summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/arm64/abi
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
commit2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch)
tree848558de17fb3008cdf4d861b01ac7781903ce39 /tools/testing/selftests/arm64/abi
parentInitial commit. (diff)
downloadlinux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz
linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip
Adding upstream version 6.1.76.upstream/6.1.76
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/testing/selftests/arm64/abi')
-rw-r--r--tools/testing/selftests/arm64/abi/.gitignore4
-rw-r--r--tools/testing/selftests/arm64/abi/Makefile15
-rw-r--r--tools/testing/selftests/arm64/abi/hwcap.c336
-rw-r--r--tools/testing/selftests/arm64/abi/ptrace.c241
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi-asm.S317
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi.c504
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi.h15
-rw-r--r--tools/testing/selftests/arm64/abi/tpidr2.c298
8 files changed, 1730 insertions, 0 deletions
diff --git a/tools/testing/selftests/arm64/abi/.gitignore b/tools/testing/selftests/arm64/abi/.gitignore
new file mode 100644
index 000000000..44f8b80f3
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/.gitignore
@@ -0,0 +1,4 @@
+hwcap
+ptrace
+syscall-abi
+tpidr2
diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile
new file mode 100644
index 000000000..a6d30c620
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/Makefile
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021 ARM Limited
+
+TEST_GEN_PROGS := hwcap ptrace syscall-abi tpidr2
+
+include ../../lib.mk
+
+$(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S
+
+# Build with nolibc since TPIDR2 is intended to be actively managed by
+# libc and we're trying to test the functionality that it depends on here.
+$(OUTPUT)/tpidr2: tpidr2.c
+ $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ -static -include ../../../../include/nolibc/nolibc.h \
+ -ffreestanding -Wall $^ -o $@ -lgcc
diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
new file mode 100644
index 000000000..9f1a7b5c6
--- /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 000000000..be952511a
--- /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-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
new file mode 100644
index 000000000..b523c21c2
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
@@ -0,0 +1,317 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+//
+// Assembly portion of the syscall ABI test
+
+//
+// Load values from memory into registers, invoke a syscall and save the
+// register values back to memory for later checking. The syscall to be
+// invoked is configured in x8 of the input GPR data.
+//
+// x0: SVE VL, 0 for FP only
+// x1: SME VL
+//
+// GPRs: gpr_in, gpr_out
+// FPRs: fpr_in, fpr_out
+// Zn: z_in, z_out
+// Pn: p_in, p_out
+// FFR: ffr_in, ffr_out
+// ZA: za_in, za_out
+// SVCR: svcr_in, svcr_out
+
+#include "syscall-abi.h"
+
+.arch_extension sve
+
+/*
+ * 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
+
+.globl do_syscall
+do_syscall:
+ // Store callee saved registers x19-x29 (80 bytes) plus x0 and x1
+ stp x29, x30, [sp, #-112]!
