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

Pull arm64 updates from Catalin Marinas:

 - Support for arm64 SME 2 and 2.1. SME2 introduces a new 512-bit
   architectural register (ZT0, for the look-up table feature) that
   Linux needs to save/restore

 - Include TPIDR2 in the signal context and add the corresponding
   kselftests

 - Perf updates: Arm SPEv1.2 support, HiSilicon uncore PMU updates, ACPI
   support to the Marvell DDR and TAD PMU drivers, reset DTM_PMU_CONFIG
   (ARM CMN) at probe time

 - Support for DYNAMIC_FTRACE_WITH_CALL_OPS on arm64

 - Permit EFI boot with MMU and caches on. Instead of cleaning the
   entire loaded kernel image to the PoC and disabling the MMU and
   caches before branching to the kernel bare metal entry point, leave
   the MMU and caches enabled and rely on EFI's cacheable 1:1 mapping of
   all of system RAM to populate the initial page tables

 - Expose the AArch32 (compat) ELF_HWCAP features to user in an arm64
   kernel (the arm32 kernel only defines the values)

 - Harden the arm64 shadow call stack pointer handling: stash the shadow
   stack pointer in the task struct on interrupt, load it directly from
   this structure

 - Signal handling cleanups to remove redundant validation of size
   information and avoid reading the same data from userspace twice

 - Refactor the hwcap macros to make use of the automatically generated
   ID registers. It should make new hwcaps writing less error prone

 - Further arm64 sysreg conversion and some fixes

 - arm64 kselftest fixes and improvements

 - Pointer authentication cleanups: don't sign leaf functions, unify
   asm-arch manipulation

 - Pseudo-NMI code generation optimisations

 - Minor fixes for SME and TPIDR2 handling

 - Miscellaneous updates: ARCH_FORCE_MAX_ORDER is now selectable,
   replace strtobool() to kstrtobool() in the cpufeature.c code, apply
   dynamic shadow call stack in two passes, intercept pfn changes in
   set_pte_at() without the required break-before-make sequence, attempt
   to dump all instructions on unhandled kernel faults

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (130 commits)
  arm64: fix .idmap.text assertion for large kernels
  kselftest/arm64: Don't require FA64 for streaming SVE+ZA tests
  kselftest/arm64: Copy whole EXTRA context
  arm64: kprobes: Drop ID map text from kprobes blacklist
  perf: arm_spe: Print the version of SPE detected
  perf: arm_spe: Add support for SPEv1.2 inverted event filtering
  perf: Add perf_event_attr::config3
  arm64/sme: Fix __finalise_el2 SMEver check
  drivers/perf: fsl_imx8_ddr_perf: Remove set-but-not-used variable
  arm64/signal: Only read new data when parsing the ZT context
  arm64/signal: Only read new data when parsing the ZA context
  arm64/signal: Only read new data when parsing the SVE context
  arm64/signal: Avoid rereading context frame sizes
  arm64/signal: Make interface for restore_fpsimd_context() consistent
  arm64/signal: Remove redundant size validation from parse_user_sigframe()
  arm64/signal: Don't redundantly verify FPSIMD magic
  arm64/cpufeature: Use helper macros to specify hwcaps
  arm64/cpufeature: Always use symbolic name for feature value in hwcaps
  arm64/sysreg: Initial unsigned annotations for ID registers
  arm64/sysreg: Initial annotation of signed ID registers
  ...

31 files changed, 1535 insertions, 111 deletions

diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 9f255bc5f31c..93333a90bf3a 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/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 */
@@ -159,6 +231,49 @@ static const struct hwcap_data {
 		.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,
 		.hwcap_bit = HWCAP_SVE,
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
index acd5e9f3bc0b..df3230fdac39 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
+++ b/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
@@ -92,8 +124,11 @@ do_syscall:
 	str	x29, [x2], #8		// FP
 	str	x30, [x2], #8		// LR
 
-	// Load FPRs if we're not doing SVE
+	// Load FPRs if we're not doing neither SVE nor streaming SVE
 	cbnz	x0, 1f
+	ldr	x2, =svcr_in
+	tbnz	x2, #SVCR_SM_SHIFT, 1f
+
 	ldr	x2, =fpr_in
 	ldp	q0, q1, [x2]
 	ldp	q2, q3, [x2, #16 * 2]
@@ -111,10 +146,11 @@ do_syscall:
 	ldp	q26, q27, [x2, #16 * 26]
 	ldp	q28, q29, [x2, #16 * 28]
 	ldp	q30, q31, [x2, #16 * 30]
+
+	b	2f
 1:
 
