interface */
+	memset(&za_in, 0, sizeof(za_in));
+	za_in.vl = sme_vl;
+	za_in.size = sizeof(za_in);
+
+	ret = set_za(child, &za_in);
+	if (ret != 0) {
+		ksft_print_msg("Failed to disable ZA\n");
+		fail = true;
+	}
+
+	/* Write ZT */
+	fill_buf(zt, sizeof(zt));
+	ret = set_zt(child, zt);
+	if (ret != 0) {
+		ksft_print_msg("Failed to set ZT\n");
+		fail = true;
+	}
+
+	/* Read back ZA and check for register data */
+	za_out = NULL;
+	za_out_size = 0;
+	if (get_za(child, (void **)&za_out, &za_out_size)) {
+		/* Should have an unchanged VL */
+		if (za_out->vl != sme_vl) {
+			ksft_print_msg("VL changed from %d to %d\n",
+				       sme_vl, za_out->vl);
+			fail = true;
+		}
+		vq = __sve_vq_from_vl(za_out->vl);
+		za_data = (char *)za_out + ZA_PT_ZA_OFFSET;
+
+		/* Should have register data */
+		if (za_out->size < ZA_PT_SIZE(vq)) {
+			ksft_print_msg("ZA data less than expected: %u < %u\n",
+				       za_out->size, ZA_PT_SIZE(vq));
+			fail = true;
+			vq = 0;
+		}
+
+		/* That register data should be non-zero */
+		for (i = 0; i < ZA_PT_ZA_SIZE(vq); i++) {
+			if (za_data[i]) {
+				ksft_print_msg("ZA byte %d is %x\n",
+					       i, za_data[i]);
+				fail = true;
+			}
+		}
+	} else {
+		ksft_print_msg("Failed to read ZA\n");
+		fail = true;
+	}
+
+	ksft_test_result(!fail, "ptrace_enable_za_via_zt\n");
+}
+
+static int do_parent(pid_t child)
+{
+	int ret = EXIT_FAILURE;
+	pid_t pid;
+	int status;
+	siginfo_t si;
+
+	/* Attach to the child */
+	while (1) {
+		int sig;
+
+		pid = wait(&status);
+		if (pid == -1) {
+			perror("wait");
+			goto error;
+		}
+
+		/*
+		 * This should never happen but it's hard to flag in
+		 * the framework.
+		 */
+		if (pid != child)
+			continue;
+
+		if (WIFEXITED(status) || WIFSIGNALED(status))
+			ksft_exit_fail_msg("Child died unexpectedly\n");
+
+		if (!WIFSTOPPED(status))
+			goto error;
+
+		sig = WSTOPSIG(status);
+
+		if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &si)) {
+			if (errno == ESRCH)
+				goto disappeared;
+
+			if (errno == EINVAL) {
+				sig = 0; /* bust group-stop */
+				goto cont;
+			}
+
+			ksft_test_result_fail("PTRACE_GETSIGINFO: %s\n",
+					      strerror(errno));
+			goto error;
+		}
+
+		if (sig == SIGSTOP && si.si_code == SI_TKILL &&
+		    si.si_pid == pid)
+			break;
+
+	cont:
+		if (ptrace(PTRACE_CONT, pid, NULL, sig)) {
+			if (errno == ESRCH)
+				goto disappeared;
+
+			ksft_test_result_fail("PTRACE_CONT: %s\n",
+					      strerror(errno));
+			goto error;
+		}
+	}
+
+	ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
+
+	ptrace_za_disabled_read_zt(child);
+	ptrace_set_get_zt(child);
+	ptrace_enable_za_via_zt(child);
+
+	ret = EXIT_SUCCESS;
+
+error:
+	kill(child, SIGKILL);
+
+disappeared:
+	return ret;
+}
+
+int main(void)
+{
+	int ret = EXIT_SUCCESS;
+	pid_t child;
+
+	srandom(getpid());
+
+	ksft_print_header();
+
+	if (!(getauxval(AT_HWCAP2) & HWCAP2_SME2)) {
+		ksft_set_plan(1);
+		ksft_exit_skip("SME2 not available\n");
+	}
+
+	/* We need a valid SME VL to enable/disable ZA */
+	sme_vl = prctl(PR_SME_GET_VL);
+	if (sme_vl == -1) {
+		ksft_set_plan(1);
+		ksft_exit_skip("Failed to read SME VL: %d (%s)\n",
+			       errno, strerror(errno));
+	}
+
+	ksft_set_plan(EXPECTED_TESTS);
+
+	child = fork();
+	if (!child)
+		return do_child();
+
+	if (do_parent(child))
+		ret = EXIT_FAILURE;
+
+	ksft_print_cnts();
+
+	return ret;
+}