+ mov x29, sp
+ stp x0, x1, [sp, #16]
+ stp x19, x20, [sp, #32]
+ stp x21, x22, [sp, #48]
+ stp x23, x24, [sp, #64]
+ stp x25, x26, [sp, #80]
+ stp x27, x28, [sp, #96]
+
+ // Set SVCR if we're doing SME
+ cbz x1, 1f
+ adrp x2, svcr_in
+ ldr x2, [x2, :lo12:svcr_in]
+ msr S3_3_C4_C2_2, x2
+1:
+
+ // Load ZA if it's enabled - uses x12 as scratch due to SME LDR
+ tbz x2, #SVCR_ZA_SHIFT, 1f
+ mov w12, #0
+ ldr x2, =za_in
+2: _ldr_za 12, 2
+ add x2, x2, x1
+ add x12, x12, #1
+ cmp x1, x12
+ bne 2b
+1:
+
+ // Load GPRs x8-x28, and save our SP/FP for later comparison
+ ldr x2, =gpr_in
+ add x2, x2, #64
+ ldp x8, x9, [x2], #16
+ ldp x10, x11, [x2], #16
+ ldp x12, x13, [x2], #16
+ ldp x14, x15, [x2], #16
+ ldp x16, x17, [x2], #16
+ ldp x18, x19, [x2], #16
+ ldp x20, x21, [x2], #16
+ ldp x22, x23, [x2], #16
+ ldp x24, x25, [x2], #16
+ ldp x26, x27, [x2], #16
+ ldr x28, [x2], #8
+ str x29, [x2], #8 // FP
+ str x30, [x2], #8 // LR
+
+ // Load FPRs if we're not doing SVE
+ cbnz x0, 1f
+ ldr x2, =fpr_in
+ ldp q0, q1, [x2]
+ ldp q2, q3, [x2, #16 * 2]
+ ldp q4, q5, [x2, #16 * 4]
+ ldp q6, q7, [x2, #16 * 6]
+ ldp q8, q9, [x2, #16 * 8]
+ ldp q10, q11, [x2, #16 * 10]
+ ldp q12, q13, [x2, #16 * 12]
+ ldp q14, q15, [x2, #16 * 14]
+ ldp q16, q17, [x2, #16 * 16]
+ ldp q18, q19, [x2, #16 * 18]
+ ldp q20, q21, [x2, #16 * 20]
+ ldp q22, q23, [x2, #16 * 22]
+ ldp q24, q25, [x2, #16 * 24]
+ ldp q26, q27, [x2, #16 * 26]
+ ldp q28, q29, [x2, #16 * 28]
+ ldp q30, q31, [x2, #16 * 30]
+1:
+
+ // Load the SVE registers if we're doing SVE/SME
+ cbz x0, 1f
+
+ ldr x2, =z_in
+ ldr z0, [x2, #0, MUL VL]
+ ldr z1, [x2, #1, MUL VL]
+ ldr z2, [x2, #2, MUL VL]
+ ldr z3, [x2, #3, MUL VL]
+ ldr z4, [x2, #4, MUL VL]
+ ldr z5, [x2, #5, MUL VL]
+ ldr z6, [x2, #6, MUL VL]
+ ldr z7, [x2, #7, MUL VL]
+ ldr z8, [x2, #8, MUL VL]
+ ldr z9, [x2, #9, MUL VL]
+ ldr z10, [x2, #10, MUL VL]
+ ldr z11, [x2, #11, MUL VL]
+ ldr z12, [x2, #12, MUL VL]
+ ldr z13, [x2, #13, MUL VL]
+ ldr z14, [x2, #14, MUL VL]
+ ldr z15, [x2, #15, MUL VL]
+ ldr z16, [x2, #16, MUL VL]
+ ldr z17, [x2, #17, MUL VL]
+ ldr z18, [x2, #18, MUL VL]
+ ldr z19, [x2, #19, MUL VL]
+ ldr z20, [x2, #20, MUL VL]
+ ldr z21, [x2, #21, MUL VL]
+ ldr z22, [x2, #22, MUL VL]
+ ldr z23, [x2, #23, MUL VL]
+ ldr z24, [x2, #24, MUL VL]
+ ldr z25, [x2, #25, MUL VL]
+ ldr z26, [x2, #26, MUL VL]
+ ldr z27, [x2, #27, MUL VL]
+ ldr z28, [x2, #28, MUL VL]
+ ldr z29, [x2, #29, MUL VL]
+ ldr z30, [x2, #30, MUL VL]
+ ldr z31, [x2, #31, MUL VL]
+
+ // Only set a non-zero FFR, test patterns must be zero since the
+ // syscall should clear it - this lets us handle FA64.
