diff options
Diffstat (limited to 'tools/testing/selftests/arm64')
63 files changed, 4444 insertions, 273 deletions
diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile index 1e8d9a8f59df..9460cbe81bcc 100644 --- a/tools/testing/selftests/arm64/Makefile +++ b/tools/testing/selftests/arm64/Makefile @@ -17,16 +17,7 @@ top_srcdir = $(realpath ../../../../) # Additional include paths needed by kselftest.h and local headers CFLAGS += -I$(top_srcdir)/tools/testing/selftests/ -# Guessing where the Kernel headers could have been installed -# depending on ENV config -ifeq ($(KBUILD_OUTPUT),) -khdr_dir = $(top_srcdir)/usr/include -else -# the KSFT preferred location when KBUILD_OUTPUT is set -khdr_dir = $(KBUILD_OUTPUT)/kselftest/usr/include -endif - -CFLAGS += -I$(khdr_dir) +CFLAGS += $(KHDR_INCLUDES) export CFLAGS export top_srcdir diff --git a/tools/testing/selftests/arm64/abi/.gitignore b/tools/testing/selftests/arm64/abi/.gitignore index b79cf5814c23..44f8b80f37e3 100644 --- a/tools/testing/selftests/arm64/abi/.gitignore +++ b/tools/testing/selftests/arm64/abi/.gitignore @@ -1 +1,4 @@ +hwcap +ptrace syscall-abi +tpidr2 diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile index 96eba974ac8d..a6d30c620908 100644 --- a/tools/testing/selftests/arm64/abi/Makefile +++ b/tools/testing/selftests/arm64/abi/Makefile @@ -1,8 +1,15 @@ # SPDX-License-Identifier: GPL-2.0 # Copyright (C) 2021 ARM Limited -TEST_GEN_PROGS := syscall-abi +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 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-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S index 983467cfcee0..b523c21c2278 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S +++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S @@ -9,15 +9,42 @@ // 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 @@ -30,6 +57,24 @@ do_syscall: 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 @@ -68,7 +113,7 @@ do_syscall: ldp q30, q31, [x2, #16 * 30] 1: - // Load the SVE registers if we're doing SVE + // Load the SVE registers if we're doing SVE/SME cbz x0, 1f ldr x2, =z_in @@ -105,9 +150,14 @@ do_syscall: 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] @@ -169,6 +219,24 @@ do_syscall: 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 @@ -224,6 +292,10 @@ do_syscall: 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] @@ -237,4 +309,9 @@ do_syscall: 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 index d8eeeafb50dc..dd7ebe536d05 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi.c +++ b/tools/testing/selftests/arm64/abi/syscall-abi.c @@ -18,10 +18,13 @@ #include "../../kselftest.h" -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) +#include "syscall-abi.h" + #define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1) -extern void do_syscall(int sve_vl); +static int default_sme_vl; + +extern void do_syscall(int sve_vl, int sme_vl); static void fill_random(void *buf, size_t size) { @@ -49,14 +52,15 @@ static struct syscall_cfg { uint64_t gpr_in[NUM_GPR]; uint64_t gpr_out[NUM_GPR]; -static void setup_gpr(struct syscall_cfg *cfg, int sve_vl) +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) +static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr) { int errors = 0; int i; @@ -80,13 +84,15 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl) 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) +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) +static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { int errors = 0; int i; @@ -106,17 +112,21 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_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) +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) +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; @@ -125,18 +135,39 @@ static int check_z(struct syscall_cfg *cfg, int sve_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. - */ for (i = 0; i < SVE_NUM_ZREGS; i++) { - void *in = &z_in[reg_size * i]; - void *out = &z_out[reg_size * 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 (memcmp(in, 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++; + 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++; + } } } @@ -146,13 +177,15 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl) 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) +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) +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 */ @@ -162,9 +195,9 @@ static int check_p(struct syscall_cfg *cfg, int sve_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", @@ -176,9 +209,20 @@ static int check_p(struct syscall_cfg *cfg, int sve_vl) 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) +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. @@ -187,7 +231,8 @@ static void setup_ffr(struct syscall_cfg *cfg, int sve_vl) fill_random(ffr_out, sizeof(ffr_out)); } -static int check_ffr(struct syscall_cfg *cfg, int sve_vl) +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; @@ -196,9 +241,13 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl) if (!sve_vl) return 0; - /* After a syscall the P registers should be preserved or zeroed */ + 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] && (ffr_in[i] != ffr_out[i])) + if (ffr_out[i]) errors++; if (errors) ksft_print_msg("%s SVE VL %d FFR non-zero\n", @@ -207,8 +256,65 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl) return errors; } -typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl); -typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl); +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 @@ -226,20 +332,23 @@ static struct { { 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) +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); + regset[i].setup(cfg, sve_vl, sme_vl, svcr); - do_syscall(sve_vl); + do_syscall(sve_vl, sme_vl); for (i = 0; i < ARRAY_SIZE(regset); i++) - errors += regset[i].check(cfg, sve_vl); + errors += regset[i].check(cfg, sve_vl, sme_vl, svcr); return errors == 0; } @@ -247,9 +356,10 @@ static bool do_test(struct syscall_cfg *cfg, int sve_vl) 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), + ksft_test_result(do_test(cfg, 0, default_sme_vl, 0), "%s FPSIMD\n", cfg->name); if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) @@ -266,8 +376,36 @@ static void test_one_syscall(struct syscall_cfg *cfg) 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), + 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; + + 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); + } } } @@ -300,14 +438,54 @@ int sve_count_vls(void) 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; + + 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(); - ksft_set_plan(ARRAY_SIZE(syscalls) * (sve_count_vls() + 1)); + 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]); 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 000000000000..bda5a87ad381 --- /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 000000000000..351a098b503a --- /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; +} diff --git a/tools/testing/selftests/arm64/bti/Makefile b/tools/testing/selftests/arm64/bti/Makefile index 73e013c082a6..ccdac414ad94 100644 --- a/tools/testing/selftests/arm64/bti/Makefile +++ b/tools/testing/selftests/arm64/bti/Makefile @@ -10,7 +10,7 @@ PROGS := $(patsubst %,gen/%,$(TEST_GEN_PROGS)) # cases for statically linked and dynamically lined binaries are # slightly different. -CFLAGS_NOBTI = -DBTI=0 +CFLAGS_NOBTI = -mbranch-protection=none -DBTI=0 CFLAGS_BTI = -mbranch-protection=standard -DBTI=1 CFLAGS_COMMON = -ffreestanding -Wall -Wextra $(CFLAGS) @@ -39,7 +39,7 @@ BTI_OBJS = \ teststubs-bti.o \ trampoline-bti.o gen/btitest: $(BTI_OBJS) - $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^ + $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^ NOBTI_OBJS = \ test-nobti.o \ @@ -50,7 +50,7 @@ NOBTI_OBJS = \ teststubs-nobti.o \ trampoline-nobti.o gen/nobtitest: $(NOBTI_OBJS) - $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^ + $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^ # Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list # to account for any OUTPUT target-dirs optionally provided by diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index c50d86331ed2..df79d29664a1 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -1,8 +1,14 @@ fp-pidbench +fp-stress fpsimd-test +rdvl-sme rdvl-sve sve-probe-vls sve-ptrace sve-test +ssve-test vec-syscfg vlset +za-fork +za-ptrace +za-test diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index 95f0b877a060..36db61358ed5 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -1,24 +1,45 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I../../../../../usr/include/ -TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg -TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \ - rdvl-sve \ - sve-test sve-stress \ +# A proper top_srcdir is needed by KSFT(lib.mk) +top_srcdir = $(realpath ../../../../../) + +CFLAGS += -I$(top_srcdir)/usr/include/ + +TEST_GEN_PROGS := fp-stress \ + sve-ptrace sve-probe-vls \ + vec-syscfg \ + za-fork za-ptrace +TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \ + rdvl-sme rdvl-sve \ + sve-test \ + ssve-test \ + za-test \ vlset +TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress -all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED) +EXTRA_CLEAN += $(OUTPUT)/asm-utils.o $(OUTPUT)/rdvl.o $(OUTPUT)/za-fork-asm.o -fp-pidbench: fp-pidbench.S asm-utils.o +# Build with nolibc to avoid effects due to libc's clone() support +$(OUTPUT)/fp-pidbench: fp-pidbench.S $(OUTPUT)/asm-utils.o + $(CC) -nostdlib $^ -o $@ +$(OUTPUT)/fpsimd-test: fpsimd-test.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ -fpsimd-test: fpsimd-test.o asm-utils.o +$(OUTPUT)/rdvl-sve: rdvl-sve.c $(OUTPUT)/rdvl.o +$(OUTPUT)/rdvl-sme: rdvl-sme.c $(OUTPUT)/rdvl.o +$(OUTPUT)/sve-ptrace: sve-ptrace.c +$(OUTPUT)/sve-probe-vls: sve-probe-vls.c $(OUTPUT)/rdvl.o +$(OUTPUT)/sve-test: sve-test.