diff options
Diffstat (limited to 'tools/testing')
75 files changed, 3839 insertions, 864 deletions
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 5a931456e718..ac35c61f65f5 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -16,7 +16,7 @@ assert sys.version_info >= (3, 7), "Python version is too old" from collections import namedtuple from enum import Enum, auto -from typing import Iterable +from typing import Iterable, Sequence import kunit_config import kunit_json @@ -186,6 +186,26 @@ def run_tests(linux: kunit_kernel.LinuxSourceTree, exec_result.elapsed_time)) return parse_result +# Problem: +# $ kunit.py run --json +# works as one would expect and prints the parsed test results as JSON. +# $ kunit.py run --json suite_name +# would *not* pass suite_name as the filter_glob and print as json. +# argparse will consider it to be another way of writing +# $ kunit.py run --json=suite_name +# i.e. it would run all tests, and dump the json to a `suite_name` file. +# So we hackily automatically rewrite --json => --json=stdout +pseudo_bool_flag_defaults = { + '--json': 'stdout', + '--raw_output': 'kunit', +} +def massage_argv(argv: Sequence[str]) -> Sequence[str]: + def massage_arg(arg: str) -> str: + if arg not in pseudo_bool_flag_defaults: + return arg + return f'{arg}={pseudo_bool_flag_defaults[arg]}' + return list(map(massage_arg, argv)) + def add_common_opts(parser) -> None: parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' @@ -303,7 +323,7 @@ def main(argv, linux=None): help='Specifies the file to read results from.', type=str, nargs='?', metavar='input_file') - cli_args = parser.parse_args(argv) + cli_args = parser.parse_args(massage_argv(argv)) if get_kernel_root_path(): os.chdir(get_kernel_root_path()) diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 619c4554cbff..1edcc8373b4e 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -408,6 +408,14 @@ class KUnitMainTest(unittest.TestCase): self.assertNotEqual(call, mock.call(StrContains('Testing complete.'))) self.assertNotEqual(call, mock.call(StrContains(' 0 tests run'))) + def test_run_raw_output_does_not_take_positional_args(self): + # --raw_output is a string flag, but we don't want it to consume + # any positional arguments, only ones after an '=' + self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) + kunit.main(['run', '--raw_output', 'filter_glob'], self.linux_source_mock) + self.linux_source_mock.run_kernel.assert_called_once_with( + args=None, build_dir='.kunit', filter_glob='filter_glob', timeout=300) + def test_exec_timeout(self): timeout = 3453 kunit.main(['exec', '--timeout', str(timeout)], self.linux_source_mock) diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index f2abdd6ba12e..ba1488c7c315 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -9,12 +9,12 @@ TEST_PROGS_EXTENDED := fpsimd-test fpsimd-stress \ all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED) -fpsimd-test: fpsimd-test.o +fpsimd-test: fpsimd-test.o asm-utils.o $(CC) -nostdlib $^ -o $@ rdvl-sve: rdvl-sve.o rdvl.o -sve-ptrace: sve-ptrace.o sve-ptrace-asm.o +sve-ptrace: sve-ptrace.o sve-probe-vls: sve-probe-vls.o rdvl.o -sve-test: sve-test.o +sve-test: sve-test.o asm-utils.o $(CC) -nostdlib $^ -o $@ vec-syscfg: vec-syscfg.o rdvl.o vlset: vlset.o diff --git a/tools/testing/selftests/arm64/fp/TODO b/tools/testing/selftests/arm64/fp/TODO index b6b7ebfcf362..44004e53da33 100644 --- a/tools/testing/selftests/arm64/fp/TODO +++ b/tools/testing/selftests/arm64/fp/TODO @@ -1,4 +1,7 @@ - Test unsupported values in the ABIs. -- More coverage for ptrace (eg, vector length conversions). -- Coverage for signals. -- Test PR_SVE_VL_INHERITY after a double fork. +- More coverage for ptrace: + - Get/set of FFR. + - Ensure ptraced processes actually see the register state visible through + the ptrace interface. + - Big endian. +- Test PR_SVE_VL_INHERIT after a double fork. diff --git a/tools/testing/selftests/arm64/fp/asm-utils.S b/tools/testing/selftests/arm64/fp/asm-utils.S new file mode 100644 index 000000000000..4b9728efc18d --- /dev/null +++ b/tools/testing/selftests/arm64/fp/asm-utils.S @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2015-2021 ARM Limited. +// Original author: Dave Martin <Dave.Martin@arm.com> +// +// Utility functions for assembly code. + +#include <asm/unistd.h> +#include "assembler.h" + +// Print a single character x0 to stdout +// Clobbers x0-x2,x8 +function putc + str x0, [sp, #-16]! + + mov x0, #1 // STDOUT_FILENO + mov x1, sp + mov x2, #1 + mov x8, #__NR_write + svc #0 + + add sp, sp, #16 + ret +endfunction +.globl putc + +// Print a NUL-terminated string starting at address x0 to stdout +// Clobbers x0-x3,x8 +function puts + mov x1, x0 + + mov x2, #0 +0: ldrb w3, [x0], #1 + cbz w3, 1f + add x2, x2, #1 + b 0b + +1: mov w0, #1 // STDOUT_FILENO + mov x8, #__NR_write + svc #0 + + ret +endfunction +.globl puts + +// Print an unsigned decimal number x0 to stdout +// Clobbers x0-x4,x8 +function putdec + mov x1, sp + str x30, [sp, #-32]! // Result can't be > 20 digits + + mov x2, #0 + strb w2, [x1, #-1]! // Write the NUL terminator + + mov x2, #10 +0: udiv x3, x0, x2 // div-mod loop to generate the digits + msub x0, x3, x2, x0 + add w0, w0, #'0' + strb w0, [x1, #-1]! + mov x0, x3 + cbnz x3, 0b + + ldrb w0, [x1] + cbnz w0, 1f + mov w0, #'0' // Print "0" for 0, not "" + strb w0, [x1, #-1]! + +1: mov x0, x1 + bl puts + + ldr x30, [sp], #32 + ret +endfunction +.globl putdec + +// Print an unsigned decimal number x0 to stdout, followed by a newline +// Clobbers x0-x5,x8 +function putdecn + mov x5, x30 + + bl putdec + mov x0, #'\n' + bl putc + + ret x5 +endfunction +.globl putdecn + +// Clobbers x0-x3,x8 +function puthexb + str x30, [sp, #-0x10]! + + mov w3, w0 + lsr w0, w0, #4 + bl puthexnibble + mov w0, w3 + + ldr x30, [sp], #0x10 + // fall through to puthexnibble +endfunction +.globl puthexb + +// Clobbers x0-x2,x8 +function puthexnibble + and w0, w0, #0xf + cmp w0, #10 + blo 1f + add w0, w0, #'a' - ('9' + 1) +1: add w0, w0, #'0' + b putc +endfunction +.globl puthexnibble + +// x0=data in, x1=size in, clobbers x0-x5,x8 +function dumphex + str x30, [sp, #-0x10]! + + mov x4, x0 + mov x5, x1 + +0: subs x5, x5, #1 + b.lo 1f + ldrb w0, [x4], #1 + bl puthexb + b 0b + +1: ldr x30, [sp], #0x10 + ret +endfunction +.globl dumphex + + // Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. +// Clobbers x0-x3 +function memcpy + cmp x2, #0 + b.eq 1f +0: ldrb w3, [x1], #1 + strb w3, [x0], #1 + subs x2, x2, #1 + b.ne 0b +1: ret +endfunction +.globl memcpy + +// Fill x1 bytes starting at x0 with 0xae (for canary purposes) +// Clobbers x1, x2. +function memfill_ae + mov w2, #0xae + b memfill +endfunction +.globl memfill_ae + +// Fill x1 bytes starting at x0 with 0. +// Clobbers x1, x2. +function memclr + mov w2, #0 +endfunction +.globl memclr + // fall through to memfill + +// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 +// Clobbers x1 +function memfill + cmp x1, #0 + b.eq 1f + +0: strb w2, [x0], #1 + subs x1, x1, #1 + b.ne 0b + +1: ret +endfunction +.globl memfill diff --git a/tools/testing/selftests/arm64/fp/assembler.h b/tools/testing/selftests/arm64/fp/assembler.h index 8944f2189206..90bd433d2665 100644 --- a/tools/testing/selftests/arm64/fp/assembler.h +++ b/tools/testing/selftests/arm64/fp/assembler.h @@ -54,4 +54,15 @@ endfunction .purgem \name\()_entry .endm +// Utility macro to print a literal string +// Clobbers x0-x4,x8 +.macro puts string + .pushsection .rodata.str1.1, "aMS", 1 +.L__puts_literal\@: .string "\string" + .popsection + + ldr x0, =.L__puts_literal\@ + bl puts +.endm + #endif /* ! ASSEMBLER_H */ diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S index 0dbd594c2747..e21e8ea52c7e 100644 --- a/tools/testing/selftests/arm64/fp/fpsimd-test.S +++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S @@ -33,131 +33,6 @@ define_accessor setv, NVR, _vldr define_accessor getv, NVR, _vstr -// Print a single character x0 to stdout -// Clobbers x0-x2,x8 -function putc - str x0, [sp, #-16]! - - mov x0, #1 // STDOUT_FILENO - mov x1, sp - mov x2, #1 - mov x8, #__NR_write - svc #0 - - add sp, sp, #16 - ret -endfunction - -// Print a NUL-terminated string starting at address x0 to stdout -// Clobbers x0-x3,x8 -function puts - mov x1, x0 - - mov x2, #0 -0: ldrb w3, [x0], #1 - cbz w3, 1f - add x2, x2, #1 - b 0b - -1: mov w0, #1 // STDOUT_FILENO - mov x8, #__NR_write - svc #0 - - ret -endfunction - -// Utility macro to print a literal string -// Clobbers x0-x4,x8 -.macro puts string - .pushsection .rodata.str1.1, "aMS", 1 -.L__puts_literal\@: .string "\string" - .popsection - - ldr x0, =.L__puts_literal\@ - bl puts -.endm - -// Print an unsigned decimal number x0 to stdout -// Clobbers x0-x4,x8 -function putdec - mov x1, sp - str x30, [sp, #-32]! // Result can't be > 20 digits - - mov x2, #0 - strb w2, [x1, #-1]! // Write the NUL terminator - - mov x2, #10 -0: udiv x3, x0, x2 // div-mod loop to generate the digits - msub x0, x3, x2, x0 - add w0, w0, #'0' - strb w0, [x1, #-1]! - mov x0, x3 - cbnz x3, 0b - - ldrb w0, [x1] - cbnz w0, 1f - mov w0, #'0' // Print "0" for 0, not "" - strb w0, [x1, #-1]! - -1: mov x0, x1 - bl puts - - ldr x30, [sp], #32 - ret -endfunction - -// Print an unsigned decimal number x0 to stdout, followed by a newline -// Clobbers x0-x5,x8 -function putdecn - mov x5, x30 - - bl putdec - mov x0, #'\n' - bl putc - - ret x5 -endfunction - - -// Clobbers x0-x3,x8 -function puthexb - str x30, [sp, #-0x10]! - - mov w3, w0 - lsr w0, w0, #4 - bl puthexnibble - mov w0, w3 - - ldr x30, [sp], #0x10 - // fall through to puthexnibble -endfunction -// Clobbers x0-x2,x8 -function puthexnibble - and w0, w0, #0xf - cmp w0, #10 - blo 1f - add w0, w0, #'a' - ('9' + 1) -1: add w0, w0, #'0' - b putc -endfunction - -// x0=data in, x1=size in, clobbers x0-x5,x8 -function dumphex - str x30, [sp, #-0x10]! - - mov x4, x0 - mov x5, x1 - -0: subs x5, x5, #1 - b.lo 1f - ldrb w0, [x4], #1 - bl puthexb - b 0b - -1: ldr x30, [sp], #0x10 - ret -endfunction - // Declare some storate space to shadow the SVE register contents: .pushsection .text .data @@ -168,18 +43,6 @@ 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 SVE registers // x0: pid (16 bits) // x1: register number (6 bits) @@ -227,33 +90,6 @@ function setup_vreg ret x4 endfunction -// Fill x1 bytes starting at x0 with 0xae (for canary purposes) -// Clobbers x1, x2. -function memfill_ae - mov w2, #0xae - b memfill -endfunction - -// Fill x1 bytes starting at x0 with 0. -// Clobbers x1, x2. -function memclr - mov w2, #0 -endfunction - // fall through to memfill - -// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 -// Clobbers x1 -function memfill - cmp x1, #0 - b.eq 1f - -0: strb w2, [x0], #1 - subs x1, x1, #1 - b.ne 0b - -1: ret -endfunction - // 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. diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace-asm.S b/tools/testing/selftests/arm64/fp/sve-ptrace-asm.S deleted file mode 100644 index 3e81f9fab574..000000000000 --- a/tools/testing/selftests/arm64/fp/sve-ptrace-asm.S +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -// Copyright (C) 2015-2019 ARM Limited. -// Original author: Dave Martin <Dave.Martin@arm.com> -#include <asm/unistd.h> - -.arch_extension sve - -.globl sve_store_patterns - -sve_store_patterns: - mov x1, x0 - - index z0.b, #0, #1 - str q0, [x1] - - mov w8, #__NR_getpid - svc #0 - str q0, [x1, #0x10] - - mov z1.d, z0.d - str q0, [x1, #0x20] - - mov w8, #__NR_getpid - svc #0 - str q0, [x1, #0x30] - - mov z1.d, z0.d - str q0, [x1, #0x40] - - ret - -.size sve_store_patterns, . - sve_store_patterns -.type sve_store_patterns, @function diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index 612d3899614a..c4417bc48d4f 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -1,15 +1,17 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2015-2020 ARM Limited. + * Copyright (C) 2015-2021 ARM Limited. * Original author: Dave Martin <Dave.Martin@arm.com> */ #include <errno.h> +#include <stdbool.h> #include <stddef.