+ ldr x2, =ffr_in
+ ldr p0, [x2, #0]
+ ldr x2, [x2, #0]
+ cbz x2, 2f
+ wrffr p0.b
+2:
+
+ ldr x2, =p_in
+ ldr p0, [x2, #0, MUL VL]
+ ldr p1, [x2, #1, MUL VL]
+ ldr p2, [x2, #2, MUL VL]
+ ldr p3, [x2, #3, MUL VL]
+ ldr p4, [x2, #4, MUL VL]
+ ldr p5, [x2, #5, MUL VL]
+ ldr p6, [x2, #6, MUL VL]
+ ldr p7, [x2, #7, MUL VL]
+ ldr p8, [x2, #8, MUL VL]
+ ldr p9, [x2, #9, MUL VL]
+ ldr p10, [x2, #10, MUL VL]
+ ldr p11, [x2, #11, MUL VL]
+ ldr p12, [x2, #12, MUL VL]
+ ldr p13, [x2, #13, MUL VL]
+ ldr p14, [x2, #14, MUL VL]
+ ldr p15, [x2, #15, MUL VL]
+1:
+
+ // Do the syscall
+ svc #0
+
+ // Save GPRs x8-x30
+ ldr x2, =gpr_out
+ add x2, x2, #64
+ stp x8, x9, [x2], #16
+ stp x10, x11, [x2], #16
+ stp x12, x13, [x2], #16
+ stp x14, x15, [x2], #16
+ stp x16, x17, [x2], #16
+ stp x18, x19, [x2], #16
+ stp x20, x21, [x2], #16
+ stp x22, x23, [x2], #16
+ stp x24, x25, [x2], #16
+ stp x26, x27, [x2], #16
+ stp x28, x29, [x2], #16
+ str x30, [x2]
+
+ // Restore x0 and x1 for feature checks
+ ldp x0, x1, [sp, #16]
+
+ // Save FPSIMD state
+ ldr x2, =fpr_out
+ stp q0, q1, [x2]
+ stp q2, q3, [x2, #16 * 2]
+ stp q4, q5, [x2, #16 * 4]
+ stp q6, q7, [x2, #16 * 6]
+ stp q8, q9, [x2, #16 * 8]
+ stp q10, q11, [x2, #16 * 10]
+ stp q12, q13, [x2, #16 * 12]
+ stp q14, q15, [x2, #16 * 14]
+ stp q16, q17, [x2, #16 * 16]
+ stp q18, q19, [x2, #16 * 18]
+ stp q20, q21, [x2, #16 * 20]
+ stp q22, q23, [x2, #16 * 22]
+ stp q24, q25, [x2, #16 * 24]
+ stp q26, q27, [x2, #16 * 26]
+ stp q28, q29, [x2, #16 * 28]
+ stp q30, q31, [x2, #16 * 30]
+
+ // Save SVCR if we're doing SME
+ cbz x1, 1f
+ mrs x2, S3_3_C4_C2_2
+ adrp x3, svcr_out
+ str x2, [x3, :lo12:svcr_out]
+1:
+
+ // Save ZA if it's enabled - uses x12 as scratch due to SME STR
+ tbz x2, #SVCR_ZA_SHIFT, 1f
+ mov w12, #0
+ ldr x2, =za_out
+2: _str_za 12, 2
+ add x2, x2, x1
+ add x12, x12, #1
+ cmp x1, x12
+ bne 2b
+1:
+
+ // Save the SVE state if we have some
+ cbz x0, 1f
+
+ ldr x2, =z_out
+ str z0, [x2, #0, MUL VL]
+ str z1, [x2, #1, MUL VL]
+ str z2, [x2, #2, MUL VL]
+ str z3, [x2, #3, MUL VL]
+ str z4, [x2, #4, MUL VL]
+ str z5, [x2, #5, MUL VL]
+ str z6, [x2, #6, MUL VL]
+ str z7, [x2, #7, MUL VL]
+ str z8, [x2, #8, MUL VL]
+ str z9, [x2, #9, MUL VL]
+ str z10, [x2, #10, MUL VL]
+ str z11, [x2, #11, MUL VL]
+ str z12, [x2, #12, MUL VL]
+ str z13, [x2, #13, MUL VL]
+ str z14, [x2, #14, MUL VL]
+ str z15, [x2, #15, MUL VL]
+ str z16, [x2, #16, MUL VL]
+ str z17, [x2, #17, MUL VL]
+ str z18, [x2, #18, MUL VL]
+ str z19, [x2, #19, MUL VL]
+ str z20, [x2, #20, MUL VL]
+ str z21, [x2, #21, MUL VL]
+ str z22, [x2, #22, MUL VL]
+ str z23, [x2, #23, MUL VL]