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ -rdvl-sve: rdvl-sve.o rdvl.o -sve-ptrace: sve-ptrace.o -sve-probe-vls: sve-probe-vls.o rdvl.o -sve-test: sve-test.o asm-utils.o +$(OUTPUT)/ssve-test: sve-test.S $(OUTPUT)/asm-utils.o + $(CC) -DSSVE -nostdlib $^ -o $@ +$(OUTPUT)/vec-syscfg: vec-syscfg.c $(OUTPUT)/rdvl.o +$(OUTPUT)/vlset: vlset.c +$(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o + $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ + -include ../../../../include/nolibc/nolibc.h \ + -static -ffreestanding -Wall $^ -o $@ +$(OUTPUT)/za-ptrace: za-ptrace.c +$(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ -vec-syscfg: vec-syscfg.o rdvl.o -vlset: vlset.o include ../../lib.mk 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/rdvl-sme.c b/tools/testing/selftests/arm64/fp/rdvl-sme.c new file mode 100644 index 000000000000..49b0b2e08bac --- /dev/null +++ b/tools/testing/selftests/arm64/fp/rdvl-sme.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <stdio.h> + +#include "rdvl.h" + +int main(void) +{ + int vl = rdvl_sme(); + + printf("%d\n", vl); + + return 0; +} diff --git a/tools/testing/selftests/arm64/fp/rdvl.S b/tools/testing/selftests/arm64/fp/rdvl.S index c916c1c9defd..20dc29996dc6 100644 --- a/tools/testing/selftests/arm64/fp/rdvl.S +++ b/tools/testing/selftests/arm64/fp/rdvl.S @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only // Copyright (C) 2021 ARM Limited. +#include "sme-inst.h" + .arch_extension sve .globl rdvl_sve @@ -8,3 +10,11 @@ rdvl_sve: hint 34 // BTI C rdvl x0, #1 ret + +.globl rdvl_sme +rdvl_sme: + hint 34 // BTI C + + rdsvl 0, 1 + + ret diff --git a/tools/testing/selftests/arm64/fp/rdvl.h b/tools/testing/selftests/arm64/fp/rdvl.h index 7c9d953fc9e7..5d323679fbc9 100644 --- a/tools/testing/selftests/arm64/fp/rdvl.h +++ b/tools/testing/selftests/arm64/fp/rdvl.h @@ -3,6 +3,7 @@ #ifndef RDVL_H #define RDVL_H +int rdvl_sme(void); int rdvl_sve(void); #endif diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h new file mode 100644 index 000000000000..7191e53ca1c0 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/sme-inst.h @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021-2 ARM Limited. +// Original author: Mark Brown <broonie@kernel.org> + +#ifndef SME_INST_H +#define SME_INST_H + +/* + * RDSVL X\nx, #\imm + */ +.macro rdsvl nx, imm + .inst 0x4bf5800 \ + | (\imm << 5) \ + | (\nx) +.endm + +.macro smstop + msr S0_3_C4_C6_3, xzr +.endm + +.macro smstart_za + msr S0_3_C4_C5_3, xzr +.endm + +.macro smstart_sm + msr S0_3_C4_C3_3, xzr +.endm + +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _ldr_za nw, nxbase, offset=0 + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _str_za nw, nxbase, offset=0 + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +#endif diff --git a/tools/testing/selftests/arm64/fp/ssve-stress b/tools/testing/selftests/arm64/fp/ssve-stress new file mode 100644 index 000000000000..e2bd2cc184ad --- /dev/null +++ b/tools/testing/selftests/arm64/fp/ssve-stress @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2015-2019 ARM Limited. +# Original author: Dave Martin <Dave.Martin@arm.com> + +set -ue + +NR_CPUS=`nproc` + +pids= +logs= + +cleanup () { + trap - INT TERM CHLD + set +e + + if [ -n "$pids" ]; then + kill $pids + wait $pids + pids= + fi + + if [ -n "$logs" ]; then + cat $logs + rm $logs + logs= + fi +} + +interrupt () { + cleanup + exit 0 +} + +child_died () { + cleanup + exit 1 +} + +trap interrupt INT TERM EXIT + +for x in `seq 0 $((NR_CPUS * 4))`; do + log=`mktemp` + logs=$logs\ $log + ./ssve-test >$log & + pids=$pids\ $! +done + +# Wait for all child processes to be created: +sleep 10 + +while :; do + kill -USR1 $pids +done & +pids=$pids\ $! + +wait + +exit 1 diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index af798b9d232c..8c4847977583 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -21,13 +21,15 @@ #include "../../kselftest.h" -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) - /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ #ifndef NT_ARM_SVE #define NT_ARM_SVE 0x405 #endif +#ifndef NT_ARM_SSVE +#define NT_ARM_SSVE 0x40b +#endif + struct vec_type { const char *name; unsigned long hwcap_type; @@ -44,11 +46,18 @@ static const struct vec_type vec_types[] = { .regset = NT_ARM_SVE, .prctl_set = PR_SVE_SET_VL, }, + { + .name = "Streaming SVE", + .hwcap_type = AT_HWCAP2, + .hwcap = HWCAP2_SME, + .regset = NT_ARM_SSVE, + .prctl_set = PR_SME_SET_VL, + }, }; -#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3) +#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 4) #define FLAG_TESTS 2 -#define FPSIMD_TESTS 3 +#define FPSIMD_TESTS 2 #define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types)) @@ -80,6 +89,15 @@ static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd) return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov); } +static int set_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd) +{ + struct iovec iov; + + iov.iov_base = fpsimd; + iov.iov_len = sizeof(*fpsimd); + return ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov); +} + static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type, void **buf, size_t *size) { @@ -242,28 +260,24 @@ static void check_u32(unsigned int vl, const char *reg, /* Access the FPSIMD registers via the SVE regset */ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type) { - void *svebuf = NULL; - size_t svebufsz = 0; + void *svebuf; struct user_sve_header *sve; struct user_fpsimd_state *fpsimd, new_fpsimd; unsigned int i, j; unsigned char *p; + int ret; - /* New process should start with FPSIMD registers only */ - sve = get_sve(child, type, &svebuf, &svebufsz); - if (!sve) { - ksft_test_result_fail("get_sve(%s): %s\n", - type->name, strerror(errno)); - + svebuf = malloc(SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD)); + if (!svebuf) { + ksft_test_result_fail("Failed to allocate FPSIMD buffer\n"); return; - } else { - ksft_test_result_pass("get_sve(%s FPSIMD)\n", type->name); } - ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, - "Set FPSIMD registers via %s\n", type->name); - if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) - goto out; + memset(svebuf, 0, SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD)); + sve = svebuf; + sve->flags = SVE_PT_REGS_FPSIMD; + sve->size = SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD); + sve->vl = 16; /* We don't care what the VL is */ /* Try to set a known FPSIMD state via PT_REGS_SVE */ fpsimd = (struct user_fpsimd_state *)((char *)sve + @@ -275,12 +289,11 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type) p[j] = j; } - if (set_sve(child, type, sve)) { - ksft_test_result_fail("set_sve(%s FPSIMD): %s\n", - type->name, strerror(errno)); - + ret = set_sve(child, type, sve); + ksft_test_result(ret == 0, "%s FPSIMD set via SVE: %d\n", + type->name, ret); + if (ret) goto out; - } /* Verify via the FPSIMD regset */ if (get_fpsimd(child, &new_fpsimd)) { @@ -397,7 +410,7 @@ out: free(write_buf); } -/* Validate attempting to set SVE data and read SVE data */ +/* Validate attempting to set SVE data and read it via the FPSIMD regset */ static void ptrace_set_sve_get_fpsimd_data(pid_t child, const struct vec_type *type, unsigned int vl) @@ -480,6 +493,115 @@ out: free(write_buf); } +/* Validate attempting to set FPSIMD data and read it via the SVE regset */ +static void ptrace_set_fpsimd_get_sve_data(pid_t child, + const struct vec_type *type, + unsigned int vl) +{ + void *read_buf = NULL; + unsigned char *p; + struct user_sve_header *read_sve; + unsigned int vq = sve_vq_from_vl(vl); + struct user_fpsimd_state write_fpsimd; + int ret, i, j; + size_t read_sve_size = 0; + size_t expected_size; + int errors = 0; + + if (__BYTE_ORDER == __BIG_ENDIAN) { + ksft_test_result_skip("Big endian not supported\n"); + return; + } + + for (i = 0; i < 32; ++i) { + p = (unsigned char *)&write_fpsimd.vregs[i]; + + for (j = 0; j < sizeof(write_fpsimd.vregs[i]); ++j) + p[j] = j; + } + + ret = set_fpsimd(child, &write_fpsimd); + if (ret != 0) { + ksft_test_result_fail("Failed to set FPSIMD state: %d\n)", + ret); + return; + } + + if (!get_sve(child, type, (void **)&read_buf, &read_sve_size)) { + ksft_test_result_fail("Failed to read %s VL %u data\n", + type->name, vl); + return; + } + read_sve = read_buf; + + if (read_sve->vl != vl) { + ksft_test_result_fail("Child VL != expected VL %d\n", + read_sve->vl, vl); + goto out; + } + + /* The kernel may return either SVE or FPSIMD format */ + switch (read_sve->flags & SVE_PT_REGS_MASK) { + case SVE_PT_REGS_FPSIMD: + expected_size = SVE_PT_FPSIMD_SIZE(vq, SVE_PT_REGS_FPSIMD); + if (read_sve_size < expected_size) { + ksft_test_result_fail("Read %d bytes, expected %d\n", + read_sve_size, expected_size); + goto out; + } + + ret = memcmp(&write_fpsimd, read_buf + SVE_PT_FPSIMD_OFFSET, + sizeof(write_fpsimd)); + if (ret != 0) { + ksft_print_msg("Read FPSIMD data mismatch\n"); + errors++; + } + break; + + case SVE_PT_REGS_SVE: + expected_size = SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + if (read_sve_size < expected_size) { + ksft_test_result_fail("Read %d bytes, expected %d\n", + read_sve_size, expected_size); + goto out; + } + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + __uint128_t tmp = 0; + + /* + * Z regs are stored endianness invariant, this won't + * work for big endian + */ + memcpy(&tmp, read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + sizeof(tmp)); + + if (tmp != write_fpsimd.vregs[i]) { + ksft_print_msg("Mismatch in FPSIMD for %s VL %u Z%d/V%d\n", + type->name, vl, i, i); + errors++; + } + } + + check_u32(vl, "FPSR", &write_fpsimd.fpsr, + read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors); + check_u32(vl, "FPCR", &write_fpsimd.fpcr, + read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors); + break; + default: + ksft_print_msg("Unexpected regs type %d\n", + read_sve->flags & SVE_PT_REGS_MASK); + errors++; + break; + } + + ksft_test_result(errors == 0, "Set FPSIMD, read via SVE for %s VL %u\n", + type->name, vl); + +out: + free(read_buf); +} + static int do_parent(pid_t child) { int ret = EXIT_FAILURE; @@ -489,6 +611,8 @@ static int do_parent(pid_t child) unsigned int vq, vl; bool vl_supported; + ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); + /* Attach to the child */ while (1) { int sig; @@ -548,16 +672,21 @@ static int do_parent(pid_t child) if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) { ptrace_sve_fpsimd(child, &vec_types[i]); } else { - ksft_test_result_skip("%s FPSIMD get via SVE\n", - vec_types[i].name); ksft_test_result_skip("%s FPSIMD set via SVE\n", vec_types[i].name); - ksft_test_result_skip("%s set read via FPSIMD\n", + ksft_test_result_skip("%s FPSIMD read\n", vec_types[i].name); } /* prctl() flags */ - ptrace_set_get_inherit(child, &vec_types[i]); + if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) { + ptrace_set_get_inherit(child, &vec_types[i]); + } else { + ksft_test_result_skip("%s SVE_PT_VL_INHERIT set\n", + vec_types[i].name); + ksft_test_result_skip("%s SVE_PT_VL_INHERIT cleared\n", + vec_types[i].name); + } /* Step through every possible VQ */ for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { @@ -578,11 +707,14 @@ static int do_parent(pid_t child) if (vl_supported) { ptrace_set_sve_get_sve_data(child, &vec_types[i], vl); ptrace_set_sve_get_fpsimd_data(child, &vec_types[i], vl); + ptrace_set_fpsimd_get_sve_data(child, &vec_types[i], vl); } else { ksft_test_result_skip("%s set SVE get SVE for VL %d\n", vec_types[i].name, vl); ksft_test_result_skip("%s set SVE get FPSIMD for VL %d\n", vec_types[i].name, vl); + ksft_test_result_skip("%s set FPSIMD get SVE for VL %d\n", + vec_types[i].name, vl); } } } diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index f5b1b48ffff2..2a18cb4c528c 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -13,6 +13,7 @@ #include <asm/unistd.h> #include "assembler.h" #include "asm-offsets.h" +#include "sme-inst.h" #define NZR 32 #define NPR 16 @@ -156,6 +157,7 @@ endfunction // We fill the upper lanes of FFR with zeros. // Beware: corrupts P0. function setup_ffr +#ifndef SSVE mov x4, x30 and w0, w0, #0x3 @@ -178,6 +180,9 @@ function setup_ffr wrffr p0.b ret x4 +#else + ret +#endif endfunction // Trivial memory compare: compare x2 bytes starting at address x0 with @@ -260,6 +265,7 @@ endfunction // Beware -- corrupts P0. // Clobbers x0-x5. function check_ffr +#ifndef SSVE mov x3, x30 ldr x4, =scratch @@ -280,6 +286,9 @@ function check_ffr mov x2, x5 mov x30, x3 b memcmp +#else + ret +#endif endfunction // Any SVE register modified here can cause corruption in the main @@ -295,10 +304,21 @@ function irritator_handler movi v0.8b, #1 movi v9.16b, #2 movi v31.8b, #3 +#ifndef SSVE // And P0 rdffr p0.b // And FFR wrffr p15.b +#endif + + ret +endfunction + +function tickle_handler + // Increment the signal count (x23): + ldr x0, [x2, #ucontext_regs + 8 * 23] + add x0, x0, #1 + str x0, [x2, #ucontext_regs + 8 * 23] ret endfunction @@ -359,6 +379,35 @@ 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 +#endif + // Sanity-check and report the vector length rdvl x19, #8 @@ -389,23 +438,9 @@ _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 mov x22, #0 // generation number, increments per iteration .Ltest_loop: diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c index c90658811a83..9bcfcdc34ee9 100644 --- a/tools/testing/selftests/arm64/fp/vec-syscfg.c +++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c @@ -51,6 +51,16 @@ static struct vec_data vec_data[] = { .prctl_set = PR_SVE_SET_VL, .default_vl_file = "/proc/sys/abi/sve_default_vector_length", }, + { + .name = "SME", + .hwcap_type = AT_HWCAP2, + .hwcap = HWCAP2_SME, + .rdvl = rdvl_sme, + .rdvl_binary = "./rdvl-sme", + .prctl_get = PR_SME_GET_VL, + .prctl_set = PR_SME_SET_VL, + .default_vl_file = "/proc/sys/abi/sme_default_vector_length", + }, }; static int stdio_read_integer(FILE *f, const char *what, int *val) diff --git a/tools/testing/selftests/arm64/fp/vlset.c b/tools/testing/selftests/arm64/fp/vlset.c index 308d27a68226..76912a581a95 100644 --- a/tools/testing/selftests/arm64/fp/vlset.c +++ b/tools/testing/selftests/arm64/fp/vlset.c @@ -22,12 +22,15 @@ static int inherit = 0; static int no_inherit = 0; static int force = 0; static unsigned long vl; +static int set_ctl = PR_SVE_SET_VL; +static int get_ctl = PR_SVE_GET_VL; static const struct option options[] = { { "force", no_argument, NULL, 'f' }, { "inherit", no_argument, NULL, 'i' }, { "max", no_argument, NULL, 'M' }, { "no-inherit", no_argument, &no_inherit, 1 }, + { "sme", no_argument, NULL, 's' }, { "help", no_argument, NULL, '?' }, {} }; @@ -50,6 +53,9 @@ static int parse_options(int argc, char **argv) case 'M': vl = SVE_VL_MAX; break; case 'f': force = 1; break; case 'i': inherit = 1; break; + case 's': set_ctl = PR_SME_SET_VL; + get_ctl = PR_SME_GET_VL; + break; case 0: break; default: goto error; } @@ -125,14 +131,14 @@ int main(int argc, char **argv) if (inherit) flags |= PR_SVE_VL_INHERIT; - t = prctl(PR_SVE_SET_VL, vl | flags); + t = prctl(set_ctl, vl | flags); if (t < 0) { fprintf(stderr, "%s: PR_SVE_SET_VL: %s\n", program_name, strerror(errno)); goto error; } - t = prctl(PR_SVE_GET_VL); + t = prctl(get_ctl); if (t == -1) { fprintf(stderr, "%s: PR_SVE_GET_VL: %s\n", program_name, strerror(errno)); diff --git a/tools/testing/selftests/arm64/fp/za-fork-asm.S b/tools/testing/selftests/arm64/fp/za-fork-asm.S new file mode 100644 index 000000000000..2fafadd491c3 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-fork-asm.S @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021 ARM Limited. + +#include "sme-inst.h" + +.arch_extension sve + +#define MAGIC 42 + +#define MAXVL 2048 +#define MAXVL_B (MAXVL / 8) + +.pushsection .text +.data +.align 4 +scratch: + .space MAXVL_B +.popsection + +.globl fork_test +fork_test: + smstart_za + + // For simplicity just set one word in one vector, other tests + // cover general data corruption issues. + ldr x0, =scratch + mov x1, #MAGIC + str x1, [x0] + mov w12, wzr + _ldr_za 12, 0 // ZA.H[W12] loaded from [X0] + + // Tail call into the C portion that does the fork & verify + b fork_test_c + +.globl verify_fork +verify_fork: + // SVCR should have ZA=1, SM=0 + mrs x0, S3_3_C4_C2_2 + and x1, x0, #3 + cmp x1, #2 + beq 1f + mov x0, xzr + b 100f +1: + + // ZA should still have the value we loaded + ldr x0, =scratch + mov w12, wzr + _str_za 12, 0 // ZA.H[W12] stored to [X0] + ldr x1, [x0] + cmp x1, #MAGIC + beq 2f + mov x0, xzr + b 100f + +2: + // All tests passed + mov x0, #1 +100: + ret + diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c new file mode 100644 index 000000000000..ff475c649e96 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-fork.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 ARM Limited. + * Original author: Mark Brown <broonie@kernel.org> + */ + +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/sched.h> +#include <linux/wait.h> + +#define EXPECTED_TESTS 1 + +static void putstr(const char *str) +{ + write(1, str, strlen(str)); +} + +static void putnum(unsigned int num) +{ + char c; + + if (num / 10) + putnum(num / 10); + + c = '0' + (num % 10); + write(1, &c, 1); +} + +static int tests_run; +static int tests_passed; +static int tests_failed; +static int tests_skipped; + +static void print_summary(void) +{ + if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS) + putstr("# UNEXPECTED TEST COUNT: "); + + putstr("# Totals: pass:"); + putnum(tests_passed); + putstr(" fail:"); + putnum(tests_failed); + putstr(" xfail:0 xpass:0 skip:"); + putnum(tests_skipped); + putstr(" error:0\n"); +} + +int fork_test(void); +int verify_fork(void); + +/* + * If we fork the value in the parent should be unchanged and the + * child should start with the same value. This is called from the + * fork_test() asm function. + */ +int fork_test_c(void) +{ + pid_t newpid, waiting; + int child_status, parent_result; + + newpid = fork(); + if (newpid == 0) { + /* In child */ + if (!verify_fork()) { + putstr("# ZA state invalid in child\n"); + exit(0); + } else { + exit(1); + } + } + if (newpid < 0) { + putstr("# fork() failed: -"); + putnum(-newpid); + putstr("\n"); + return 0; + } + + parent_result = verify_fork(); + if (!parent_result) + putstr("# ZA state invalid in parent\n"); + + for (;;) { + waiting = waitpid(newpid, &child_status, 0); + + if (waiting < 0) { + if (errno == EINTR) + continue; + putstr("# waitpid() failed: "); + putnum(errno); + putstr("\n"); + return 0; + } + if (waiting != newpid) { + putstr("# waitpid() returned wrong PID\n"); + return 0; + } + + if (!WIFEXITED(child_status)) { + putstr("# child did not exit\n"); + return 0; + } + + return WEXITSTATUS(child_status) && parent_result; + } +} + +#define run_test(name) \ + if (name()) { \ + tests_passed++; \ + } else { \ + tests_failed++; \ + putstr("not "); \ + } \ + putstr("ok "); \ + putnum(++tests_run); \ + putstr(" " #name "\n"); + +int main(int argc, char **argv) +{ + int ret, i; + + putstr("TAP version 13\n"); + putstr("1.."); + putnum(EXPECTED_TESTS); + putstr("\n"); + + putstr("# PID: "); + putnum(getpid()); + putstr("\n"); + + /* + * This test is run with nolibc which doesn't support hwcap and + * it's probably disproportionate to implement so instead check + * for the default vector length configuration in /proc. + */ + ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0); + if (ret >= 0) { + run_test(fork_test); + + } else { + putstr("# SME support not present\n"); + + for (i = 0; i < EXPECTED_TESTS; i++) { + putstr("ok "); + putnum(i); + putstr(" skipped\n"); + } + + tests_skipped += EXPECTED_TESTS; + } + + print_summary(); + + return 0; +} diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c new file mode 100644 index 000000000000..bf6158654056 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-ptrace.c @@ -0,0 +1,356 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 ARM Limited. + */ +#include <errno.