Adding upstream version 6.1.76.upstream/6.1.76

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

28 files changed, 4897 insertions, 0 deletions

diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
new file mode 100644
index 000000000..df79d2966
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -0,0 +1,14 @@
+fp-pidbench
+fp-stress
+fpsimd-test
+rdvl-sme
+rdvl-sve
+sve-probe-vls
+sve-ptrace
+sve-test
+ssve-test
+vec-syscfg
+vlset
+za-fork
+za-ptrace
+za-test
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
new file mode 100644
index 000000000..932ec8792
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# A proper top_srcdir is needed by KSFT(lib.mk)
+top_srcdir = $(realpath ../../../../../)
+
+CFLAGS += $(KHDR_INCLUDES)
+
+TEST_GEN_PROGS := fp-stress \
+	sve-ptrace sve-probe-vls \
+	vec-syscfg \
+	za-fork za-ptrace
+TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
+	rdvl-sme rdvl-sve \
+	sve-test \
+	ssve-test \
+	za-test \
+	vlset
+TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress
+
+EXTRA_CLEAN += $(OUTPUT)/asm-utils.o $(OUTPUT)/rdvl.o $(OUTPUT)/za-fork-asm.o
+
+# Build with nolibc to avoid effects due to libc's clone() support
+$(OUTPUT)/fp-pidbench: fp-pidbench.S $(OUTPUT)/asm-utils.o
+	$(CC) -nostdlib $^ -o $@
+$(OUTPUT)/fpsimd-test: fpsimd-test.S $(OUTPUT)/asm-utils.o
+	$(CC) -nostdlib $^ -o $@
+$(OUTPUT)/rdvl-sve: rdvl-sve.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/rdvl-sme: rdvl-sme.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/sve-ptrace: sve-ptrace.c
+$(OUTPUT)/sve-probe-vls: sve-probe-vls.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/sve-test: sve-test.S $(OUTPUT)/asm-utils.o
+	$(CC) -nostdlib $^ -o $@
+$(OUTPUT)/ssve-test: sve-test.S $(OUTPUT)/asm-utils.o
+	$(CC) -DSSVE -nostdlib $^ -o $@
+$(OUTPUT)/vec-syscfg: vec-syscfg.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/vlset: vlset.c
+$(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o
+	$(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+		-include ../../../../include/nolibc/nolibc.h \
+		-static -ffreestanding -Wall $^ -o $@
+$(OUTPUT)/za-ptrace: za-ptrace.c
+$(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o
+	$(CC) -nostdlib $^ -o $@
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/arm64/fp/README b/tools/testing/selftests/arm64/fp/README
new file mode 100644
index 000000000..03e3dad86
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/README
@@ -0,0 +1,100 @@
+This directory contains a mix of tests integrated with kselftest and
+standalone stress tests.
+
+kselftest tests
+===============
+
+sve-probe-vls - Checks the SVE vector length enumeration interface
+sve-ptrace - Checks the SVE ptrace interface
+
+Running the non-kselftest tests
+===============================
+
+sve-stress performs an SVE context switch stress test, as described
+below.
+
+(The fpsimd-stress test works the same way; just substitute "fpsimd" for
+"sve" in the following commands.)
+
+
+The test runs until killed by the user.
+
+If no context switch error was detected, you will see output such as
+the following:
+
+$ ./sve-stress
+(wait for some time)
+^C
+Vector length:        512 bits
+PID:    1573
+Terminated by signal 15, no error, iterations=9467, signals=1014
+Vector length:  512 bits
+PID:    1575
+Terminated by signal 15, no error, iterations=9448, signals=1028
+Vector length:  512 bits
+PID:    1577
+Terminated by signal 15, no error, iterations=9436, signals=1039
+Vector length:  512 bits
+PID:    1579
+Terminated by signal 15, no error, iterations=9421, signals=1039
+Vector length:  512 bits
+PID:    1581
+Terminated by signal 15, no error, iterations=9403, signals=1039
+Vector length:  512 bits
+PID:    1583
+Terminated by signal 15, no error, iterations=9385, signals=1036
+Vector length:  512 bits
+PID:    1585
+Terminated by signal 15, no error, iterations=9376, signals=1039
+Vector length:  512 bits
+PID:    1587
+Terminated by signal 15, no error, iterations=9361, signals=1039
+Vector length:  512 bits
+PID:    1589
+Terminated by signal 15, no error, iterations=9350, signals=1039
+
+
+If an error was detected, details of the mismatch will be printed
+instead of "no error".
+
+Ideally, the test should be allowed to run for many minutes or hours
+to maximise test coverage.
+
+
+KVM stress testing
+==================
+
+To try to reproduce the bugs that we have been observing, sve-stress
+should be run in parallel in two KVM guests, while simultaneously
+running on the host.
+
+1) Start 2 guests, using the following command for each:
+
+$ lkvm run --console=virtio -pconsole=hvc0 --sve Image
+
+(Depending on the hardware GIC implementation, you may also need
+--irqchip=gicv3.  New kvmtool defaults to that if appropriate, but I
+can't remember whether my branch is new enough for that.  Try without
+the option first.)
+
+Kvmtool occupies the terminal until you kill it (Ctrl+A x),
+or until the guest terminates.  It is therefore recommended to run
+each instance in separate terminal (use screen or ssh etc.)  This
+allows multiple guests to be run in parallel while running other
+commands on the host.
+
+Within the guest, the host filesystem is accessible, mounted on /host.
+
+2) Run the sve-stress on *each* guest with the Vector-Length set to 32:
+guest$ ./vlset --inherit 32 ./sve-stress
+
+3) Run the sve-stress on the host with the maximum Vector-Length:
+host$ ./vlset --inherit --max ./sve-stress
+
+
+Again, the test should be allowed to run for many minutes or hours to
+maximise test coverage.
+
+If no error is detected, you will see output from each sve-stress
+instance similar to that illustrated above; otherwise details of the
+observed mismatches will be printed.
diff --git a/tools/testing/selftests/arm64/fp/TODO b/tools/testing/selftests/arm64/fp/TODO
new file mode 100644
index 000000000..44004e53d
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/TODO
@@ -0,0 +1,7 @@
+- Test unsupported values in the ABIs.
+- More coverage for ptrace:
+ - Get/set of FFR.
+ - Ensure ptraced processes actually see the register state visible through
+   the ptrace interface.
+ - Big endian.
+- Test PR_SVE_VL_INHERIT after a double fork.
diff --git a/tools/testing/selftests/arm64/fp/asm-offsets.h b/tools/testing/selftests/arm64/fp/asm-offsets.h
new file mode 100644
index 000000000..757b2fd75
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/asm-offsets.h
@@ -0,0 +1,12 @@
+#define sa_sz 32
+#define sa_flags 8
+#define sa_handler 0
+#define sa_mask_sz 8
+#define SIGUSR1 10
+#define SIGUSR2 12
+#define SIGTERM 15
+#define SIGINT 2
+#define SIGABRT 6
+#define SA_NODEFER 1073741824
+#define SA_SIGINFO 4
+#define ucontext_regs 184
diff --git a/tools/testing/selftests/arm64/fp/asm-utils.S b/tools/testing/selftests/arm64/fp/asm-utils.S
new file mode 100644
index 000000000..4b9728efc
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/asm-utils.S
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2015-2021 ARM Limited.
+// Original author: Dave Martin <Dave.Martin@arm.com>
+//
+// Utility functions for assembly code.
+
+#include <asm/unistd.h>
+#include "assembler.h"
+
+// Print a single character x0 to stdout
+// Clobbers x0-x2,x8
+function putc
+	str	x0, [sp, #-16]!
+
+	mov	x0, #1			// STDOUT_FILENO
+	mov	x1, sp
+	mov	x2, #1
+	mov	x8, #__NR_write
+	svc	#0
+
+	add	sp, sp, #16
+	ret
+endfunction
+.globl	putc
+	
+// Print a NUL-terminated string starting at address x0 to stdout
+// Clobbers x0-x3,x8
+function puts
+	mov	x1, x0
+
+	mov	x2, #0
+0:	ldrb	w3, [x0], #1
+	cbz	w3, 1f
+	add	x2, x2, #1
+	b	0b
+
+1:	mov	w0, #1			// STDOUT_FILENO
+	mov	x8, #__NR_write
+	svc	#0
+
+	ret
+endfunction
+.globl	puts
+
+// Print an unsigned decimal number x0 to stdout
+// Clobbers x0-x4,x8
+function putdec
+	mov	x1, sp
+	str	x30, [sp, #-32]!	// Result can't be > 20 digits
+
+	mov	x2, #0
+	strb	w2, [x1, #-1]!		// Write the NUL terminator
+
+	mov	x2, #10
+0:	udiv	x3, x0, x2		// div-mod loop to generate the digits
+	msub	x0, x3, x2, x0
+	add	w0, w0, #'0'
+	strb	w0, [x1, #-1]!
+	mov	x0, x3
+	cbnz	x3, 0b
+
+	ldrb	w0, [x1]
+	cbnz	w0, 1f
+	mov	w0, #'0'		// Print "0" for 0, not ""
+	strb	w0, [x1, #-1]!
+
+1:	mov	x0, x1
+	bl	puts
+
+	ldr	x30, [sp], #32
+	ret
+endfunction
+.globl	putdec
+
+// Print an unsigned decimal number x0 to stdout, followed by a newline
+// Clobbers x0-x5,x8
+function putdecn
+	mov	x5, x30
+
+	bl	putdec
+	mov	x0, #'\n'
+	bl	putc
+
+	ret	x5
+endfunction
+.globl	putdecn
+
+// Clobbers x0-x3,x8
+function puthexb
+	str	x30, [sp, #-0x10]!
+
+	mov	w3, w0
+	lsr	w0, w0, #4
+	bl	puthexnibble
+	mov	w0, w3
+
+	ldr	x30, [sp], #0x10
+	// fall through to puthexnibble
+endfunction
+.globl	puthexb
+
+// Clobbers x0-x2,x8
+function puthexnibble
+	and	w0, w0, #0xf
+	cmp	w0, #10
+	blo	1f
+	add	w0, w0, #'a' - ('9' + 1)
+1:	add	w0, w0, #'0'
+	b	putc
+endfunction
+.globl	puthexnibble
+
+// x0=data in, x1=size in, clobbers x0-x5,x8
+function dumphex
+	str	x30, [sp, #-0x10]!
+
+	mov	x4, x0
+	mov	x5, x1
+
+0:	subs	x5, x5, #1
+	b.lo	1f
+	ldrb	w0, [x4], #1
+	bl	puthexb
+	b	0b
+
+1:	ldr	x30, [sp], #0x10
+	ret
+endfunction
+.globl	dumphex
+
+	// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0.
+// Clobbers x0-x3
+function memcpy
+	cmp	x2, #0
+	b.eq	1f
+0:	ldrb	w3, [x1], #1
+	strb	w3, [x0], #1
+	subs	x2, x2, #1
+	b.ne	0b
+1:	ret
+endfunction
+.globl	memcpy
+
+// Fill x1 bytes starting at x0 with 0xae (for canary purposes)
+// Clobbers x1, x2.
+function memfill_ae
+	mov	w2, #0xae
+	b	memfill
+endfunction
+.globl	memfill_ae
+	
+// Fill x1 bytes starting at x0 with 0.
+// Clobbers x1, x2.
+function memclr
+	mov	w2, #0
+endfunction
+.globl	memclr
+	// fall through to memfill
+
+// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2
+// Clobbers x1
+function memfill
+	cmp	x1, #0
+	b.eq	1f
+
+0:	strb	w2, [x0], #1
+	subs	x1, x1, #1
+	b.ne	0b
+
+1:	ret
+endfunction
+.globl	memfill
diff --git a/tools/testing/selftests/arm64/fp/assembler.h b/tools/testing/selftests/arm64/fp/assembler.h
new file mode 100644
index 000000000..90bd433d2
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/assembler.h
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2015-2019 ARM Limited.
+// Original author: Dave Martin <Dave.Martin@arm.com>
+
+#ifndef ASSEMBLER_H
+#define ASSEMBLER_H
+
+.macro __for from:req, to:req
+	.if (\from) == (\to)
+		_for__body %\from
+	.else
+		__for \from, %(\from) + ((\to) - (\from)) / 2
+		__for %(\from) + ((\to) - (\from)) / 2 + 1, \to
+	.endif
+.endm
+
+.macro _for var:req, from:req, to:req, insn:vararg
+	.macro _for__body \var:req
+		.noaltmacro
+		\insn
+		.altmacro
+	.endm
+
+	.altmacro
+	__for \from, \to
+	.noaltmacro
+
+	.purgem _for__body
+.endm
+
+.macro function name
+	.macro endfunction
+		.type \name, @function
+		.purgem endfunction
+	.endm
+\name:
+.endm
+
+.macro define_accessor name, num, insn
+	.macro \name\()_entry n
+		\insn \n, 1
+		ret
+	.endm
+
+function \name
+	adr	x2, .L__accessor_tbl\@
+	add	x2, x2, x0, lsl #3
+	br	x2
+
+.L__accessor_tbl\@:
+	_for x, 0, (\num) - 1, \name\()_entry \x
+endfunction
+
+	.purgem \name\()_entry
+.endm
+
+// Utility macro to print a literal string
+// Clobbers x0-x4,x8
+.macro puts string
+	.pushsection .rodata.str1.1, "aMS", 1
+.L__puts_literal\@: .string "\string"
+	.popsection
+
+	ldr	x0, =.L__puts_literal\@
+	bl	puts
+.endm
+
+#endif /* ! ASSEMBLER_H */
diff --git a/tools/testing/selftests/arm64/fp/fp-pidbench.S b/tools/testing/selftests/arm64/fp/fp-pidbench.S
new file mode 100644
index 000000000..16a436389
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fp-pidbench.S
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+//
+// Trivial syscall overhead benchmark.
+//
+// This is implemented in asm to ensure that we don't have any issues with
+// system libraries using instructions that disrupt the test.
