Merge branch arm64/for-next/sme2 into kvmarm/next

Merge the SME2 branch to fix up a rather annoying conflict due to the
EL2 finalization refactor.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

16 files changed, 1109 insertions, 5 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..6ddf392329c9 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
@@ -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
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
index dd7ebe536d05..9800f9dc6b35 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi.c
+++ b/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]);
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/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c
index f8b2f41aac36..520385fcfede 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;
@@ -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);
 	}
 
 	/*
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/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/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore
index e8d2b57f73ec..b7fbb65183e8 100644
--- a/tools/testing/selftests/arm64/signal/.gitignore
+++ b/tools/testing/selftests/arm64/signal/.gitignore
@@ -5,4 +5,5 @@ sme_*
 ssve_*
 sve_*
 za_*
+zt_*
 !*.[ch]
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..07f518f0e58d 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
@@ -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,
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
index d2eda7b5de26..27d495fa52f8 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;
@@ -177,6 +198,13 @@ 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 +262,9 @@ 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 +276,11 @@ 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/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,
+};