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

Pull arm64 updates from Catalin Marinas:

 - arm64 perf: DDR PMU driver for Alibaba's T-Head Yitian 710 SoC, SVE
   vector granule register added to the user regs together with SVE perf
   extensions documentation.

 - SVE updates: add HWCAP for SVE EBF16, update the SVE ABI
   documentation to match the actual kernel behaviour (zeroing the
   registers on syscall rather than "zeroed or preserved" previously).

 - More conversions to automatic system registers generation.

 - vDSO: use self-synchronising virtual counter access in gettimeofday()
   if the architecture supports it.

 - arm64 stacktrace cleanups and improvements.

 - arm64 atomics improvements: always inline assembly, remove LL/SC
   trampolines.

 - Improve the reporting of EL1 exceptions: rework BTI and FPAC
   exception handling, better EL1 undefs reporting.

 - Cortex-A510 erratum 2658417: remove BF16 support due to incorrect
   result.

 - arm64 defconfig updates: build CoreSight as a module, enable options
   necessary for docker, memory hotplug/hotremove, enable all PMUs
   provided by Arm.

 - arm64 ptrace() support for TPIDR2_EL0 (register provided with the SME
   extensions).

 - arm64 ftraces updates/fixes: fix module PLTs with mcount, remove
   unused function.

 - kselftest updates for arm64: simple HWCAP validation, FP stress test
   improvements, validation of ZA regs in signal handlers, include
   larger SVE and SME vector lengths in signal tests, various cleanups.

 - arm64 alternatives (code patching) improvements to robustness and
   consistency: replace cpucap static branches with equivalent
   alternatives, associate callback alternatives with a cpucap.

 - Miscellaneous updates: optimise kprobe performance of patching
   single-step slots, simplify uaccess_mask_ptr(), move MTE registers
   initialisation to C, support huge vmalloc() mappings, run softirqs on
   the per-CPU IRQ stack, compat (arm32) misalignment fixups for
   multiword accesses.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (126 commits)
  arm64: alternatives: Use vdso/bits.h instead of linux/bits.h
  arm64/kprobe: Optimize the performance of patching single-step slot
  arm64: defconfig: Add Coresight as module
  kselftest/arm64: Handle EINTR while reading data from children
  kselftest/arm64: Flag fp-stress as exiting when we begin finishing up
  kselftest/arm64: Don't repeat termination handler for fp-stress
  ARM64: reloc_test: add __init/__exit annotations to module init/exit funcs
  arm64/mm: fold check for KFENCE into can_set_direct_map()
  arm64: ftrace: fix module PLTs with mcount
  arm64: module: Remove unused plt_entry_is_initialized()
  arm64: module: Make plt_equals_entry() static
  arm64: fix the build with binutils 2.27
  kselftest/arm64: Don't enable v8.5 for MTE selftest builds
  arm64: uaccess: simplify uaccess_mask_ptr()
  arm64: asm/perf_regs.h: Avoid C++-style comment in UAPI header
  kselftest/arm64: Fix typo in hwcap check
  arm64: mte: move register initialization to C
  arm64: mm: handle ARM64_KERNEL_USES_PMD_MAPS in vmemmap_populate()
  arm64: dma: Drop cache invalidation from arch_dma_prep_coherent()
  arm64/sve: Add Perf extensions documentation
  ...

32 files changed, 1555 insertions, 168 deletions

diff --git a/tools/testing/selftests/arm64/abi/.gitignore b/tools/testing/selftests/arm64/abi/.gitignore
index b9e54417250d..44f8b80f37e3 100644
--- a/tools/testing/selftests/arm64/abi/.gitignore
+++ b/tools/testing/selftests/arm64/abi/.gitignore
@@ -1,2 +1,4 @@
+hwcap
+ptrace
 syscall-abi
 tpidr2
diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile
index c8d7f2495eb2..a6d30c620908 100644
--- a/tools/testing/selftests/arm64/abi/Makefile
+++ b/tools/testing/selftests/arm64/abi/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (C) 2021 ARM Limited
 
