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
  ...

13 files changed, 764 insertions, 12 deletions

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