tools/testing/selftests/arm64/fp/zt-test.S

+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021-2 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+//
+// Scalable Matrix Extension ZT context switch test
+// Repeatedly writes unique test patterns into ZT0
+// and reads them back to verify integrity.
+
+#include <asm/unistd.h>
+#include "assembler.h"
+#include "asm-offsets.h"
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define ZT_SZ	512
+#define ZT_B	(ZT_SZ / 8)
+
+// Declare some storage space to shadow ZT register contents and a
+// scratch buffer.
+.pushsection .text
+.data
+.align 4
+ztref:
+	.space	ZT_B
+scratch:
+	.space	ZT_B
+.popsection
+
+
+// Generate a test pattern for storage in ZT
+// x0: pid
+// x1: generation
+
+// These values are used to construct a 32-bit pattern that is repeated in the
+// scratch buffer as many times as will fit:
+// bits 31:24	generation number (increments once per test_loop)
+// bits 23: 8	pid
+// bits  7: 0	32-bit lane index
+
+function pattern
+	mov	w3, wzr
+	bfi	w3, w0, #8, #16		// PID
+	bfi	w3, w1, #24, #8		// Generation
+
+	ldr	x0, =scratch
+	mov	w1, #ZT_B / 4
+
+0:	str	w3, [x0], #4
+	add	w3, w3, #1		// Lane
+	subs	w1, w1, #1
+	b.ne	0b
+
+	ret
+endfunction
+
+// Set up test pattern in a ZT horizontal vector
+// x0: pid
+// x1: generation
+function setup_zt
+	mov	x4, x30
+
+	bl	pattern			// Get pattern in scratch buffer
+	ldr	x0, =ztref
+	ldr	x1, =scratch
+	mov	x2, #ZT_B
+	bl	memcpy
+
+	ldr	x0, =ztref
+	_ldr_zt 0			// load zt0 from pointer x0
+
+	ret	x4
+endfunction
+
+// Trivial memory compare: compare x2 bytes starting at address x0 with
+// bytes starting at address x1.
+// Returns only if all bytes match; otherwise, the program is aborted.
+// Clobbers x0-x5.
+function memcmp
+	cbz	x2, 2f
+
+	stp	x0, x1, [sp, #-0x20]!
+	str	x2, [sp, #0x10]
+
+	mov	x5, #0
+0:	ldrb	w3, [x0, x5]
+	ldrb	w4, [x1, x5]
+	add	x5, x5, #1
+	cmp	w3, w4
+	b.ne	1f
+	subs	x2, x2, #1
+	b.ne	0b
+
+1:	ldr	x2, [sp, #0x10]
+	ldp	x0, x1, [sp], #0x20
+	b.ne	barf
+
+2:	ret
+endfunction
+
+// Verify that a ZT vector matches its shadow in memory, else abort
+// Clobbers x0-x3
+function check_zt
+	mov	x3, x30
+
+	ldr	x0, =scratch		// Poison scratch
+	mov	x1, #ZT_B
+	bl	memfill_ae
+
+	ldr	x0, =scratch
+	_str_zt 0
+
+	ldr	x0, =ztref
+	ldr	x1, =scratch
+	mov	x2, #ZT_B
+	mov	x30, x3
+	b	memcmp
+endfunction
+
+// Any SME register modified here can cause corruption in the main
+// thread -- but *only* the locations modified here.
+function irritator_handler
+	// Increment the irritation signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	// Corrupt some random ZT data
+#if 0
+	adr	x0, .text + (irritator_handler - .text) / 16 * 16
+	movi	v0.8b, #1
+	movi	v9.16b, #2
+	movi	v31.8b, #3
+#endif