+ str z24, [x2, #24, MUL VL]
+ str z25, [x2, #25, MUL VL]
+ str z26, [x2, #26, MUL VL]
+ str z27, [x2, #27, MUL VL]
+ str z28, [x2, #28, MUL VL]
+ str z29, [x2, #29, MUL VL]
+ str z30, [x2, #30, MUL VL]
+ str z31, [x2, #31, MUL VL]
+
+ ldr x2, =p_out
+ str p0, [x2, #0, MUL VL]
+ str p1, [x2, #1, MUL VL]
+ str p2, [x2, #2, MUL VL]
+ str p3, [x2, #3, MUL VL]
+ str p4, [x2, #4, MUL VL]
+ str p5, [x2, #5, MUL VL]
+ str p6, [x2, #6, MUL VL]
+ str p7, [x2, #7, MUL VL]
+ str p8, [x2, #8, MUL VL]
+ str p9, [x2, #9, MUL VL]
+ str p10, [x2, #10, MUL VL]
+ str p11, [x2, #11, MUL VL]
+ str p12, [x2, #12, MUL VL]
+ str p13, [x2, #13, MUL VL]
+ str p14, [x2, #14, MUL VL]
+ str p15, [x2, #15, MUL VL]
+
+ // Only save FFR if we wrote a value for SME
+ ldr x2, =ffr_in
+ ldr x2, [x2, #0]
+ cbz x2, 1f
+ ldr x2, =ffr_out
+ rdffr p0.b
+ str p0, [x2, #0]
+1:
+
+ // Restore callee saved registers x19-x30
+ ldp x19, x20, [sp, #32]
+ ldp x21, x22, [sp, #48]
+ ldp x23, x24, [sp, #64]
+ ldp x25, x26, [sp, #80]
+ ldp x27, x28, [sp, #96]
+ ldp x29, x30, [sp], #112
+
+ // Clear SVCR if we were doing SME so future tests don't have ZA
+ cbz x1, 1f
+ msr S3_3_C4_C2_2, xzr
+1:
+
+ ret
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
new file mode 100644
index 000000000..ffe719b50
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -0,0 +1,504 @@
+// 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 <asm/hwcap.h>
+#include <asm/sigcontext.h>
+#include <asm/unistd.h>
+
+#include "../../kselftest.h"
+
+#include "syscall-abi.h"
+
+#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
+
+static int default_sme_vl;
+
+extern void do_syscall(int sve_vl, int sme_vl);
+
+static void fill_random(void *buf, size_t size)
+{
+ int i;
+ uint32_t *lbuf = buf;
+
+ /* random() returns a 32 bit number regardless of the size of long */
+ for (i = 0; i < size / sizeof(uint32_t); i++)
+ lbuf[i] = random();
+}
+
+/*
+ * We also repeat the test for several syscalls to try to expose different
+ * behaviour.
+ */
+static struct syscall_cfg {
+ int syscall_nr;
+ const char *name;
+} syscalls[] = {
+ { __NR_getpid, "getpid()" },
+ { __NR_sched_yield, "sched_yield()" },
+};
+
+#define NUM_GPR 31
+uint64_t gpr_in[NUM_GPR];
+uint64_t gpr_out[NUM_GPR];
+
+static void setup_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ fill_random(gpr_in, sizeof(gpr_in));
+ gpr_in[8] = cfg->syscall_nr;
+ memset(gpr_out, 0, sizeof(gpr_out));
+}
+
+static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr)
+{
+ int errors = 0;
+ int i;
+
+ /*
+ * GPR x0-x7 may be clobbered, and all others should be preserved.