-TEST_GEN_PROGS := syscall-abi tpidr2
+TEST_GEN_PROGS := hwcap ptrace syscall-abi tpidr2
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
new file mode 100644
index 000000000000..9f1a7b5c6193
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 ARM Limited.
+ */
+
+#include <errno.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/prctl.h>
+#include <asm/hwcap.h>
+#include <asm/sigcontext.h>
+#include <asm/unistd.h>
+
+#include "../../kselftest.h"
+
+#define TESTS_PER_HWCAP 2
+
+/*
+ * Function expected to generate SIGILL when the feature is not
+ * supported and return when it is supported. If SIGILL is generated
+ * then the handler must be able to skip over the instruction safely.
+ *
+ * Note that it is expected that for many architecture extensions
+ * there are no specific traps due to no architecture state being
+ * added so we may not fault if running on a kernel which doesn't know
+ * to add the hwcap.
+ */
+typedef void (*sigill_fn)(void);
+
+static void rng_sigill(void)
+{
+	asm volatile("mrs x0, S3_3_C2_C4_0" : : : "x0");
+}
+
+static void sme_sigill(void)
+{
+	/* RDSVL x0, #0 */
+	asm volatile(".inst 0x04bf5800" : : : "x0");
+}
+
+static void sve_sigill(void)
+{
+	/* RDVL x0, #0 */
+	asm volatile(".inst 0x04bf5000" : : : "x0");
+}
+
+static void sve2_sigill(void)
+{
+	/* SQABS Z0.b, P0/M, Z0.B */
+	asm volatile(".inst 0x4408A000" : : : "z0");
+}
+
+static void sveaes_sigill(void)
+{
+	/* AESD z0.b, z0.b, z0.b */
+	asm volatile(".inst 0x4522e400" : : : "z0");
+}
+
+static void svepmull_sigill(void)
+{
+	/* PMULLB Z0.Q, Z0.D, Z0.D */
+	asm volatile(".inst 0x45006800" : : : "z0");
+}
+
+static void svebitperm_sigill(void)
+{
+	/* BDEP Z0.B, Z0.B, Z0.B */
+	asm volatile(".inst 0x4500b400" : : : "z0");
+}
+
+static void svesha3_sigill(void)
+{
+	/* EOR3 Z0.D, Z0.D, Z0.D, Z0.D */
+	asm volatile(".inst 0x4203800" : : : "z0");
+}
+
+static void svesm4_sigill(void)
+{
+	/* SM4E Z0.S, Z0.S, Z0.S */
+	asm volatile(".inst 0x4523e000" : : : "z0");
+}
+
+static void svei8mm_sigill(void)
+{
+	/* USDOT Z0.S, Z0.B, Z0.B[0] */
+	asm volatile(".inst 0x44a01800" : : : "z0");
+}
+
+static void svef32mm_sigill(void)
+{
+	/* FMMLA Z0.S, Z0.S, Z0.S */
+	asm volatile(".inst 0x64a0e400" : : : "z0");
+}
+
+static void svef64mm_sigill(void)
+{
+	/* FMMLA Z0.D, Z0.D, Z0.D */
+	asm volatile(".inst 0x64e0e400" : : : "z0");
+}
+
+static void svebf16_sigill(void)
+{
+	/* BFCVT Z0.H, P0/M, Z0.S */
+	asm volatile(".inst 0x658aa000" : : : "z0");
+}
+
+static const struct hwcap_data {
+	const char *name;
+	unsigned long at_hwcap;
+	unsigned long hwcap_bit;
+	const char *cpuinfo;
+	sigill_fn sigill_fn;
+	bool sigill_reliable;
+} hwcaps[] = {
+	{
+		.name = "RNG",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_RNG,
+		.cpuinfo = "rng",
+		.sigill_fn = rng_sigill,
+	},
+	{
+		.name = "SME",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME,
+		.cpuinfo = "sme",
+		.sigill_fn = sme_sigill,
+		.sigill_reliable = true,
+	},
+	{
+		.name = "SVE",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SVE,
+		.cpuinfo = "sve",
+		.sigill_fn = sve_sigill,
+		.sigill_reliable = true,
+	},
+	{
+		.name = "SVE 2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVE2,
+		.cpuinfo = "sve2",
+		.sigill_fn = sve2_sigill,
+	},
+	{
+		.name = "SVE AES",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVEAES,
+		.cpuinfo = "sveaes",
+		.sigill_fn = sveaes_sigill,
+	},
+	{
+		.name = "SVE2 PMULL",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVEPMULL,
+		.cpuinfo = "svepmull",
+		.sigill_fn = svepmull_sigill,
+	},
+	{
+		.name = "SVE2 BITPERM",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVEBITPERM,
+		.cpuinfo = "svebitperm",
+		.sigill_fn = svebitperm_sigill,
+	},
+	{
+		.name = "SVE2 SHA3",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVESHA3,
+		.cpuinfo = "svesha3",
+		.sigill_fn = svesha3_sigill,
+	},
+	{
+		.name = "SVE2 SM4",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVESM4,
+		.cpuinfo = "svesm4",
+		.sigill_fn = svesm4_sigill,
+	},
+	{
+		.name = "SVE2 I8MM",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVEI8MM,
+		.cpuinfo = "svei8mm",
+		.sigill_fn = svei8mm_sigill,
+	},
+	{
+		.name = "SVE2 F32MM",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVEF32MM,
+		.cpuinfo = "svef32mm",
+		.sigill_fn = svef32mm_sigill,
+	},
+	{
+		.name = "SVE2 F64MM",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVEF64MM,
+		.cpuinfo = "svef64mm",
+		.sigill_fn = svef64mm_sigill,
+	},
+	{
+		.name = "SVE2 BF16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVEBF16,
+		.cpuinfo = "svebf16",
+		.sigill_fn = svebf16_sigill,
+	},
+	{
+		.name = "SVE2 EBF16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVE_EBF16,
+		.cpuinfo = "sveebf16",
+	},
+};
+
+static bool seen_sigill;
+
+static void handle_sigill(int sig, siginfo_t *info, void *context)
+{
+	ucontext_t *uc = context;
+
+	seen_sigill = true;
+
+	/* Skip over the offending instruction */
+	uc->uc_mcontext.pc += 4;
+}
+
+bool cpuinfo_present(const char *name)
+{
+	FILE *f;
+	char buf[2048], name_space[30], name_newline[30];
+	char *s;
+
+	/*
+	 * The feature should appear with a leading space and either a
+	 * trailing space or a newline.
+	 */
+	snprintf(name_space, sizeof(name_space), " %s ", name);
+	snprintf(name_newline, sizeof(name_newline), " %s\n", name);
+
+	f = fopen("/proc/cpuinfo", "r");
+	if (!f) {
+		ksft_print_msg("Failed to open /proc/cpuinfo\n");
+		return false;
+	}
+
+	while (fgets(buf, sizeof(buf), f)) {
+		/* Features: line? */
+		if (strncmp(buf, "Features\t:", strlen("Features\t:")) != 0)
+			continue;
+
+		/* All CPUs should be symmetric, don't read any more */
+		fclose(f);
+
+		s = strstr(buf, name_space);
+		if (s)
+			return true;
+		s = strstr(buf, name_newline);
+		if (s)
+			return true;
+
+		return false;
+	}
+
+	ksft_print_msg("Failed to find Features in /proc/cpuinfo\n");
+	fclose(f);
+	return false;
+}
+
+int main(void)
+{
+	const struct hwcap_data *hwcap;
+	int i, ret;
+	bool have_cpuinfo, have_hwcap;
+	struct sigaction sa;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(hwcaps) * TESTS_PER_HWCAP);
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handle_sigill;
+	sa.sa_flags = SA_RESTART | SA_SIGINFO;
+	sigemptyset(&sa.sa_mask);
+	ret = sigaction(SIGILL, &sa, NULL);
+	if (ret < 0)
+		ksft_exit_fail_msg("Failed to install SIGILL handler: %s (%d)\n",
+				   strerror(errno), errno);
+
+	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+		hwcap = &hwcaps[i];