 	// Load the SVE registers if we're doing SVE/SME
-	cbz	x0, 1f
 
 	ldr	x2, =z_in
 	ldr	z0, [x2, #0, MUL VL]
@@ -155,9 +191,9 @@ do_syscall:
 	ldr	x2, =ffr_in
 	ldr	p0, [x2]
 	ldr	x2, [x2, #0]
-	cbz	x2, 2f
+	cbz	x2, 1f
 	wrffr	p0.b
-2:
+1:
 
 	ldr	x2, =p_in
 	ldr	p0, [x2, #0, MUL VL]
@@ -176,7 +212,7 @@ do_syscall:
 	ldr	p13, [x2, #13, MUL VL]
 	ldr	p14, [x2, #14, MUL VL]
 	ldr	p15, [x2, #15, MUL VL]
-1:
+2:
 
 	// Do the syscall
 	svc	#0
@@ -235,6 +271,15 @@ 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
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
index dd7ebe536d05..18cc123e2347 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi.c
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -20,10 +20,13 @@
 
 #include "syscall-abi.h"
 
-#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
-
 static int default_sme_vl;
 
+static int sve_vl_count;
+static unsigned int sve_vls[SVE_VQ_MAX];
+static int sme_vl_count;
+static unsigned int sme_vls[SVE_VQ_MAX];
+
 extern void do_syscall(int sve_vl, int sme_vl);
 
 static void fill_random(void *buf, size_t size)
@@ -83,6 +86,7 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t s
 #define NUM_FPR 32
 uint64_t fpr_in[NUM_FPR * 2];
 uint64_t fpr_out[NUM_FPR * 2];
+uint64_t fpr_zero[NUM_FPR * 2];
 
 static void setup_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		      uint64_t svcr)
@@ -97,7 +101,7 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	int errors = 0;
 	int i;
 
-	if (!sve_vl) {
+	if (!sve_vl && !(svcr & SVCR_SM_MASK)) {
 		for (i = 0; i < ARRAY_SIZE(fpr_in); i++) {
 			if (fpr_in[i] != fpr_out[i]) {
 				ksft_print_msg("%s Q%d/%d mismatch %llx != %llx\n",
@@ -109,6 +113,18 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		}
 	}
 
+	/*
+	 * In streaming mode the whole register set should be cleared
+	 * by the transition out of streaming mode.
+	 */
+	if (svcr & SVCR_SM_MASK) {
+		if (memcmp(fpr_zero, fpr_out, sizeof(fpr_out)) != 0) {
+			ksft_print_msg("%s FPSIMD registers non-zero exiting SM\n",
+				       cfg->name);
+			errors++;
+		}
+	}
+
 	return errors;
 }
 
@@ -284,8 +300,8 @@ static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	return errors;
 }
 
-uint8_t za_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
-uint8_t za_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+uint8_t za_in[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)];
+uint8_t za_out[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)];
 
 static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		     uint64_t svcr)
@@ -311,6 +327,35 @@ 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 +379,7 @@ 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,
@@ -355,73 +401,78 @@ static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 
 static void test_one_syscall(struct syscall_cfg *cfg)
 {
-	int sve_vq, sve_vl;
-	int sme_vq, sme_vl;
+	int sve, sme;
+	int ret;
 
 	/* FPSIMD only case */
 	ksft_test_result(do_test(cfg, 0, default_sme_vl, 0),
 			 "%s FPSIMD\n", cfg->name);
 
-	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
-		return;
-
-	for (sve_vq = SVE_VQ_MAX; sve_vq > 0; --sve_vq) {
-		sve_vl = prctl(PR_SVE_SET_VL, sve_vq * 16);
-		if (sve_vl == -1)
+	for (sve = 0; sve < sve_vl_count; sve++) {
+		ret = prctl(PR_SVE_SET_VL, sve_vls[sve]);
+		if (ret == -1)
 			ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
 					   strerror(errno), errno);
 
-		sve_vl &= PR_SVE_VL_LEN_MASK;
-
-		if (sve_vq != sve_vq_from_vl(sve_vl))
-			sve_vq = sve_vq_from_vl(sve_vl);
-
-		ksft_test_result(do_test(cfg, sve_vl, default_sme_vl, 0),
-				 "%s SVE VL %d\n", cfg->name, sve_vl);
-
-		if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
-			continue;
+		ksft_test_result(do_test(cfg, sve_vls[sve], default_sme_vl, 0),
+				 "%s SVE VL %d\n", cfg->name, sve_vls[sve]);
 