+ */
+ for (i = 9; i < ARRAY_SIZE(gpr_in); i++) {
+ if (gpr_in[i] != gpr_out[i]) {
+ ksft_print_msg("%s SVE VL %d mismatch in GPR %d: %llx != %llx\n",
+ cfg->name, sve_vl, i,
+ gpr_in[i], gpr_out[i]);
+ errors++;
+ }
+ }
+
+ return errors;
+}
+
+#define NUM_FPR 32
+uint64_t fpr_in[NUM_FPR * 2];
+uint64_t fpr_out[NUM_FPR * 2];
+
+static void setup_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ fill_random(fpr_in, sizeof(fpr_in));
+ memset(fpr_out, 0, sizeof(fpr_out));
+}
+
+static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ int errors = 0;
+ int i;
+
+ if (!sve_vl) {
+ for (i = 0; i < ARRAY_SIZE(fpr_in); i++) {
+ if (fpr_in[i] != fpr_out[i]) {
+ ksft_print_msg("%s Q%d/%d mismatch %llx != %llx\n",
+ cfg->name,
+ i / 2, i % 2,
+ fpr_in[i], fpr_out[i]);
+ errors++;
+ }
+ }
+ }
+
+ 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_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)
+{
+ fill_random(z_in, sizeof(z_in));
+ fill_random(z_out, sizeof(z_out));
+}
+
+static int check_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ size_t reg_size = sve_vl;
+ int errors = 0;
+ int i;
+
+ if (!sve_vl)
+ return 0;
+
+ for (i = 0; i < SVE_NUM_ZREGS; i++) {
+ 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++;
+ }
+ }
+ }
+
+ return errors;
+}
+
+uint8_t p_in[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)];
+uint8_t p_out[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)];
+
+static void setup_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ fill_random(p_in, sizeof(p_in));
+ fill_random(p_out, sizeof(p_out));
+}
+
+static int check_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ size_t reg_size = sve_vq_from_vl(sve_vl) * 2; /* 1 bit per VL byte */
+
+ int errors = 0;
+ int i;
+
+ if (!sve_vl)
+ return 0;
+
+ /* After a syscall the P registers should be zeroed */
+ for (i = 0; i < SVE_NUM_PREGS * reg_size; i++)
+ if (p_out[i])
+ errors++;
+ if (errors)
+ ksft_print_msg("%s SVE VL %d predicate registers non-zero\n",
+ cfg->name, sve_vl);
+
+ return errors;
+}
+
+uint8_t ffr_in[__SVE_PREG_SIZE(SVE_VQ_MAX)];
+uint8_t ffr_out[__SVE_PREG_SIZE(SVE_VQ_MAX)];
+
+static void setup_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ /*
+ * If we are in streaming mode and do not have FA64 then FFR
+ * is unavailable.
+ */
+ if ((svcr & SVCR_SM_MASK) &&
+ !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)) {
+ memset(&ffr_in, 0, sizeof(ffr_in));
+ return;
+ }
+
+ /*
+ * It is only valid to set a contiguous set of bits starting
+ * at 0. For now since we're expecting this to be cleared by
+ * a syscall just set all bits.
+ */
+ memset(ffr_in, 0xff, sizeof(ffr_in));
+ fill_random(ffr_out, sizeof(ffr_out));
+}
+
+static int check_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ size_t reg_size = sve_vq_from_vl(sve_vl) * 2; /* 1 bit per VL byte */
+ int errors = 0;
+ int i;
+
+ if (!sve_vl)
+ return 0;
+
+ if ((svcr & SVCR_SM_MASK) &&
+ !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64))
+ return 0;
+
+ /* After a syscall FFR should be zeroed */
+ for (i = 0; i < reg_size; i++)
+ if (ffr_out[i])
+ errors++;
+ if (errors)
+ ksft_print_msg("%s SVE VL %d FFR non-zero\n",
+ cfg->name, sve_vl);
+
+ return errors;
+}
+
+uint64_t svcr_in, svcr_out;
+
+static void setup_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ svcr_in = svcr;
+}
+
+static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ int errors = 0;
+
+ if (svcr_out & SVCR_SM_MASK) {
+ ksft_print_msg("%s Still in SM, SVCR %llx\n",
+ cfg->name, svcr_out);
+ errors++;
+ }
+
+ if ((svcr_in & SVCR_ZA_MASK) != (svcr_out & SVCR_ZA_MASK)) {
+ ksft_print_msg("%s PSTATE.ZA changed, SVCR %llx != %llx\n",
+ cfg->name, svcr_in, svcr_out);
+ errors++;
+ }
+
+ return errors;
+}
+
+uint8_t za_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+uint8_t za_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+
+static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ fill_random(za_in, sizeof(za_in));
+ memset(za_out, 0, sizeof(za_out));
+}
+
+static int check_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ size_t reg_size = sme_vl * sme_vl;
+ int errors = 0;
+
+ if (!(svcr & SVCR_ZA_MASK))
+ return 0;
+
+ if (memcmp(za_in, za_out, reg_size) != 0) {
+ ksft_print_msg("SME VL %d ZA does not match\n", sme_vl);
+ errors++;
+ }
+
+ return errors;
+}
+
+typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr);
+typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr);
+
+/*
+ * Each set of registers has a setup function which is called before
+ * the syscall to fill values in a global variable for loading by the
+ * test code and a check function which validates that the results are
+ * as expected. Vector lengths are passed everywhere, a vector length
+ * of 0 should be treated as do not test.