+
+		have_hwcap = getauxval(hwcap->at_hwcap) & hwcap->hwcap_bit;
+		have_cpuinfo = cpuinfo_present(hwcap->cpuinfo);
+
+		if (have_hwcap)
+			ksft_print_msg("%s present\n", hwcap->name);
+
+		ksft_test_result(have_hwcap == have_cpuinfo,
+				 "cpuinfo_match_%s\n", hwcap->name);
+
+		if (hwcap->sigill_fn) {
+			seen_sigill = false;
+			hwcap->sigill_fn();
+
+			if (have_hwcap) {
+				/* Should be able to use the extension */
+				ksft_test_result(!seen_sigill, "sigill_%s\n",
+						 hwcap->name);
+			} else if (hwcap->sigill_reliable) {
+				/* Guaranteed a SIGILL */
+				ksft_test_result(seen_sigill, "sigill_%s\n",
+						 hwcap->name);
+			} else {
+				/* Missing SIGILL might be fine */
+				ksft_print_msg("SIGILL %sreported for %s\n",
+					       seen_sigill ? "" : "not ",
+					       hwcap->name);
+				ksft_test_result_skip("sigill_%s\n",
+						      hwcap->name);
+			}
+		} else {
+			ksft_test_result_skip("sigill_%s\n",
+					      hwcap->name);
+		}
+	}
+
+	ksft_print_cnts();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c
new file mode 100644
index 000000000000..be952511af22
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/ptrace.c
@@ -0,0 +1,241 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 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"
+
+#define EXPECTED_TESTS 7
+
+#define MAX_TPIDRS 2
+
+static bool have_sme(void)
+{
+	return getauxval(AT_HWCAP2) & HWCAP2_SME;
+}
+
+static void test_tpidr(pid_t child)
+{
+	uint64_t read_val[MAX_TPIDRS];
+	uint64_t write_val[MAX_TPIDRS];
+	struct iovec read_iov, write_iov;
+	bool test_tpidr2 = false;
+	int ret, i;
+
+	read_iov.iov_base = read_val;
+	write_iov.iov_base = write_val;
+
+	/* Should be able to read a single TPIDR... */
+	read_iov.iov_len = sizeof(uint64_t);
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_TLS, &read_iov);
+	ksft_test_result(ret == 0, "read_tpidr_one\n");
+
+	/* ...write a new value.. */
+	write_iov.iov_len = sizeof(uint64_t);
+	write_val[0] = read_val[0]++;
+	ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_TLS, &write_iov);
+	ksft_test_result(ret == 0, "write_tpidr_one\n");
+
+	/* ...then read it back */
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_TLS, &read_iov);
+	ksft_test_result(ret == 0 && write_val[0] == read_val[0],
+			 "verify_tpidr_one\n");
+
+	/* If we have TPIDR2 we should be able to read it */
+	read_iov.iov_len = sizeof(read_val);
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_TLS, &read_iov);
+	if (ret == 0) {
+		/* If we have SME there should be two TPIDRs */
+		if (read_iov.iov_len >= sizeof(read_val))
+			test_tpidr2 = true;
+
+		if (have_sme() && test_tpidr2) {
+			ksft_test_result(test_tpidr2, "count_tpidrs\n");
+		} else {
+			ksft_test_result(read_iov.iov_len % sizeof(uint64_t) == 0,
+					 "count_tpidrs\n");
+		}
+	} else {
+		ksft_test_result_fail("count_tpidrs\n");
+	}
+
+	if (test_tpidr2) {
+		/* Try to write new values to all known TPIDRs... */
+		write_iov.iov_len = sizeof(write_val);
+		for (i = 0; i < MAX_TPIDRS; i++)
+			write_val[i] = read_val[i] + 1;
+		ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_TLS, &write_iov);
+
+		ksft_test_result(ret == 0 &&
+				 write_iov.iov_len == sizeof(write_val),
+				 "tpidr2_write\n");
+
+		/* ...then read them back */
+		read_iov.iov_len = sizeof(read_val);
+		ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_TLS, &read_iov);
+
+		if (have_sme()) {
+			/* Should read back the written value */
+			ksft_test_result(ret == 0 &&
+					 read_iov.iov_len >= sizeof(read_val) &&
+					 memcmp(read_val, write_val,
+						sizeof(read_val)) == 0,
+					 "tpidr2_read\n");
+		} else {
+			/* TPIDR2 should read as zero */
+			ksft_test_result(ret == 0 &&
+					 read_iov.iov_len >= sizeof(read_val) &&
+					 read_val[0] == write_val[0] &&
+					 read_val[1] == 0,
+					 "tpidr2_read\n");
+		}
+
+		/* Writing only TPIDR... */
+		write_iov.iov_len = sizeof(uint64_t);
+		memcpy(write_val, read_val, sizeof(read_val));
+		write_val[0] += 1;
+		ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_TLS, &write_iov);
+
+		if (ret == 0) {
+			/* ...should leave TPIDR2 untouched */
+			read_iov.iov_len = sizeof(read_val);
+			ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_TLS,
+				     &read_iov);
+
+			ksft_test_result(ret == 0 &&
+					 read_iov.iov_len >= sizeof(read_val) &&
+					 memcmp(read_val, write_val,
+						sizeof(read_val)) == 0,
+					 "write_tpidr_only\n");
+		} else {
+			ksft_test_result_fail("write_tpidr_only\n");
+		}
+	} else {
+		ksft_test_result_skip("tpidr2_write\n");
+		ksft_test_result_skip("tpidr2_read\n");
+		ksft_test_result_skip("write_tpidr_only\n");
+	}
+}
+
+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 do_parent(pid_t child)
+{
+	int ret = EXIT_FAILURE;
+	pid_t pid;
+	int status;
+	siginfo_t si;
+
+	/* Attach to the child */
+	while (1) {
+		int sig;
+
+		pid = wait(&status);
+		if (pid == -1) {
+			perror("wait");
+			goto error;
+		}
+
+		/*
+		 * This should never happen but it's hard to flag in
+		 * the framework.
+		 */
+		if (pid != child)
+			continue;
+
+		if (WIFEXITED(status) || WIFSIGNALED(status))
+			ksft_exit_fail_msg("Child died unexpectedly\n");
+
+		if (!WIFSTOPPED(status))
+			goto error;
+
+		sig = WSTOPSIG(status);
+
+		if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &si)) {
+			if (errno == ESRCH)
+				goto disappeared;
+
+			if (errno == EINVAL) {
+				sig = 0; /* bust group-stop */
+				goto cont;
+			}
+
+			ksft_test_result_fail("PTRACE_GETSIGINFO: %s\n",
+					      strerror(errno));
+			goto error;
+		}
+
+		if (sig == SIGSTOP && si.si_code == SI_TKILL &&
+		    si.si_pid == pid)
+			break;
+
+	cont:
+		if (ptrace(PTRACE_CONT, pid, NULL, sig)) {
+			if (errno == ESRCH)
+				goto disappeared;
+
+			ksft_test_result_fail("PTRACE_CONT: %s\n",
+					      strerror(errno));
+			goto error;
+		}
+	}
+
+	ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
+
+	test_tpidr(child);
+
+	ret = EXIT_SUCCESS;
+
+error:
+	kill(child, SIGKILL);
+
+disappeared:
+	return ret;
+}
+
+int main(void)
+{
+	int ret = EXIT_SUCCESS;
+	pid_t child;
+
+	srandom(getpid());
+
+	ksft_print_header();
+
+	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/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
index b632bfe9e022..dd7ebe536d05 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi.c
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -112,9 +112,11 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	return errors;
 }
 