+
+	ret
+endfunction
+
+function tickle_handler
+	// Increment the signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	ret
+endfunction
+
+function terminate_handler
+	mov	w21, w0
+	mov	x20, x2
+
+	puts	"Terminated by signal "
+	mov	w0, w21
+	bl	putdec
+	puts	", no error, iterations="
+	ldr	x0, [x20, #ucontext_regs + 8 * 22]
+	bl	putdec
+	puts	", signals="
+	ldr	x0, [x20, #ucontext_regs + 8 * 23]
+	bl	putdecn
+
+	mov	x0, #0
+	mov	x8, #__NR_exit
+	svc	#0
+endfunction
+
+// w0: signal number
+// x1: sa_action
+// w2: sa_flags
+// Clobbers x0-x6,x8
+function setsignal
+	str	x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]!
+
+	mov	w4, w0
+	mov	x5, x1
+	mov	w6, w2
+
+	add	x0, sp, #16
+	mov	x1, #sa_sz
+	bl	memclr
+
+	mov	w0, w4
+	add	x1, sp, #16
+	str	w6, [x1, #sa_flags]
+	str	x5, [x1, #sa_handler]
+	mov	x2, #0
+	mov	x3, #sa_mask_sz
+	mov	x8, #__NR_rt_sigaction
+	svc	#0
+
+	cbz	w0, 1f
+
+	puts	"sigaction failure\n"
+	b	.Labort
+
+1:	ldr	x30, [sp], #((sa_sz + 15) / 16 * 16 + 16)
+	ret
+endfunction
+
+// Main program entry point
+.globl _start
+function _start
+	mov	x23, #0		// signal count
+
+	mov	w0, #SIGINT
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, irritator_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	smstart_za
+
+	// Obtain our PID, to ensure test pattern uniqueness between processes
+	mov	x8, #__NR_getpid
+	svc	#0
+	mov	x20, x0
+
+	puts	"PID:\t"
+	mov	x0, x20
+	bl	putdecn
+
+	mov	x22, #0		// generation number, increments per iteration
+.Ltest_loop:
+	mov	x0, x20
+	mov	x1, x22
+	bl	setup_zt
+
+	mov	x8, #__NR_sched_yield	// Encourage preemption
+	svc	#0
+
+	mrs	x0, S3_3_C4_C2_2	// SVCR should have ZA=1,SM=0
+	and	x1, x0, #3
+	cmp	x1, #2
+	b.ne	svcr_barf
+
+	bl	check_zt
+
+	add	x22, x22, #1	// Everything still working
+	b	.Ltest_loop
+
+.Labort:
+	mov	x0, #0
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+endfunction
+
+function barf
+// fpsimd.c acitivty log dump hack
+//	ldr	w0, =0xdeadc0de
+//	mov	w8, #__NR_exit
+//	svc	#0
+// end hack
+	smstop
+	mov	x10, x0	// expected data
+	mov	x11, x1	// actual data
+	mov	x12, x2	// data size
+
+	puts	"Mismatch: PID="
+	mov	x0, x20
+	bl	putdec
+	puts	", iteration="
+	mov	x0, x22
+	bl	putdec
+	puts	"\tExpected ["
+	mov	x0, x10
+	mov	x1, x12
+	bl	dumphex
+	puts	"]\n\tGot      ["
+	mov	x0, x11
+	mov	x1, x12
+	bl	dumphex
+	puts	"]\n"
+
+	mov	x8, #__NR_getpid
+	svc	#0
+// fpsimd.c acitivty log dump hack
+//	ldr	w0, =0xdeadc0de
+//	mov	w8, #__NR_exit
+//	svc	#0
+// ^ end of hack
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+//	mov	x8, #__NR_exit
+//	mov	x1, #1
+//	svc	#0
+endfunction
+
+function svcr_barf
+	mov	x10, x0
+
+	puts	"Bad SVCR: "
+	mov	x0, x10
+	bl	putdecn
+
+	mov	x8, #__NR_exit
+	mov	x1, #1
+	svc	#0
+endfunction