+
+#include <asm/unistd.h>
+#include "assembler.h"
+
+.arch_extension sve
+
+.macro test_loop per_loop
+	mov	x10, x20
+	mov	x8, #__NR_getpid
+	mrs	x11, CNTVCT_EL0
+1:
+	\per_loop
+	svc	#0
+	sub	x10, x10, #1
+	cbnz	x10, 1b
+
+	mrs	x12, CNTVCT_EL0
+	sub	x0, x12, x11
+	bl	putdec
+	puts	"\n"
+.endm
+
+// Main program entry point
+.globl _start
+function _start
+_start:
+	puts	"Iterations per test: "
+	mov	x20, #10000
+	lsl	x20, x20, #8
+	mov	x0, x20
+	bl	putdec
+	puts	"\n"
+
+	// Test having never used SVE
+	puts	"No SVE: "
+	test_loop
+
+	// Check for SVE support - should use hwcap but that's hard in asm
+	mrs	x0, ID_AA64PFR0_EL1
+	ubfx	x0, x0, #32, #4
+	cbnz	x0, 1f
+	puts	"System does not support SVE\n"
+	b	out
+1:
+
+	// Execute a SVE instruction
+	puts	"SVE VL: "
+	rdvl	x0, #8
+	bl	putdec
+	puts	"\n"
+
+	puts	"SVE used once: "
+	test_loop
+
+	// Use SVE per syscall
+	puts	"SVE used per syscall: "
+	test_loop "rdvl x0, #8"
+
+	//  And we're done
+out:
+	mov	x0, #0
+	mov	x8, #__NR_exit
+	svc	#0
diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c
new file mode 100644
index 000000000..4e62a9199
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fp-stress.c
@@ -0,0 +1,555 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 ARM Limited.
+ */
+
+#define _GNU_SOURCE
+#define _POSIX_C_SOURCE 199309L
+
+#include <errno.h>
+#include <getopt.h>
+#include <poll.h>
+#include <signal.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/epoll.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+#include <asm/hwcap.h>
+
+#include "../../kselftest.h"
+
+#define MAX_VLS 16
+
+struct child_data {
+	char *name, *output;
+	pid_t pid;
+	int stdout;
+	bool output_seen;
+	bool exited;
+	int exit_status;
+};
+
+static int epoll_fd;
+static struct child_data *children;
+static int num_children;
+static bool terminate;
+
+static void drain_output(bool flush);
+
+static int num_processors(void)
+{
+	long nproc = sysconf(_SC_NPROCESSORS_CONF);
+	if (nproc < 0) {
+		perror("Unable to read number of processors\n");
+		exit(EXIT_FAILURE);
+	}
+
+	return nproc;
+}
+
+static void child_start(struct child_data *child, const char *program)
+{
+	int ret, pipefd[2], i;
+	struct epoll_event ev;
+
+	ret = pipe(pipefd);
+	if (ret != 0)
+		ksft_exit_fail_msg("Failed to create stdout pipe: %s (%d)\n",
+				   strerror(errno), errno);
+
+	child->pid = fork();
+	if (child->pid == -1)
+		ksft_exit_fail_msg("fork() failed: %s (%d)\n",
+				   strerror(errno), errno);
+
+	if (!child->pid) {
+		/*
+		 * In child, replace stdout with the pipe, errors to
+		 * stderr from here as kselftest prints to stdout.
+		 */
+		ret = dup2(pipefd[1], 1);
+		if (ret == -1) {
+			fprintf(stderr, "dup2() %d\n", errno);
+			exit(EXIT_FAILURE);
+		}
+
+		/*
+		 * Very dumb mechanism to clean open FDs other than
+		 * stdio. We don't want O_CLOEXEC for the pipes...
+		 */
+		for (i = 3; i < 8192; i++)
+			close(i);
+
+		ret = execl(program, program, NULL);
+		fprintf(stderr, "execl(%s) failed: %d (%s)\n",
+			program, errno, strerror(errno));
+
+		exit(EXIT_FAILURE);
+	} else {
+		/*
+		 * In parent, remember the child and close our copy of the
+		 * write side of stdout.
+		 */
+		close(pipefd[1]);
+		child->stdout = pipefd[0];
+		child->output = NULL;
+		child->exited = false;
+		child->output_seen = false;
+
+		ev.events = EPOLLIN | EPOLLHUP;
+		ev.data.ptr = child;
+
+		ret = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, child->stdout, &ev);
+		if (ret < 0) {
+			ksft_exit_fail_msg("%s EPOLL_CTL_ADD failed: %s (%d)\n",
+					   child->name, strerror(errno), errno);
+		}
+
+		/*
+		 * Keep output flowing during child startup so logs
+		 * are more timely, can help debugging.
+		 */
+		drain_output(false);
+	}
+}
+
+static bool child_output_read(struct child_data *child)
+{
+	char read_data[1024];
+	char work[1024];
+	int ret, len, cur_work, cur_read;
+
+	ret = read(child->stdout, read_data, sizeof(read_data));
+	if (ret < 0) {
+		if (errno == EINTR)
+			return true;
+
+		ksft_print_msg("%s: read() failed: %s (%d)\n",
+			       child->name, strerror(errno),
+			       errno);
+		return false;
+	}
+	len = ret;
+
+	child->output_seen = true;
+
+	/* Pick up any partial read */
+	if (child->output) {
+		strncpy(work, child->output, sizeof(work) - 1);
+		cur_work = strnlen(work, sizeof(work));
+		free(child->output);
+		child->output = NULL;
+	} else {
+		cur_work = 0;
+	}
+
+	cur_read = 0;
+	while (cur_read < len) {
+		work[cur_work] = read_data[cur_read++];
+
+		if (work[cur_work] == '\n') {
+			work[cur_work] = '\0';
+			ksft_print_msg("%s: %s\n", child->name, work);
+			cur_work = 0;
+		} else {
+			cur_work++;
+		}
+	}
+
+	if (cur_work) {
+		work[cur_work] = '\0';
+		ret = asprintf(&child->output, "%s", work);
+		if (ret == -1)
+			ksft_exit_fail_msg("Out of memory\n");
+	}
+
+	return false;
+}
+
+static void child_output(struct child_data *child, uint32_t events,
+			 bool flush)
+{
+	bool read_more;
+
+	if (events & EPOLLIN) {
+		do {
+			read_more = child_output_read(child);
+		} while (read_more);
+	}
+
+	if (events & EPOLLHUP) {
+		close(child->stdout);
+		child->stdout = -1;
+		flush = true;
+	}
+
+	if (flush && child->output) {
+		ksft_print_msg("%s: %s<EOF>\n", child->name, child->output);
+		free(child->output);
+		child->output = NULL;
+	}
+}
+
+static void child_tickle(struct child_data *child)
+{
+	if (child->output_seen && !child->exited)
+		kill(child->pid, SIGUSR2);
+}
+
+static void child_stop(struct child_data *child)
+{
+	if (!child->exited)
+		kill(child->pid, SIGTERM);
+}
+
+static void child_cleanup(struct child_data *child)
+{
+	pid_t ret;
+	int status;
+	bool fail = false;
+
+	if (!child->exited) {
+		do {
+			ret = waitpid(child->pid, &status, 0);
+			if (ret == -1 && errno == EINTR)
+				continue;
+
+			if (ret == -1) {
+				ksft_print_msg("waitpid(%d) failed: %s (%d)\n",
+					       child->pid, strerror(errno),
+					       errno);
+				fail = true;
+				break;
+			}
+		} while (!WIFEXITED(status));
+		child->exit_status = WEXITSTATUS(status);
+	}
+
+	if (!child->output_seen) {
+		ksft_print_msg("%s no output seen\n", child->name);
+		fail = true;
+	}
+
+	if (child->exit_status != 0) {
+		ksft_print_msg("%s exited with error code %d\n",
+			       child->name, child->exit_status);
+		fail = true;
+	}
+
+	ksft_test_result(!fail, "%s\n", child->name);
+}
+
+static void handle_child_signal(int sig, siginfo_t *info, void *context)
+{
+	int i;
+	bool found = false;
+
+	for (i = 0; i < num_children; i++) {
+		if (children[i].pid == info->si_pid) {
+			children[i].exited = true;
+			children[i].exit_status = info->si_status;
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
+		ksft_print_msg("SIGCHLD for unknown PID %d with status %d\n",
+			       info->si_pid, info->si_status);
+}
+
+static void handle_exit_signal(int sig, siginfo_t *info, void *context)
+{
+	int i;
+
+	/* If we're already exiting then don't signal again */
+	if (terminate)
+		return;
+
+	ksft_print_msg("Got signal, exiting...\n");
+
+	terminate = true;
+
+	/*
+	 * This should be redundant, the main loop should clean up
+	 * after us, but for safety stop everything we can here.
+	 */
+	for (i = 0; i < num_children; i++)
+		child_stop(&children[i]);
+}
+
+static void start_fpsimd(struct child_data *child, int cpu, int copy)
+{
+	int ret;
+
+	child_start(child, "./fpsimd-test");
+
+	ret = asprintf(&child->name, "FPSIMD-%d-%d", cpu, copy);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
+static void start_sve(struct child_data *child, int vl, int cpu)
+{
+	int ret;
+
+	ret = prctl(PR_SVE_SET_VL, vl | PR_SVE_VL_INHERIT);
+	if (ret < 0)
+		ksft_exit_fail_msg("Failed to set SVE VL %d\n", vl);
+
+	child_start(child, "./sve-test");
+
+	ret = asprintf(&child->name, "SVE-VL-%d-%d", vl, cpu);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
+static void start_ssve(struct child_data *child, int vl, int cpu)
+{
+	int ret;
+
+	ret = prctl(PR_SME_SET_VL, vl | PR_SME_VL_INHERIT);
+	if (ret < 0)
+		ksft_exit_fail_msg("Failed to set SME VL %d\n", ret);
+
+	child_start(child, "./ssve-test");
+
+	ret = asprintf(&child->name, "SSVE-VL-%d-%d", vl, cpu);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
+static void start_za(struct child_data *child, int vl, int cpu)
+{
+	int ret;
+
+	ret = prctl(PR_SME_SET_VL, vl | PR_SVE_VL_INHERIT);
+	if (ret < 0)
+		ksft_exit_fail_msg("Failed to set SME VL %d\n", ret);
+
+	child_start(child, "./za-test");
+
+	ret = asprintf(&child->name, "ZA-VL-%d-%d", vl, cpu);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
+static void probe_vls(int vls[], int *vl_count, int set_vl)
+{
+	unsigned int vq;
+	int vl;
+
+	*vl_count = 0;
+
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(set_vl, vq * 16);
+		if (vl == -1)
+			ksft_exit_fail_msg("SET_VL failed: %s (%d)\n",
+					   strerror(errno), errno);
+
+		vl &= PR_SVE_VL_LEN_MASK;
+
+		vq = sve_vq_from_vl(vl);
+
+		vls[*vl_count] = vl;
+		*vl_count += 1;
+	}
+}
+
+/* Handle any pending output without blocking */
+static void drain_output(bool flush)
+{
+	struct epoll_event ev;
+	int ret = 1;
+
+	while (ret > 0) {
+		ret = epoll_wait(epoll_fd, &ev, 1, 0);
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_print_msg("epoll_wait() failed: %s (%d)\n",
+				       strerror(errno), errno);
+		}
+
+		if (ret == 1)
+			child_output(ev.data.ptr, ev.events, flush);
+	}
+}
+
+static const struct option options[] = {
+	{ "timeout",	required_argument, NULL, 't' },
+	{ }
+};
+
+int main(int argc, char **argv)
+{
+	int ret;
+	int timeout = 10;
+	int cpus, tests, i, j, c;
+	int sve_vl_count, sme_vl_count, fpsimd_per_cpu;
+	int sve_vls[MAX_VLS], sme_vls[MAX_VLS];
+	struct epoll_event ev;
+	struct sigaction sa;
+
+	while ((c = getopt_long(argc, argv, "t:", options, NULL)) != -1) {
+		switch (c) {
+		case 't':
+			ret = sscanf(optarg, "%d", &timeout);
+			if (ret != 1)
+				ksft_exit_fail_msg("Failed to parse timeout %s\n",
+						   optarg);
+			break;
+		default:
+			ksft_exit_fail_msg("Unknown argument\n");
+		}
+	}
+
+	cpus = num_processors();
+	tests = 0;
+
+	if (getauxval(AT_HWCAP) & HWCAP_SVE) {
+		probe_vls(sve_vls, &sve_vl_count, PR_SVE_SET_VL);
+		tests += sve_vl_count * cpus;
+	} else {
+		sve_vl_count = 0;
+	}
+
+	if (getauxval(AT_HWCAP2) & HWCAP2_SME) {
+		probe_vls(sme_vls, &sme_vl_count, PR_SME_SET_VL);
+		tests += sme_vl_count * cpus * 2;
+	} else {
+		sme_vl_count = 0;
+	}
+
+	/* Force context switching if we only have FPSIMD */
+	if (!sve_vl_count && !sme_vl_count)
+		fpsimd_per_cpu = 2;
+	else
+		fpsimd_per_cpu = 1;
+	tests += cpus * fpsimd_per_cpu;
+
+	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);
+
+	if (timeout > 0)
+		ksft_print_msg("Will run for %ds\n", timeout);
+	else
+		ksft_print_msg("Will run until terminated\n");
+
+	children = calloc(sizeof(*children), tests);
+	if (!children)
+		ksft_exit_fail_msg("Unable to allocate child data\n");
+
+	ret = epoll_create1(EPOLL_CLOEXEC);
+	if (ret < 0)
+		ksft_exit_fail_msg("epoll_create1() failed: %s (%d)\n",
+				   strerror(errno), ret);
+	epoll_fd = ret;
+
+	/* Get signal handers ready before we start any children */
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handle_exit_signal;
+	sa.sa_flags = SA_RESTART | SA_SIGINFO;
+	sigemptyset(&sa.sa_mask);
+	ret = sigaction(SIGINT, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGINT handler: %s (%d)\n",
+			       strerror(errno), errno);
+	ret = sigaction(SIGTERM, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGTERM handler: %s (%d)\n",
+			       strerror(errno), errno);
+	sa.sa_sigaction = handle_child_signal;
+	ret = sigaction(SIGCHLD, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGCHLD handler: %s (%d)\n",
+			       strerror(errno), errno);
+
+	for (i = 0; i < cpus; i++) {
+		for (j = 0; j < fpsimd_per_cpu; j++)
+			start_fpsimd(&children[num_children++], i, j);
+
+		for (j = 0; j < sve_vl_count; j++)
+			start_sve(&children[num_children++], sve_vls[j], i);
+
+		for (j = 0; j < sme_vl_count; j++) {
+			start_ssve(&children[num_children++], sme_vls[j], i);
+			start_za(&children[num_children++], sme_vls[j], i);
+		}
+	}
+
+	for (;;) {
+		/* Did we get a signal asking us to exit? */
+		if (terminate)
+			break;
+
+		/*
+		 * Timeout is counted in seconds with no output, the
+		 * tests print during startup then are silent when
+		 * running so this should ensure they all ran enough
+		 * to install the signal handler, this is especially
+		 * useful in emulation where we will both be slow and
+		 * likely to have a large set of VLs.