+ */
+static struct {
+ setup_fn setup;
+ check_fn check;
+} regset[] = {
+ { setup_gpr, check_gpr },
+ { setup_fpr, check_fpr },
+ { setup_z, check_z },
+ { setup_p, check_p },
+ { setup_ffr, check_ffr },
+ { setup_svcr, check_svcr },
+ { setup_za, check_za },
+};
+
+static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ int errors = 0;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(regset); i++)
+ regset[i].setup(cfg, sve_vl, sme_vl, svcr);
+
+ do_syscall(sve_vl, sme_vl);
+
+ for (i = 0; i < ARRAY_SIZE(regset); i++)
+ errors += regset[i].check(cfg, sve_vl, sme_vl, svcr);
+
+ return errors == 0;
+}
+
+static void test_one_syscall(struct syscall_cfg *cfg)
+{
+ int sve_vq, sve_vl;
+ int sme_vq, sme_vl;
+
+ /* FPSIMD only case */
+ ksft_test_result(do_test(cfg, 0, default_sme_vl, 0),
+ "%s FPSIMD\n", cfg->name);
+
+ if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
+ return;
+
+ for (sve_vq = SVE_VQ_MAX; sve_vq > 0; --sve_vq) {
+ sve_vl = prctl(PR_SVE_SET_VL, sve_vq * 16);
+ if (sve_vl == -1)
+ ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
+ strerror(errno), errno);
+
+ sve_vl &= PR_SVE_VL_LEN_MASK;
+
+ if (sve_vq != sve_vq_from_vl(sve_vl))
+ sve_vq = sve_vq_from_vl(sve_vl);
+
+ ksft_test_result(do_test(cfg, sve_vl, default_sme_vl, 0),
+ "%s SVE VL %d\n", cfg->name, sve_vl);
+
+ if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
+ continue;
+
+ for (sme_vq = SVE_VQ_MAX; sme_vq > 0; --sme_vq) {
+ sme_vl = prctl(PR_SME_SET_VL, sme_vq * 16);
+ if (sme_vl == -1)
+ ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
+ strerror(errno), errno);
+
+ sme_vl &= PR_SME_VL_LEN_MASK;
+
+ /* Found lowest VL */
+ if (sve_vq_from_vl(sme_vl) > sme_vq)
+ break;
+
+ if (sme_vq != sve_vq_from_vl(sme_vl))
+ sme_vq = sve_vq_from_vl(sme_vl);
+
+ ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+ SVCR_ZA_MASK | SVCR_SM_MASK),
+ "%s SVE VL %d/SME VL %d SM+ZA\n",
+ cfg->name, sve_vl, sme_vl);
+ ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+ SVCR_SM_MASK),
+ "%s SVE VL %d/SME VL %d SM\n",
+ cfg->name, sve_vl, sme_vl);
+ ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+ SVCR_ZA_MASK),
+ "%s SVE VL %d/SME VL %d ZA\n",
+ cfg->name, sve_vl, sme_vl);
+ }
+ }
+}
+
+int sve_count_vls(void)
+{
+ unsigned int vq;
+ int vl_count = 0;
+ int vl;
+
+ if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
+ return 0;
+
+ /*
+ * 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 (vq != sve_vq_from_vl(vl))
+ vq = sve_vq_from_vl(vl);
+
+ vl_count++;
+ }
+
+ return vl_count;
+}
+
+int sme_count_vls(void)
+{
+ unsigned int vq;
+ int vl_count = 0;
+ int vl;
+
+ if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
+ return 0;
+