+#define SVE_Z_SHARED_BYTES (128 / 8)
+
 static uint8_t z_zero[__SVE_ZREG_SIZE(SVE_VQ_MAX)];
-uint8_t z_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
-uint8_t z_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+uint8_t z_in[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+uint8_t z_out[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
 
 static void setup_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		    uint64_t svcr)
@@ -133,22 +135,39 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	if (!sve_vl)
 		return 0;
 
-	/*
-	 * After a syscall the low 128 bits of the Z registers should
-	 * be preserved and the rest be zeroed or preserved, except if
-	 * we were in streaming mode in which case the low 128 bits may
-	 * also be cleared by the transition out of streaming mode.
-	 */
 	for (i = 0; i < SVE_NUM_ZREGS; i++) {
-		void *in = &z_in[reg_size * i];
-		void *out = &z_out[reg_size * i];
-
-		if ((memcmp(in, out, SVE_VQ_BYTES) != 0) &&
-		    !((svcr & SVCR_SM_MASK) &&
-		      memcmp(z_zero, out, SVE_VQ_BYTES) == 0)) {
-			ksft_print_msg("%s SVE VL %d Z%d low 128 bits changed\n",
-				       cfg->name, sve_vl, i);
-			errors++;
+		uint8_t *in = &z_in[reg_size * i];
+		uint8_t *out = &z_out[reg_size * i];
+
+		if (svcr & SVCR_SM_MASK) {
+			/*
+			 * In streaming mode the whole register should
+			 * be cleared by the transition out of
+			 * streaming mode.
+			 */
+			if (memcmp(z_zero, out, reg_size) != 0) {
+				ksft_print_msg("%s SVE VL %d Z%d non-zero\n",
+					       cfg->name, sve_vl, i);
+				errors++;
+			}
+		} else {
+			/*
+			 * For standard SVE the low 128 bits should be
+			 * preserved and any additional bits cleared.
+			 */
+			if (memcmp(in, out, SVE_Z_SHARED_BYTES) != 0) {
+				ksft_print_msg("%s SVE VL %d Z%d low 128 bits changed\n",
+					       cfg->name, sve_vl, i);
+				errors++;
+			}
+
+			if (reg_size > SVE_Z_SHARED_BYTES &&
+			    (memcmp(z_zero, out + SVE_Z_SHARED_BYTES,
+				    reg_size - SVE_Z_SHARED_BYTES) != 0)) {
+				ksft_print_msg("%s SVE VL %d Z%d high bits non-zero\n",
+					       cfg->name, sve_vl, i);
+				errors++;
+			}
 		}
 	}
 
@@ -176,9 +195,9 @@ static int check_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	if (!sve_vl)
 		return 0;
 
-	/* After a syscall the P registers should be preserved or zeroed */
+	/* After a syscall the P registers should be zeroed */
 	for (i = 0; i < SVE_NUM_PREGS * reg_size; i++)
-		if (p_out[i] && (p_in[i] != p_out[i]))
+		if (p_out[i])
 			errors++;
 	if (errors)
 		ksft_print_msg("%s SVE VL %d predicate registers non-zero\n",
@@ -226,9 +245,9 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	    !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64))
 		return 0;
 
-	/* After a syscall the P registers should be preserved or zeroed */
+	/* After a syscall FFR should be zeroed */
 	for (i = 0; i < reg_size; i++)
-		if (ffr_out[i] && (ffr_in[i] != ffr_out[i]))
+		if (ffr_out[i])
 			errors++;
 	if (errors)
 		ksft_print_msg("%s SVE VL %d FFR non-zero\n",
diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index ea947af63882..df79d29664a1 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -1,4 +1,5 @@
 fp-pidbench
+fp-stress
 fpsimd-test
 rdvl-sme
 rdvl-sve
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index a7c2286bf65b..36db61358ed5 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -5,7 +5,10 @@ top_srcdir = $(realpath ../../../../../)
 
 CFLAGS += -I$(top_srcdir)/usr/include/
 
-TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg za-fork za-ptrace
+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 \
diff --git a/tools/testing/selftests/arm64/fp/asm-offsets.h b/tools/testing/selftests/arm64/fp/asm-offsets.h
index a180851496ec..757b2fd75dd7 100644
--- a/tools/testing/selftests/arm64/fp/asm-offsets.h
+++ b/tools/testing/selftests/arm64/fp/asm-offsets.h
@@ -3,6 +3,7 @@
 #define sa_handler 0
 #define sa_mask_sz 8
 #define SIGUSR1 10
+#define SIGUSR2 12
 #define SIGTERM 15
 #define SIGINT 2
 #define SIGABRT 6
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 000000000000..4e62a9199f97
--- /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-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
index e21e8ea52c7e..918d04885a33 100644
--- a/tools/testing/selftests/arm64/fp/fpsimd-test.S
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -151,6 +151,15 @@ function irritator_handler
 	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
@@ -207,6 +216,30 @@ endfunction
 .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
@@ -237,24 +270,6 @@ _start:
 	mov	x0, x20
 	bl	putdecn
 