+		 */
+		ret = epoll_wait(epoll_fd, &ev, 1, 1000);
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_exit_fail_msg("epoll_wait() failed: %s (%d)\n",
+					   strerror(errno), errno);
+		}
+
+		/* Output? */
+		if (ret == 1) {
+			child_output(ev.data.ptr, ev.events, false);
+			continue;
+		}
+
+		/* Otherwise epoll_wait() timed out */
+
+		for (i = 0; i < num_children; i++)
+			child_tickle(&children[i]);
+
+		/* Negative timeout means run indefinitely */
+		if (timeout < 0)
+			continue;
+		if (--timeout == 0)
+			break;
+	}
+
+	ksft_print_msg("Finishing up...\n");
+	terminate = true;
+
+	for (i = 0; i < tests; i++)
+		child_stop(&children[i]);
+
+	drain_output(false);
+
+	for (i = 0; i < tests; i++)
+		child_cleanup(&children[i]);
+
+	drain_output(true);
+
+	ksft_print_cnts();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/fpsimd-stress b/tools/testing/selftests/arm64/fp/fpsimd-stress
new file mode 100755
index 000000000..781b5b022
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fpsimd-stress
@@ -0,0 +1,60 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+	trap - INT TERM CHLD
+	set +e
+
+	if [ -n "$pids" ]; then
+		kill $pids
+		wait $pids
+		pids=
+	fi
+
+	if [ -n "$logs" ]; then
+		cat $logs
+		rm $logs
+		logs=
+	fi
+}
+
+interrupt () {
+	cleanup
+	exit 0
+}
+
+child_died () {
+	cleanup
+	exit 1
+}
+
+trap interrupt INT TERM EXIT
+trap child_died CHLD
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+	log=`mktemp`
+	logs=$logs\ $log
+	./fpsimd-test >$log &
+	pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+	kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
new file mode 100644
index 000000000..918d04885
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2015-2019 ARM Limited.
+// Original author: Dave Martin <Dave.Martin@arm.com>
+//
+// Simple FPSIMD context switch test
+// Repeatedly writes unique test patterns into each FPSIMD register
+// and reads them back to verify integrity.
+//
+// for x in `seq 1 NR_CPUS`; do fpsimd-test & pids=$pids\ $! ; done
+// (leave it running for as long as you want...)
+// kill $pids
+
+#include <asm/unistd.h>
+#include "assembler.h"
+#include "asm-offsets.h"
+
+#define NVR	32
+#define MAXVL_B	(128 / 8)
+
+.macro _vldr Vn:req, Xt:req
+	ld1	{v\Vn\().2d}, [x\Xt]
+.endm
+
+.macro _vstr Vn:req, Xt:req
+	st1	{v\Vn\().2d}, [x\Xt]
+.endm
+
+// Generate accessor functions to read/write programmatically selected
+// FPSIMD registers.
+// x0 is the register index to access
+// x1 is the memory address to read from (getv,setp) or store to (setv,setp)
+// All clobber x0-x2
+define_accessor setv, NVR, _vldr
+define_accessor getv, NVR, _vstr
+
+// Declare some storate space to shadow the SVE register contents:
+.pushsection .text
+.data
+.align 4
+vref:
+	.space	MAXVL_B * NVR
+scratch:
+	.space	MAXVL_B
+.popsection
+
+// Generate a test pattern for storage in SVE registers
+// x0: pid	(16 bits)
+// x1: register number (6 bits)
+// x2: generation (4 bits)
+function pattern
+	orr	w1, w0, w1, lsl #16
+	orr	w2, w1, w2, lsl #28
+
+	ldr	x0, =scratch
+	mov	w1, #MAXVL_B / 4
+
+0:	str	w2, [x0], #4
+	add	w2, w2, #(1 << 22)
+	subs	w1, w1, #1
+	bne	0b
+
+	ret
+endfunction
+
+// Get the address of shadow data for FPSIMD V-register V<xn>
+.macro _adrv xd, xn, nrtmp
+	ldr	\xd, =vref
+	mov	x\nrtmp, #16
+	madd	\xd, x\nrtmp, \xn, \xd
+.endm
+
+// Set up test pattern in a FPSIMD V-register
+// x0: pid
+// x1: register number
+// x2: generation
+function setup_vreg
+	mov	x4, x30
+
+	mov	x6, x1
+	bl	pattern
+	_adrv	x0, x6, 2
+	mov	x5, x0
+	ldr	x1, =scratch
+	bl	memcpy
+
+	mov	x0, x6
+	mov	x1, x5
+	bl	setv
+
+	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, 1f
+
+	mov	x5, #0
+0:	ldrb	w3, [x0, x5]
+	ldrb	w4, [x1, x5]
+	add	x5, x5, #1
+	cmp	w3, w4
+	b.ne	barf
+	subs	x2, x2, #1
+	b.ne	0b
+
+1:	ret
+endfunction
+
+// Verify that a FPSIMD V-register matches its shadow in memory, else abort
+// x0: reg number
+// Clobbers x0-x5.
+function check_vreg
+	mov	x3, x30
+
+	_adrv	x5, x0, 6
+	mov	x4, x0
+	ldr	x7, =scratch
+
+	mov	x0, x7
+	mov	x1, x6
+	bl	memfill_ae
+
+	mov	x0, x4
+	mov	x1, x7
+	bl	getv
+
+	mov	x0, x5
+	mov	x1, x7
+	mov	x2, x6
+	mov	x30, x3
+	b	memcmp
+endfunction
+
+// Any SVE register modified here can cause corruption in the main
+// thread -- but *only* the registers 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 V-regs
+	adr	x0, .text + (irritator_handler - .text) / 16 * 16
+	movi	v0.8b, #7
+	movi	v9.16b, #9
+	movi	v31.8b, #31
+
+	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
+_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
+
+	// Sanity-check and report the vector length
+
+	mov	x19, #128
+	cmp	x19, #128
+	b.lo	1f
+	cmp	x19, #2048
+	b.hi	1f
+	tst	x19, #(8 - 1)
+	b.eq	2f
+
+1:	puts	"Bad vector length: "
+	mov	x0, x19
+	bl	putdecn
+	b	.Labort
+
+2:	puts	"Vector length:\t"
+	mov	x0, x19
+	bl	putdec
+	puts	" bits\n"
+
+	// 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	x21, #0		// Set up V-regs & shadow with test pattern
+0:	mov	x0, x20
+	mov	x1, x21
+	and	x2, x22, #0xf
+	bl	setup_vreg
+	add	x21, x21, #1
+	cmp	x21, #NVR
+	b.lo	0b
+
+// Can't do this when SVE state is volatile across SVC:
+	mov	x8, #__NR_sched_yield	// Encourage preemption
+	svc	#0
+
+	mov	x21, #0
+0:	mov	x0, x21
+	bl	check_vreg
+	add	x21, x21, #1
+	cmp	x21, #NVR
+	b.lo	0b
+
+	add	x22, x22, #1
+	b	.Ltest_loop
+
+.Labort:
+	mov	x0, #0
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+endfunction
+
+function barf
+	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	", reg="
+	mov	x0, x21
+	bl	putdecn
+	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_exit
+	mov	x1, #1
+	svc	#0
+endfunction
diff --git a/tools/testing/selftests/arm64/fp/rdvl-sme.c b/tools/testing/selftests/arm64/fp/rdvl-sme.c
new file mode 100644
index 000000000..49b0b2e08
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/rdvl-sme.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <stdio.h>
+
+#include "rdvl.h"
+
+int main(void)
+{
+	int vl = rdvl_sme();
+
+	printf("%d\n", vl);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/rdvl-sve.c b/tools/testing/selftests/arm64/fp/rdvl-sve.c
new file mode 100644
index 000000000..7f8a13a18
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/rdvl-sve.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <stdio.h>
+
+#include "rdvl.h"
+
+int main(void)
+{
+	int vl = rdvl_sve();
+
+	printf("%d\n", vl);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/rdvl.S b/tools/testing/selftests/arm64/fp/rdvl.S
new file mode 100644
index 000000000..20dc29996
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/rdvl.S
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+
+#include "sme-inst.h"
+
+.arch_extension sve
+
+.globl rdvl_sve
+rdvl_sve:
+	hint	34			// BTI C
+	rdvl	x0, #1
+	ret
+
+.globl rdvl_sme
+rdvl_sme:
+	hint	34			// BTI C
+
+	rdsvl	0, 1
+
+	ret
diff --git a/tools/testing/selftests/arm64/fp/rdvl.h b/tools/testing/selftests/arm64/fp/rdvl.h
new file mode 100644
index 000000000..5d323679f
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/rdvl.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef RDVL_H
+#define RDVL_H
+
+int rdvl_sme(void);
+int rdvl_sve(void);
+
+#endif
diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h
new file mode 100644
index 000000000..7191e53ca
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/sme-inst.h
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021-2 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+
+#ifndef SME_INST_H
+#define SME_INST_H
+
+/*
+ * RDSVL X\nx, #\imm
+ */
+.macro rdsvl nx, imm
+	.inst	0x4bf5800			\
+		| (\imm << 5)			\
+		| (\nx)
+.endm
+
+.macro smstop
+	msr	S0_3_C4_C6_3, xzr
+.endm
+
+.macro smstart_za
+	msr	S0_3_C4_C5_3, xzr
+.endm
+
+.macro smstart_sm
+	msr	S0_3_C4_C3_3, xzr
+.endm
+
+/*
+ * LDR (vector to ZA array):
+ *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _ldr_za nw, nxbase, offset=0
+	.inst	0xe1000000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ *	STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _str_za nw, nxbase, offset=0
+	.inst	0xe1200000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+#endif
diff --git a/tools/testing/selftests/arm64/fp/ssve-stress b/tools/testing/selftests/arm64/fp/ssve-stress
new file mode 100644
index 000000000..e2bd2cc18
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/ssve-stress
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+	trap - INT TERM CHLD
+	set +e
+
+	if [ -n "$pids" ]; then
+		kill $pids
+		wait $pids
+		pids=
+	fi
+
+	if [ -n "$logs" ]; then
+		cat $logs
+		rm $logs
+		logs=
+	fi
+}
+
+interrupt () {
+	cleanup
+	exit 0
+}
+
+child_died () {
+	cleanup
+	exit 1
+}
+
+trap interrupt INT TERM EXIT
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+	log=`mktemp`
+	logs=$logs\ $log
+	./ssve-test >$log &
+	pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+	kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
diff --git a/tools/testing/selftests/arm64/fp/sve-probe-vls.c b/tools/testing/selftests/arm64/fp/sve-probe-vls.c
new file mode 100644
index 000000000..a24eca7a4
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/sve-probe-vls.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015-2020 ARM Limited.
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+#include <assert.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <asm/sigcontext.h>
+
+#include "../../kselftest.h"
+#include "rdvl.h"
+
+int main(int argc, char **argv)
+{
+	unsigned int vq;
+	int vl;
+	static unsigned int vqs[SVE_VQ_MAX];
+	unsigned int nvqs = 0;
+
+	ksft_print_header();
+	ksft_set_plan(2);
+
+	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
+		ksft_exit_skip("SVE not available\n");
+
+	/*
+	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 */
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(PR_SVE_SET_VL, vq * 16);
+		if (vl == -1)
+			ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
+					   strerror(errno), errno);
+
+		vl &= PR_SVE_VL_LEN_MASK;
+
+		if (rdvl_sve() != vl)
+			ksft_exit_fail_msg("PR_SVE_SET_VL reports %d, RDVL %d\n",
+					   vl, rdvl_sve());
+
+		if (!sve_vl_valid(vl))
+			ksft_exit_fail_msg("VL %d invalid\n", vl);
+		vq = sve_vq_from_vl(vl);
+
+		if (!(nvqs < SVE_VQ_MAX))
+			ksft_exit_fail_msg("Too many VLs %u >= SVE_VQ_MAX\n",
+					   nvqs);
+		vqs[nvqs++] = vq;
+	}
+	ksft_test_result_pass("Enumerated %d vector lengths\n", nvqs);
+	ksft_test_result_pass("All vector lengths valid\n");
+
+	/* Print out the vector lengths in ascending order: */
+	while (nvqs--)
+		ksft_print_msg("%u\n", 16 * vqs[nvqs]);
+
+	ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
new file mode 100644
index 000000000..8c4847977
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -0,0 +1,754 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015-2021 ARM Limited.