+ /* Ensure we configure a SME VL, used to flag if SVCR is set */
+ default_sme_vl = 16;
+
+ /*
+ * Enumerate up to SVE_VQ_MAX vector lengths
+ */
+ for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+ vl = prctl(PR_SME_SET_VL, vq * 16);
+ if (vl == -1)
+ ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
+ strerror(errno), errno);
+
+ vl &= PR_SME_VL_LEN_MASK;
+
+ /* Found lowest VL */
+ if (sve_vq_from_vl(vl) > vq)
+ break;
+
+ if (vq != sve_vq_from_vl(vl))
+ vq = sve_vq_from_vl(vl);
+
+ vl_count++;
+ }
+
+ return vl_count;
+}
+
+int main(void)
+{
+ int i;
+ int tests = 1; /* FPSIMD */
+
+ srandom(getpid());
+
+ ksft_print_header();
+ tests += sve_count_vls();
+ tests += (sve_count_vls() * sme_count_vls()) * 3;
+ ksft_set_plan(ARRAY_SIZE(syscalls) * tests);
+
+ if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
+ ksft_print_msg("SME with FA64\n");
+ else if (getauxval(AT_HWCAP2) & HWCAP2_SME)
+ ksft_print_msg("SME without FA64\n");
+
+ for (i = 0; i < ARRAY_SIZE(syscalls); i++)
+ test_one_syscall(&syscalls[i]);
+
+ ksft_print_cnts();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.h b/tools/testing/selftests/arm64/abi/syscall-abi.h
new file mode 100644
index 000000000..bda5a87ad
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 ARM Limited.
+ */
+
+#ifndef SYSCALL_ABI_H
+#define SYSCALL_ABI_H
+
+#define SVCR_ZA_MASK 2
+#define SVCR_SM_MASK 1
+
+#define SVCR_ZA_SHIFT 1
+#define SVCR_SM_SHIFT 0
+
+#endif
diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c
new file mode 100644
index 000000000..351a098b5
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/tpidr2.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#define SYS_TPIDR2 "S3_3_C13_C0_5"
+
+#define EXPECTED_TESTS 5
+
+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 set_tpidr2(uint64_t val)
+{
+ asm volatile (
+ "msr " SYS_TPIDR2 ", %0\n"
+ :
+ : "r"(val)
+ : "cc");
+}
+
+static uint64_t get_tpidr2(void)
+{
+ uint64_t val;
+
+ asm volatile (
+ "mrs %0, " SYS_TPIDR2 "\n"
+ : "=r"(val)
+ :
+ : "cc");
+
+ return val;
+}
+
+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");
+}
+
+/* Processes should start with TPIDR2 == 0 */
+static int default_value(void)
+{
+ return get_tpidr2() == 0;
+}
+
+/* If we set TPIDR2 we should read that value */
+static int write_read(void)
+{
+ set_tpidr2(getpid());
+
+ return getpid() == get_tpidr2();
+}
+
+/* If we set a value we should read the same value after scheduling out */
+static int write_sleep_read(void)
+{
+ set_tpidr2(getpid());
+
+ msleep(100);
+
+ return getpid() == get_tpidr2();
+}
+
+/*
+ * If we fork the value in the parent should be unchanged and the
+ * child should start with the same value and be able to set its own
+ * value.