-		for (sme_vq = SVE_VQ_MAX; sme_vq > 0; --sme_vq) {
-			sme_vl = prctl(PR_SME_SET_VL, sme_vq * 16);
-			if (sme_vl == -1)
+		for (sme = 0; sme < sme_vl_count; sme++) {
+			ret = prctl(PR_SME_SET_VL, sme_vls[sme]);
+			if (ret == -1)
 				ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
 						   strerror(errno), errno);
 
-			sme_vl &= PR_SME_VL_LEN_MASK;
-
-			if (sme_vq != sve_vq_from_vl(sme_vl))
-				sme_vq = sve_vq_from_vl(sme_vl);
-
-			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+			ksft_test_result(do_test(cfg, sve_vls[sve],
+						 sme_vls[sme],
 						 SVCR_ZA_MASK | SVCR_SM_MASK),
 					 "%s SVE VL %d/SME VL %d SM+ZA\n",
-					 cfg->name, sve_vl, sme_vl);
-			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
-						 SVCR_SM_MASK),
+					 cfg->name, sve_vls[sve],
+					 sme_vls[sme]);
+			ksft_test_result(do_test(cfg, sve_vls[sve],
+						 sme_vls[sme], SVCR_SM_MASK),
 					 "%s SVE VL %d/SME VL %d SM\n",
-					 cfg->name, sve_vl, sme_vl);
-			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
-						 SVCR_ZA_MASK),
+					 cfg->name, sve_vls[sve],
+					 sme_vls[sme]);
+			ksft_test_result(do_test(cfg, sve_vls[sve],
+						 sme_vls[sme], SVCR_ZA_MASK),
 					 "%s SVE VL %d/SME VL %d ZA\n",
-					 cfg->name, sve_vl, sme_vl);
+					 cfg->name, sve_vls[sve],
+					 sme_vls[sme]);
 		}
 	}
+
+	for (sme = 0; sme < sme_vl_count; sme++) {
+		ret = prctl(PR_SME_SET_VL, sme_vls[sme]);
+		if (ret == -1)
+			ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
+						   strerror(errno), errno);
+
+		ksft_test_result(do_test(cfg, 0, sme_vls[sme],
+					 SVCR_ZA_MASK | SVCR_SM_MASK),
+				 "%s SME VL %d SM+ZA\n",
+				 cfg->name, sme_vls[sme]);
+		ksft_test_result(do_test(cfg, 0, sme_vls[sme], SVCR_SM_MASK),
+				 "%s SME VL %d SM\n",
+				 cfg->name, sme_vls[sme]);
+		ksft_test_result(do_test(cfg, 0, sme_vls[sme], SVCR_ZA_MASK),
+				 "%s SME VL %d ZA\n",
+				 cfg->name, sme_vls[sme]);
+	}
 }
 
-int sve_count_vls(void)
+void sve_count_vls(void)
 {
 	unsigned int vq;
-	int vl_count = 0;
 	int vl;
 
 	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
-		return 0;
+		return;
 
 	/*
 	 * Enumerate up to SVE_VQ_MAX vector lengths
 	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+	for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) {
 		vl = prctl(PR_SVE_SET_VL, vq * 16);
 		if (vl == -1)
 			ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
@@ -432,28 +483,22 @@ int sve_count_vls(void)
 		if (vq != sve_vq_from_vl(vl))
 			vq = sve_vq_from_vl(vl);
 
-		vl_count++;
+		sve_vls[sve_vl_count++] = vl;
 	}
-
-	return vl_count;
 }
 
-int sme_count_vls(void)
+void sme_count_vls(void)
 {
 	unsigned int vq;
-	int vl_count = 0;
 	int vl;
 
 	if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
-		return 0;
-
-	/* Ensure we configure a SME VL, used to flag if SVCR is set */
-	default_sme_vl = 16;
+		return;
 
 	/*
 	 * Enumerate up to SVE_VQ_MAX vector lengths
 	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+	for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) {
 		vl = prctl(PR_SME_SET_VL, vq * 16);
 		if (vl == -1)
 			ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
@@ -461,31 +506,47 @@ int sme_count_vls(void)
 
 		vl &= PR_SME_VL_LEN_MASK;
 
+		/* Found lowest VL */
+		if (sve_vq_from_vl(vl) > vq)
+			break;
+
 		if (vq != sve_vq_from_vl(vl))
 			vq = sve_vq_from_vl(vl);
 