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+#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_SVE
+#define NT_ARM_SVE 0x405
+#endif
+
+#ifndef NT_ARM_SSVE
+#define NT_ARM_SSVE 0x40b
+#endif
+
+struct vec_type {
+	const char *name;
+	unsigned long hwcap_type;
+	unsigned long hwcap;
+	int regset;
+	int prctl_set;
+};
+
+static const struct vec_type vec_types[] = {
+	{
+		.name = "SVE",
+		.hwcap_type = AT_HWCAP,
+		.hwcap = HWCAP_SVE,
+		.regset = NT_ARM_SVE,
+		.prctl_set = PR_SVE_SET_VL,
+	},
+	{
+		.name = "Streaming SVE",
+		.hwcap_type = AT_HWCAP2,
+		.hwcap = HWCAP2_SME,
+		.regset = NT_ARM_SSVE,
+		.prctl_set = PR_SME_SET_VL,
+	},
+};
+
+#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 4)
+#define FLAG_TESTS 2
+#define FPSIMD_TESTS 2
+
+#define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types))
+
+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 int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
+{
+	struct iovec iov;
+
+	iov.iov_base = fpsimd;
+	iov.iov_len = sizeof(*fpsimd);
+	return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov);
+}
+
+static int set_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
+{
+	struct iovec iov;
+
+	iov.iov_base = fpsimd;
+	iov.iov_len = sizeof(*fpsimd);
+	return ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov);
+}
+
+static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
+				       void **buf, size_t *size)
+{
+	struct user_sve_header *sve;
+	void *p;
+	size_t sz = sizeof *sve;
+	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, type->regset, &iov))
+			goto error;
+
+		sve = *buf;
+		if (sve->size <= sz)
+			break;
+
+		sz = sve->size;
+	}
+
+	return sve;
+
+error:
+	return NULL;
+}
+
+static int set_sve(pid_t pid, const struct vec_type *type,
+		   const struct user_sve_header *sve)
+{
+	struct iovec iov;
+
+	iov.iov_base = (void *)sve;
+	iov.iov_len = sve->size;
+	return ptrace(PTRACE_SETREGSET, pid, type->regset, &iov);
+}
+
+/* Validate setting and getting the inherit flag */
+static void ptrace_set_get_inherit(pid_t child, const struct vec_type *type)
+{
+	struct user_sve_header sve;
+	struct user_sve_header *new_sve = NULL;
+	size_t new_sve_size = 0;
+	int ret;
+
+	/* First set the flag */
+	memset(&sve, 0, sizeof(sve));
+	sve.size = sizeof(sve);
+	sve.vl = sve_vl_from_vq(SVE_VQ_MIN);
+	sve.flags = SVE_PT_VL_INHERIT;
+	ret = set_sve(child, type, &sve);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set %s SVE_PT_VL_INHERIT\n",
+				      type->name);
+		return;
+	}
+
+	/*
+	 * Read back the new register state and verify that we have
+	 * set the flags we expected.
+	 */
+	if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) {
+		ksft_test_result_fail("Failed to read %s SVE flags\n",
+				      type->name);
+		return;
+	}
+
+	ksft_test_result(new_sve->flags & SVE_PT_VL_INHERIT,
+			 "%s SVE_PT_VL_INHERIT set\n", type->name);
+
+	/* Now clear */
+	sve.flags &= ~SVE_PT_VL_INHERIT;
+	ret = set_sve(child, type, &sve);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to clear %s SVE_PT_VL_INHERIT\n",
+				      type->name);
+		return;
+	}
+
+	if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) {
+		ksft_test_result_fail("Failed to read %s SVE flags\n",
+				      type->name);
+		return;
+	}
+
+	ksft_test_result(!(new_sve->flags & SVE_PT_VL_INHERIT),
+			 "%s SVE_PT_VL_INHERIT cleared\n", type->name);
+
+	free(new_sve);
+}
+
+/* Validate attempting to set the specfied VL via ptrace */
+static void ptrace_set_get_vl(pid_t child, const struct vec_type *type,
+			      unsigned int vl, bool *supported)
+{
+	struct user_sve_header sve;
+	struct user_sve_header *new_sve = NULL;
+	size_t new_sve_size = 0;
+	int ret, prctl_vl;
+
+	*supported = false;
+
+	/* Check if the VL is supported in this process */
+	prctl_vl = prctl(type->prctl_set, vl);
+	if (prctl_vl == -1)
+		ksft_exit_fail_msg("prctl(PR_%s_SET_VL) failed: %s (%d)\n",
+				   type->name, strerror(errno), errno);
+
+	/* If the VL is not supported then a supported VL will be returned */
+	*supported = (prctl_vl == vl);
+
+	/* Set the VL by doing a set with no register payload */
+	memset(&sve, 0, sizeof(sve));
+	sve.size = sizeof(sve);
+	sve.vl = vl;
+	ret = set_sve(child, type, &sve);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set %s VL %u\n",
+				      type->name, vl);
+		return;
+	}
+
+	/*
+	 * Read back the new register state and verify that we have the
+	 * same VL that we got from prctl() on ourselves.
+	 */
+	if (!get_sve(child, type, (void **)&new_sve, &new_sve_size)) {
+		ksft_test_result_fail("Failed to read %s VL %u\n",
+				      type->name, vl);
+		return;
+	}
+
+	ksft_test_result(new_sve->vl = prctl_vl, "Set %s VL %u\n",
+			 type->name, vl);
+
+	free(new_sve);
+}
+
+static void check_u32(unsigned int vl, const char *reg,
+		      uint32_t *in, uint32_t *out, int *errors)
+{
+	if (*in != *out) {
+		printf("# VL %d %s wrote %x read %x\n",
+		       vl, reg, *in, *out);
+		(*errors)++;
+	}
+}
+
+/* Access the FPSIMD registers via the SVE regset */
+static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
+{
+	void *svebuf;
+	struct user_sve_header *sve;
+	struct user_fpsimd_state *fpsimd, new_fpsimd;
+	unsigned int i, j;
+	unsigned char *p;
+	int ret;
+
+	svebuf = malloc(SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+	if (!svebuf) {
+		ksft_test_result_fail("Failed to allocate FPSIMD buffer\n");
+		return;
+	}
+
+	memset(svebuf, 0, SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+	sve = svebuf;
+	sve->flags = SVE_PT_REGS_FPSIMD;
+	sve->size = SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD);
+	sve->vl = 16;  /* We don't care what the VL is */
+
+	/* Try to set a known FPSIMD state via PT_REGS_SVE */
+	fpsimd = (struct user_fpsimd_state *)((char *)sve +
+					      SVE_PT_FPSIMD_OFFSET);
+	for (i = 0; i < 32; ++i) {
+		p = (unsigned char *)&fpsimd->vregs[i];
+
+		for (j = 0; j < sizeof(fpsimd->vregs[i]); ++j)
+			p[j] = j;
+	}
+
+	ret = set_sve(child, type, sve);
+	ksft_test_result(ret == 0, "%s FPSIMD set via SVE: %d\n",
+			 type->name, ret);
+	if (ret)
+		goto out;
+
+	/* Verify via the FPSIMD regset */
+	if (get_fpsimd(child, &new_fpsimd)) {
+		ksft_test_result_fail("get_fpsimd(): %s\n",
+				      strerror(errno));
+		goto out;
+	}
+	if (memcmp(fpsimd, &new_fpsimd, sizeof(*fpsimd)) == 0)
+		ksft_test_result_pass("%s get_fpsimd() gave same state\n",
+				      type->name);
+	else
+		ksft_test_result_fail("%s get_fpsimd() gave different state\n",
+				      type->name);
+
+out:
+	free(svebuf);
+}
+
+/* Validate attempting to set SVE data and read SVE data */
+static void ptrace_set_sve_get_sve_data(pid_t child,
+					const struct vec_type *type,
+					unsigned int vl)
+{
+	void *write_buf;
+	void *read_buf = NULL;
+	struct user_sve_header *write_sve;
+	struct user_sve_header *read_sve;
+	size_t read_sve_size = 0;
+	unsigned int vq = sve_vq_from_vl(vl);
+	int ret, i;
+	size_t data_size;
+	int errors = 0;
+
+	data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+	write_buf = malloc(data_size);
+	if (!write_buf) {
+		ksft_test_result_fail("Error allocating %d byte buffer for %s VL %u\n",
+				      data_size, type->name, vl);
+		return;
+	}
+	write_sve = write_buf;
+
+	/* Set up some data and write it out */
+	memset(write_sve, 0, data_size);
+	write_sve->size = data_size;
+	write_sve->vl = vl;
+	write_sve->flags = SVE_PT_REGS_SVE;
+
+	for (i = 0; i < __SVE_NUM_ZREGS; i++)
+		fill_buf(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i),
+			 SVE_PT_SVE_ZREG_SIZE(vq));
+
+	for (i = 0; i < __SVE_NUM_PREGS; i++)
+		fill_buf(write_buf + SVE_PT_SVE_PREG_OFFSET(vq, i),
+			 SVE_PT_SVE_PREG_SIZE(vq));
+
+	fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE);
+	fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE);
+
+	/* TODO: Generate a valid FFR pattern */
+
+	ret = set_sve(child, type, write_sve);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set %s VL %u data\n",
+				      type->name, vl);
+		goto out;
+	}
+
+	/* Read the data back */
+	if (!get_sve(child, type, (void **)&read_buf, &read_sve_size)) {
+		ksft_test_result_fail("Failed to read %s VL %u data\n",
+				      type->name, vl);
+		goto out;
+	}
+	read_sve = read_buf;
+
+	/* We might read more data if there's extensions we don't know */
+	if (read_sve->size < write_sve->size) {
+		ksft_test_result_fail("%s wrote %d bytes, only read %d\n",
+				      type->name, write_sve->size,
+				      read_sve->size);
+		goto out_read;
+	}
+
+	for (i = 0; i < __SVE_NUM_ZREGS; i++) {
+		if (memcmp(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i),
+			   read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i),
+			   SVE_PT_SVE_ZREG_SIZE(vq)) != 0) {
+			printf("# Mismatch in %u Z%d\n", vl, i);
+			errors++;
+		}
+	}
+
+	for (i = 0; i < __SVE_NUM_PREGS; i++) {
+		if (memcmp(write_buf + SVE_PT_SVE_PREG_OFFSET(vq, i),
+			   read_buf + SVE_PT_SVE_PREG_OFFSET(vq, i),
+			   SVE_PT_SVE_PREG_SIZE(vq)) != 0) {
+			printf("# Mismatch in %u P%d\n", vl, i);
+			errors++;
+		}
+	}
+
+	check_u32(vl, "FPSR", write_buf + SVE_PT_SVE_FPSR_OFFSET(vq),
+		  read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors);
+	check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq),
+		  read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors);
+
+	ksft_test_result(errors == 0, "Set and get %s data for VL %u\n",
+			 type->name, vl);
+
+out_read:
+	free(read_buf);
+out:
+	free(write_buf);
+}
+
+/* Validate attempting to set SVE data and read it via the FPSIMD regset */
+static void ptrace_set_sve_get_fpsimd_data(pid_t child,
+					   const struct vec_type *type,
+					   unsigned int vl)
+{
+	void *write_buf;
+	struct user_sve_header *write_sve;
+	unsigned int vq = sve_vq_from_vl(vl);
+	struct user_fpsimd_state fpsimd_state;
+	int ret, i;
+	size_t data_size;
+	int errors = 0;
+
+	if (__BYTE_ORDER == __BIG_ENDIAN) {
+		ksft_test_result_skip("Big endian not supported\n");
+		return;
+	}
+
+	data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+	write_buf = malloc(data_size);
+	if (!write_buf) {
+		ksft_test_result_fail("Error allocating %d byte buffer for %s VL %u\n",
+				      data_size, type->name, vl);
+		return;
+	}
+	write_sve = write_buf;
+
+	/* Set up some data and write it out */
+	memset(write_sve, 0, data_size);
+	write_sve->size = data_size;
+	write_sve->vl = vl;
+	write_sve->flags = SVE_PT_REGS_SVE;
+
+	for (i = 0; i < __SVE_NUM_ZREGS; i++)
+		fill_buf(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i),
+			 SVE_PT_SVE_ZREG_SIZE(vq));
+
+	fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE);
+	fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE);
+
+	ret = set_sve(child, type, write_sve);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set %s VL %u data\n",
+				      type->name, vl);
+		goto out;
+	}
+
+	/* Read the data back */
+	if (get_fpsimd(child, &fpsimd_state)) {
+		ksft_test_result_fail("Failed to read %s VL %u FPSIMD data\n",
+				      type->name, vl);
+		goto out;
+	}
+
+	for (i = 0; i < __SVE_NUM_ZREGS; i++) {
+		__uint128_t tmp = 0;
+
+		/*
+		 * Z regs are stored endianness invariant, this won't
+		 * work for big endian
+		 */
+		memcpy(&tmp, write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i),
+		       sizeof(tmp));
+