tools/testing/selftests/arm64/signal/.gitignore

@@ -6,4 +6,5 @@ ssve_*
 sve_*
 tpidr2_siginfo
 za_*
+zt_*
 !*.[ch]

tools/testing/selftests/arm64/signal/test_signals.h

@@ -34,6 +34,7 @@ enum {
 	FSVE_BIT,
 	FSME_BIT,
 	FSME_FA64_BIT,
+	FSME2_BIT,
 	FMAX_END
 };
 
@@ -41,6 +42,7 @@ enum {
 #define FEAT_SVE		(1UL << FSVE_BIT)
 #define FEAT_SME		(1UL << FSME_BIT)
 #define FEAT_SME_FA64		(1UL << FSME_FA64_BIT)
+#define FEAT_SME2		(1UL << FSME2_BIT)
 
 /*
  * A descriptor used to describe and configure a test case.

tools/testing/selftests/arm64/signal/test_signals_utils.c

@@ -29,6 +29,7 @@ static char const *const feats_names[FMAX_END] = {
 	" SVE ",
 	" SME ",
 	" FA64 ",
+	" SME2 ",
 };
 
 #define MAX_FEATS_SZ	128
@@ -323,6 +324,8 @@ int test_init(struct tdescr *td)
 			td->feats_supported |= FEAT_SME;
 		if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
 			td->feats_supported |= FEAT_SME_FA64;
+		if (getauxval(AT_HWCAP2) & HWCAP2_SME2)
+			td->feats_supported |= FEAT_SME2;
 		if (feats_ok(td)) {
 			if (td->feats_required & td->feats_supported)
 				fprintf(stderr,

tools/testing/selftests/arm64/signal/testcases/testcases.c

@@ -108,6 +108,26 @@ bool validate_za_context(struct za_context *za, char **err)
 	return true;
 }
 
+bool validate_zt_context(struct zt_context *zt, char **err)
+{
+	if (!zt || !err)
+		return false;
+
+	/* If the context is present there should be at least one register */
+	if (zt->nregs == 0) {
+		*err = "no registers";
+		return false;
+	}
+
+	/* Size should agree with the number of registers */
+	if (zt->head.size != ZT_SIG_CONTEXT_SIZE(zt->nregs)) {
+		*err = "register count does not match size";
+		return false;
+	}
+
+	return true;
+}
+
 bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 {
 	bool terminated = false;
@@ -117,6 +137,7 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 	struct extra_context *extra = NULL;
 	struct sve_context *sve = NULL;
 	struct za_context *za = NULL;
+	struct zt_context *zt = NULL;
 	struct _aarch64_ctx *head =
 		(struct _aarch64_ctx *)uc->uc_mcontext.__reserved;
 	void *extra_data = NULL;
@@ -181,6 +202,13 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			za = (struct za_context *)head;
 			new_flags |= ZA_CTX;
 			break;
+		case ZT_MAGIC:
+			if (flags & ZT_CTX)
+				*err = "Multiple ZT_MAGIC";
+			/* Size is validated in validate_za_context() */
+			zt = (struct zt_context *)head;
+			new_flags |= ZT_CTX;
+			break;
 		case EXTRA_MAGIC:
 			if (flags & EXTRA_CTX)
 				*err = "Multiple EXTRA_MAGIC";
@@ -238,6 +266,9 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 		if (new_flags & ZA_CTX)
 			if (!validate_za_context(za, err))
 				return false;
+		if (new_flags & ZT_CTX)
+			if (!validate_zt_context(zt, err))
+				return false;
 
 		flags |= new_flags;
 