-		vl_count++;
+		sme_vls[sme_vl_count++] = vl;
 	}
 
-	return vl_count;
+	/* Ensure we configure a SME VL, used to flag if SVCR is set */
+	default_sme_vl = sme_vls[0];
 }
 
 int main(void)
 {
 	int i;
 	int tests = 1;  /* FPSIMD */
+	int sme_ver;
 
 	srandom(getpid());
 
 	ksft_print_header();
-	tests += sve_count_vls();
-	tests += (sve_count_vls() * sme_count_vls()) * 3;
+
+	sve_count_vls();
+	sme_count_vls();
+
+	tests += sve_vl_count;
+	tests += sme_vl_count * 3;
+	tests += (sve_vl_count * sme_vl_count) * 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]);
diff --git a/tools/testing/selftests/arm64/bti/test.c b/tools/testing/selftests/arm64/bti/test.c
index 67b77ab83c20..2cd8dcee5aec 100644
--- a/tools/testing/selftests/arm64/bti/test.c
+++ b/tools/testing/selftests/arm64/bti/test.c
@@ -6,6 +6,7 @@
 
 #include "system.h"
 
+#include <stdbool.h>
 #include <stddef.h>
 #include <linux/errno.h>
 #include <linux/auxvec.h>
@@ -101,7 +102,8 @@ static void handler(int n, siginfo_t *si __always_unused,
 	uc->uc_mcontext.pstate &= ~PSR_BTYPE_MASK;
 }
 
-static int skip_all;
+/* Does the system have BTI? */
+static bool have_bti;
 
 static void __do_test(void (*trampoline)(void (*)(void)),
 		      void (*fn)(void),
@@ -109,19 +111,11 @@ static void __do_test(void (*trampoline)(void (*)(void)),
 		      const char *name,
 		      int expect_sigill)
 {
-	if (skip_all) {
-		test_skipped++;
-		putstr("ok ");
-		putnum(test_num);
-		putstr(" ");
-		puttestname(name, trampoline_name);
-		putstr(" # SKIP\n");
-
-		return;
-	}
-
-	/* Branch Target exceptions should only happen in BTI binaries: */
-	if (!BTI)
+	/*
+	 * Branch Target exceptions should only happen for BTI
+	 * binaries running on a system with BTI:
+	 */
+	if (!BTI || !have_bti)
 		expect_sigill = 0;
 
 	sigill_expected = expect_sigill;
@@ -199,9 +193,10 @@ void start(int *argcp)
 		putstr("# HWCAP2_BTI present\n");
 		if (!(hwcap & HWCAP_PACA))
 			putstr("# Bad hardware?  Expect problems.\n");
+		have_bti = true;
 	} else {
 		putstr("# HWCAP2_BTI not present\n");
-		skip_all = 1;
+		have_bti = false;
 	}
 
 	putstr("# Test binary");
diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index df79d29664a1..ebc86757bdd8 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -12,3 +12,5 @@ vlset
 za-fork
 za-ptrace
 za-test
+zt-ptrace
+zt-test
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index 36db61358ed5..50a70220ba6c 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/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
diff --git a/tools/testing/selftests/arm64/fp/assembler.h b/tools/testing/selftests/arm64/fp/assembler.h
index 90bd433d2665..9b38a0da407d 100644
--- a/tools/testing/selftests/arm64/fp/assembler.h
+++ b/tools/testing/selftests/arm64/fp/assembler.h
@@ -57,7 +57,7 @@ endfunction
 // Utility macro to print a literal string
 // Clobbers x0-x4,x8
 .macro puts string
-	.pushsection .rodata.str1.1, "aMS", 1
+	.pushsection .rodata.str1.1, "aMS", @progbits, 1
 .L__puts_literal\@: .string "\string"
 	.popsection
 
diff --git a/tools/testing/selftests/arm64/fp/fp-pidbench.S b/tools/testing/selftests/arm64/fp/fp-pidbench.S
index 16a436389bfc..73830f6bc99b 100644
--- a/tools/testing/selftests/arm64/fp/fp-pidbench.S
+++ b/tools/testing/selftests/arm64/fp/fp-pidbench.S
@@ -31,7 +31,6 @@
 // Main program entry point
 .globl _start
 function _start
-_start:
 	puts	"Iterations per test: "
 	mov	x20, #10000
 	lsl	x20, x20, #8
diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c
index f8b2f41aac36..dd31647b00a2 100644
--- a/tools/testing/selftests/arm64/fp/fp-stress.c
+++ b/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;
@@ -377,7 +390,7 @@ static void probe_vls(int vls[], int *vl_count, int set_vl)
 
 	*vl_count = 0;
 
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+	for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) {
 		vl = prctl(set_vl, vq * 16);
 		if (vl == -1)
 			ksft_exit_fail_msg("SET_VL failed: %s (%d)\n",
@@ -385,6 +398,9 @@ static void probe_vls(int vls[], int *vl_count, int set_vl)
 
 		vl &= PR_SVE_VL_LEN_MASK;
 