+		if (tmp != fpsimd_state.vregs[i]) {
+			printf("# Mismatch in FPSIMD for %s VL %u Z%d\n",
+			       type->name, vl, i);
+			errors++;
+		}
+	}
+
+	check_u32(vl, "FPSR", write_buf + SVE_PT_SVE_FPSR_OFFSET(vq),
+		  &fpsimd_state.fpsr, &errors);
+	check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq),
+		  &fpsimd_state.fpcr, &errors);
+
+	ksft_test_result(errors == 0, "Set and get FPSIMD data for %s VL %u\n",
+			 type->name, vl);
+
+out:
+	free(write_buf);
+}
+
+/* Validate attempting to set FPSIMD data and read it via the SVE regset */
+static void ptrace_set_fpsimd_get_sve_data(pid_t child,
+					   const struct vec_type *type,
+					   unsigned int vl)
+{
+	void *read_buf = NULL;
+	unsigned char *p;
+	struct user_sve_header *read_sve;
+	unsigned int vq = sve_vq_from_vl(vl);
+	struct user_fpsimd_state write_fpsimd;
+	int ret, i, j;
+	size_t read_sve_size = 0;
+	size_t expected_size;
+	int errors = 0;
+
+	if (__BYTE_ORDER == __BIG_ENDIAN) {
+		ksft_test_result_skip("Big endian not supported\n");
+		return;
+	}
+
+	for (i = 0; i < 32; ++i) {
+		p = (unsigned char *)&write_fpsimd.vregs[i];
+
+		for (j = 0; j < sizeof(write_fpsimd.vregs[i]); ++j)
+			p[j] = j;
+	}
+
+	ret = set_fpsimd(child, &write_fpsimd);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set FPSIMD state: %d\n)",
+				      ret);
+		return;
+	}
+
+	if (!get_sve(child, type, (void **)&read_buf, &read_sve_size)) {
+		ksft_test_result_fail("Failed to read %s VL %u data\n",
+				      type->name, vl);
+		return;
+	}
+	read_sve = read_buf;
+
+	if (read_sve->vl != vl) {
+		ksft_test_result_fail("Child VL != expected VL %d\n",
+				      read_sve->vl, vl);
+		goto out;
+	}
+
+	/* The kernel may return either SVE or FPSIMD format */
+	switch (read_sve->flags & SVE_PT_REGS_MASK) {
+	case SVE_PT_REGS_FPSIMD:
+		expected_size = SVE_PT_FPSIMD_SIZE(vq, SVE_PT_REGS_FPSIMD);
+		if (read_sve_size < expected_size) {
+			ksft_test_result_fail("Read %d bytes, expected %d\n",
+					      read_sve_size, expected_size);
+			goto out;
+		}
+
+		ret = memcmp(&write_fpsimd, read_buf + SVE_PT_FPSIMD_OFFSET,
+			     sizeof(write_fpsimd));
+		if (ret != 0) {
+			ksft_print_msg("Read FPSIMD data mismatch\n");
+			errors++;
+		}
+		break;
+
+	case SVE_PT_REGS_SVE:
+		expected_size = SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+		if (read_sve_size < expected_size) {
+			ksft_test_result_fail("Read %d bytes, expected %d\n",
+					      read_sve_size, expected_size);
+			goto out;
+		}
+
+		for (i = 0; i < __SVE_NUM_ZREGS; i++) {
+			__uint128_t tmp = 0;
+
+			/*
+			 * Z regs are stored endianness invariant, this won't
+			 * work for big endian
+			 */
+			memcpy(&tmp, read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i),
+			       sizeof(tmp));
+
+			if (tmp != write_fpsimd.vregs[i]) {
+				ksft_print_msg("Mismatch in FPSIMD for %s VL %u Z%d/V%d\n",
+					       type->name, vl, i, i);
+				errors++;
+			}
+		}
+
+		check_u32(vl, "FPSR", &write_fpsimd.fpsr,
+			  read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors);
+		check_u32(vl, "FPCR", &write_fpsimd.fpcr,
+			  read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors);
+		break;
+	default:
+		ksft_print_msg("Unexpected regs type %d\n",
+			       read_sve->flags & SVE_PT_REGS_MASK);
+		errors++;
+		break;
+	}
+
+	ksft_test_result(errors == 0, "Set FPSIMD, read via SVE for %s VL %u\n",
+			 type->name, vl);
+
+out:
+	free(read_buf);
+}
+
+static int do_parent(pid_t child)
+{
+	int ret = EXIT_FAILURE;
+	pid_t pid;
+	int status, i;
+	siginfo_t si;
+	unsigned int vq, vl;
+	bool vl_supported;
+
+	ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
+
+	/* 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;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(vec_types); i++) {
+		/* FPSIMD via SVE regset */
+		if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
+			ptrace_sve_fpsimd(child, &vec_types[i]);
+		} else {
+			ksft_test_result_skip("%s FPSIMD set via SVE\n",
+					      vec_types[i].name);
+			ksft_test_result_skip("%s FPSIMD read\n",
+					      vec_types[i].name);
+		}
+
+		/* prctl() flags */
+		if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
+			ptrace_set_get_inherit(child, &vec_types[i]);
+		} else {
+			ksft_test_result_skip("%s SVE_PT_VL_INHERIT set\n",
+					      vec_types[i].name);
+			ksft_test_result_skip("%s SVE_PT_VL_INHERIT cleared\n",
+					      vec_types[i].name);
+		}
+
+		/* Step through every possible VQ */
+		for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+			vl = sve_vl_from_vq(vq);
+
+			/* First, try to set this vector length */
+			if (getauxval(vec_types[i].hwcap_type) &
+			    vec_types[i].hwcap) {
+				ptrace_set_get_vl(child, &vec_types[i], vl,
+						  &vl_supported);
+			} else {
+				ksft_test_result_skip("%s get/set VL %d\n",
+						      vec_types[i].name, vl);
+				vl_supported = false;
+			}
+
+			/* If the VL is supported validate data set/get */
+			if (vl_supported) {
+				ptrace_set_sve_get_sve_data(child, &vec_types[i], vl);
+				ptrace_set_sve_get_fpsimd_data(child, &vec_types[i], vl);
+				ptrace_set_fpsimd_get_sve_data(child, &vec_types[i], vl);
+			} else {
+				ksft_test_result_skip("%s set SVE get SVE for VL %d\n",
+						      vec_types[i].name, vl);
+				ksft_test_result_skip("%s set SVE get FPSIMD for VL %d\n",
+						      vec_types[i].name, vl);
+				ksft_test_result_skip("%s set FPSIMD get SVE for VL %d\n",
+						      vec_types[i].name, vl);
+			}
+		}
+	}
+
+	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();
+	ksft_set_plan(EXPECTED_TESTS);
+
+	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
+		ksft_exit_skip("SVE not available\n");
+
+	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/sve-stress b/tools/testing/selftests/arm64/fp/sve-stress
new file mode 100755
index 000000000..24dd0922c
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/sve-stress
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+	trap - INT TERM CHLD
+	set +e
+
+	if [ -n "$pids" ]; then
+		kill $pids
+		wait $pids
+		pids=
+	fi
+
+	if [ -n "$logs" ]; then
+		cat $logs
+		rm $logs
+		logs=
+	fi
+}
+
+interrupt () {
+	cleanup
+	exit 0
+}
+
+child_died () {
+	cleanup
+	exit 1
+}
+
+trap interrupt INT TERM EXIT
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+	log=`mktemp`
+	logs=$logs\ $log
+	./sve-test >$log &
+	pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+	kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
new file mode 100644
index 000000000..2a18cb4c5
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -0,0 +1,556 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2015-2019 ARM Limited.
+// Original author: Dave Martin <Dave.Martin@arm.com>
+//
+// Simple Scalable Vector Extension context switch test
+// Repeatedly writes unique test patterns into each SVE register
+// and reads them back to verify integrity.
+//
+// for x in `seq 1 NR_CPUS`; do sve-test & pids=$pids\ $! ; done
+// (leave it running for as long as you want...)
+// kill $pids
+
+#include <asm/unistd.h>
+#include "assembler.h"
+#include "asm-offsets.h"
+#include "sme-inst.h"
+
+#define NZR	32
+#define NPR	16
+#define MAXVL_B	(2048 / 8)
+
+.arch_extension sve
+
+.macro _sve_ldr_v zt, xn
+	ldr	z\zt, [x\xn]
+.endm
+
+.macro _sve_str_v zt, xn
+	str	z\zt, [x\xn]
+.endm
+
+.macro _sve_ldr_p pt, xn
+	ldr	p\pt, [x\xn]
+.endm
+
+.macro _sve_str_p pt, xn
+	str	p\pt, [x\xn]
+.endm
+
+// Generate accessor functions to read/write programmatically selected
+// SVE registers.
+// x0 is the register index to access
+// x1 is the memory address to read from (getz,setp) or store to (setz,setp)
+// All clobber x0-x2
+define_accessor setz, NZR, _sve_ldr_v
+define_accessor getz, NZR, _sve_str_v
+define_accessor setp, NPR, _sve_ldr_p
+define_accessor getp, NPR, _sve_str_p
+
+// Declare some storate space to shadow the SVE register contents:
+.pushsection .text
+.data
+.align 4
+zref:
+	.space	MAXVL_B * NZR
+pref:
+	.space	MAXVL_B / 8 * NPR
+ffrref:
+	.space	MAXVL_B / 8
+scratch:
+	.space	MAXVL_B
+.popsection
+
+// Generate a test pattern for storage in SVE registers
+// x0: pid	(16 bits)
+// x1: register number (6 bits)
+// x2: generation (4 bits)
+
+// These values are used to constuct a 32-bit pattern that is repeated in the
+// scratch buffer as many times as will fit:
+// bits 31:28	generation number (increments once per test_loop)
+// bits 27:22	32-bit lane index
+// bits 21:16	register number
+// bits 15: 0	pid
+
+function pattern
+	orr	w1, w0, w1, lsl #16
+	orr	w2, w1, w2, lsl #28
+
+	ldr	x0, =scratch
+	mov	w1, #MAXVL_B / 4
+
+0:	str	w2, [x0], #4
+	add	w2, w2, #(1 << 22)
+	subs	w1, w1, #1
+	bne	0b
+
+	ret
+endfunction
+
+// Get the address of shadow data for SVE Z-register Z<xn>
+.macro _adrz xd, xn, nrtmp
+	ldr	\xd, =zref
+	rdvl	x\nrtmp, #1
+	madd	\xd, x\nrtmp, \xn, \xd
+.endm
+
+// Get the address of shadow data for SVE P-register P<xn - NZR>
+.macro _adrp xd, xn, nrtmp
+	ldr	\xd, =pref
+	rdvl	x\nrtmp, #1
+	lsr	x\nrtmp, x\nrtmp, #3
+	sub	\xn, \xn, #NZR
+	madd	\xd, x\nrtmp, \xn, \xd
+.endm
+
+// Set up test pattern in a SVE Z-register
+// x0: pid
+// x1: register number
+// x2: generation
+function setup_zreg
+	mov	x4, x30
+
+	mov	x6, x1
+	bl	pattern
+	_adrz	x0, x6, 2
+	mov	x5, x0
+	ldr	x1, =scratch
+	bl	memcpy
+
+	mov	x0, x6
+	mov	x1, x5
+	bl	setz
+
+	ret	x4
+endfunction
+
+// Set up test pattern in a SVE P-register
+// x0: pid
+// x1: register number
+// x2: generation
+function setup_preg
+	mov	x4, x30
+
+	mov	x6, x1
+	bl	pattern
+	_adrp	x0, x6, 2
+	mov	x5, x0
+	ldr	x1, =scratch
+	bl	memcpy
+
+	mov	x0, x6
+	mov	x1, x5
+	bl	setp
+
+	ret	x4
+endfunction
+
+// Set up test pattern in the FFR
+// x0: pid
+// x2: generation
+//
+// We need to generate a canonical FFR value, which consists of a number of
+// low "1" bits, followed by a number of zeros. This gives us 17 unique values
+// per 16 bits of FFR, so we create a 4 bit signature out of the PID and
+// generation, and use that as the initial number of ones in the pattern.
+// We fill the upper lanes of FFR with zeros.
+// Beware: corrupts P0.
+function setup_ffr
+#ifndef SSVE
+	mov	x4, x30
+
+	and	w0, w0, #0x3
+	bfi	w0, w2, #2, #2
+	mov	w1, #1
+	lsl	w1, w1, w0
+	sub	w1, w1, #1
+
+	ldr	x0, =ffrref
+	strh	w1, [x0], 2
+	rdvl	x1, #1
+	lsr	x1, x1, #3
+	sub	x1, x1, #2
+	bl	memclr
+
+	mov	x0, #0
+	ldr	x1, =ffrref
+	bl	setp
+
+	wrffr	p0.b
+
+	ret	x4
+#else
+	ret
+#endif
+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 SVE Z-register matches its shadow in memory, else abort
+// x0: reg number
+// Clobbers x0-x7.
+function check_zreg
+	mov	x3, x30
+
+	_adrz	x5, x0, 6
+	mov	x4, x0
+	ldr	x7, =scratch
+
+	mov	x0, x7
+	mov	x1, x6
+	bl	memfill_ae
+
+	mov	x0, x4
+	mov	x1, x7
+	bl	getz
+
+	mov	x0, x5
+	mov	x1, x7
+	mov	x2, x6
+	mov	x30, x3
+	b	memcmp
+endfunction
+
+// Verify that a SVE P-register matches its shadow in memory, else abort
+// x0: reg number
+// Clobbers x0-x7.
+function check_preg
+	mov	x3, x30
+
+	_adrp	x5, x0, 6
+	mov	x4, x0
+	ldr	x7, =scratch
+
+	mov	x0, x7
+	mov	x1, x6
+	bl	memfill_ae
+
+	mov	x0, x4
+	mov	x1, x7
+	bl	getp
+
+	mov	x0, x5
+	mov	x1, x7
+	mov	x2, x6
+	mov	x30, x3
+	b	memcmp
+endfunction
+
+// Verify that the FFR matches its shadow in memory, else abort
+// Beware -- corrupts P0.
+// Clobbers x0-x5.