-	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	x22, #0		// generation number, increments per iteration
 .Ltest_loop:
 
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 589264231a2d..2a18cb4c528c 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -314,6 +314,15 @@ function irritator_handler
 	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
@@ -370,6 +379,30 @@ endfunction
 .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
@@ -405,24 +438,6 @@ _start:
 	mov	x0, x20
 	bl	putdecn
 
-	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
-
 #ifdef SSVE
 	smstart_sm		// syscalls will have exited streaming mode
 #endif
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
index 9ab6f9cd9623..53c54af65704 100644
--- a/tools/testing/selftests/arm64/fp/za-test.S
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -167,6 +167,15 @@ function irritator_handler
 	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
@@ -223,6 +232,30 @@ endfunction
 .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
 
@@ -255,24 +288,6 @@ _start:
 	mov	x0, x20
 	bl	putdecn
 
-	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	x22, #0		// generation number, increments per iteration
 .Ltest_loop:
 	rdsvl	0, 8
@@ -287,12 +302,7 @@ _start:
 	subs	x21, x21, #1
 	b.ne	0b
 
-	and	x8, x22, #127		// Every 128 interations...
-	cbz	x8, 0f
-	mov	x8, #__NR_getpid	// (otherwise minimal syscall)
-	b	1f
-0:
-	mov	x8, #__NR_sched_yield	// ...encourage preemption
+	mov	x8, #__NR_sched_yield	// encourage preemption
 1:
 	svc	#0
 
diff --git a/tools/testing/selftests/arm64/mte/Makefile b/tools/testing/selftests/arm64/mte/Makefile
index a5a0744423d8..037046f5784e 100644
--- a/tools/testing/selftests/arm64/mte/Makefile
+++ b/tools/testing/selftests/arm64/mte/Makefile
@@ -11,11 +11,8 @@ LDFLAGS += -pthread
 SRCS := $(filter-out mte_common_util.c,$(wildcard *.c))
 PROGS := $(patsubst %.c,%,$(SRCS))
 
-#Add mte compiler option
-CFLAGS += -march=armv8.5-a+memtag
-
 #check if the compiler works well
-mte_cc_support := $(shell if ($(CC) $(CFLAGS) -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi)
+mte_cc_support := $(shell if ($(CC) $(CFLAGS) -march=armv8.5-a+memtag -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi)
 
 ifeq ($(mte_cc_support),1)
 # Generated binaries to be installed by top KSFT script
diff --git a/tools/testing/selftests/arm64/mte/mte_helper.S b/tools/testing/selftests/arm64/mte/mte_helper.S
index a02c04cd0aac..a55dbbc56ed1 100644
--- a/tools/testing/selftests/arm64/mte/mte_helper.S
+++ b/tools/testing/selftests/arm64/mte/mte_helper.S
@@ -3,6 +3,8 @@
 
 #include "mte_def.h"
 
+.arch	armv8.5-a+memtag
+
 #define ENTRY(name) \
 	.globl name ;\
 	.p2align 2;\
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index b588d10afd5b..308e229e58ab 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -165,15 +165,64 @@ static bool handle_signal_ok(struct tdescr *td,
 }
 
 static bool handle_signal_copyctx(struct tdescr *td,
-				  siginfo_t *si, void *uc)
+				  siginfo_t *si, void *uc_in)
 {
+	ucontext_t *uc = uc_in;
+	struct _aarch64_ctx *head;
+	struct extra_context *extra, *copied_extra;
+	size_t offset = 0;
+	size_t to_copy;
+
+	ASSERT_GOOD_CONTEXT(uc);
+
 	/* Mangling PC to avoid loops on original BRK instr */
-	((ucontext_t *)uc)->uc_mcontext.pc += 4;
-	memcpy(td->live_uc, uc, td->live_sz);
-	ASSERT_GOOD_CONTEXT(td->live_uc);
+	uc->uc_mcontext.pc += 4;
+
+	/*
+	 * Check for an preserve any extra data too with fixups.
+	 */
+	head = (struct _aarch64_ctx *)uc->uc_mcontext.__reserved;
+	head = get_header(head, EXTRA_MAGIC, td->live_sz, &offset);
+	if (head) {
+		extra = (struct extra_context *)head;
+
+		/*
+		 * The extra buffer must be immediately after the
+		 * extra_context and a 16 byte terminator. Include it
+		 * in the copy, this was previously validated in
+		 * ASSERT_GOOD_CONTEXT().
+		 */
+		to_copy = offset + sizeof(struct extra_context) + 16 +
+			extra->size;
+		copied_extra = (struct extra_context *)&(td->live_uc->uc_mcontext.__reserved[offset]);
+	} else {
+		copied_extra = NULL;
+		to_copy = sizeof(ucontext_t);
+	}
+
+	if (to_copy > td->live_sz) {
+		fprintf(stderr,
+			"Not enough space to grab context, %lu/%lu bytes\n",
+			td->live_sz, to_copy);
+		return false;
+	}
+
+	memcpy(td->live_uc, uc, to_copy);
+
+	/*
+	 * If there was any EXTRA_CONTEXT fix up the size to be the
+	 * struct extra_context and the following terminator record,
+	 * this means that the rest of the code does not need to have
+	 * special handling for the record and we don't need to fix up
+	 * datap for the new location.
+	 */
+	if (copied_extra)
+		copied_extra->head.size = sizeof(*copied_extra) + 16;
+
 	td->live_uc_valid = 1;
 	fprintf(stderr,
-		"GOOD CONTEXT grabbed from sig_copyctx handler\n");
+		"%lu byte GOOD CONTEXT grabbed from sig_copyctx handler\n",
+		to_copy);
 
 	return true;
 }
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h
index f3aa99ba67bb..222093f51b67 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.h
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h
@@ -56,7 +56,8 @@ static inline bool feats_ok(struct tdescr *td)
  * at sizeof(ucontext_t).
  */
 static __always_inline bool get_current_context(struct tdescr *td,
-						ucontext_t *dest_uc)
+						ucontext_t *dest_uc,
+						size_t dest_sz)
 {
 	static volatile bool seen_already;
 