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/ptrace.h> +#include <sys/types.h> +#include <sys/uio.h> +#include <sys/wait.h> +#include <asm/sigcontext.h> +#include <asm/ptrace.h> + +#include "../../kselftest.h" + +/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ +#ifndef NT_ARM_ZA +#define NT_ARM_ZA 0x40c +#endif + +#define EXPECTED_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3) + +static void fill_buf(char *buf, size_t size) +{ + int i; + + for (i = 0; i < size; i++) + buf[i] = random(); +} + +static int do_child(void) +{ + if (ptrace(PTRACE_TRACEME, -1, NULL, NULL)) + ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno)); + + if (raise(SIGSTOP)) + ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno)); + + return EXIT_SUCCESS; +} + +static struct user_za_header *get_za(pid_t pid, void **buf, size_t *size) +{ + struct user_za_header *za; + void *p; + size_t sz = sizeof(*za); + struct iovec iov; + + while (1) { + if (*size < sz) { + p = realloc(*buf, sz); + if (!p) { + errno = ENOMEM; + goto error; + } + + *buf = p; + *size = sz; + } + + iov.iov_base = *buf; + iov.iov_len = sz; + if (ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZA, &iov)) + goto error; + + za = *buf; + if (za->size <= sz) + break; + + sz = za->size; + } + + return za; + +error: + return NULL; +} + +static int set_za(pid_t pid, const struct user_za_header *za) +{ + struct iovec iov; + + iov.iov_base = (void *)za; + iov.iov_len = za->size; + return ptrace(PTRACE_SETREGSET, pid, NT_ARM_ZA, &iov); +} + +/* Validate attempting to set the specfied VL via ptrace */ +static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported) +{ + struct user_za_header za; + struct user_za_header *new_za = NULL; + size_t new_za_size = 0; + int ret, prctl_vl; + + *supported = false; + + /* Check if the VL is supported in this process */ + prctl_vl = prctl(PR_SME_SET_VL, vl); + if (prctl_vl == -1) + ksft_exit_fail_msg("prctl(PR_SME_SET_VL) failed: %s (%d)\n", + strerror(errno), errno); + + /* If the VL is not supported then a supported VL will be returned */ + *supported = (prctl_vl == vl); + + /* Set the VL by doing a set with no register payload */ + memset(&za, 0, sizeof(za)); + za.size = sizeof(za); + za.vl = vl; + ret = set_za(child, &za); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u\n", vl); + return; + } + + /* + * Read back the new register state and verify that we have the + * same VL that we got from prctl() on ourselves. + */ + if (!get_za(child, (void **)&new_za, &new_za_size)) { + ksft_test_result_fail("Failed to read VL %u\n", vl); + return; + } + + ksft_test_result(new_za->vl = prctl_vl, "Set VL %u\n", vl); + + free(new_za); +} + +/* Validate attempting to set no ZA data and read it back */ +static void ptrace_set_no_data(pid_t child, unsigned int vl) +{ + void *read_buf = NULL; + struct user_za_header write_za; + struct user_za_header *read_za; + size_t read_za_size = 0; + int ret; + + /* Set up some data and write it out */ + memset(&write_za, 0, sizeof(write_za)); + write_za.size = ZA_PT_ZA_OFFSET; + write_za.vl = vl; + + ret = set_za(child, &write_za); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u no data\n", vl); + return; + } + + /* Read the data back */ + if (!get_za(child, (void **)&read_buf, &read_za_size)) { + ksft_test_result_fail("Failed to read VL %u no data\n", vl); + return; + } + read_za = read_buf; + + /* We might read more data if there's extensions we don't know */ + if (read_za->size < write_za.size) { + ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n", + vl, write_za.size, read_za->size); + goto out_read; + } + + ksft_test_result(read_za->size == write_za.size, + "Disabled ZA for VL %u\n", vl); + +out_read: + free(read_buf); +} + +/* Validate attempting to set data and read it back */ +static void ptrace_set_get_data(pid_t child, unsigned int vl) +{ + void *write_buf; + void *read_buf = NULL; + struct user_za_header *write_za; + struct user_za_header *read_za; + size_t read_za_size = 0; + unsigned int vq = sve_vq_from_vl(vl); + int ret; + size_t data_size; + + data_size = ZA_PT_SIZE(vq); + write_buf = malloc(data_size); + if (!write_buf) { + ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n", + data_size, vl); + return; + } + write_za = write_buf; + + /* Set up some data and write it out */ + memset(write_za, 0, data_size); + write_za->size = data_size; + write_za->vl = vl; + + fill_buf(write_buf + ZA_PT_ZA_OFFSET, ZA_PT_ZA_SIZE(vq)); + + ret = set_za(child, write_za); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u data\n", vl); + goto out; + } + + /* Read the data back */ + if (!get_za(child, (void **)&read_buf, &read_za_size)) { + ksft_test_result_fail("Failed to read VL %u data\n", vl); + goto out; + } + read_za = read_buf; + + /* We might read more data if there's extensions we don't know */ + if (read_za->size < write_za->size) { + ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n", + vl, write_za->size, read_za->size); + goto out_read; + } + + ksft_test_result(memcmp(write_buf + ZA_PT_ZA_OFFSET, + read_buf + ZA_PT_ZA_OFFSET, + ZA_PT_ZA_SIZE(vq)) == 0, + "Data match for VL %u\n", vl); + +out_read: + free(read_buf); +out: + free(write_buf); +} + +static int do_parent(pid_t child) +{ + int ret = EXIT_FAILURE; + pid_t pid; + int status; + siginfo_t si; + unsigned int vq, vl; + bool vl_supported; + + /* Attach to the child */ + while (1) { + int sig; + + pid = wait(&status); + if (pid == -1) { + perror("wait"); + goto error; + } + + /* + * This should never happen but it's hard to flag in + * the framework. + */ + if (pid != child) + continue; + + if (WIFEXITED(status) || WIFSIGNALED(status)) + ksft_exit_fail_msg("Child died unexpectedly\n"); + + if (!WIFSTOPPED(status)) + goto error; + + sig = WSTOPSIG(status); + + if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &si)) { + if (errno == ESRCH) + goto disappeared; + + if (errno == EINVAL) { + sig = 0; /* bust group-stop */ + goto cont; + } + + ksft_test_result_fail("PTRACE_GETSIGINFO: %s\n", + strerror(errno)); + goto error; + } + + if (sig == SIGSTOP && si.si_code == SI_TKILL && + si.si_pid == pid) + break; + + cont: + if (ptrace(PTRACE_CONT, pid, NULL, sig)) { + if (errno == ESRCH) + goto disappeared; + + ksft_test_result_fail("PTRACE_CONT: %s\n", + strerror(errno)); + goto error; + } + } + + ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); + + /* Step through every possible VQ */ + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + vl = sve_vl_from_vq(vq); + + /* First, try to set this vector length */ + ptrace_set_get_vl(child, vl, &vl_supported); + + /* If the VL is supported validate data set/get */ + if (vl_supported) { + ptrace_set_no_data(child, vl); + ptrace_set_get_data(child, vl); + } else { + ksft_test_result_skip("Disabled ZA for VL %u\n", vl); + ksft_test_result_skip("Get and set data for VL %u\n", + vl); + } + } + + ret = EXIT_SUCCESS; + +error: + kill(child, SIGKILL); + +disappeared: + return ret; +} + +int main(void) +{ + int ret = EXIT_SUCCESS; + pid_t child; + + srandom(getpid()); + + ksft_print_header(); + + if (!(getauxval(AT_HWCAP2) & HWCAP2_SME)) { + ksft_set_plan(1); + ksft_exit_skip("SME not available\n"); + } + + ksft_set_plan(EXPECTED_TESTS); + + child = fork(); + if (!child) + return do_child(); + + if (do_parent(child)) + ret = EXIT_FAILURE; + + ksft_print_cnts(); + + return ret; +} diff --git a/tools/testing/selftests/arm64/fp/za-stress b/tools/testing/selftests/arm64/fp/za-stress new file mode 100644 index 000000000000..5ac386b55b95 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-stress @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2015-2019 ARM Limited. +# Original author: Dave Martin <Dave.Martin@arm.com> + +set -ue + +NR_CPUS=`nproc` + +pids= +logs= + +cleanup () { + trap - INT TERM CHLD + set +e + + if [ -n "$pids" ]; then + kill $pids + wait $pids + pids= + fi + + if [ -n "$logs" ]; then + cat $logs + rm $logs + logs= + fi +} + +interrupt () { + cleanup + exit 0 +} + +child_died () { + cleanup + exit 1 +} + +trap interrupt INT TERM EXIT + +for x in `seq 0 $((NR_CPUS * 4))`; do + log=`mktemp` + logs=$logs\ $log + ./za-test >$log & + pids=$pids\ $! +done + +# Wait for all child processes to be created: +sleep 10 + +while :; do + kill -USR1 $pids +done & +pids=$pids\ $! + +wait + +exit 1 diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S new file mode 100644 index 000000000000..53c54af65704 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-test.S @@ -0,0 +1,398 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021 ARM Limited. +// Original author: Mark Brown <broonie@kernel.org> +// +// Scalable Matrix Extension ZA context switch test +// Repeatedly writes unique test patterns into each ZA tile +// and reads them back to verify integrity. +// +// for x in `seq 1 NR_CPUS`; do sve-test & pids=$pids\ $! ; done +// (leave it running for as long as you want...) +// kill $pids + +#include <asm/unistd.h> +#include "assembler.h" +#include "asm-offsets.h" +#include "sme-inst.h" + +.arch_extension sve + +#define MAXVL 2048 +#define MAXVL_B (MAXVL / 8) + +// Declare some storage space to shadow ZA register contents and a +// scratch buffer for a vector. +.pushsection .text +.data +.align 4 +zaref: + .space MAXVL_B * MAXVL_B +scratch: + .space MAXVL_B +.popsection + +// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. +// Clobbers x0-x3 +function memcpy + cmp x2, #0 + b.eq 1f +0: ldrb w3, [x1], #1 + strb w3, [x0], #1 + subs x2, x2, #1 + b.ne 0b +1: ret +endfunction + +// Generate a test pattern for storage in ZA +// x0: pid +// x1: row in ZA +// x2: generation + +// These values are used to constuct a 32-bit pattern that is repeated in the +// scratch buffer as many times as will fit: +// bits 31:28 generation number (increments once per test_loop) +// bits 27:16 pid +// bits 15: 8 row number +// bits 7: 0 32-bit lane index + +function pattern + mov w3, wzr + bfi w3, w0, #16, #12 // PID + bfi w3, w1, #8, #8 // Row + bfi w3, w2, #28, #4 // Generation + + ldr x0, =scratch + mov w1, #MAXVL_B / 4 + +0: str w3, [x0], #4 + add w3, w3, #1 // Lane + subs w1, w1, #1 + b.ne 0b + + ret +endfunction + +// Get the address of shadow data for ZA horizontal vector xn +.macro _adrza xd, xn, nrtmp + ldr \xd, =zaref + rdsvl \nrtmp, 1 + madd \xd, x\nrtmp, \xn, \xd +.endm + +// Set up test pattern in a ZA horizontal vector +// x0: pid +// x1: row number +// x2: generation +function setup_za + mov x4, x30 + mov x12, x1 // Use x12 for vector select + + bl pattern // Get pattern in scratch buffer + _adrza x0, x12, 2 // Shadow buffer pointer to x0 and x5 + mov x5, x0 + ldr x1, =scratch + bl