+		if (*vl_count && (vl == vls[*vl_count - 1]))
+			break;
+
 		vq = sve_vq_from_vl(vl);
 
 		vls[*vl_count] = vl;
@@ -426,6 +442,7 @@ 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 +475,13 @@ 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 +492,9 @@ 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 +552,9 @@ 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);
 	}
 
 	/*
diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
index 918d04885a33..8b960d01ed2e 100644
--- a/tools/testing/selftests/arm64/fp/fpsimd-test.S
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -215,7 +215,6 @@ endfunction
 // Main program entry point
 .globl _start
 function _start
-_start:
 	mov	x23, #0		// signal count
 
 	mov	w0, #SIGINT
diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h
index 7191e53ca1c0..9292bba5400b 100644
--- a/tools/testing/selftests/arm64/fp/sme-inst.h
+++ b/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
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index 8c4847977583..6d61992fe8a0 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -30,6 +30,16 @@
 #define NT_ARM_SSVE 0x40b
 #endif
 
+/*
+ * The architecture defines the maximum VQ as 16 but for extensibility
+ * the kernel specifies the SVE_VQ_MAX as 512 resulting in us running
+ * a *lot* more tests than are useful if we use it.  Until the
+ * architecture is extended let's limit our coverage to what is
+ * currently allowed, plus one extra to ensure we cover constraining
+ * the VL as expected.
+ */
+#define TEST_VQ_MAX 17
+
 struct vec_type {
 	const char *name;
 	unsigned long hwcap_type;
@@ -55,7 +65,7 @@ static const struct vec_type vec_types[] = {
 	},
 };
 
-#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 4)
+#define VL_TESTS (((TEST_VQ_MAX - SVE_VQ_MIN) + 1) * 4)
 #define FLAG_TESTS 2
 #define FPSIMD_TESTS 2
 
@@ -689,7 +699,7 @@ static int do_parent(pid_t child)
 		}
 
 		/* Step through every possible VQ */
-		for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+		for (vq = SVE_VQ_MIN; vq <= TEST_VQ_MAX; vq++) {
 			vl = sve_vl_from_vq(vq);
 
 			/* First, try to set this vector length */
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 2a18cb4c528c..4328895dfc87 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -378,7 +378,6 @@ endfunction
 // Main program entry point
 .globl _start
 function _start
-_start:
 	mov	x23, #0		// Irritation signal count
 
 	mov	w0, #SIGINT
diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c
index bf6158654056..ac27d87396fc 100644
--- a/tools/testing/selftests/arm64/fp/za-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/za-ptrace.c
@@ -25,7 +25,17 @@
 #define NT_ARM_ZA 0x40c
 #endif
 
-#define EXPECTED_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
+/*
+ * The architecture defines the maximum VQ as 16 but for extensibility
+ * the kernel specifies the SVE_VQ_MAX as 512 resulting in us running
+ * a *lot* more tests than are useful if we use it.  Until the
+ * architecture is extended let's limit our coverage to what is
+ * currently allowed, plus one extra to ensure we cover constraining
+ * the VL as expected.
+ */
+#define TEST_VQ_MAX 17
+
+#define EXPECTED_TESTS (((TEST_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
 
 static void fill_buf(char *buf, size_t size)
 {
@@ -301,7 +311,7 @@ static int do_parent(pid_t child)
 	ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
 
 	/* Step through every possible VQ */
-	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+	for (vq = SVE_VQ_MIN; vq <= TEST_VQ_MAX; vq++) {
 		vl = sve_vl_from_vq(vq);
 
 		/* First, try to set this vector length */
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
index 53c54af65704..9dcd70911397 100644
--- a/tools/testing/selftests/arm64/fp/za-test.S
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -231,7 +231,6 @@ endfunction
 // Main program entry point
 .globl _start
 function _start
-_start:
 	mov	x23, #0		// signal count
 
 	mov	w0, #SIGINT
diff --git a/tools/testing/selftests/arm64/fp/zt-ptrace.c b/tools/testing/selftests/arm64/fp/zt-ptrace.c
new file mode 100644
index 000000000000..996d9614a131
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/zt-ptrace.c
@@ -0,0 +1,365 @@
+// 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;
+}
diff --git a/tools/testing/selftests/arm64/fp/zt-test.S b/tools/testing/selftests/arm64/fp/zt-test.S
new file mode 100644
index 000000000000..d63286397638
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/zt-test.S
@@ -0,0 +1,316 @@
+// 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
diff --git a/tools/testing/selftests/arm64/mte/Makefile b/tools/testing/selftests/arm64/mte/Makefile
index 037046f5784e..0d7ac3db8390 100644
--- a/tools/testing/selftests/arm64/mte/Makefile
+++ b/tools/testing/selftests/arm64/mte/Makefile
@@ -1,24 +1,33 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (C) 2020 ARM Limited
 