@@ -64,7 +65,7 @@ static __always_inline bool get_current_context(struct tdescr *td,
 	/* it's a genuine invocation..reinit */
 	seen_already = 0;
 	td->live_uc_valid = 0;
-	td->live_sz = sizeof(*dest_uc);
+	td->live_sz = dest_sz;
 	memset(dest_uc, 0x00, td->live_sz);
 	td->live_uc = dest_uc;
 	/*
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c
index 8dc600a7d4fd..8c7f00ea9823 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c
@@ -21,7 +21,7 @@ static int fake_sigreturn_bad_magic_run(struct tdescr *td,
 	struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head;
 
 	/* just to fill the ucontext_t with something real */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	/* need at least 2*HDR_SZ space: KSFT_BAD_MAGIC + terminator. */
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c
index b3c362100666..1c03f6b638e0 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c
@@ -24,7 +24,7 @@ static int fake_sigreturn_bad_size_run(struct tdescr *td,
 	struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head;
 
 	/* just to fill the ucontext_t with something real */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	resv_sz = GET_SF_RESV_SIZE(sf);
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c
index a44b88bfc81a..bc22f64b544e 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c
@@ -21,7 +21,7 @@ static int fake_sigreturn_bad_size_for_magic0_run(struct tdescr *td,
 	struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head;
 
 	/* just to fill the ucontext_t with something real */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	/* at least HDR_SZ for the badly sized terminator. */
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c
index afe8915f0998..63e3906b631c 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c
@@ -21,7 +21,7 @@ static int fake_sigreturn_duplicated_fpsimd_run(struct tdescr *td,
 	struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head;
 
 	/* just to fill the ucontext_t with something real */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	head = get_starting_head(shead, sizeof(struct fpsimd_context) + HDR_SZ,
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c
index 1e089e66f9f3..d00625ff12c2 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c
@@ -19,7 +19,7 @@ static int fake_sigreturn_misaligned_run(struct tdescr *td,
 					 siginfo_t *si, ucontext_t *uc)
 {
 	/* just to fill the ucontext_t with something real */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	/* Forcing sigframe on misaligned SP (16 + 3) */
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c
index 08ecd8073a1a..f805138cb20d 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c
@@ -23,7 +23,7 @@ static int fake_sigreturn_missing_fpsimd_run(struct tdescr *td,
 	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
 
 	/* just to fill the ucontext_t with something real */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	resv_sz = GET_SF_RESV_SIZE(sf);
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
index 7ed762b7202f..ebd5815b54bb 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
@@ -54,7 +54,7 @@ static int fake_sigreturn_ssve_change_vl(struct tdescr *td,
 	struct sve_context *sve;
 
 	/* Get a signal context with a SME ZA frame in it */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	resv_sz = GET_SF_RESV_SIZE(sf);
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
index 915821375b0a..e2a452190511 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
@@ -56,7 +56,7 @@ static int fake_sigreturn_sve_change_vl(struct tdescr *td,
 	struct sve_context *sve;
 
 	/* Get a signal context with a SVE frame in it */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	resv_sz = GET_SF_RESV_SIZE(sf);
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_vl.c b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c
index 13ff3b35cbaf..75f387f2db81 100644
--- a/tools/testing/selftests/arm64/signal/testcases/sme_vl.c
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c
@@ -34,7 +34,7 @@ static int sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
 	struct za_context *za;
 
 	/* Get a signal context which should have a ZA frame in it */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	resv_sz = GET_SF_RESV_SIZE(sf);
diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
index 9022a6cab4b3..d0a178945b1a 100644
--- a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
@@ -13,7 +13,10 @@
 #include "test_signals_utils.h"
 #include "testcases.h"
 
-struct fake_sigframe sf;
+static union {
+	ucontext_t uc;
+	char buf[1024 * 64];
+} context;
 static unsigned int vls[SVE_VQ_MAX];
 unsigned int nvls = 0;
 
@@ -55,8 +58,8 @@ static void setup_ssve_regs(void)
 static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 			 unsigned int vl)
 {
-	size_t resv_sz, offset;
-	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
 	struct sve_context *ssve;
 	int ret;
 
@@ -73,11 +76,11 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 	 * in it.
 	 */
 	setup_ssve_regs();
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &context.uc, sizeof(context)))
 		return 1;
 
-	resv_sz = GET_SF_RESV_SIZE(sf);
-	head = get_header(head, SVE_MAGIC, resv_sz, &offset);
+	head = get_header(head, SVE_MAGIC, GET_BUF_RESV_SIZE(context),
+			  &offset);
 	if (!head) {
 		fprintf(stderr, "No SVE context\n");
 		return 1;
@@ -101,16 +104,6 @@ static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
 	int i;
 
 	for (i = 0; i < nvls; i++) {
-		/*
-		 * TODO: the signal test helpers can't currently cope
-		 * with signal frames bigger than struct sigcontext,
-		 * skip VLs that will trigger that.
-		 */
-		if (vls[i] > 64) {
-			printf("Skipping VL %u due to stack size\n", vls[i]);
-			continue;
-		}
-
 		if (do_one_sme_vl(td, si, uc, vls[i]))
 			return 1;
 	}
diff --git a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
index 4b2418aa08a9..8b16eabbb769 100644
--- a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
@@ -13,7 +13,10 @@
 #include "test_signals_utils.h"
 #include "testcases.h"
 
-struct fake_sigframe sf;
+static union {
+	ucontext_t uc;
+	char buf[1024 * 64];
+} context;
 static unsigned int vls[SVE_VQ_MAX];
 unsigned int nvls = 0;
 
@@ -55,8 +58,8 @@ static void setup_sve_regs(void)
 static int do_one_sve_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 			 unsigned int vl)
 {
-	size_t resv_sz, offset;
-	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
 	struct sve_context *sve;
 
 	fprintf(stderr, "Testing VL %d\n", vl);
@@ -71,11 +74,11 @@ static int do_one_sve_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 	 * in it.
 	 */
 	setup_sve_regs();
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &context.uc, sizeof(context)))
 		return 1;
 