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <unistd.h> #include <sys/auxv.h> +#include <sys/prctl.h> #include <sys/ptrace.h> #include <sys/types.h> #include <sys/uio.h> @@ -19,40 +21,22 @@ #include "../../kselftest.h" +#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3) +#define FPSIMD_TESTS 5 + +#define EXPECTED_TESTS (VL_TESTS + FPSIMD_TESTS) + /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ #ifndef NT_ARM_SVE #define NT_ARM_SVE 0x405 #endif -/* Number of registers filled in by sve_store_patterns */ -#define NR_VREGS 5 - -void sve_store_patterns(__uint128_t v[NR_VREGS]); - -static void dump(const void *buf, size_t size) -{ - size_t i; - const unsigned char *p = buf; - - for (i = 0; i < size; ++i) - printf(" %.2x", *p++); -} - -static int check_vregs(const __uint128_t vregs[NR_VREGS]) +static void fill_buf(char *buf, size_t size) { int i; - int ok = 1; - - for (i = 0; i < NR_VREGS; ++i) { - printf("# v[%d]:", i); - dump(&vregs[i], sizeof vregs[i]); - putchar('\n'); - - if (vregs[i] != vregs[0]) - ok = 0; - } - return ok; + for (i = 0; i < size; i++) + buf[i] = random(); } static int do_child(void) @@ -66,6 +50,15 @@ static int do_child(void) return EXIT_SUCCESS; } +static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd) +{ + struct iovec iov; + + iov.iov_base = fpsimd; + iov.iov_len = sizeof(*fpsimd); + return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov); +} + static struct user_sve_header *get_sve(pid_t pid, void **buf, size_t *size) { struct user_sve_header *sve; @@ -112,25 +105,335 @@ static int set_sve(pid_t pid, const struct user_sve_header *sve) return ptrace(PTRACE_SETREGSET, pid, NT_ARM_SVE, &iov); } -static void dump_sve_regs(const struct user_sve_header *sve, unsigned int num, - unsigned int vlmax) +/* Validate setting and getting the inherit flag */ +static void ptrace_set_get_inherit(pid_t child) +{ + struct user_sve_header sve; + struct user_sve_header *new_sve = NULL; + size_t new_sve_size = 0; + int ret; + + /* First set the flag */ + memset(&sve, 0, sizeof(sve)); + sve.size = sizeof(sve); + sve.vl = sve_vl_from_vq(SVE_VQ_MIN); + sve.flags = SVE_PT_VL_INHERIT; + ret = set_sve(child, &sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set SVE_PT_VL_INHERIT\n"); + return; + } + + /* + * Read back the new register state and verify that we have + * set the flags we expected. + */ + if (!get_sve(child, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read SVE flags\n"); + return; + } + + ksft_test_result(new_sve->flags & SVE_PT_VL_INHERIT, + "SVE_PT_VL_INHERIT set\n"); + + /* Now clear */ + sve.flags &= ~SVE_PT_VL_INHERIT; + ret = set_sve(child, &sve); + if (ret != 0) { + ksft_test_result_fail("Failed to clear SVE_PT_VL_INHERIT\n"); + return; + } + + if (!get_sve(child, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read SVE flags\n"); + return; + } + + ksft_test_result(!(new_sve->flags & SVE_PT_VL_INHERIT), + "SVE_PT_VL_INHERIT cleared\n"); + + free(new_sve); +} + +/* 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_sve_header sve; + struct user_sve_header *new_sve = NULL; + size_t new_sve_size = 0; + int ret, prctl_vl; + + *supported = false; + + /* Check if the VL is supported in this process */ + prctl_vl = prctl(PR_SVE_SET_VL, vl); + if (prctl_vl == -1) + ksft_exit_fail_msg("prctl(PR_SVE_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(&sve, 0, sizeof(sve)); + sve.size = sizeof(sve); + sve.vl = vl; + ret = set_sve(child, &sve); + 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_sve(child, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read VL %u\n", vl); + return; + } + + ksft_test_result(new_sve->vl = prctl_vl, "Set VL %u\n", vl); + + free(new_sve); +} + +static void check_u32(unsigned int vl, const char *reg, + uint32_t *in, uint32_t *out, int *errors) +{ + if (*in != *out) { + printf("# VL %d %s wrote %x read %x\n", + vl, reg, *in, *out); + (*errors)++; + } +} + +/* Access the FPSIMD registers via the SVE regset */ +static void ptrace_sve_fpsimd(pid_t child) { - unsigned int vq; - unsigned int i; + void *svebuf = NULL; + size_t svebufsz = 0; + struct user_sve_header *sve; + struct user_fpsimd_state *fpsimd, new_fpsimd; + unsigned int i, j; + unsigned char *p; + + /* New