-# preserve CC value from top level Makefile
-ifeq ($(CC),cc)
-CC := $(CROSS_COMPILE)gcc
-endif
-
 CFLAGS += -std=gnu99 -I. -pthread
 LDFLAGS += -pthread
 SRCS := $(filter-out mte_common_util.c,$(wildcard *.c))
 PROGS := $(patsubst %.c,%,$(SRCS))
 
+ifeq ($(LLVM),)
+# For GCC check that the toolchain has MTE support.
+
+# preserve CC value from top level Makefile
+ifeq ($(CC),cc)
+CC := $(CROSS_COMPILE)gcc
+endif
+
 #check if the compiler works well
 mte_cc_support := $(shell if ($(CC) $(CFLAGS) -march=armv8.5-a+memtag -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi)
 
+else
+
+# All supported clang versions also support MTE.
+mte_cc_support := 1
+
+endif
+
 ifeq ($(mte_cc_support),1)
 # Generated binaries to be installed by top KSFT script
 TEST_GEN_PROGS := $(PROGS)
 
-# Get Kernel headers installed and use them.
 else
     $(warning compiler "$(CC)" does not support the ARMv8.5 MTE extension.)
     $(warning test program "mte" will not be created.)
diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore
index e8d2b57f73ec..8ab4c86837fd 100644
--- a/tools/testing/selftests/arm64/signal/.gitignore
+++ b/tools/testing/selftests/arm64/signal/.gitignore
@@ -4,5 +4,7 @@ fake_sigreturn_*
 sme_*
 ssve_*
 sve_*
+tpidr2_siginfo
 za_*
+zt_*
 !*.[ch]
diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile
index be7520a863b0..8f5febaf1a9a 100644
--- a/tools/testing/selftests/arm64/signal/Makefile
+++ b/tools/testing/selftests/arm64/signal/Makefile
@@ -22,6 +22,10 @@ $(TEST_GEN_PROGS): $(PROGS)
 
 # Common test-unit targets to build common-layout test-cases executables
 # Needs secondary expansion to properly include the testcase c-file in pre-reqs
+COMMON_SOURCES := test_signals.c test_signals_utils.c testcases/testcases.c \
+	signals.S
+COMMON_HEADERS := test_signals.h test_signals_utils.h testcases/testcases.h
+
 .SECONDEXPANSION:
-$(PROGS): test_signals.c test_signals_utils.c testcases/testcases.c signals.S $$@.c test_signals.h test_signals_utils.h testcases/testcases.h
-	$(CC) $(CFLAGS) $^ -o $@
+$(PROGS): $$@.c ${COMMON_SOURCES} ${COMMON_HEADERS}
+	$(CC) $(CFLAGS) ${@}.c ${COMMON_SOURCES} -o $@
diff --git a/tools/testing/selftests/arm64/signal/test_signals.c b/tools/testing/selftests/arm64/signal/test_signals.c
index 416b1ff43199..00051b40d71e 100644
--- a/tools/testing/selftests/arm64/signal/test_signals.c
+++ b/tools/testing/selftests/arm64/signal/test_signals.c
@@ -12,12 +12,10 @@
 #include "test_signals.h"
 #include "test_signals_utils.h"
 
-struct tdescr *current;
+struct tdescr *current = &tde;
 
 int main(int argc, char *argv[])
 {
-	current = &tde;
-
 	ksft_print_msg("%s :: %s\n", current->name, current->descr);
 	if (test_setup(current) && test_init(current)) {
 		test_run(current);
diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h
index 0c645834ddc3..1e6273d81575 100644
--- a/tools/testing/selftests/arm64/signal/test_signals.h
+++ b/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.
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index 308e229e58ab..40be8443949d 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/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
@@ -192,8 +193,10 @@ static bool handle_signal_copyctx(struct tdescr *td,
 		 * in the copy, this was previously validated in
 		 * ASSERT_GOOD_CONTEXT().
 		 */
-		to_copy = offset + sizeof(struct extra_context) + 16 +
-			extra->size;
+		to_copy = __builtin_offsetof(ucontext_t,
+					     uc_mcontext.__reserved);
+		to_copy += offset + sizeof(struct extra_context) + 16;
+		to_copy += extra->size;
 		copied_extra = (struct extra_context *)&(td->live_uc->uc_mcontext.__reserved[offset]);
 	} else {
 		copied_extra = NULL;
@@ -323,6 +326,8 @@ 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,
diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
index d0a178945b1a..3d37daafcff5 100644
--- a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
@@ -34,6 +34,10 @@ static bool sme_get_vls(struct tdescr *td)
 
 		vl &= PR_SME_VL_LEN_MASK;
 