-	resv_sz = GET_SF_RESV_SIZE(sf);
-	head = get_header(head, SVE_MAGIC, resv_sz, &offset);
+	head = get_header(head, SVE_MAGIC, GET_BUF_RESV_SIZE(context),
+			  &offset);
 	if (!head) {
 		fprintf(stderr, "No SVE context\n");
 		return 1;
@@ -99,14 +102,6 @@ static int sve_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
 	int i;
 
 	for (i = 0; i < nvls; i++) {
-		/*
-		 * TODO: the signal test helpers can't currently cope
-		 * with signal frames bigger than struct sigcontext,
-		 * skip VLs that will trigger that.
-		 */
-		if (vls[i] > 64)
-			continue;
-
 		if (do_one_sve_vl(td, si, uc, vls[i]))
 			return 1;
 	}
diff --git a/tools/testing/selftests/arm64/signal/testcases/sve_vl.c b/tools/testing/selftests/arm64/signal/testcases/sve_vl.c
index 92904653add1..aa835acec062 100644
--- a/tools/testing/selftests/arm64/signal/testcases/sve_vl.c
+++ b/tools/testing/selftests/arm64/signal/testcases/sve_vl.c
@@ -34,7 +34,7 @@ static int sve_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
 	struct sve_context *sve;
 
 	/* Get a signal context which should have a SVE frame in it */
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	resv_sz = GET_SF_RESV_SIZE(sf);
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
index 84c36bee4d82..e1c625b20ac4 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.c
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c
@@ -25,7 +25,8 @@ struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
 	return found;
 }
 
-bool validate_extra_context(struct extra_context *extra, char **err)
+bool validate_extra_context(struct extra_context *extra, char **err,
+			    void **extra_data, size_t *extra_size)
 {
 	struct _aarch64_ctx *term;
 
@@ -33,7 +34,7 @@ bool validate_extra_context(struct extra_context *extra, char **err)
 		return false;
 
 	fprintf(stderr, "Validating EXTRA...\n");
-	term = GET_RESV_NEXT_HEAD(extra);
+	term = GET_RESV_NEXT_HEAD(&extra->head);
 	if (!term || term->magic || term->size) {
 		*err = "Missing terminator after EXTRA context";
 		return false;
@@ -42,11 +43,14 @@ bool validate_extra_context(struct extra_context *extra, char **err)
 		*err = "Extra DATAP misaligned";
 	else if (extra->size & 0x0fUL)
 		*err = "Extra SIZE misaligned";
-	else if (extra->datap != (uint64_t)term + sizeof(*term))
+	else if (extra->datap != (uint64_t)term + 0x10UL)
 		*err = "Extra DATAP misplaced (not contiguous)";
 	if (*err)
 		return false;
 
+	*extra_data = (void *)extra->datap;
+	*extra_size = extra->size;
+
 	return true;
 }
 
@@ -105,11 +109,14 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 	bool terminated = false;
 	size_t offs = 0;
 	int flags = 0;
+	int new_flags;
 	struct extra_context *extra = NULL;
 	struct sve_context *sve = NULL;
 	struct za_context *za = NULL;
 	struct _aarch64_ctx *head =
 		(struct _aarch64_ctx *)uc->uc_mcontext.__reserved;
+	void *extra_data = NULL;
+	size_t extra_sz = 0;
 
 	if (!err)
 		return false;
@@ -120,12 +127,24 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			return false;
 		}
 
+		new_flags = 0;
+
 		switch (head->magic) {
 		case 0:
-			if (head->size)
+			if (head->size) {
 				*err = "Bad size for terminator";
-			else
+			} else if (extra_data) {
+				/* End of main data, walking the extra data */
+				head = extra_data;
+				resv_sz = extra_sz;
+				offs = 0;
+
+				extra_data = NULL;
+				extra_sz = 0;
+				continue;
+			} else {
 				terminated = true;
+			}
 			break;
 		case FPSIMD_MAGIC:
 			if (flags & FPSIMD_CTX)
@@ -133,7 +152,7 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			else if (head->size !=
 				 sizeof(struct fpsimd_context))
 				*err = "Bad size for fpsimd_context";
-			flags |= FPSIMD_CTX;
+			new_flags |= FPSIMD_CTX;
 			break;
 		case ESR_MAGIC:
 			if (head->size != sizeof(struct esr_context))
@@ -144,14 +163,14 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 				*err = "Multiple SVE_MAGIC";
 			/* Size is validated in validate_sve_context() */
 			sve = (struct sve_context *)head;
-			flags |= SVE_CTX;
+			new_flags |= SVE_CTX;
 			break;
 		case ZA_MAGIC:
 			if (flags & ZA_CTX)
 				*err = "Multiple ZA_MAGIC";
 			/* Size is validated in validate_za_context() */
 			za = (struct za_context *)head;
-			flags |= ZA_CTX;
+			new_flags |= ZA_CTX;
 			break;
 		case EXTRA_MAGIC:
 			if (flags & EXTRA_CTX)
@@ -159,7 +178,7 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			else if (head->size !=
 				 sizeof(struct extra_context))
 				*err = "Bad size for extra_context";
-			flags |= EXTRA_CTX;
+			new_flags |= EXTRA_CTX;
 			extra = (struct extra_context *)head;
 			break;
 		case KSFT_BAD_MAGIC:
@@ -192,16 +211,19 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			return false;
 		}
 
-		if (flags & EXTRA_CTX)
-			if (!validate_extra_context(extra, err))
+		if (new_flags & EXTRA_CTX)
+			if (!validate_extra_context(extra, err,
+						    &extra_data, &extra_sz))
 				return false;
-		if (flags & SVE_CTX)
+		if (new_flags & SVE_CTX)
 			if (!validate_sve_context(sve, err))
 				return false;
-		if (flags & ZA_CTX)
+		if (new_flags & ZA_CTX)
 			if (!validate_za_context(za, err))
 				return false;
 
+		flags |= new_flags;
+
 		head = GET_RESV_NEXT_HEAD(head);
 	}
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h
index 49f1d5de7b5b..040afded0b76 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.h
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h
@@ -30,6 +30,13 @@
 #define GET_SF_RESV_SIZE(sf) \
 	sizeof((sf).uc.uc_mcontext.__reserved)
 