process should start with FPSIMD registers only */ + sve = get_sve(child, &svebuf, &svebufsz); + if (!sve) { + ksft_test_result_fail("get_sve: %s\n", strerror(errno)); + + return; + } else { + ksft_test_result_pass("get_sve(FPSIMD)\n"); + } - if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_SVE) - ksft_exit_fail_msg("Dumping non-SVE register\n"); + ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, + "Set FPSIMD registers\n"); + if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) + goto out; - if (vlmax > sve->vl) - vlmax = sve->vl; + /* Try to set a known FPSIMD state via PT_REGS_SVE */ + fpsimd = (struct user_fpsimd_state *)((char *)sve + + SVE_PT_FPSIMD_OFFSET); + for (i = 0; i < 32; ++i) { + p = (unsigned char *)&fpsimd->vregs[i]; - vq = sve_vq_from_vl(sve->vl); - for (i = 0; i < num; ++i) { - printf("# z%u:", i); - dump((const char *)sve + SVE_PT_SVE_ZREG_OFFSET(vq, i), - vlmax); - printf("%s\n", vlmax == sve->vl ? "" : " ..."); + for (j = 0; j < sizeof(fpsimd->vregs[i]); ++j) + p[j] = j; } + + if (set_sve(child, sve)) { + ksft_test_result_fail("set_sve(FPSIMD): %s\n", + strerror(errno)); + + goto out; + } + + /* Verify via the FPSIMD regset */ + if (get_fpsimd(child, &new_fpsimd)) { + ksft_test_result_fail("get_fpsimd(): %s\n", + strerror(errno)); + goto out; + } + if (memcmp(fpsimd, &new_fpsimd, sizeof(*fpsimd)) == 0) + ksft_test_result_pass("get_fpsimd() gave same state\n"); + else + ksft_test_result_fail("get_fpsimd() gave different state\n"); + +out: + free(svebuf); +} + +/* Validate attempting to set SVE data and read SVE data */ +static void ptrace_set_sve_get_sve_data(pid_t child, unsigned int vl) +{ + void *write_buf; + void *read_buf = NULL; + struct user_sve_header *write_sve; + struct user_sve_header *read_sve; + size_t read_sve_size = 0; + unsigned int vq = sve_vq_from_vl(vl); + int ret, i; + size_t data_size; + int errors = 0; + + data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + write_buf = malloc(data_size); + if (!write_buf) { + ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n", + data_size, vl); + return; + } + write_sve = write_buf; + + /* Set up some data and write it out */ + memset(write_sve, 0, data_size); + write_sve->size = data_size; + write_sve->vl = vl; + write_sve->flags = SVE_PT_REGS_SVE; + + for (i = 0; i < __SVE_NUM_ZREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)); + + for (i = 0; i < __SVE_NUM_PREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + SVE_PT_SVE_PREG_SIZE(vq)); + + fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE); + fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE); + + /* TODO: Generate a valid FFR pattern */ + + ret = set_sve(child, write_sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u data\n", vl); + goto out; + } + + /* Read the data back */ + if (!get_sve(child, (void **)&read_buf, &read_sve_size)) { + ksft_test_result_fail("Failed to read VL %u data\n", vl); + goto out; + } + read_sve = read_buf; + + /* We might read more data if there's extensions we don't know */ + if (read_sve->size < write_sve->size) { + ksft_test_result_fail("Wrote %d bytes, only read %d\n", + write_sve->size, read_sve->size); + goto out_read; + } + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + if (memcmp(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)) != 0) { + printf("# Mismatch in %u Z%d\n", vl, i); + errors++; + } + } + + for (i = 0; i < __SVE_NUM_PREGS; i++) { + if (memcmp(write_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + read_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + SVE_PT_SVE_PREG_SIZE(vq)) != 0) { + printf("# Mismatch in %u P%d\n", vl, i); + errors++; + } + } + + check_u32(vl, "FPSR", write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), + read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors); + check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), + read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors); + + ksft_test_result(errors == 0, "Set and get SVE data for VL %u\n", vl); + +out_read: + free(read_buf); +out: + free(write_buf); +} + +/* Validate attempting to set SVE data and read SVE data */ +static void ptrace_set_sve_get_fpsimd_data(pid_t child, unsigned int vl) +{ + void *write_buf; + struct user_sve_header *write_sve; + unsigned int vq = sve_vq_from_vl(vl); + struct user_fpsimd_state fpsimd_state; + int ret, i; + size_t data_size; + int errors = 0; + + if (__BYTE_ORDER == __BIG_ENDIAN) { + ksft_test_result_skip("Big endian not supported\n"); + return; + } + + data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + write_buf = malloc(data_size); + if (!write_buf) { + ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n", + data_size, vl); + return; + } + write_sve = write_buf; + + /* Set up some data and write it out */ + memset(write_sve, 0, data_size); + write_sve->size = data_size; + write_sve->vl = vl; + write_sve->flags = SVE_PT_REGS_SVE; + + for (i = 0; i < __SVE_NUM_ZREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)); + + fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE); + fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE); + + ret = set_sve(child, write_sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u data\n", vl); + goto out; + } + + /* Read the data back */ + if (get_fpsimd(child, &fpsimd_state)) { + ksft_test_result_fail("Failed to read VL %u FPSIMD data\n", + vl); + goto out; + } + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + __uint128_t tmp = 0; + + /* + * Z regs are stored endianness invariant, this won't + * work for big endian + */ + memcpy(&tmp, write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + sizeof(tmp)); + + if (tmp != fpsimd_state.vregs[i]) { + printf("# Mismatch in FPSIMD for VL %u Z%d\n", vl, i); + errors++; + } + } + + check_u32(vl, "FPSR", write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), + &fpsimd_state.fpsr, &errors); + check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), + &fpsimd_state.fpcr, &errors); + + ksft_test_result(errors == 0, "Set and get FPSIMD data for VL %u\n", + vl); + +out: + free(write_buf); } static int do_parent(pid_t child) @@ -139,13 +442,8 @@ static int do_parent(pid_t child) pid_t pid; int status; siginfo_t si; - void *svebuf = NULL, *newsvebuf; - size_t svebufsz = 0, newsvebufsz; - struct user_sve_header *sve, *new_sve; - struct user_fpsimd_state *fpsimd; - unsigned int i, j; - unsigned char *p; - unsigned int vq; + unsigned int vq, vl; + bool vl_supported; /* Attach to the child */ while (1) { @@ -167,8 +465,6 @@ static int do_parent(pid_t child) if (WIFEXITED(status) || WIFSIGNALED(status)) ksft_exit_fail_msg("Child died unexpectedly\n"); - ksft_test_result(WIFSTOPPED(status), "WIFSTOPPED(%d)\n", - status); if (!WIFSTOPPED(status)) goto error; @@ -203,98 +499,27 @@ static int do_parent(pid_t child) } } - sve = get_sve(pid, &svebuf, &svebufsz); - if (!sve) { - int e = errno; + /* FPSIMD via SVE regset */ + ptrace_sve_fpsimd(child); - ksft_test_result_fail("get_sve: %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; + /* prctl() flags */ + ptrace_set_get_inherit(child); - goto error; - } else { - ksft_test_result_pass("get_sve\n"); - } - - ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, - "FPSIMD registers\n"); - if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) - goto error; - - fpsimd = (struct user_fpsimd_state *)((char *)sve + - SVE_PT_FPSIMD_OFFSET); - for (i = 0; i < 32; ++i) { - p = (unsigned char *)&fpsimd->vregs[i]; - - for (j = 0; j < sizeof fpsimd->vregs[i]; ++j) - p[j] = j; - } - - if (set_sve(pid, sve)) { - int e = errno; - - ksft_test_result_fail("set_sve(FPSIMD): %s\n", - strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } + /* Step through every possible VQ */ + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + vl = sve_vl_from_vq(vq); - vq = sve_vq_from_vl(sve->vl); + /* First, try to set this vector length */ + ptrace_set_get_vl(child, vl, &vl_supported); - newsvebufsz = SVE_PT_SVE_ZREG_OFFSET(vq, 1); - new_sve = newsvebuf = malloc(newsvebufsz); - if (!new_sve) { - errno = ENOMEM; - perror(NULL); - goto error; - } - - *new_sve = *sve; - new_sve->flags &= ~SVE_PT_REGS_MASK; - new_sve->flags |= SVE_PT_REGS_SVE; - memset((char *)new_sve + SVE_PT_SVE_ZREG_OFFSET(vq, 0), - 0, SVE_PT_SVE_ZREG_SIZE(vq)); - new_sve->size = SVE_PT_SVE_ZREG_OFFSET(vq, 1); - if (set_sve(pid, new_sve)) { - int e = errno; - - ksft_test_result_fail("set_sve(ZREG): %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } - - new_sve = get_sve(pid, &newsvebuf, &newsvebufsz); - if (!new_sve) { - int e = errno; - - ksft_test_result_fail("get_sve(ZREG): %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } - - ksft_test_result((new_sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE, - "SVE registers\n"); - if ((new_sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_SVE) - goto error; - - dump_sve_regs(new_sve, 3, sizeof fpsimd->vregs[0]); - - p = (unsigned char *)new_sve + SVE_PT_SVE_ZREG_OFFSET(vq, 1); - for (i = 0; i < sizeof fpsimd->vregs[0]; ++i) { - unsigned char expected = i; - - if (__BYTE_ORDER == __BIG_ENDIAN) - expected = sizeof fpsimd->vregs[0] - 1 - expected; - - ksft_test_result(p[i] == expected, "p[%d] == expected\n", i); - if (p[i] != expected) - goto error; + /* If the VL is supported validate data set/get */ + if (vl_supported) { + ptrace_set_sve_get_sve_data(child, vl); + ptrace_set_sve_get_fpsimd_data(child, vl); + } else { + ksft_test_result_skip("set SVE get SVE for VL %d\n", vl); + ksft_test_result_skip("set SVE get FPSIMD for VL %d\n", vl); + } } ret = EXIT_SUCCESS; @@ -309,20 +534,16 @@ disappeared: int main(void) { int ret = EXIT_SUCCESS; - __uint128_t v[NR_VREGS]; pid_t child; + srandom(getpid()); + ksft_print_header(); - ksft_set_plan(20); + ksft_set_plan(EXPECTED_TESTS); if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) ksft_exit_skip("SVE not available\n"); - sve_store_patterns(v); - - if (!check_vregs(v)) - ksft_exit_fail_msg("Initial check_vregs() failed\n"); - child = fork(); if (!child) return do_child(); diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index e3e08d9c7020..f5b1b48ffff2 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -46,130 +46,6 @@ define_accessor getz, NZR, _sve_str_v define_accessor setp, NPR, _sve_ldr_p define_accessor getp, NPR, _sve_str_p -// Print a single character x0 to stdout -// Clobbers x0-x2,x8 -function putc - str x0, [sp, #-16]! - - mov x0, #1 // STDOUT_FILENO - mov x1, sp - mov x2, #1 - mov x8, #__NR_write - svc #0 - - add sp, sp, #16 - ret -endfunction - -// Print a NUL-terminated string starting at address x0 to stdout -// Clobbers x0-x3,x8 -function puts - mov x1, x0 - - mov x2, #0 -0: ldrb w3, [x0], #1 - cbz w3, 1f - add x2, x2, #1 - b 0b - -1: mov w0, #1 // STDOUT_FILENO - mov x8, #__NR_write - svc #0 - - ret -endfunction - -// Utility macro to print a literal string -// Clobbers x0-x4,x8 -.macro puts string - .pushsection .rodata.str1.1, "aMS", 1 -.L__puts_literal\@: .string "\string" - .popsection - - ldr x0, =.L__puts_literal\@ - bl puts -.endm - -// Print an unsigned decimal number x0 to stdout -// Clobbers x0-x4,x8 -function putdec - mov x1, sp - str x30, [sp, #-32]! // Result can't be > 20 digits - - mov x2, #0 - strb w2, [x1, #-1]! // Write the NUL terminator - - mov x2, #10 -0: udiv x3, x0, x2 // div-mod loop to generate the digits - msub x0, x3, x2, x0 - add w0, w0, #'0' - strb w0, [x1, #-1]! - mov x0, x3 - cbnz x3, 0b - - ldrb w0, [x1] - cbnz w0, 1f - mov w0, #'0' // Print "0" for 0, not "" - strb w0, [x1, #-1]! - -1: mov x0, x1 - bl puts - - ldr x30, [sp], #32 - ret -endfunction - -// Print an unsigned decimal number x0 to stdout, followed by a newline -// Clobbers x0-x5,x8 -function putdecn - mov x5, x30 - - bl putdec - mov x0, #'\n' - bl putc - - ret x5 -endfunction - -// Clobbers x0-x3,x8 -function puthexb - str x30, [sp, #-0x10]! - - mov w3, w0 - lsr w0, w0, #4 - bl puthexnibble - mov w0, w3 - - ldr x30, [sp], #0x10 - // fall through to puthexnibble -endfunction -// Clobbers x0-x2,x8 -function puthexnibble - and w0, w0, #0xf - cmp w0, #10 - blo 1f - add w0, w0, #'a' - ('9' + 1) -1: add w0, w0, #'0' - b putc -endfunction - -// x0=data in, x1=size