memcpy // length set up in x2 by _adrza + + _ldr_za 12, 5 // load vector w12 from pointer x5 + + ret x4 +endfunction + +// Trivial memory compare: compare x2 bytes starting at address x0 with +// bytes starting at address x1. +// Returns only if all bytes match; otherwise, the program is aborted. +// Clobbers x0-x5. +function memcmp + cbz x2, 2f + + stp x0, x1, [sp, #-0x20]! + str x2, [sp, #0x10] + + mov x5, #0 +0: ldrb w3, [x0, x5] + ldrb w4, [x1, x5] + add x5, x5, #1 + cmp w3, w4 + b.ne 1f + subs x2, x2, #1 + b.ne 0b + +1: ldr x2, [sp, #0x10] + ldp x0, x1, [sp], #0x20 + b.ne barf + +2: ret +endfunction + +// Verify that a ZA vector matches its shadow in memory, else abort +// x0: row number +// Clobbers x0-x7 and x12. +function check_za + mov x3, x30 + + mov x12, x0 + _adrza x5, x0, 6 // pointer to expected value in x5 + mov x4, x0 + ldr x7, =scratch // x7 is scratch + + mov x0, x7 // Poison scratch + mov x1, x6 + bl memfill_ae + + _str_za 12, 7 // save vector w12 to pointer x7 + + mov x0, x5 + mov x1, x7 + mov x2, x6 + mov x30, x3 + b memcmp +endfunction + +// Any SME register modified here can cause corruption in the main +// thread -- but *only* the locations modified here. +function irritator_handler + // Increment the irritation signal count (x23): + ldr x0, [x2, #ucontext_regs + 8 * 23] + add x0, x0, #1 + str x0, [x2, #ucontext_regs + 8 * 23] + + // Corrupt some random ZA data +#if 0 + adr x0, .text + (irritator_handler - .text) / 16 * 16 + movi v0.8b, #1 + movi v9.16b, #2 + movi v31.8b, #3 +#endif + + ret +endfunction + +function tickle_handler + // Increment the signal count (x23): + ldr x0, [x2, #ucontext_regs + 8 * 23] + add x0, x0, #1 + str x0, [x2, #ucontext_regs + 8 * 23] + + ret +endfunction + +function terminate_handler + mov w21, w0 + mov x20, x2 + + puts "Terminated by signal " + mov w0, w21 + bl putdec + puts ", no error, iterations=" + ldr x0, [x20, #ucontext_regs + 8 * 22] + bl putdec + puts ", signals=" + ldr x0, [x20, #ucontext_regs + 8 * 23] + bl putdecn + + mov x0, #0 + mov x8, #__NR_exit + svc #0 +endfunction + +// w0: signal number +// x1: sa_action +// w2: sa_flags +// Clobbers x0-x6,x8 +function setsignal + str x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]! + + mov w4, w0 + mov x5, x1 + mov w6, w2 + + add x0, sp, #16 + mov x1, #sa_sz + bl memclr + + mov w0, w4 + add x1, sp, #16 + str w6, [x1, #sa_flags] + str x5, [x1, #sa_handler] + mov x2, #0 + mov x3, #sa_mask_sz + mov x8, #__NR_rt_sigaction + svc #0 + + cbz w0, 1f + + puts "sigaction failure\n" + b .Labort + +1: ldr x30, [sp], #((sa_sz + 15) / 16 * 16 + 16) + ret +endfunction + +// Main program entry point +.globl _start +function _start +_start: + mov x23, #0 // signal count + + mov w0, #SIGINT + adr x1, terminate_handler + mov w2, #SA_SIGINFO + bl setsignal + + mov w0, #SIGTERM + adr x1, terminate_handler + mov w2, #SA_SIGINFO + bl setsignal + + mov w0, #SIGUSR1 + adr x1, irritator_handler + mov w2, #SA_SIGINFO + orr w2, w2, #SA_NODEFER + bl setsignal + + mov w0, #SIGUSR2 + adr x1, tickle_handler + mov w2, #SA_SIGINFO + orr w2, w2, #SA_NODEFER + bl setsignal + + puts "Streaming mode " + smstart_za + + // Sanity-check and report the vector length + + rdsvl 19, 8 + cmp x19, #128 + b.lo 1f + cmp x19, #2048 + b.hi 1f + tst x19, #(8 - 1) + b.eq 2f + +1: puts "bad vector length: " + mov x0, x19 + bl putdecn + b .Labort + +2: puts "vector length:\t" + mov x0, x19 + bl putdec + puts " bits\n" + + // Obtain our PID, to ensure test pattern uniqueness between processes + mov x8, #__NR_getpid + svc #0 + mov x20, x0 + + puts "PID:\t" + mov x0, x20 + bl putdecn + + mov x22, #0 // generation number, increments per iteration +.Ltest_loop: + rdsvl 0, 8 + cmp x0, x19 + b.ne vl_barf + + rdsvl 21, 1 // Set up ZA & shadow with test pattern +0: mov x0, x20 + sub x1, x21, #1 + mov x2, x22 + bl setup_za + subs x21, x21, #1 + b.ne 0b + + mov x8, #__NR_sched_yield // encourage preemption +1: + svc #0 + + mrs x0, S3_3_C4_C2_2 // SVCR should have ZA=1,SM=0 + and x1, x0, #3 + cmp x1, #2 + b.ne svcr_barf + + rdsvl 21, 1 // Verify that the data made it through + rdsvl 24, 1 // Verify that the data made it through +0: sub x0, x24, x21 + bl check_za + subs x21, x21, #1 + bne 0b + + add x22, x22, #1 // Everything still working + b .Ltest_loop + +.Labort: + mov x0, #0 + mov x1, #SIGABRT + mov x8, #__NR_kill + svc #0 +endfunction + +function barf +// fpsimd.c acitivty log dump hack +// ldr w0, =0xdeadc0de +// mov w8, #__NR_exit +// svc #0 +// end hack + smstop + mov x10, x0 // expected data + mov x11, x1 // actual data + mov x12, x2 // data size + + puts "Mismatch: PID=" + mov x0, x20 + bl putdec + puts ", iteration=" + mov x0, x22 + bl putdec + puts ", row=" + mov x0, x21 + bl putdecn + puts "\tExpected [" + mov x0, x10 + mov x1, x12 + bl dumphex + puts "]\n\tGot [" + mov x0, x11 + mov x1, x12 + bl dumphex + puts "]\n" + + mov x8, #__NR_getpid + svc #0 +// fpsimd.c acitivty log dump hack +// ldr w0, =0xdeadc0de +// mov w8, #__NR_exit +// svc #0 +// ^ end of hack + mov x1, #SIGABRT + mov x8, #__NR_kill + svc #0 +// mov x8, #__NR_exit +// mov x1, #1 +// svc #0 +endfunction + +function vl_barf + mov x10, x0 + + puts "Bad active VL: " + mov x0, x10 + bl putdecn + + mov x8, #__NR_exit + mov x1, #1 + svc #0 +endfunction + +function svcr_barf + mov x10, x0 + + puts "Bad SVCR: " + mov x0, x10 + bl putdecn + + mov x8, #__NR_exit + mov x1, #1 + svc #0 +endfunction diff --git a/tools/testing/selftests/arm64/mte/.gitignore b/tools/testing/selftests/arm64/mte/.gitignore index d1fe4ddf1669..052d0f9f92b3 100644 --- a/tools/testing/selftests/arm64/mte/.gitignore +++ b/tools/testing/selftests/arm64/mte/.gitignore @@ -3,5 +3,6 @@ check_gcr_el1_cswitch check_tags_inclusion check_child_memory check_mmap_options +check_prctl check_ksm_options check_user_mem diff --git a/tools/testing/selftests/arm64/mte/Makefile b/tools/testing/selftests/arm64/mte/Makefile index 409e3e53d00a..037046f5784e 100644 --- a/tools/testing/selftests/arm64/mte/Makefile +++ b/tools/testing/selftests/arm64/mte/Makefile @@ -11,18 +11,14 @@ 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 TEST_GEN_PROGS := $(PROGS) # Get Kernel headers installed and use them. -KSFT_KHDR_INSTALL := 1 else $(warning compiler "$(CC)" does not support the ARMv8.5 MTE extension.) $(warning test program "mte" will not be created.) diff --git a/tools/testing/selftests/arm64/mte/check_child_memory.c b/tools/testing/selftests/arm64/mte/check_child_memory.c index 43bd94f853ba..7597fc632cad 100644 --- a/tools/testing/selftests/arm64/mte/check_child_memory.c +++ b/tools/testing/selftests/arm64/mte/check_child_memory.c @@ -85,9 +85,9 @@ static int check_child_memory_mapping(int mem_type, int mode, int mapping) { char *ptr; int run, result; - int item = sizeof(sizes)/sizeof(int); + int item = ARRAY_SIZE(sizes); - item = sizeof(sizes)/sizeof(int); + item = ARRAY_SIZE(sizes); mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); for (run = 0; run < item; run++) { ptr = (char *)mte_allocate_memory_tag_range(sizes[run], mem_type, mapping, @@ -107,7 +107,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping) { char *ptr, *map_ptr; int run, fd, map_size, result = KSFT_PASS; - int total = sizeof(sizes)/sizeof(int); + int total = ARRAY_SIZE(sizes); mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); for (run = 0; run < total; run++) { @@ -144,7 +144,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping) int main(int argc, char *argv[]) { int err; - int item = sizeof(sizes)/sizeof(int); + int item = ARRAY_SIZE(sizes); page_size = getpagesize(); if (!page_size) { diff --git a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c index a876db1f096a..325bca0de0f6 100644 --- a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c +++ b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c @@ -19,17 +19,6 @@ #include "kselftest.h" #include "mte_common_util.h" -#define PR_SET_TAGGED_ADDR_CTRL 55 -#define PR_GET_TAGGED_ADDR_CTRL 56 -# define PR_TAGGED_ADDR_ENABLE (1UL << 0) -# define PR_MTE_TCF_SHIFT 1 -# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TAG_SHIFT 3 -# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) - #include "mte_def.h" #define NUM_ITERATIONS 1024 diff --git a/tools/testing/selftests/arm64/mte/check_prctl.c b/tools/testing/selftests/arm64/mte/check_prctl.c new file mode 100644 index 000000000000..f139a33a43ef --- /dev/null +++ b/tools/testing/selftests/arm64/mte/check_prctl.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2022 ARM Limited + +#include <stdbool.h> +#include <stdio.h> +#include <string.h> + +#include <sys/auxv.h> +#include <sys/prctl.h> + +#include <asm/hwcap.h> + +#include "kselftest.h" + +static int set_tagged_addr_ctrl(int val) +{ + int ret; + + ret = prctl(PR_SET_TAGGED_ADDR_CTRL, val, 0, 0, 0); + if (ret < 0) + ksft_print_msg("PR_SET_TAGGED_ADDR_CTRL: failed %d %d (%s)\n", + ret, errno, strerror(errno)); + return ret; +} + +static int get_tagged_addr_ctrl(void) +{ + int ret; + + ret = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0); + if (ret < 0) + ksft_print_msg("PR_GET_TAGGED_ADDR_CTRL failed: %d %d (%s)\n", + ret, errno, strerror(errno)); + return ret; +} + +/* + * Read the current mode without having done any configuration, should + * run first. + */ +void check_basic_read(void) +{ + int ret; + + ret = get_tagged_addr_ctrl(); + if (ret < 0) { + ksft_test_result_fail("check_basic_read\n"); + return; + } + + if (ret & PR_MTE_TCF_SYNC) + ksft_print_msg("SYNC enabled\n"); + if (ret & PR_MTE_TCF_ASYNC) + ksft_print_msg("ASYNC enabled\n"); + + /* Any configuration is valid */ + ksft_test_result_pass("check_basic_read\n"); +} + +/* + * Attempt to set a specified combination of modes. + */ +void set_mode_test(const char *name, int hwcap2, int mask) +{ + int ret; + + if ((getauxval(AT_HWCAP2) & hwcap2) != hwcap2) { + ksft_test_result_skip("%s\n", name); + return; + } + + ret = set_tagged_addr_ctrl(mask); + if (ret < 0) { + ksft_test_result_fail("%s\n", name); + return; + } + + ret = get_tagged_addr_ctrl(); + if (ret < 0) { + ksft_test_result_fail("%s\n", name); + return; + } + + if ((ret & PR_MTE_TCF_MASK) == mask) { + ksft_test_result_pass("%s\n", name); + } else { + ksft_print_msg("Got %x, expected %x\n", + (ret & PR_MTE_TCF_MASK), mask); + ksft_test_result_fail("%s\n", name); + } +} + +struct mte_mode { + int mask; + int hwcap2; + const char *name; +} mte_modes[] = { + { PR_MTE_TCF_NONE, 0, "NONE" }, + { PR_MTE_TCF_SYNC, HWCAP2_MTE, "SYNC" }, + { PR_MTE_TCF_ASYNC, HWCAP2_MTE, "ASYNC" }, + { PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC, HWCAP2_MTE, "SYNC+ASYNC" }, +}; + +int main(void) +{ + int i; + + ksft_print_header(); + ksft_set_plan(5); + + check_basic_read(); + for (i = 0; i < ARRAY_SIZE(mte_modes); i++) + set_mode_test(mte_modes[i].name, mte_modes[i].hwcap2, + mte_modes[i].mask); + + ksft_print_cnts(); + + return 0; +} diff --git a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c index deaef1f61076..2b1425b92b69 100644 --- a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c +++ b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c @@ -23,10 +23,13 @@ static int verify_mte_pointer_validity(char *ptr, int mode) { mte_initialize_current_context(mode, (uintptr_t)ptr, BUFFER_SIZE); /* Check the validity of the tagged pointer */ - memset((void *)ptr, '1', BUFFER_SIZE); + memset(ptr, '1', BUFFER_SIZE); mte_wait_after_trig(); - if (cur_mte_cxt.fault_valid) + if (cur_mte_cxt.fault_valid) { + ksft_print_msg("Unexpected fault recorded for %p-%p in mode %x\n", + ptr, ptr + BUFFER_SIZE, mode); return KSFT_FAIL; + } /* Proceed further for nonzero tags */ if (!MT_FETCH_TAG((uintptr_t)ptr)) return KSFT_PASS; @@ -34,27 +37,32 @@ static int verify_mte_pointer_validity(char *ptr, int mode) /* Check the validity outside the range */ ptr[BUFFER_SIZE] = '2'; mte_wait_after_trig(); - if (!cur_mte_cxt.fault_valid) + if (!cur_mte_cxt.fault_valid) { + ksft_print_msg("No valid fault recorded for %p in mode %x\n", + ptr, mode); return KSFT_FAIL; - else + } else { return KSFT_PASS; + } } static int check_single_included_tags(int mem_type, int mode) { char *ptr; - int tag, run, result = KSFT_PASS; + int tag, run, ret, result = KSFT_PASS; - ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); + ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; for (tag = 0; (tag < MT_TAG_COUNT) && (result == KSFT_PASS); tag++) { - mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag)); + ret = mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag)); + if (ret != 0) + result = KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) { - ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE); + ptr = mte_insert_tags(ptr, BUFFER_SIZE); /* Check tag value */ if (MT_FETCH_TAG((uintptr_t)ptr) == tag) { ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n", @@ -66,7 +74,7 @@ static int check_single_included_tags(int mem_type, int mode) result = verify_mte_pointer_validity(ptr, mode); } } - mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); + mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); return result; } @@ -76,7 +84,7 @@ static int check_multiple_included_tags(int mem_type, int mode) int tag, run, result = KSFT_PASS; unsigned long excl_mask = 0; - ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); + ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; @@ -86,7 +94,7 @@ static int check_multiple_included_tags(int mem_type, int mode) mte_switch_mode(mode, MT_INCLUDE_VALID_TAGS(excl_mask)); /* Try to catch a excluded tag by a number of tries. */ for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) { - ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE); + ptr = mte_insert_tags(ptr, BUFFER_SIZE); /* Check tag value */ if (MT_FETCH_TAG((uintptr_t)ptr) < tag) { ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n", @@ -98,21 +106,23 @@ static int check_multiple_included_tags(int mem_type, int mode) result = verify_mte_pointer_validity(ptr, mode); } } - mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); + mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); return result; } static int check_all_included_tags(int mem_type, int mode) { char *ptr; - int run, result = KSFT_PASS; + int run, ret, result = KSFT_PASS; - ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); + ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; - mte_switch_mode(mode, MT_INCLUDE_TAG_MASK); + ret = mte_switch_mode(mode, MT_INCLUDE_TAG_MASK); + if (ret != 0) + return KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) { ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE); @@ -122,20 +132,22 @@ static int check_all_included_tags(int mem_type, int mode) */ result = verify_mte_pointer_validity(ptr, mode); } - mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); + mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); return result; } static int check_none_included_tags(int mem_type, int mode) { char *ptr; - int run; + int run, ret; - ptr = (char *)mte_allocate_memory(BUFFER_SIZE, mem_type, 0, false); + ptr = mte_allocate_memory(BUFFER_SIZE, mem_type, 0, false); if (check_allocated_memory(ptr, BUFFER_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; - mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK); + ret = mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK); + if (ret != 0) + return KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ for (run = 0; run < RUNS; run++) { ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE); @@ -147,12 +159,12 @@ static int check_none_included_tags(int mem_type, int mode) } mte_initialize_current_context(mode, (uintptr_t)ptr, BUFFER_SIZE); /* Check the write validity of the untagged pointer */ - memset((void *)ptr, '1', BUFFER_SIZE); + memset(ptr, '1', BUFFER_SIZE); mte_wait_after_trig(); if (cur_mte_cxt.fault_valid) break; } - mte_free_memory((void *)ptr, BUFFER_SIZE, mem_type, false); + mte_free_memory(ptr, BUFFER_SIZE, mem_type, false); if (cur_mte_cxt.fault_valid) return KSFT_FAIL; else diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c index 1de7a0abd0ae..f4ae5f87a3b7 100644 --- a/tools/testing/selftests/arm64/mte/check_user_mem.c +++ b/tools/testing/selftests/arm64/mte/check_user_mem.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE +#include <assert.h> #include <errno.h> #include <fcntl.h> #include <signal.h> @@ -11,6 +12,7 @@ #include <string.h> #include <ucontext.h> #include <unistd.h> +#include <sys/uio.h> #include <sys/mman.h> #include "kselftest.h" @@ -19,14 +21,28 @@ static size_t page_sz; -static int check_usermem_access_fault(int mem_type, int mode, int mapping) +#define TEST_NAME_MAX 100 + +enum test_type { + READ_TEST, + WRITE_TEST, + READV_TEST, + WRITEV_TEST, + LAST_TEST, +}; + +static int check_usermem_access_fault(int mem_type, int mode, int mapping, + int tag_offset, int tag_len, + enum test_type test_type) { int fd, i, err; char val = 'A'; - size_t len, read_len; + ssize_t len, syscall_len; void *ptr, *ptr_next; + int fileoff, ptroff, size; + int sizes[] = {1, 2, 3, 8, 16, 32, 4096, page_sz}; - err = KSFT_FAIL; + err = KSFT_PASS; len = 2 * page_sz; mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); fd = create_temp_file(); @@ -43,9 +59,9 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping) } mte_initialize_current_context(mode, (uintptr_t)ptr, len); /* Copy from file into buffer with valid tag */ - read_len = read(fd, ptr, len); + syscall_len = read(fd, ptr, len); mte_wait_after_trig(); - if (cur_mte_cxt.fault_valid || read_len < len) + if (cur_mte_cxt.fault_valid || syscall_len < len) goto usermem_acc_err; /* Verify same pattern is read */ for (i = 0; i < len; i++) @@ -54,36 +70,136 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping) if (i < len) goto usermem_acc_err; - /* Tag the next half of memory with different value */ - ptr_next = (void *)((unsigned long)ptr + page_sz); + if (!tag_len) + tag_len = len - tag_offset; + /* Tag a part of memory with different value */ + ptr_next = (void *)((unsigned long)ptr + tag_offset); ptr_next = mte_insert_new_tag(ptr_next); - mte_set_tag_address_range(ptr_next, page_sz); + mte_set_tag_address_range(ptr_next, tag_len); - lseek(fd, 0, 0); - /* Copy from file into buffer with invalid tag */ - read_len = read(fd, ptr, len); - mte_wait_after_trig(); - /* - * Accessing user memory in kernel with invalid tag should fail in sync - * mode without fault but may not fail in async mode as per the - * implemented MTE userspace support in Arm64 kernel. - */ - if (mode == MTE_SYNC_ERR && - !cur_mte_cxt.fault_valid && read_len < len) { - err = KSFT_PASS; - } else if (mode == MTE_ASYNC_ERR && - !cur_mte_cxt.fault_valid && read_len == len) { - err = KSFT_PASS; + for (fileoff = 0; fileoff < 16; fileoff++) { + for (ptroff = 0; ptroff < 16; ptroff++) { + for (i = 0; i < ARRAY_SIZE(sizes); i++) { + size = sizes[i]; + lseek(fd, 0, 0); + + /* perform file operation on buffer with invalid tag */ + switch (test_type) { + case READ_TEST: + syscall_len = read(fd, ptr + ptroff, size); + break; + case WRITE_TEST: + syscall_len = write(fd, ptr + ptroff, size); + break; + case READV_TEST: { + struct iovec iov[1]; + iov[0].iov_base = ptr + ptroff; + iov[0].iov_len = size; + syscall_len = readv(fd, iov, 1); + break; + } + case WRITEV_TEST: { + struct iovec iov[1]; + iov[0].iov_base = ptr + ptroff; + iov[0].iov_len = size; + syscall_len = writev(fd, iov, 1); + break; + } + case LAST_TEST: + goto usermem_acc_err; + } + + mte_wait_after_trig(); + /* + * Accessing user memory in kernel with invalid tag should fail in sync + * mode without fault but may not fail in async mode as per the + * implemented MTE userspace support in Arm64 kernel. + */ + if (cur_mte_cxt.fault_valid) { + goto usermem_acc_err; + } + if (mode == MTE_SYNC_ERR && syscall_len < len) { + /* test passed */ + } else if (mode == MTE_ASYNC_ERR && syscall_len == size) { + /* test passed */ + } else { + goto usermem_acc_err; + } + } + } } + + goto exit; + usermem_acc_err: + err = KSFT_FAIL; +exit: mte_free_memory((void *)ptr, len, mem_type, true); close(fd); return err; } +void format_test_name(char* name, int name_len, int type, int sync, int map, int len, int offset) { + const char* test_type; + const char* mte_type; + const char* map_type; + + switch (type) { + case READ_TEST: + test_type = "read"; + break; + case WRITE_TEST: + test_type = "write"; + break; + case READV_TEST: + test_type = "readv"; + break; + case WRITEV_TEST: + test_type = "writev"; + break; + default: + assert(0); + break; + } + + switch (sync) { + case MTE_SYNC_ERR: + mte_type = "MTE_SYNC_ERR"; + break; + case MTE_ASYNC_ERR: + mte_type = "MTE_ASYNC_ERR"; + break; + default: + assert(0); + break; + } + + switch (map) { + case MAP_SHARED: + map_type = "MAP_SHARED"; + break; + case MAP_PRIVATE: + map_type = "MAP_PRIVATE"; + break; + default: + assert(0); + break; + } + + snprintf(name, name_len, + "test type: %s, %s, %s, tag len: %d, tag offset: %d\n", + test_type, mte_type, map_type, len, offset); +} + int main(int argc, char *argv[]) { int err; + int t, s, m, l, o; + int mte_sync[] = {MTE_SYNC_ERR, MTE_ASYNC_ERR}; + int maps[] = {MAP_SHARED, MAP_PRIVATE}; + int tag_lens[] = {0, MT_GRANULE_SIZE}; + int tag_offsets[] = {page_sz, MT_GRANULE_SIZE}; + char test_name[TEST_NAME_MAX]; page_sz = getpagesize(); if (!page_sz) { @@ -98,17 +214,28 @@ int main(int argc, char *argv[]) mte_register_signal(SIGSEGV, mte_default_handler); /* Set test plan */ - ksft_set_plan(4); + ksft_set_plan(64); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE), - "Check memory access from kernel in sync mode, private mapping and mmap memory\n"); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED), - "Check memory access from kernel in sync mode, shared mapping and mmap memory\n"); - - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE), - "Check memory access from kernel in async mode, private mapping and mmap memory\n"); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED), - "Check memory access from kernel in async mode, shared mapping and mmap memory\n"); + for (t = 0; t < LAST_TEST; t++) { + for (s = 0; s < ARRAY_SIZE(mte_sync); s++) { + for (m = 0; m < ARRAY_SIZE(maps); m++) { + for (l = 0; l < ARRAY_SIZE(tag_lens); l++) { + for (o = 0; o < ARRAY_SIZE(tag_offsets); o++) { + int sync = mte_sync[s]; + int map = maps[m]; + int offset = tag_offsets[o]; + int tag_len = tag_lens[l]; + int res = check_usermem_access_fault(USE_MMAP, sync, + map, offset, + tag_len, t); + format_test_name(test_name, TEST_NAME_MAX, + t, sync, map, tag_len, offset); + evaluate_test(res, test_name); + } + } + } + } + } mte_restore_setup(); ksft_print_cnts(); diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.c b/tools/testing/selftests/arm64/mte/mte_common_util.c index 0328a1e08f65..00ffd34c66d3 100644 --- a/tools/testing/selftests/arm64/mte/mte_common_util.c +++ b/tools/testing/selftests/arm64/mte/mte_common_util.c @@ -37,6 +37,10 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc) if (si->si_code == SEGV_MTEAERR) { if (cur_mte_cxt.trig_si_code == si->si_code) cur_mte_cxt.fault_valid = true; + else + ksft_print_msg("Got unexpected SEGV_MTEAERR at pc=$lx, fault addr=%lx\n", + ((ucontext_t *)uc)->uc_mcontext.pc, + addr); return; } /* Compare the context for precise error */ @@ -124,13 +128,16 @@ static void *__mte_allocate_memory_range(size_t size, int mem_type, int mapping, int prot_flag, map_flag; size_t entire_size = size + range_before + range_after; - if (mem_type != USE_MALLOC && mem_type != USE_MMAP && - mem_type != USE_MPROTECT) { + switch (mem_type) { + case USE_MALLOC: + return malloc(entire_size) + range_before; + case USE_MMAP: + case USE_MPROTECT: + break; + default: ksft_print_msg("FAIL: Invalid allocate request\n"); return NULL; } - if (mem_type == USE_MALLOC) - return malloc(entire_size) + range_before; prot_flag = PROT_READ | PROT_WRITE; if (mem_type == USE_MMAP) @@ -269,18 +276,33 @@ int mte_switch_mode(int mte_option, unsigned long incl_mask) { unsigned long en = 0; - if (!(mte_option == MTE_SYNC_ERR || mte_option == MTE_ASYNC_ERR || - mte_option == MTE_NONE_ERR || incl_mask <= MTE_ALLOW_NON_ZERO_TAG)) { - ksft_print_msg("FAIL: Invalid mte config option\n"); + switch (mte_option) { + case MTE_NONE_ERR: + case MTE_SYNC_ERR: + case MTE_ASYNC_ERR: + break; + default: + ksft_print_msg("FAIL: Invalid MTE option %x\n", mte_option); + return -EINVAL; + } + + if (incl_mask & ~MT_INCLUDE_TAG_MASK) { + ksft_print_msg("FAIL: Invalid incl_mask %lx\n", incl_mask); return -EINVAL; } + en = PR_TAGGED_ADDR_ENABLE; - if (mte_option == MTE_SYNC_ERR) + switch (mte_option) { + case MTE_SYNC_ERR: en |= PR_MTE_TCF_SYNC; - else if (mte_option == MTE_ASYNC_ERR) + break; + case MTE_ASYNC_ERR: en |= PR_MTE_TCF_ASYNC; - else if (mte_option == MTE_NONE_ERR) + break; + case MTE_NONE_ERR: en |= PR_MTE_TCF_NONE; + break; + } en |= (incl_mask << PR_MTE_TAG_SHIFT); /* Enable address tagging ABI, mte error reporting mode and tag inclusion mask. */ diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.h b/tools/testing/selftests/arm64/mte/mte_common_util.h index 195a7d1879e6..2d3e71724e55 100644 --- a/tools/testing/selftests/arm64/mte/mte_common_util.h +++ b/tools/testing/selftests/arm64/mte/mte_common_util.h @@ -75,10 +75,21 @@ unsigned int mte_get_pstate_tco(void); /* Test framework static inline functions/macros */ static inline void evaluate_test(int err, const char *msg) { - if (err == KSFT_PASS) + switch (err) { + case KSFT_PASS: ksft_test_result_pass(msg); - else if (err == KSFT_FAIL) + break; + case KSFT_FAIL: ksft_test_result_fail(msg); + break; + case KSFT_SKIP: + ksft_test_result_skip(msg); + break; + default: + ksft_test_result_error("Unknown return code %d from %s", + err, msg); + break; + } } static inline int check_allocated_memory(void *ptr, size_t size, 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/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index c1742755abb9..e8d2b57f73ec 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -1,5 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only mangle_* fake_sigreturn_* +sme_* +ssve_* sve_* +za_* !*.[ch] diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile index ac4ad0005715..be7520a863b0 100644 --- a/tools/testing/selftests/arm64/signal/Makefile +++ b/tools/testing/selftests/arm64/signal/Makefile @@ -11,7 +11,6 @@ PROGS := $(patsubst %.c,%,$(SRCS)) TEST_GEN_PROGS := $(notdir $(PROGS)) # Get Kernel headers installed and use them. -KSFT_KHDR_INSTALL := 1 # Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list # to account for any OUTPUT target-dirs optionally provided by diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index ebe8694dbef0..0c645834ddc3 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -9,9 +9,7 @@ #include <ucontext.h> /* - * Using ARCH specific and sanitized Kernel headers installed by KSFT - * framework since we asked for it by setting flag KSFT_KHDR_INSTALL - * in our Makefile. + * Using ARCH specific and sanitized Kernel headers from the tree. */ #include <asm/ptrace.h> #include <asm/hwcap.h> @@ -34,11 +32,15 @@ enum { FSSBS_BIT, FSVE_BIT, + FSME_BIT, + FSME_FA64_BIT, FMAX_END }; #define FEAT_SSBS (1UL << FSSBS_BIT) #define FEAT_SVE (1UL << FSVE_BIT) +#define FEAT_SME (1UL << FSME_BIT) +#define FEAT_SME_FA64 (1UL << FSME_FA64_BIT) /* * A descriptor used to describe and configure a test case. @@ -53,6 +55,7 @@ struct tdescr { char *name; char *descr; unsigned long feats_required; + unsigned long feats_incompatible; /* bitmask of effectively supported feats: populated at run-time */ unsigned long feats_supported; bool initialized; diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 2f8c23af3b5e..308e229e58ab 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -27,6 +27,8 @@ static int sig_copyctx = SIGTRAP; static char const *const feats_names[FMAX_END] = { " SSBS ", " SVE ", + " SME ", + " FA64 ", }; #define MAX_FEATS_SZ 128 @@ -36,6 +38,8 @@ static inline char *feats_to_string(unsigned long feats) { size_t flen = MAX_FEATS_SZ - 1; + feats_string[0] = '\0'; + for (int i = 0; i < FMAX_END; i++) { if (feats & (1UL << i)) { size_t tlen = strlen(feats_names[i]); @@ -161,15 +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; } @@ -256,7 +309,7 @@ int test_init(struct tdescr *td) td->minsigstksz = MINSIGSTKSZ; fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz); - if (td->feats_required) { + if (td->feats_required || td->feats_incompatible) { td->feats_supported = 0; /* * Checking for CPU required features using both the @@ -266,16 +319,34 @@ int test_init(struct tdescr *td) td->feats_supported |= FEAT_SSBS; if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; + if (getauxval(AT_HWCAP2) & HWCAP2_SME) + td->feats_supported |= FEAT_SME; + if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64) + td->feats_supported |= FEAT_SME_FA64; if (feats_ok(td)) { - fprintf(stderr, - "Required Features: [%s] supported\n", - feats_to_string(td->feats_required & - td->feats_supported)); + if (td->feats_required & td->feats_supported) + fprintf(stderr, + "Required Features: [%s] supported\n", + feats_to_string(td->feats_required & + td->feats_supported)); + if (!(td->feats_incompatible & td->feats_supported)) + fprintf(stderr, + "Incompatible Features: [%s] absent\n", + feats_to_string(td->feats_incompatible)); } else { - fprintf(stderr, - "Required Features: [%s] NOT supported\n", - feats_to_string(td->feats_required & - ~td->feats_supported)); + if ((td->feats_required & td->feats_supported) != + td->feats_supported) + fprintf(stderr, + "Required Features: [%s] NOT supported\n", + feats_to_string(td->feats_required & + ~td->feats_supported)); + if (td->feats_incompatible & td->feats_supported) + fprintf(stderr, + "Incompatible Features: [%s] supported\n", + feats_to_string(td->feats_incompatible & + ~td->feats_supported)); + + td->result = KSFT_SKIP; return 0; } diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h index 6772b5c8d274..222093f51b67 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.h +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h @@ -18,6 +18,8 @@ void test_result(struct tdescr *td); static inline bool feats_ok(struct tdescr *td) { + if (td->feats_incompatible & td->feats_supported) + return false; return (td->feats_required & td->feats_supported) == td->feats_required; } @@ -54,7 +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; @@ -62,7 +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 new file mode 100644 index 000000000000..ebd5815b54bb --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Attempt to change the streaming SVE vector length in a signal + * handler, this is not supported and is expected to segfault. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +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 SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SVE_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 two VLs */ + if (nvls < 2) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static int fake_sigreturn_ssve_change_vl(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct sve_context *sve; + + /* Get a signal context with a SME ZA frame in it */ + if (!get_current_context(td, &sf.uc, sizeof(sf.uc))) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, SVE_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + if (head->size != sizeof(struct sve_context)) { + fprintf(stderr, "Register data present, aborting\n"); + return 1; + } + + sve = (struct sve_context *)head; + + /* No changes are supported; init left us at minimum VL so go to max */ + fprintf(stderr, "Attempting to change VL from %d to %d\n", + sve->vl, vls[0]); + sve->vl = vls[0]; + + fake_sigreturn(&sf, sizeof(sf), 0); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_SSVE_CHANGE", + .descr = "Attempt to change Streaming SVE VL", + .feats_required = FEAT_SME, + .sig_ok = SIGSEGV, + .timeout = 3, + .init = sme_get_vls, + .run = fake_sigreturn_ssve_change_vl, +}; 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 bb50b5adbf10..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 @@ -6,6 +6,7 @@ * supported and is expected to segfault. */ +#include <kselftest.h> #include <signal.h> #include <ucontext.h> #include <sys/prctl.h> @@ -40,6 +41,7 @@ static bool sve_get_vls(struct tdescr *td) /* We need at least two VLs */ if (nvls < 2) { fprintf(stderr, "Only %d VL supported\n", nvls); + td->result = KSFT_SKIP; return false; } @@ -54,7 +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_trap_no_sm.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c new file mode 100644 index 000000000000..f9d76ae32bba --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that using a streaming mode instruction without enabling it + * generates a SIGILL. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_no_sm_trigger(struct tdescr *td) +{ + /* SMSTART ZA ; ADDHA ZA0.S, P0/M, P0/M, Z0.S */ + asm volatile(".inst 0xd503457f ; .inst 0xc0900000"); + + return 0; +} + +int sme_trap_no_sm_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME trap without SM", + .descr = "Check that we get a SIGILL if we use streaming mode without enabling it", + .timeout = 3, + .feats_required = FEAT_SME, /* We need a SMSTART ZA */ + .sanity_disabled = true, + .trigger = sme_trap_no_sm_trigger, + .run = sme_trap_no_sm_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c new file mode 100644 index 000000000000..e469ae5348e3 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that using an instruction not supported in streaming mode + * traps when in streaming mode. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_non_streaming_trigger(struct tdescr *td) +{ + /* + * The framework will handle SIGILL so we need to exit SM to + * stop any other code triggering a further SIGILL down the + * line from using a streaming-illegal instruction. + */ + asm volatile(".inst 0xd503437f; /* SMSTART ZA */ \ + cnt v0.16b, v0.16b; \ + .inst 0xd503447f /* SMSTOP ZA */"); + + return 0; +} + +int sme_trap_non_streaming_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME SM trap unsupported instruction", + .descr = "Check that we get a SIGILL if we use an unsupported instruction in streaming mode", + .feats_required = FEAT_SME, + .feats_incompatible = FEAT_SME_FA64, + .timeout = 3, + .sanity_disabled = true, + .trigger = sme_trap_non_streaming_trigger, + .run = sme_trap_non_streaming_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c new file mode 100644 index 000000000000..3a7747af4715 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that accessing ZA without enabling it generates a SIGILL. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_za_trigger(struct tdescr *td) +{ + /* ZERO ZA */ + asm volatile(".inst 0xc00800ff"); + + return 0; +} + +int sme_trap_za_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME ZA trap", + .descr = "Check that we get a SIGILL if we access ZA without enabling", + .timeout = 3, + .sanity_disabled = true, + .trigger = sme_trap_za_trigger, + .run = sme_trap_za_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_vl.c b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c new file mode 100644 index 000000000000..75f387f2db81 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Check that the SME vector length reported in signal contexts is the + * expected one. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +unsigned int vl; + +static bool get_sme_vl(struct tdescr *td) +{ + int ret = prctl(PR_SME_GET_VL); + if (ret == -1) + return false; + + vl = ret; + + return true; +} + +static int sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct za_context *za; + + /* Get a signal context which should have a ZA frame in it */ + if (!get_current_context(td, &sf.uc, sizeof(sf.uc))) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, ZA_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No ZA context\n"); + return 1; + } + za = (struct za_context *)head; + + if (za->vl != vl) { + fprintf(stderr, "ZA sigframe VL %u, expected %u\n", + za->vl, vl); + return 1; + } else { + fprintf(stderr, "got expected VL %u\n", vl); + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "SME VL", + .descr = "Check that we get the right SME VL reported", + .feats_required = FEAT_SME, + .timeout = 3, + .init = get_sme_vl, + .run = sme_vl, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c new file mode 100644 index 000000000000..d0a178945b1a --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that the streaming SVE 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 * 64]; +} 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 SVE_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 void setup_ssve_regs(void) +{ + /* smstart sm; real data is TODO */ + asm volatile(".inst 0xd503437f" : : : ); +} + +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 sve_context *ssve; + int ret; + + fprintf(stderr, "Testing VL %d\n", vl); + + ret = prctl(PR_SME_SET_VL, vl); + if (ret != vl) { + fprintf(stderr, "Failed to set VL, got %d\n", ret); + return 1; + } + + /* + * Get a signal context which should have a SVE frame and registers + * in it. + */ + setup_ssve_regs(); + if (!get_current_context(td, &context.uc, sizeof(context))) + return 1; + + head = get_header(head, SVE_MAGIC, GET_BUF_RESV_SIZE(context), + &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + ssve = (struct sve_context *)head; + if (ssve->vl != vl) { + fprintf(stderr, "Got VL %d, expected %d\n", ssve->vl, vl); + return 1; + } + + /* The actual size validation is done in get_current_context() */ + fprintf(stderr, "Got expected size %u and VL %d\n", + head->size, ssve->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 = "Streaming SVE registers", + .descr = "Check that we get the right Streaming SVE registers reported", + /* + * We shouldn't require FA64 but things like memset() used in the + * helpers might use unsupported instructions so for now disable + * the test unless we've got the full instruction set. + */ + .feats_required = FEAT_SME | FEAT_SME_FA64, + .timeout = 3, + .init = sme_get_vls, + .run = sme_regs, +}; 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 8c2a57fc2f9c..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; } @@ -75,15 +79,44 @@ bool validate_sve_context(struct sve_context *sve, char **err) return true; } +bool validate_za_context(struct za_context *za, char **err) +{ + /* Size will be rounded up to a multiple of 16 bytes */ + size_t regs_size + = ((ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za->vl)) + 15) / 16) * 16; + + if (!za || !err) + return false; + + /* Either a bare za_context or a za_context followed by regs data */ + if ((za->head.size != sizeof(struct za_context)) && + (za->head.size != regs_size)) { + *err = "bad size for ZA context"; + return false; + } + + if (!sve_vl_valid(za->vl)) { + *err = "SME VL in ZA context invalid"; + + return false; + } + + return true; +} + 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; @@ -94,12 +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) @@ -107,7 +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)) @@ -118,7 +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; + new_flags |= ZA_CTX; break; case EXTRA_MAGIC: if (flags & EXTRA_CTX) @@ -126,7 +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: @@ -159,12 +211,18 @@ 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 (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 ad884c135314..040afded0b76 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.h +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h @@ -16,7 +16,8 @@ #define FPSIMD_CTX (1 << 0) #define SVE_CTX (1 << 1) -#define EXTRA_CTX (1 << 2) +#define ZA_CTX (1 << 2) +#define EXTRA_CTX (1 << 3) #define KSFT_BAD_MAGIC 0xdeadbeef @@ -29,6 +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) @@ -78,8 +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 new file mode 100644 index 000000000000..ea45acb115d5 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c @@ -0,0 +1,134 @@ +// 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 void setup_za_regs(void) +{ + /* smstart za; real data is TODO */ + 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 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. + */ + setup_za_regs(); + 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_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; +} + +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 register", + .descr = "Check that we get the right ZA registers reported", + .feats_required = FEAT_SME, + .timeout = 3, + .init = sme_get_vls, + .run = sme_regs, +}; |