+#define GET_BUF_RESV_HEAD(buf) \
+	(struct _aarch64_ctx *)(&(buf).uc.uc_mcontext.__reserved)
+
+#define GET_BUF_RESV_SIZE(buf) \
+	(sizeof(buf) - sizeof(buf.uc) +	\
+	 sizeof((buf).uc.uc_mcontext.__reserved))
+
 #define GET_UCP_RESV_SIZE(ucp) \
 	sizeof((ucp)->uc_mcontext.__reserved)
 
@@ -79,8 +86,6 @@ struct fake_sigframe {
 
 bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err);
 
-bool validate_extra_context(struct extra_context *extra, char **err);
-
 struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
 				size_t resv_sz, size_t *offset);
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c
new file mode 100644
index 000000000000..4d6f94b6178f
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that the ZA register context in signal frames is set up as
+ * expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+static unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls = 0;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+	int vq, vl;
+
+	/*
+	 * Enumerate up to SME_VQ_MAX vector lengths
+	 */
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(PR_SME_SET_VL, vq * 16);
+		if (vl == -1)
+			return false;
+
+		vl &= PR_SME_VL_LEN_MASK;
+
+		/* Skip missing VLs */
+		vq = sve_vq_from_vl(vl);
+
+		vls[nvls++] = vl;
+	}
+
+	/* We need at least one VL */
+	if (nvls < 1) {
+		fprintf(stderr, "Only %d VL supported\n", nvls);
+		return false;
+	}
+
+	return true;
+}
+
+static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
+			 unsigned int vl)
+{
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct za_context *za;
+
+	fprintf(stderr, "Testing VL %d\n", vl);
+
+	if (prctl(PR_SME_SET_VL, vl) != vl) {
+		fprintf(stderr, "Failed to set VL\n");
+		return 1;
+	}
+
+	/*
+	 * Get a signal context which should have a SVE frame and registers
+	 * in it.
+	 */
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	head = get_header(head, ZA_MAGIC, GET_BUF_RESV_SIZE(context), &offset);
+	if (!head) {
+		fprintf(stderr, "No ZA context\n");
+		return 1;
+	}
+
+	za = (struct za_context *)head;
+	if (za->vl != vl) {
+		fprintf(stderr, "Got VL %d, expected %d\n", za->vl, vl);
+		return 1;
+	}
+
+	if (head->size != ZA_SIG_REGS_OFFSET) {
+		fprintf(stderr, "Context size %u, expected %lu\n",
+			head->size, ZA_SIG_REGS_OFFSET);
+		return 1;
+	}
+
+	/* The actual size validation is done in get_current_context() */
+	fprintf(stderr, "Got expected size %u and VL %d\n",
+		head->size, za->vl);
+
+	return 0;
+}
+
+static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	int i;
+
+	for (i = 0; i < nvls; i++) {
+		if (do_one_sme_vl(td, si, uc, vls[i]))
+			return 1;
+	}
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "ZA registers - ZA disabled",
+	.descr = "Check ZA context with ZA disabled",
+	.feats_required = FEAT_SME,
+	.timeout = 3,
+	.init = sme_get_vls,
+	.run = sme_regs,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
index b94e4f99fcac..ea45acb115d5 100644
--- a/tools/testing/selftests/arm64/signal/testcases/za_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
@@ -13,7 +13,10 @@
 #include "test_signals_utils.h"
 #include "testcases.h"
 
-struct fake_sigframe sf;
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
 static unsigned int vls[SVE_VQ_MAX];
 unsigned int nvls = 0;
 
@@ -22,10 +25,10 @@ static bool sme_get_vls(struct tdescr *td)
 	int vq, vl;
 
 	/*
-	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 * Enumerate up to SME_VQ_MAX vector lengths
 	 */
 	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
-		vl = prctl(PR_SVE_SET_VL, vq * 16);
+		vl = prctl(PR_SME_SET_VL, vq * 16);
 		if (vl == -1)
 			return false;
 
@@ -52,11 +55,13 @@ static void setup_za_regs(void)
 	asm volatile(".inst 0xd503457f" : : : );
 }
 
+static char zeros[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)];
+
 static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 			 unsigned int vl)
 {
-	size_t resv_sz, offset;
-	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
 	struct za_context *za;
 
 	fprintf(stderr, "Testing VL %d\n", vl);
@@ -71,11 +76,10 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 	 * in it.
 	 */
 	setup_za_regs();
-	if (!get_current_context(td, &sf.uc))
+	if (!get_current_context(td, &context.uc, sizeof(context)))
 		return 1;
 
-	resv_sz = GET_SF_RESV_SIZE(sf);
-	head = get_header(head, ZA_MAGIC, resv_sz, &offset);
+	head = get_header(head, ZA_MAGIC, GET_BUF_RESV_SIZE(context), &offset);
 	if (!head) {
 		fprintf(stderr, "No ZA context\n");
 		return 1;
@@ -87,10 +91,22 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 		return 1;
 	}
 
-	/* The actual size validation is done in get_current_context() */
+	if (head->size != ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(vl))) {
+		fprintf(stderr, "ZA context size %u, expected %lu\n",
+			head->size, ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(vl)));
+		return 1;
+	}
+
 	fprintf(stderr, "Got expected size %u and VL %d\n",
 		head->size, za->vl);
 
+	/* We didn't load any data into ZA so it should be all zeros */
+	if (memcmp(zeros, (char *)za + ZA_SIG_REGS_OFFSET,
+		   ZA_SIG_REGS_SIZE(sve_vq_from_vl(za->vl))) != 0) {
+		fprintf(stderr, "ZA data invalid\n");
+		return 1;
+	}
+
 	return 0;
 }
 
@@ -99,16 +115,6 @@ static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
 	int i;
 
 	for (i = 0; i < nvls; i++) {
-		/*
-		 * TODO: the signal test helpers can't currently cope
-		 * with signal frames bigger than struct sigcontext,
-		 * skip VLs that will trigger that.
-		 */
-		if (vls[i] > 32) {
-			printf("Skipping VL %u due to stack size\n", vls[i]);
-			continue;
-		}
-
 		if (do_one_sme_vl(td, si, uc, vls[i]))
 			return 1;
 	}