+function check_ffr
+#ifndef SSVE
+	mov	x3, x30
+
+	ldr	x4, =scratch
+	rdvl	x5, #1
+	lsr	x5, x5, #3
+
+	mov	x0, x4
+	mov	x1, x5
+	bl	memfill_ae
+
+	rdffr	p0.b
+	mov	x0, #0
+	mov	x1, x4
+	bl	getp
+
+	ldr	x0, =ffrref
+	mov	x1, x4
+	mov	x2, x5
+	mov	x30, x3
+	b	memcmp
+#else
+	ret
+#endif
+endfunction
+
+// Any SVE register modified here can cause corruption in the main
+// thread -- but *only* the registers 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 Z-regs
+	adr	x0, .text + (irritator_handler - .text) / 16 * 16
+	movi	v0.8b, #1
+	movi	v9.16b, #2
+	movi	v31.8b, #3
+#ifndef SSVE
+	// And P0
+	rdffr	p0.b
+	// And FFR
+	wrffr	p15.b
+#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
+_start:
+	mov	x23, #0		// Irritation 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
+
+#ifdef SSVE
+	puts	"Streaming mode "
+	smstart_sm
+#endif
+
+	// Sanity-check and report the vector length
+
+	rdvl	x19, #8
+	cmp	x19, #128
+	b.lo	1f
+	cmp	x19, #2048
+	b.hi	1f
+	tst	x19, #(8 - 1)
+	b.eq	2f
+
+1:	puts	"Bad vector length: "
+	mov	x0, x19
+	bl	putdecn
+	b	.Labort
+
+2:	puts	"Vector length:\t"
+	mov	x0, x19
+	bl	putdec
+	puts	" bits\n"
+
+	// 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
+
+#ifdef SSVE
+	smstart_sm		// syscalls will have exited streaming mode
+#endif
+
+	mov	x22, #0		// generation number, increments per iteration
+.Ltest_loop:
+	rdvl	x0, #8
+	cmp	x0, x19
+	b.ne	vl_barf
+
+	mov	x21, #0		// Set up Z-regs & shadow with test pattern
+0:	mov	x0, x20
+	mov	x1, x21
+	and	x2, x22, #0xf
+	bl	setup_zreg
+	add	x21, x21, #1
+	cmp	x21, #NZR
+	b.lo	0b
+
+	mov	x0, x20		// Set up FFR & shadow with test pattern
+	mov	x1, #NZR + NPR
+	and	x2, x22, #0xf
+	bl	setup_ffr
+
+0:	mov	x0, x20		// Set up P-regs & shadow with test pattern
+	mov	x1, x21
+	and	x2, x22, #0xf
+	bl	setup_preg
+	add	x21, x21, #1
+	cmp	x21, #NZR + NPR
+	b.lo	0b
+
+// Can't do this when SVE state is volatile across SVC:
+//	mov	x8, #__NR_sched_yield	// Encourage preemption
+//	svc	#0
+
+	mov	x21, #0
+0:	mov	x0, x21
+	bl	check_zreg
+	add	x21, x21, #1
+	cmp	x21, #NZR
+	b.lo	0b
+
+0:	mov	x0, x21
+	bl	check_preg
+	add	x21, x21, #1
+	cmp	x21, #NZR + NPR
+	b.lo	0b
+
+	bl	check_ffr
+
+	add	x22, x22, #1
+	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
+	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	", reg="
+	mov	x0, x21
+	bl	putdecn
+	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 vl_barf
+	mov	x10, x0
+
+	puts	"Bad active VL: "
+	mov	x0, x10
+	bl	putdecn
+
+	mov	x8, #__NR_exit
+	mov	x1, #1
+	svc	#0
+endfunction
diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c
new file mode 100644
index 000000000..9bcfcdc34
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c
@@ -0,0 +1,670 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 ARM Limited.
+ * Original author: Mark Brown <broonie@kernel.org>
+ */
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.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/types.h>
+#include <sys/wait.h>
+#include <asm/sigcontext.h>
+#include <asm/hwcap.h>
+
+#include "../../kselftest.h"
+#include "rdvl.h"
+
+#define ARCH_MIN_VL SVE_VL_MIN
+
+struct vec_data {
+	const char *name;
+	unsigned long hwcap_type;
+	unsigned long hwcap;
+	const char *rdvl_binary;
+	int (*rdvl)(void);
+
+	int prctl_get;
+	int prctl_set;
+	const char *default_vl_file;
+
+	int default_vl;
+	int min_vl;
+	int max_vl;
+};
+
+
+static struct vec_data vec_data[] = {
+	{
+		.name = "SVE",
+		.hwcap_type = AT_HWCAP,
+		.hwcap = HWCAP_SVE,
+		.rdvl = rdvl_sve,
+		.rdvl_binary = "./rdvl-sve",
+		.prctl_get = PR_SVE_GET_VL,
+		.prctl_set = PR_SVE_SET_VL,
+		.default_vl_file = "/proc/sys/abi/sve_default_vector_length",
+	},
+	{
+		.name = "SME",
+		.hwcap_type = AT_HWCAP2,
+		.hwcap = HWCAP2_SME,
+		.rdvl = rdvl_sme,
+		.rdvl_binary = "./rdvl-sme",
+		.prctl_get = PR_SME_GET_VL,
+		.prctl_set = PR_SME_SET_VL,
+		.default_vl_file = "/proc/sys/abi/sme_default_vector_length",
+	},
+};
+
+static int stdio_read_integer(FILE *f, const char *what, int *val)
+{
+	int n = 0;
+	int ret;
+
+	ret = fscanf(f, "%d%*1[\n]%n", val, &n);
+	if (ret < 1 || n < 1) {
+		ksft_print_msg("failed to parse integer from %s\n", what);
+		return -1;
+	}
+
+	return 0;
+}
+
+/* Start a new process and return the vector length it sees */
+static int get_child_rdvl(struct vec_data *data)
+{
+	FILE *out;
+	int pipefd[2];
+	pid_t pid, child;
+	int read_vl, ret;
+
+	ret = pipe(pipefd);
+	if (ret == -1) {
+		ksft_print_msg("pipe() failed: %d (%s)\n",
+			       errno, strerror(errno));
+		return -1;
+	}
+
+	fflush(stdout);
+
+	child = fork();
+	if (child == -1) {
+		ksft_print_msg("fork() failed: %d (%s)\n",
+			       errno, strerror(errno));
+		close(pipefd[0]);
+		close(pipefd[1]);
+		return -1;
+	}
+
+	/* Child: put vector length on the pipe */
+	if (child == 0) {
+		/*
+		 * Replace stdout with the pipe, errors to stderr from
+		 * here as kselftest prints to stdout.
+		 */
+		ret = dup2(pipefd[1], 1);
+		if (ret == -1) {
+			fprintf(stderr, "dup2() %d\n", errno);
+			exit(EXIT_FAILURE);
+		}
+
+		/* exec() a new binary which puts the VL on stdout */
+		ret = execl(data->rdvl_binary, data->rdvl_binary, NULL);
+		fprintf(stderr, "execl(%s) failed: %d (%s)\n",
+			data->rdvl_binary, errno, strerror(errno));
+
+		exit(EXIT_FAILURE);
+	}
+
+	close(pipefd[1]);
+
+	/* Parent; wait for the exit status from the child & verify it */
+	do {
+		pid = wait(&ret);
+		if (pid == -1) {
+			ksft_print_msg("wait() failed: %d (%s)\n",
+				       errno, strerror(errno));
+			close(pipefd[0]);
+			return -1;
+		}
+	} while (pid != child);
+
+	assert(pid == child);
+
+	if (!WIFEXITED(ret)) {
+		ksft_print_msg("child exited abnormally\n");
+		close(pipefd[0]);
+		return -1;
+	}
+
+	if (WEXITSTATUS(ret) != 0) {
+		ksft_print_msg("child returned error %d\n",
+			       WEXITSTATUS(ret));
+		close(pipefd[0]);
+		return -1;
+	}
+
+	out = fdopen(pipefd[0], "r");
+	if (!out) {
+		ksft_print_msg("failed to open child stdout\n");
+		close(pipefd[0]);
+		return -1;
+	}
+
+	ret = stdio_read_integer(out, "child", &read_vl);
+	fclose(out);
+	if (ret != 0)
+		return ret;
+
+	return read_vl;
+}
+
+static int file_read_integer(const char *name, int *val)
+{
+	FILE *f;
+	int ret;
+
+	f = fopen(name, "r");
+	if (!f) {
+		ksft_test_result_fail("Unable to open %s: %d (%s)\n",
+				      name, errno,
+				      strerror(errno));
+		return -1;
+	}
+
+	ret = stdio_read_integer(f, name, val);
+	fclose(f);
+
+	return ret;
+}
+
+static int file_write_integer(const char *name, int val)
+{
+	FILE *f;
+
+	f = fopen(name, "w");
+	if (!f) {
+		ksft_test_result_fail("Unable to open %s: %d (%s)\n",
+				      name, errno,
+				      strerror(errno));
+		return -1;
+	}
+
+	fprintf(f, "%d", val);
+	fclose(f);
+
+	return 0;
+}
+
+/*
+ * Verify that we can read the default VL via proc, checking that it
+ * is set in a freshly spawned child.
+ */
+static void proc_read_default(struct vec_data *data)
+{
+	int default_vl, child_vl, ret;
+
+	ret = file_read_integer(data->default_vl_file, &default_vl);
+	if (ret != 0)
+		return;
+
+	/* Is this the actual default seen by new processes? */
+	child_vl = get_child_rdvl(data);
+	if (child_vl != default_vl) {
+		ksft_test_result_fail("%s is %d but child VL is %d\n",
+				      data->default_vl_file,
+				      default_vl, child_vl);
+		return;
+	}
+
+	ksft_test_result_pass("%s default vector length %d\n", data->name,
+			      default_vl);
+	data->default_vl = default_vl;
+}
+
+/* Verify that we can write a minimum value and have it take effect */
+static void proc_write_min(struct vec_data *data)
+{
+	int ret, new_default, child_vl;
+
+	if (geteuid() != 0) {
+		ksft_test_result_skip("Need to be root to write to /proc\n");
+		return;
+	}
+
+	ret = file_write_integer(data->default_vl_file, ARCH_MIN_VL);
+	if (ret != 0)
+		return;
+
+	/* What was the new value? */
+	ret = file_read_integer(data->default_vl_file, &new_default);
+	if (ret != 0)
+		return;
+
+	/* Did it take effect in a new process? */
+	child_vl = get_child_rdvl(data);
+	if (child_vl != new_default) {
+		ksft_test_result_fail("%s is %d but child VL is %d\n",
+				      data->default_vl_file,
+				      new_default, child_vl);
+		return;
+	}
+
+	ksft_test_result_pass("%s minimum vector length %d\n", data->name,
+			      new_default);
+	data->min_vl = new_default;
+
+	file_write_integer(data->default_vl_file, data->default_vl);
+}
+
+/* Verify that we can write a maximum value and have it take effect */
+static void proc_write_max(struct vec_data *data)
+{
+	int ret, new_default, child_vl;
+
+	if (geteuid() != 0) {
+		ksft_test_result_skip("Need to be root to write to /proc\n");
+		return;
+	}
+
+	/* -1 is accepted by the /proc interface as the maximum VL */
+	ret = file_write_integer(data->default_vl_file, -1);
+	if (ret != 0)
+		return;
+
+	/* What was the new value? */
+	ret = file_read_integer(data->default_vl_file, &new_default);
+	if (ret != 0)
+		return;
+
+	/* Did it take effect in a new process? */
+	child_vl = get_child_rdvl(data);
+	if (child_vl != new_default) {
+		ksft_test_result_fail("%s is %d but child VL is %d\n",
+				      data->default_vl_file,
+				      new_default, child_vl);
+		return;
+	}
+
+	ksft_test_result_pass("%s maximum vector length %d\n", data->name,
+			      new_default);
+	data->max_vl = new_default;
+
+	file_write_integer(data->default_vl_file, data->default_vl);
+}
+
+/* Can we read back a VL from prctl? */
+static void prctl_get(struct vec_data *data)
+{
+	int ret;
+
+	ret = prctl(data->prctl_get);
+	if (ret == -1) {
+		ksft_test_result_fail("%s prctl() read failed: %d (%s)\n",
+				      data->name, errno, strerror(errno));
+		return;
+	}
+
+	/* Mask out any flags */
+	ret &= PR_SVE_VL_LEN_MASK;
+
+	/* Is that what we can read back directly? */
+	if (ret == data->rdvl())
+		ksft_test_result_pass("%s current VL is %d\n",
+				      data->name, ret);
+	else
+		ksft_test_result_fail("%s prctl() VL %d but RDVL is %d\n",
+				      data->name, ret, data->rdvl());
+}
+
+/* Does the prctl let us set the VL we already have? */
+static void prctl_set_same(struct vec_data *data)
+{
+	int cur_vl = data->rdvl();
+	int ret;
+
+	ret = prctl(data->prctl_set, cur_vl);
+	if (ret < 0) {
+		ksft_test_result_fail("%s prctl set failed: %d (%s)\n",
+				      data->name, errno, strerror(errno));
+		return;
+	}
+
+	ksft_test_result(cur_vl == data->rdvl(),
+			 "%s set VL %d and have VL %d\n",
+			 data->name, cur_vl, data->rdvl());
+}
+
+/* Can we set a new VL for this process? */
+static void prctl_set(struct vec_data *data)
+{
+	int ret;
+
+	if (data->min_vl == data->max_vl) {
+		ksft_test_result_skip("%s only one VL supported\n",
+				      data->name);
+		return;
+	}
+
+	/* Try to set the minimum VL */
+	ret = prctl(data->prctl_set, data->min_vl);
+	if (ret < 0) {
+		ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n",
+				      data->name, data->min_vl,
+				      errno, strerror(errno));
+		return;
+	}
+
+	if ((ret & PR_SVE_VL_LEN_MASK) != data->min_vl) {
+		ksft_test_result_fail("%s prctl set %d but return value is %d\n",
+				      data->name, data->min_vl, data->rdvl());
+		return;
+	}
+
+	if (data->rdvl() != data->min_vl) {
+		ksft_test_result_fail("%s set %d but RDVL is %d\n",
+				      data->name, data->min_vl, data->rdvl());
+		return;
+	}
+
+	/* Try to set the maximum VL */
+	ret = prctl(data->prctl_set, data->max_vl);
+	if (ret < 0) {
+		ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n",
+				      data->name, data->max_vl,
+				      errno, strerror(errno));
+		return;
+	}
+
+	if ((ret & PR_SVE_VL_LEN_MASK) != data->max_vl) {
+		ksft_test_result_fail("%s prctl() set %d but return value is %d\n",
+				      data->name, data->max_vl, data->rdvl());
+		return;
+	}
+
+	/* The _INHERIT flag should not be present when we read the VL */
+	ret = prctl(data->prctl_get);
+	if (ret == -1) {
+		ksft_test_result_fail("%s prctl() read failed: %d (%s)\n",
+				      data->name, errno, strerror(errno));
+		return;
+	}
+
+	if (ret & PR_SVE_VL_INHERIT) {
+		ksft_test_result_fail("%s prctl() reports _INHERIT\n",
+				      data->name);
+		return;
+	}
+
+	ksft_test_result_pass("%s prctl() set min/max\n", data->name);
+}
+
+/* If we didn't request it a new VL shouldn't affect the child */
+static void prctl_set_no_child(struct vec_data *data)
+{
+	int ret, child_vl;
+
+	if (data->min_vl == data->max_vl) {
+		ksft_test_result_skip("%s only one VL supported\n",
+				      data->name);
+		return;
+	}
+
+	ret = prctl(data->prctl_set, data->min_vl);
+	if (ret < 0) {