+ */
+static int write_fork_read(void)
+{
+ pid_t newpid, waiting, oldpid;
+ int status;
+
+ set_tpidr2(getpid());
+
+ oldpid = getpid();
+ newpid = fork();
+ if (newpid == 0) {
+ /* In child */
+ if (get_tpidr2() != oldpid) {
+ putstr("# TPIDR2 changed in child: ");
+ putnum(get_tpidr2());
+ putstr("\n");
+ exit(0);
+ }
+
+ set_tpidr2(getpid());
+ if (get_tpidr2() == getpid()) {
+ exit(1);
+ } else {
+ putstr("# Failed to set TPIDR2 in child\n");
+ exit(0);
+ }
+ }
+ if (newpid < 0) {
+ putstr("# fork() failed: -");
+ putnum(-newpid);
+ putstr("\n");
+ return 0;
+ }
+
+ for (;;) {
+ waiting = waitpid(newpid, &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(status)) {
+ putstr("# child did not exit\n");
+ return 0;
+ }
+
+ if (getpid() != get_tpidr2()) {
+ putstr("# TPIDR2 corrupted in parent\n");
+ return 0;
+ }
+
+ return WEXITSTATUS(status);
+ }
+}
+
+/*
+ * sys_clone() has a lot of per architecture variation so just define
+ * it here rather than adding it to nolibc, plus the raw API is a
+ * little more convenient for this test.
+ */
+static int sys_clone(unsigned long clone_flags, unsigned long newsp,
+ int *parent_tidptr, unsigned long tls,
+ int *child_tidptr)
+{
+ return my_syscall5(__NR_clone, clone_flags, newsp, parent_tidptr, tls,
+ child_tidptr);
+}
+
+/*
+ * If we clone with CLONE_SETTLS then the value in the parent should
+ * be unchanged and the child should start with zero and be able to
+ * set its own value.
+ */
+static int write_clone_read(void)
+{
+ int parent_tid, child_tid;
+ pid_t parent, waiting;
+ int ret, status;
+
+ parent = getpid();
+ set_tpidr2(parent);
+
+ ret = sys_clone(CLONE_SETTLS, 0, &parent_tid, 0, &child_tid);
+ if (ret == -1) {
+ putstr("# clone() failed\n");
+ putnum(errno);
+ putstr("\n");
+ return 0;
+ }
+
+ if (ret == 0) {
+ /* In child */
+ if (get_tpidr2() != 0) {
+ putstr("# TPIDR2 non-zero in child: ");
+ putnum(get_tpidr2());
+ putstr("\n");
+ exit(0);
+ }
+
+ if (gettid() == 0)
+ putstr("# Child TID==0\n");
+ set_tpidr2(gettid());
+ if (get_tpidr2() == gettid()) {
+ exit(1);
+ } else {
+ putstr("# Failed to set TPIDR2 in child\n");
+ exit(0);
+ }
+ }
+
+ for (;;) {
+ waiting = wait4(ret, &status, __WCLONE, NULL);
+
+ if (waiting < 0) {
+ if (errno == EINTR)
+ continue;
+ putstr("# wait4() failed: ");
+ putnum(errno);
+ putstr("\n");
+ return 0;
+ }
+ if (waiting != ret) {
+ putstr("# wait4() returned wrong PID ");
+ putnum(waiting);
+ putstr("\n");
+ return 0;
+ }
+
+ if (!WIFEXITED(status)) {
+ putstr("# child did not exit\n");
+ return 0;
+ }
+
+ if (parent != get_tpidr2()) {
+ putstr("# TPIDR2 corrupted in parent\n");
+ return 0;
+ }
+
+ return WEXITSTATUS(status);
+ }
+}
+
+#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(default_value);
+ run_test(write_read);
+ run_test(write_sleep_read);
+ run_test(write_fork_read);
+ run_test(write_clone_read);
+
+ } else {
+ putstr("# SME support not present\n");
+
+ for (i = 0; i < EXPECTED_TESTS; i++) {
+ putstr("ok ");
+ putnum(i);
+ putstr(" skipped, TPIDR2 not supported\n");
+ }
+
+ tests_skipped += EXPECTED_TESTS;
+ }
+
+ print_summary();
+
+ return 0;
+}