+		/* Did we find the lowest supported VL? */
+		if (vq < sve_vq_from_vl(vl))
+			break;
+
 		/* Skip missing VLs */
 		vq = sve_vq_from_vl(vl);
 
@@ -92,6 +96,11 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 		return 1;
 	}
 
+	if (!(ssve->flags & SVE_SIG_FLAG_SM)) {
+		fprintf(stderr, "SVE_SIG_FLAG_SM not set in SVE record\n");
+		return 1;
+	}
+
 	/* The actual size validation is done in get_current_context() */
 	fprintf(stderr, "Got expected size %u and VL %d\n",
 		head->size, ssve->vl);
@@ -116,12 +125,7 @@ static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
 struct tdescr tde = {
 	.name = "Streaming SVE registers",
 	.descr = "Check that we get the right Streaming SVE registers reported",
-	/*
-	 * We shouldn't require FA64 but things like memset() used in the
-	 * helpers might use unsupported instructions so for now disable
-	 * the test unless we've got the full instruction set.
-	 */
-	.feats_required = FEAT_SME | FEAT_SME_FA64,
+	.feats_required = FEAT_SME,
 	.timeout = 3,
 	.init = sme_get_vls,
 	.run = sme_regs,
diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c
new file mode 100644
index 000000000000..9dc5f128bbc0
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that both the streaming SVE and ZA register context in
+ * signal frames is set up as expected when enabled simultaneously.
+ */
+
+#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 unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls = 0;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+	int vq, vl;
+
+	/*
+	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 */
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(PR_SME_SET_VL, vq * 16);
+		if (vl == -1)
+			return false;
+
+		vl &= PR_SME_VL_LEN_MASK;
+
+		/* Did we find the lowest supported VL? */
+		if (vq < sve_vq_from_vl(vl))
+			break;
+
+		/* Skip missing VLs */
+		vq = sve_vq_from_vl(vl);
+
+		vls[nvls++] = vl;
+	}
+
+	/* We need at least one VL */
+	if (nvls < 1) {
+		fprintf(stderr, "Only %d VL supported\n", nvls);
+		return false;
+	}
+
+	return true;
+}
+
+static void setup_regs(void)
+{
+	/* smstart sm; real data is TODO */
+	asm volatile(".inst 0xd503437f" : : : );
+
+	/* smstart za; real data is TODO */
+	asm volatile(".inst 0xd503457f" : : : );
+}
+
+static char zeros[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)];
+
+static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
+			 unsigned int vl)
+{
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct _aarch64_ctx *regs;
+	struct sve_context *ssve;
+	struct za_context *za;
+	int ret;
+
+	fprintf(stderr, "Testing VL %d\n", vl);
+
+	ret = prctl(PR_SME_SET_VL, vl);
+	if (ret != vl) {
+		fprintf(stderr, "Failed to set VL, got %d\n", ret);
+		return 1;
+	}
+
+	/*
+	 * Get a signal context which should have the SVE and ZA
+	 * frames in it.
+	 */
+	setup_regs();
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	regs = get_header(head, SVE_MAGIC, GET_BUF_RESV_SIZE(context),
+			  &offset);
+	if (!regs) {
+		fprintf(stderr, "No SVE context\n");
+		return 1;
+	}
+
+	ssve = (struct sve_context *)regs;
+	if (ssve->vl != vl) {
+		fprintf(stderr, "Got SSVE VL %d, expected %d\n", ssve->vl, vl);
+		return 1;
+	}
+
+	if (!(ssve->flags & SVE_SIG_FLAG_SM)) {
+		fprintf(stderr, "SVE_SIG_FLAG_SM not set in SVE record\n");
+		return 1;
+	}
+
+	fprintf(stderr, "Got expected SSVE size %u and VL %d\n",
+		regs->size, ssve->vl);
+
+	regs = get_header(head, ZA_MAGIC, GET_BUF_RESV_SIZE(context),
+			  &offset);
+	if (!regs) {
+		fprintf(stderr, "No ZA context\n");
+		return 1;
+	}
+
+	za = (struct za_context *)regs;
+	if (za->vl != vl) {
+		fprintf(stderr, "Got ZA VL %d, expected %d\n", za->vl, vl);
+		return 1;
+	}
+
+	fprintf(stderr, "Got expected ZA size %u and VL %d\n",
+		regs->size, za->vl);
+
+	/* We didn't load any data into ZA so it should be all zeros */
+	if (memcmp(zeros, (char *)za + ZA_SIG_REGS_OFFSET,
+		   ZA_SIG_REGS_SIZE(sve_vq_from_vl(za->vl))) != 0) {
+		fprintf(stderr, "ZA data invalid\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	int i;
+
+	for (i = 0; i < nvls; i++) {
+		if (do_one_sme_vl(td, si, uc, vls[i]))
+			return 1;
+	}
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "Streaming SVE registers",
+	.descr = "Check that we get the right Streaming SVE registers reported",
+	.feats_required = FEAT_SME,
+	.timeout = 3,
+	.init = sme_get_vls,
+	.run = sme_regs,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
index d2eda7b5de26..9f580b55b388 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.c
+++ b/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;
@@ -163,6 +184,10 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			if (head->size != sizeof(struct esr_context))
 				*err = "Bad size for esr_context";
 			break;
+		case TPIDR2_MAGIC:
+			if (head->size != sizeof(struct tpidr2_context))
+				*err = "Bad size for tpidr2_context";
+			break;
 		case SVE_MAGIC:
 			if (flags & SVE_CTX)
 				*err = "Multiple SVE_MAGIC";
@@ -177,6 +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";
@@ -234,6 +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;
 