+		ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n",
+				      data->name, data->min_vl,
+				      errno, strerror(errno));
+		return;
+	}
+
+	/* Ensure the default VL is different */
+	ret = file_write_integer(data->default_vl_file, data->max_vl);
+	if (ret != 0)
+		return;
+
+	/* Check that the child has the default we just set */
+	child_vl = get_child_rdvl(data);
+	if (child_vl != data->max_vl) {
+		ksft_test_result_fail("%s is %d but child VL is %d\n",
+				      data->default_vl_file,
+				      data->max_vl, child_vl);
+		return;
+	}
+
+	ksft_test_result_pass("%s vector length used default\n", data->name);
+
+	file_write_integer(data->default_vl_file, data->default_vl);
+}
+
+/* If we didn't request it a new VL shouldn't affect the child */
+static void prctl_set_for_child(struct vec_data *data)
+{
+	int ret, child_vl;
+
+	if (data->min_vl == data->max_vl) {
+		ksft_test_result_skip("%s only one VL supported\n",
+				      data->name);
+		return;
+	}
+
+	ret = prctl(data->prctl_set, data->min_vl | PR_SVE_VL_INHERIT);
+	if (ret < 0) {
+		ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n",
+				      data->name, data->min_vl,
+				      errno, strerror(errno));
+		return;
+	}
+
+	/* The _INHERIT flag should be present when we read the VL */
+	ret = prctl(data->prctl_get);
+	if (ret == -1) {
+		ksft_test_result_fail("%s prctl() read failed: %d (%s)\n",
+				      data->name, errno, strerror(errno));
+		return;
+	}
+	if (!(ret & PR_SVE_VL_INHERIT)) {
+		ksft_test_result_fail("%s prctl() does not report _INHERIT\n",
+				      data->name);
+		return;
+	}
+
+	/* Ensure the default VL is different */
+	ret = file_write_integer(data->default_vl_file, data->max_vl);
+	if (ret != 0)
+		return;
+
+	/* Check that the child inherited our VL */
+	child_vl = get_child_rdvl(data);
+	if (child_vl != data->min_vl) {
+		ksft_test_result_fail("%s is %d but child VL is %d\n",
+				      data->default_vl_file,
+				      data->min_vl, child_vl);
+		return;
+	}
+
+	ksft_test_result_pass("%s vector length was inherited\n", data->name);
+
+	file_write_integer(data->default_vl_file, data->default_vl);
+}
+
+/* _ONEXEC takes effect only in the child process */
+static void prctl_set_onexec(struct vec_data *data)
+{
+	int ret, child_vl;
+
+	if (data->min_vl == data->max_vl) {
+		ksft_test_result_skip("%s only one VL supported\n",
+				      data->name);
+		return;
+	}
+
+	/* Set a known value for the default and our current VL */
+	ret = file_write_integer(data->default_vl_file, data->max_vl);
+	if (ret != 0)
+		return;
+
+	ret = prctl(data->prctl_set, data->max_vl);
+	if (ret < 0) {
+		ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n",
+				      data->name, data->min_vl,
+				      errno, strerror(errno));
+		return;
+	}
+
+	/* Set a different value for the child to have on exec */
+	ret = prctl(data->prctl_set, data->min_vl | PR_SVE_SET_VL_ONEXEC);
+	if (ret < 0) {
+		ksft_test_result_fail("%s prctl set failed for %d: %d (%s)\n",
+				      data->name, data->min_vl,
+				      errno, strerror(errno));
+		return;
+	}
+
+	/* Our current VL should stay the same */
+	if (data->rdvl() != data->max_vl) {
+		ksft_test_result_fail("%s VL changed by _ONEXEC prctl()\n",
+				      data->name);
+		return;
+	}
+
+	/* Check that the child inherited our VL */
+	child_vl = get_child_rdvl(data);
+	if (child_vl != data->min_vl) {
+		ksft_test_result_fail("Set %d _ONEXEC but child VL is %d\n",
+				      data->min_vl, child_vl);
+		return;
+	}
+
+	ksft_test_result_pass("%s vector length set on exec\n", data->name);
+
+	file_write_integer(data->default_vl_file, data->default_vl);
+}
+
+/* For each VQ verify that setting via prctl() does the right thing */
+static void prctl_set_all_vqs(struct vec_data *data)
+{
+	int ret, vq, vl, new_vl;
+	int errors = 0;
+
+	if (!data->min_vl || !data->max_vl) {
+		ksft_test_result_skip("%s Failed to enumerate VLs, not testing VL setting\n",
+				      data->name);
+		return;
+	}
+
+	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+		vl = sve_vl_from_vq(vq);
+
+		/* Attempt to set the VL */
+		ret = prctl(data->prctl_set, vl);
+		if (ret < 0) {
+			errors++;
+			ksft_print_msg("%s prctl set failed for %d: %d (%s)\n",
+				       data->name, vl,
+				       errno, strerror(errno));
+			continue;
+		}
+
+		new_vl = ret & PR_SVE_VL_LEN_MASK;
+
+		/* Check that we actually have the reported new VL */
+		if (data->rdvl() != new_vl) {
+			ksft_print_msg("Set %s VL %d but RDVL reports %d\n",
+				       data->name, new_vl, data->rdvl());
+			errors++;
+		}
+
+		/* Was that the VL we asked for? */
+		if (new_vl == vl)
+			continue;
+
+		/* Should round up to the minimum VL if below it */
+		if (vl < data->min_vl) {
+			if (new_vl != data->min_vl) {
+				ksft_print_msg("%s VL %d returned %d not minimum %d\n",
+					       data->name, vl, new_vl,
+					       data->min_vl);
+				errors++;
+			}
+
+			continue;
+		}
+
+		/* Should round down to maximum VL if above it */
+		if (vl > data->max_vl) {
+			if (new_vl != data->max_vl) {
+				ksft_print_msg("%s VL %d returned %d not maximum %d\n",
+					       data->name, vl, new_vl,
+					       data->max_vl);
+				errors++;
+			}
+
+			continue;
+		}
+
+		/* Otherwise we should've rounded down */
+		if (!(new_vl < vl)) {
+			ksft_print_msg("%s VL %d returned %d, did not round down\n",
+				       data->name, vl, new_vl);
+			errors++;
+
+			continue;
+		}
+	}
+
+	ksft_test_result(errors == 0, "%s prctl() set all VLs, %d errors\n",
+			 data->name, errors);
+}
+
+typedef void (*test_type)(struct vec_data *);
+
+static const test_type tests[] = {
+	/*
+	 * The default/min/max tests must be first and in this order
+	 * to provide data for other tests.
+	 */
+	proc_read_default,
+	proc_write_min,
+	proc_write_max,
+
+	prctl_get,
+	prctl_set_same,
+	prctl_set,
+	prctl_set_no_child,
+	prctl_set_for_child,
+	prctl_set_onexec,
+	prctl_set_all_vqs,
+};
+
+int main(void)
+{
+	int i, j;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests) * ARRAY_SIZE(vec_data));
+
+	for (i = 0; i < ARRAY_SIZE(vec_data); i++) {
+		struct vec_data *data = &vec_data[i];
+		unsigned long supported;
+
+		supported = getauxval(data->hwcap_type) & data->hwcap;
+
+		for (j = 0; j < ARRAY_SIZE(tests); j++) {
+			if (supported)
+				tests[j](data);
+			else
+				ksft_test_result_skip("%s not supported\n",
+						      data->name);
+		}
+	}
+
+	ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/arm64/fp/vlset.c b/tools/testing/selftests/arm64/fp/vlset.c
new file mode 100644
index 000000000..76912a581
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/vlset.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015-2019 ARM Limited.
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+#define _GNU_SOURCE
+#include <assert.h>
+#include <errno.h>
+#include <limits.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <getopt.h>
+#include <unistd.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <asm/hwcap.h>
+#include <asm/sigcontext.h>
+
+static int inherit = 0;
+static int no_inherit = 0;
+static int force = 0;
+static unsigned long vl;
+static int set_ctl = PR_SVE_SET_VL;
+static int get_ctl = PR_SVE_GET_VL;
+
+static const struct option options[] = {
+	{ "force",	no_argument, NULL, 'f' },
+	{ "inherit",	no_argument, NULL, 'i' },
+	{ "max",	no_argument, NULL, 'M' },
+	{ "no-inherit",	no_argument, &no_inherit, 1 },
+	{ "sme",	no_argument, NULL, 's' },
+	{ "help",	no_argument, NULL, '?' },
+	{}
+};
+
+static char const *program_name;
+
+static int parse_options(int argc, char **argv)
+{
+	int c;
+	char *rest;
+
+	program_name = strrchr(argv[0], '/');
+	if (program_name)
+		++program_name;
+	else
+		program_name = argv[0];
+
+	while ((c = getopt_long(argc, argv, "Mfhi", options, NULL)) != -1)
+		switch (c) {
+		case 'M':	vl = SVE_VL_MAX; break;
+		case 'f':	force = 1; break;
+		case 'i':	inherit = 1; break;
+		case 's':	set_ctl = PR_SME_SET_VL;
+				get_ctl = PR_SME_GET_VL;
+				break;
+		case 0:		break;
+		default:	goto error;
+		}
+
+	if (inherit && no_inherit)
+		goto error;
+
+	if (!vl) {
+		/* vector length */
+		if (optind >= argc)
+			goto error;
+
+		errno = 0;
+		vl = strtoul(argv[optind], &rest, 0);
+		if (*rest) {
+			vl = ULONG_MAX;
+			errno = EINVAL;
+		}
+		if (vl == ULONG_MAX && errno) {
+			fprintf(stderr, "%s: %s: %s\n",
+				program_name, argv[optind], strerror(errno));
+			goto error;
+		}
+
+		++optind;
+	}
+
+	/* command */
+	if (optind >= argc)
+		goto error;
+
+	return 0;
+
+error:
+	fprintf(stderr,
+		"Usage: %s [-f | --force] "
+		"[-i | --inherit | --no-inherit] "
+		"{-M | --max | <vector length>} "
+		"<command> [<arguments> ...]\n",
+		program_name);
+	return -1;
+}
+
+int main(int argc, char **argv)
+{
+	int ret = 126;	/* same as sh(1) command-not-executable error */
+	long flags;
+	char *path;
+	int t, e;
+
+	if (parse_options(argc, argv))
+		return 2;	/* same as sh(1) builtin incorrect-usage */
+
+	if (vl & ~(vl & PR_SVE_VL_LEN_MASK)) {
+		fprintf(stderr, "%s: Invalid vector length %lu\n",
+			program_name, vl);
+		return 2;	/* same as sh(1) builtin incorrect-usage */
+	}
+
+	if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) {
+		fprintf(stderr, "%s: Scalable Vector Extension not present\n",
+			program_name);
+
+		if (!force)
+			goto error;
+
+		fputs("Going ahead anyway (--force):  "
+		      "This is a debug option.  Don't rely on it.\n",
+		      stderr);
+	}
+
+	flags = PR_SVE_SET_VL_ONEXEC;
+	if (inherit)
+		flags |= PR_SVE_VL_INHERIT;
+
+	t = prctl(set_ctl, vl | flags);
+	if (t < 0) {
+		fprintf(stderr, "%s: PR_SVE_SET_VL: %s\n",
+			program_name, strerror(errno));
+		goto error;
+	}
+
+	t = prctl(get_ctl);
+	if (t == -1) {
+		fprintf(stderr, "%s: PR_SVE_GET_VL: %s\n",
+			program_name, strerror(errno));
+		goto error;
+	}
+	flags = PR_SVE_VL_LEN_MASK;
+	flags = t & ~flags;
+
+	assert(optind < argc);
+	path = argv[optind];
+
+	execvp(path, &argv[optind]);
+	e = errno;
+	if (errno == ENOENT)
+		ret = 127;	/* same as sh(1) not-found error */
+	fprintf(stderr, "%s: %s: %s\n", program_name, path, strerror(e));
+
+error:
+	return ret;		/* same as sh(1) not-executable error */
+}
diff --git a/tools/testing/selftests/arm64/fp/za-fork-asm.S b/tools/testing/selftests/arm64/fp/za-fork-asm.S
new file mode 100644
index 000000000..2fafadd49
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-fork-asm.S
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define MAGIC     42
+
+#define MAXVL     2048
+#define MAXVL_B   (MAXVL / 8)
+
+.pushsection .text
+.data
+.align 4
+scratch:
+	.space	MAXVL_B
+.popsection
+
+.globl fork_test
+fork_test:
+	smstart_za
+
+	// For simplicity just set one word in one vector, other tests
+	// cover general data corruption issues.
+	ldr	x0, =scratch
+	mov	x1, #MAGIC
+	str	x1, [x0]
+	mov	w12, wzr
+	_ldr_za 12, 0			// ZA.H[W12] loaded from [X0]
+
+	// Tail call into the C portion that does the fork & verify
+	b	fork_test_c
+
+.globl verify_fork
+verify_fork:
+	// SVCR should have ZA=1, SM=0
+	mrs	x0, S3_3_C4_C2_2
+	and	x1, x0, #3
+	cmp	x1, #2
+	beq	1f
+	mov	x0, xzr
+	b	100f
+1:
+
+	// ZA should still have the value we loaded
+	ldr	x0, =scratch
+	mov	w12, wzr
+	_str_za 12, 0			// ZA.H[W12] stored to [X0]
+	ldr	x1, [x0]
+	cmp	x1, #MAGIC
+	beq	2f
+	mov	x0, xzr
+	b	100f
+
+2:
+	// All tests passed
+	mov	x0, #1
+100:
+	ret
+
diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c
new file mode 100644
index 000000000..ff475c649
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-fork.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 ARM Limited.
+ * Original author: Mark Brown <broonie@kernel.org>
+ */
+
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#define EXPECTED_TESTS 1
+
+static void putstr(const char *str)
+{
+	write(1, str, strlen(str));
+}
+
+static void putnum(unsigned int num)
+{
+	char c;
+
+	if (num / 10)
+		putnum(num / 10);
+
+	c = '0' + (num % 10);
+	write(1, &c, 1);
+}
+
+static int tests_run;
+static int tests_passed;
+static int tests_failed;
+static int tests_skipped;
+
+static void print_summary(void)
+{
+	if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS)
+		putstr("# UNEXPECTED TEST COUNT: ");
+
+	putstr("# Totals: pass:");
+	putnum(tests_passed);
+	putstr(" fail:");
+	putnum(tests_failed);
+	putstr(" xfail:0 xpass:0 skip:");
+	putnum(tests_skipped);
+	putstr(" error:0\n");
+}
+
+int fork_test(void);
+int verify_fork(void);
+
+/*
+ * If we fork the value in the parent should be unchanged and the
+ * child should start with the same value.  This is called from the
+ * fork_test() asm function.