@@ -249,6 +280,11 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 		return false;
 	}
 
+	if (terminated && (flags & ZT_CTX) && !(flags & ZA_CTX)) {
+		*err = "ZT context but no ZA context";
+		return false;
+	}
+
 	return true;
 }
 

tools/testing/selftests/arm64/signal/testcases/testcases.h

@@ -18,6 +18,7 @@
 #define SVE_CTX		(1 << 1)
 #define ZA_CTX		(1 << 2)
 #define EXTRA_CTX	(1 << 3)
+#define ZT_CTX		(1 << 4)
 
 #define KSFT_BAD_MAGIC	0xdeadbeef
 

tools/testing/selftests/arm64/signal/testcases/zt_no_regs.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that using an instruction not supported in streaming mode
+ * traps when in streaming mode.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+int zt_no_regs_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+
+	/*
+	 * Get a signal context which should not have a ZT frame and
+	 * registers in it.
+	 */
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	head = get_header(head, ZT_MAGIC, GET_BUF_RESV_SIZE(context), &offset);
+	if (head) {
+		fprintf(stderr, "Got unexpected ZT context\n");
+		return 1;
+	}
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "ZT register data not present",
+	.descr = "Validate that ZT is not present when ZA is disabled",
+	.feats_required = FEAT_SME2,
+	.timeout = 3,
+	.sanity_disabled = true,
+	.run = zt_no_regs_run,
+};

tools/testing/selftests/arm64/signal/testcases/zt_regs.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that using an instruction not supported in streaming mode
+ * traps when in streaming mode.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+static void enable_za(void)
+{
+	/* smstart za; real data is TODO */
+	asm volatile(".inst 0xd503457f" : : : );
+}
+
+int zt_regs_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct zt_context *zt;
+	char *zeros;
+
+	/*
+	 * Get a signal context which should have a ZT frame and registers
+	 * in it.
+	 */
+	enable_za();
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	head = get_header(head, ZT_MAGIC, GET_BUF_RESV_SIZE(context), &offset);
+	if (!head) {
+		fprintf(stderr, "No ZT context\n");
+		return 1;
+	}
+
+	zt = (struct zt_context *)head;
+	if (zt->nregs == 0) {
+		fprintf(stderr, "Got context with no registers\n");
+		return 1;
+	}
+
+	fprintf(stderr, "Got expected size %u for %d registers\n",
+		head->size, zt->nregs);
+
+	/* We didn't load any data into ZT so it should be all zeros */
+	zeros = malloc(ZT_SIG_REGS_SIZE(zt->nregs));
+	if (!zeros) {
+		fprintf(stderr, "Out of memory, nregs=%u\n", zt->nregs);
+		return 1;
+	}
+	memset(zeros, 0, ZT_SIG_REGS_SIZE(zt->nregs));
+
+	if (memcmp(zeros, (char *)zt + ZT_SIG_REGS_OFFSET,
+		   ZT_SIG_REGS_SIZE(zt->nregs)) != 0) {
+		fprintf(stderr, "ZT data invalid\n");
+		return 1;
+	}
+
+	free(zeros);
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "ZT register data",
+	.descr = "Validate that ZT is present and has data when ZA is enabled",
+	.feats_required = FEAT_SME2,
+	.timeout = 3,
+	.sanity_disabled = true,
+	.run = zt_regs_run,
+};