@@ -245,6 +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;
 }
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h
index 040afded0b76..a08ab0d6207a 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.h
+++ b/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
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c b/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c
new file mode 100644
index 000000000000..6a2c82bf7ead
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 ARM Limited
+ *
+ * Verify that the TPIDR2 register context in signal frames is set up as
+ * expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+#include <asm/sigcontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+#define SYS_TPIDR2 "S3_3_C13_C0_5"
+
+static uint64_t get_tpidr2(void)
+{
+	uint64_t val;
+
+	asm volatile (
+		"mrs	%0, " SYS_TPIDR2 "\n"
+		: "=r"(val)
+		:
+		: "cc");
+
+	return val;
+}
+
+int tpidr2_present(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct tpidr2_context *tpidr2_ctx;
+	size_t offset;
+	bool in_sigframe;
+	bool have_sme;
+	__u64 orig_tpidr2;
+
+	have_sme = getauxval(AT_HWCAP2) & HWCAP2_SME;
+	if (have_sme)
+		orig_tpidr2 = get_tpidr2();
+
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	tpidr2_ctx = (struct tpidr2_context *)
+		get_header(head, TPIDR2_MAGIC, td->live_sz, &offset);
+
+	in_sigframe = tpidr2_ctx != NULL;
+
+	fprintf(stderr, "TPIDR2 sigframe %s on system %s SME\n",
+		in_sigframe ? "present" : "absent",
+		have_sme ? "with" : "without");
+
+	td->pass = (in_sigframe == have_sme);
+
+	/*
+	 * Check that the value we read back was the one present at
+	 * the time that the signal was triggered.  TPIDR2 is owned by
+	 * libc so we can't safely choose the value and it is possible
+	 * that we may need to revisit this in future if something
+	 * starts deciding to set a new TPIDR2 between us reading and
+	 * the signal.
+	 */
+	if (have_sme && tpidr2_ctx) {
+		if (tpidr2_ctx->tpidr2 != orig_tpidr2) {
+			fprintf(stderr, "TPIDR2 in frame is %llx, was %llx\n",
+				tpidr2_ctx->tpidr2, orig_tpidr2);
+			td->pass = false;
+		}
+	}
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "TPIDR2",
+	.descr = "Validate that TPIDR2 is present as expected",
+	.timeout = 3,
+	.run = tpidr2_present,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
index ea45acb115d5..174ad6656696 100644
--- a/tools/testing/selftests/arm64/signal/testcases/za_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
@@ -34,6 +34,10 @@ static bool sme_get_vls(struct tdescr *td)
 
 		vl &= PR_SME_VL_LEN_MASK;
 
+		/* Did we find the lowest supported VL? */
+		if (vq < sve_vq_from_vl(vl))
+			break;
+
 		/* Skip missing VLs */
 		vq = sve_vq_from_vl(vl);
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/zt_no_regs.c b/tools/testing/selftests/arm64/signal/testcases/zt_no_regs.c
new file mode 100644
index 000000000000..34f69bcf821e
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/zt_no_regs.c
@@ -0,0 +1,51 @@
+// 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,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/zt_regs.c b/tools/testing/selftests/arm64/signal/testcases/zt_regs.c
new file mode 100644
index 000000000000..e1eb4d5c027a
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/zt_regs.c
@@ -0,0 +1,85 @@
+// 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,
+};