+ */
+int fork_test_c(void)
+{
+	pid_t newpid, waiting;
+	int child_status, parent_result;
+
+	newpid = fork();
+	if (newpid == 0) {
+		/* In child */
+		if (!verify_fork()) {
+			putstr("# ZA state invalid in child\n");
+			exit(0);
+		} else {
+			exit(1);
+		}
+	}
+	if (newpid < 0) {
+		putstr("# fork() failed: -");
+		putnum(-newpid);
+		putstr("\n");
+		return 0;
+	}
+
+	parent_result = verify_fork();
+	if (!parent_result)
+		putstr("# ZA state invalid in parent\n");
+
+	for (;;) {
+		waiting = waitpid(newpid, &child_status, 0);
+
+		if (waiting < 0) {
+			if (errno == EINTR)
+				continue;
+			putstr("# waitpid() failed: ");
+			putnum(errno);
+			putstr("\n");
+			return 0;
+		}
+		if (waiting != newpid) {
+			putstr("# waitpid() returned wrong PID\n");
+			return 0;
+		}
+
+		if (!WIFEXITED(child_status)) {
+			putstr("# child did not exit\n");
+			return 0;
+		}
+
+		return WEXITSTATUS(child_status) && parent_result;
+	}
+}
+
+#define run_test(name)			     \
+	if (name()) {			     \
+		tests_passed++;		     \
+	} else {			     \
+		tests_failed++;		     \
+		putstr("not ");		     \
+	}				     \
+	putstr("ok ");			     \
+	putnum(++tests_run);		     \
+	putstr(" " #name "\n");
+
+int main(int argc, char **argv)
+{
+	int ret, i;
+
+	putstr("TAP version 13\n");
+	putstr("1..");
+	putnum(EXPECTED_TESTS);
+	putstr("\n");
+
+	putstr("# PID: ");
+	putnum(getpid());
+	putstr("\n");
+
+	/*
+	 * This test is run with nolibc which doesn't support hwcap and
+	 * it's probably disproportionate to implement so instead check
+	 * for the default vector length configuration in /proc.
+	 */
+	ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
+	if (ret >= 0) {
+		run_test(fork_test);
+
+	} else {
+		putstr("# SME support not present\n");
+
+		for (i = 0; i < EXPECTED_TESTS; i++) {
+			putstr("ok ");
+			putnum(i);
+			putstr(" skipped\n");
+		}
+
+		tests_skipped += EXPECTED_TESTS;
+	}
+
+	print_summary();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c
new file mode 100644
index 000000000..bf6158654
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-ptrace.c
@@ -0,0 +1,356 @@
+// 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
+
+#define EXPECTED_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
+
+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);
+}
+
+/* Validate attempting to set the specfied VL via ptrace */
+static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported)
+{
+	struct user_za_header za;
+	struct user_za_header *new_za = NULL;
+	size_t new_za_size = 0;
+	int ret, prctl_vl;
+
+	*supported = false;
+
+	/* Check if the VL is supported in this process */
+	prctl_vl = prctl(PR_SME_SET_VL, vl);
+	if (prctl_vl == -1)
+		ksft_exit_fail_msg("prctl(PR_SME_SET_VL) failed: %s (%d)\n",
+				   strerror(errno), errno);
+
+	/* If the VL is not supported then a supported VL will be returned */
+	*supported = (prctl_vl == vl);
+
+	/* Set the VL by doing a set with no register payload */
+	memset(&za, 0, sizeof(za));
+	za.size = sizeof(za);
+	za.vl = vl;
+	ret = set_za(child, &za);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set VL %u\n", vl);
+		return;
+	}
+
+	/*
+	 * Read back the new register state and verify that we have the
+	 * same VL that we got from prctl() on ourselves.
+	 */
+	if (!get_za(child, (void **)&new_za, &new_za_size)) {
+		ksft_test_result_fail("Failed to read VL %u\n", vl);
+		return;
+	}
+
+	ksft_test_result(new_za->vl = prctl_vl, "Set VL %u\n", vl);
+
+	free(new_za);
+}
+
+/* Validate attempting to set no ZA data and read it back */
+static void ptrace_set_no_data(pid_t child, unsigned int vl)
+{
+	void *read_buf = NULL;
+	struct user_za_header write_za;
+	struct user_za_header *read_za;
+	size_t read_za_size = 0;
+	int ret;
+
+	/* Set up some data and write it out */
+	memset(&write_za, 0, sizeof(write_za));
+	write_za.size = ZA_PT_ZA_OFFSET;
+	write_za.vl = vl;
+
+	ret = set_za(child, &write_za);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set VL %u no data\n", vl);
+		return;
+	}
+
+	/* Read the data back */
+	if (!get_za(child, (void **)&read_buf, &read_za_size)) {
+		ksft_test_result_fail("Failed to read VL %u no data\n", vl);
+		return;
+	}
+	read_za = read_buf;
+
+	/* We might read more data if there's extensions we don't know */
+	if (read_za->size < write_za.size) {
+		ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n",
+				      vl, write_za.size, read_za->size);
+		goto out_read;
+	}
+
+	ksft_test_result(read_za->size == write_za.size,
+			 "Disabled ZA for VL %u\n", vl);
+
+out_read:
+	free(read_buf);
+}
+
+/* Validate attempting to set data and read it back */
+static void ptrace_set_get_data(pid_t child, unsigned int vl)
+{
+	void *write_buf;
+	void *read_buf = NULL;
+	struct user_za_header *write_za;
+	struct user_za_header *read_za;
+	size_t read_za_size = 0;
+	unsigned int vq = sve_vq_from_vl(vl);
+	int ret;
+	size_t data_size;
+
+	data_size = ZA_PT_SIZE(vq);
+	write_buf = malloc(data_size);
+	if (!write_buf) {
+		ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n",
+				      data_size, vl);
+		return;
+	}
+	write_za = write_buf;
+
+	/* Set up some data and write it out */
+	memset(write_za, 0, data_size);
+	write_za->size = data_size;
+	write_za->vl = vl;
+
+	fill_buf(write_buf + ZA_PT_ZA_OFFSET, ZA_PT_ZA_SIZE(vq));
+
+	ret = set_za(child, write_za);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set VL %u data\n", vl);
+		goto out;
+	}
+
+	/* Read the data back */
+	if (!get_za(child, (void **)&read_buf, &read_za_size)) {
+		ksft_test_result_fail("Failed to read VL %u data\n", vl);
+		goto out;
+	}
+	read_za = read_buf;
+
+	/* We might read more data if there's extensions we don't know */
+	if (read_za->size < write_za->size) {
+		ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n",
+				      vl, write_za->size, read_za->size);
+		goto out_read;
+	}
+
+	ksft_test_result(memcmp(write_buf + ZA_PT_ZA_OFFSET,
+				read_buf + ZA_PT_ZA_OFFSET,
+				ZA_PT_ZA_SIZE(vq)) == 0,
+			 "Data match for VL %u\n", vl);
+
+out_read:
+	free(read_buf);
+out:
+	free(write_buf);
+}
+
+static int do_parent(pid_t child)
+{
+	int ret = EXIT_FAILURE;
+	pid_t pid;
+	int status;
+	siginfo_t si;
+	unsigned int vq, vl;
+	bool vl_supported;
+
+	/* 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);
+
+	/* Step through every possible VQ */
+	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+		vl = sve_vl_from_vq(vq);
+
+		/* First, try to set this vector length */
+		ptrace_set_get_vl(child, vl, &vl_supported);
+
+		/* If the VL is supported validate data set/get */
+		if (vl_supported) {
+			ptrace_set_no_data(child, vl);
+			ptrace_set_get_data(child, vl);
+		} else {
+			ksft_test_result_skip("Disabled ZA for VL %u\n", vl);
+			ksft_test_result_skip("Get and set data for VL %u\n",
+					      vl);
+		}
+	}
+
+	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_SME)) {
+		ksft_set_plan(1);
+		ksft_exit_skip("SME not available\n");
+	}
+
+	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/za-stress b/tools/testing/selftests/arm64/fp/za-stress
new file mode 100644
index 000000000..5ac386b55
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-stress
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+	trap - INT TERM CHLD
+	set +e
+
+	if [ -n "$pids" ]; then
+		kill $pids
+		wait $pids
+		pids=
+	fi
+
+	if [ -n "$logs" ]; then
+		cat $logs
+		rm $logs
+		logs=
+	fi
+}
+
+interrupt () {
+	cleanup
+	exit 0
+}
+
+child_died () {
+	cleanup
+	exit 1
+}
+
+trap interrupt INT TERM EXIT
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+	log=`mktemp`
+	logs=$logs\ $log
+	./za-test >$log &
+	pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+	kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
new file mode 100644
index 000000000..53c54af65
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -0,0 +1,398 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+//
+// Scalable Matrix Extension ZA context switch test
+// Repeatedly writes unique test patterns into each ZA tile
+// and reads them back to verify integrity.
+//
+// for x in `seq 1 NR_CPUS`; do sve-test & pids=$pids\ $! ; done
+// (leave it running for as long as you want...)
+// kill $pids
+
+#include <asm/unistd.h>
+#include "assembler.h"
+#include "asm-offsets.h"
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define MAXVL     2048
+#define MAXVL_B   (MAXVL / 8)
+
+// Declare some storage space to shadow ZA register contents and a
+// scratch buffer for a vector.
+.pushsection .text
+.data
+.align 4
+zaref:
+	.space	MAXVL_B * MAXVL_B
+scratch:
+	.space	MAXVL_B
+.popsection
+
+// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0.
+// Clobbers x0-x3
+function memcpy
+	cmp	x2, #0
+	b.eq	1f
+0:	ldrb	w3, [x1], #1
+	strb	w3, [x0], #1
+	subs	x2, x2, #1
+	b.ne	0b
+1:	ret
+endfunction
+
+// Generate a test pattern for storage in ZA
+// x0: pid
+// x1: row in ZA
+// x2: generation
+
+// These values are used to constuct a 32-bit pattern that is repeated in the
+// scratch buffer as many times as will fit:
+// bits 31:28	generation number (increments once per test_loop)
+// bits 27:16	pid
+// bits 15: 8	row number
+// bits  7: 0	32-bit lane index
+
+function pattern
+	mov	w3, wzr
+	bfi	w3, w0, #16, #12	// PID
+	bfi	w3, w1, #8, #8		// Row
+	bfi	w3, w2, #28, #4		// Generation
+
+	ldr	x0, =scratch
+	mov	w1, #MAXVL_B / 4
+
+0:	str	w3, [x0], #4
+	add	w3, w3, #1		// Lane
+	subs	w1, w1, #1
+	b.ne	0b
+
+	ret
+endfunction
+
+// Get the address of shadow data for ZA horizontal vector xn
+.macro _adrza xd, xn, nrtmp
+	ldr	\xd, =zaref
+	rdsvl	\nrtmp, 1
+	madd	\xd, x\nrtmp, \xn, \xd
+.endm
+
+// Set up test pattern in a ZA horizontal vector
+// x0: pid
+// x1: row number
+// x2: generation
+function setup_za
+	mov	x4, x30
+	mov	x12, x1			// Use x12 for vector select
+
+	bl	pattern			// Get pattern in scratch buffer
+	_adrza	x0, x12, 2		// Shadow buffer pointer to x0 and x5
+	mov	x5, x0
+	ldr	x1, =scratch
+	bl	memcpy			// length set up in x2 by _adrza
+
+	_ldr_za 12, 5			// load vector w12 from pointer x5
+
+	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 ZA vector matches its shadow in memory, else abort
+// x0: row number
+// Clobbers x0-x7 and x12.
+function check_za
+	mov	x3, x30
+
+	mov	x12, x0
+	_adrza	x5, x0, 6		// pointer to expected value in x5
+	mov	x4, x0
+	ldr	x7, =scratch		// x7 is scratch
+
+	mov	x0, x7			// Poison scratch
+	mov	x1, x6
+	bl	memfill_ae
+
+	_str_za 12, 7			// save vector w12 to pointer x7
+
+	mov	x0, x5
+	mov	x1, x7
+	mov	x2, x6
+	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 ZA 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
+_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
+
+	puts	"Streaming mode "
+	smstart_za
+
+	// Sanity-check and report the vector length
+
+	rdsvl	19, 8
+	cmp	x19, #128
+	b.lo	1f
+	cmp	x19, #2048
+	b.hi	1f
+	tst	x19, #(8 - 1)
+	b.eq	2f
+
+1:	puts	"bad vector length: "
+	mov	x0, x19
+	bl	putdecn
+	b	.Labort
+
+2:	puts	"vector length:\t"
+	mov	x0, x19
+	bl	putdec
+	puts	" bits\n"
+
+	// 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:
+	rdsvl	0, 8
+	cmp	x0, x19
+	b.ne	vl_barf
+
+	rdsvl	21, 1		// Set up ZA & shadow with test pattern
+0:	mov	x0, x20
+	sub	x1, x21, #1
+	mov	x2, x22
+	bl	setup_za
+	subs	x21, x21, #1
+	b.ne	0b
+
+	mov	x8, #__NR_sched_yield	// encourage preemption
+1:
+	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
+
+	rdsvl	21, 1			// Verify that the data made it through
+	rdsvl	24, 1			// Verify that the data made it through
+0:	sub	x0, x24, x21
+	bl	check_za
+	subs	x21, x21, #1
+	bne	0b
+
+	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	", row="
+	mov	x0, x21
+	bl	putdecn
+	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 vl_barf
+	mov	x10, x0
+
+	puts	"Bad active VL: "
+	mov	x0, x10
+	bl	putdecn
+
+	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