in, clobbers x0-x5,x8 -function dumphex - str x30, [sp, #-0x10]! - - mov x4, x0 - mov x5, x1 - -0: subs x5, x5, #1 - b.lo 1f - ldrb w0, [x4], #1 - bl puthexb - b 0b - -1: ldr x30, [sp], #0x10 - ret -endfunction - // Declare some storate space to shadow the SVE register contents: .pushsection .text .data @@ -184,18 +60,6 @@ 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 SVE registers // x0: pid (16 bits) // x1: register number (6 bits) @@ -316,33 +180,6 @@ function setup_ffr ret x4 endfunction -// Fill x1 bytes starting at x0 with 0xae (for canary purposes) -// Clobbers x1, x2. -function memfill_ae - mov w2, #0xae - b memfill -endfunction - -// Fill x1 bytes starting at x0 with 0. -// Clobbers x1, x2. -function memclr - mov w2, #0 -endfunction - // fall through to memfill - -// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 -// Clobbers x1 -function memfill - cmp x1, #0 - b.eq 1f - -0: strb w2, [x0], #1 - subs x1, x1, #1 - b.ne 0b - -1: ret -endfunction - // 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. diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c index c02071dcb563..272b888e018e 100644 --- a/tools/testing/selftests/arm64/fp/vec-syscfg.c +++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c @@ -109,7 +109,7 @@ static int get_child_rdvl(struct vec_data *data) /* exec() a new binary which puts the VL on stdout */ ret = execl(data->rdvl_binary, data->rdvl_binary, NULL); - fprintf(stderr, "execl(%s) failed: %d\n", + fprintf(stderr, "execl(%s) failed: %d (%s)\n", data->rdvl_binary, errno, strerror(errno)); exit(EXIT_FAILURE); @@ -180,7 +180,6 @@ static int file_read_integer(const char *name, int *val) static int file_write_integer(const char *name, int val) { FILE *f; - int ret; f = fopen(name, "w"); if (!f) { @@ -192,11 +191,6 @@ static int file_write_integer(const char *name, int val) fprintf(f, "%d", val); fclose(f); - if (ret < 0) { - ksft_test_result_fail("Error writing %d to %s\n", - val, name); - return -1; - } return 0; } @@ -335,12 +329,9 @@ static void prctl_set_same(struct vec_data *data) return; } - if (cur_vl != data->rdvl()) - ksft_test_result_pass("%s current VL is %d\n", - data->name, ret); - else - ksft_test_result_fail("%s prctl() VL %d but RDVL is %d\n", - data->name, ret, data->rdvl()); + ksft_test_result(cur_vl == data->rdvl(), + "%s set VL %d and have VL %d\n", + data->name, cur_vl, data->rdvl()); } /* Can we set a new VL for this process? */ @@ -549,6 +540,82 @@ static void prctl_set_onexec(struct vec_data *data) file_write_integer(data->default_vl_file, data->default_vl); } +/* For each VQ verify that setting via prctl() does the right thing */ +static void prctl_set_all_vqs(struct vec_data *data) +{ + int ret, vq, vl, new_vl; + int errors = 0; + + if (!data->min_vl || !data->max_vl) { + ksft_test_result_skip("%s Failed to enumerate VLs, not testing VL setting\n", + data->name); + return; + } + + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + vl = sve_vl_from_vq(vq); + + /* Attempt to set the VL */ + ret = prctl(data->prctl_set, vl); + if (ret < 0) { + errors++; + ksft_print_msg("%s prctl set failed for %d: %d (%s)\n", + data->name, vl, + errno, strerror(errno)); + continue; + } + + new_vl = ret & PR_SVE_VL_LEN_MASK; + + /* Check that we actually have the reported new VL */ + if (data->rdvl() != new_vl) { + ksft_print_msg("Set %s VL %d but RDVL reports %d\n", + data->name, new_vl, data->rdvl()); + errors++; + } + + /* Was that the VL we asked for? */ + if (new_vl == vl) + continue; + + /* Should round up to the minimum VL if below it */ + if (vl < data->min_vl) { + if (new_vl != data->min_vl) { + ksft_print_msg("%s VL %d returned %d not minimum %d\n", + data->name, vl, new_vl, + data->min_vl); + errors++; + } + + continue; + } + + /* Should round down to maximum VL if above it */ + if (vl > data->max_vl) { + if (new_vl != data->max_vl) { + ksft_print_msg("%s VL %d returned %d not maximum %d\n", + data->name, vl, new_vl, + data->max_vl); + errors++; + } + + continue; + } + + /* Otherwise we should've rounded down */ + if (!(new_vl < vl)) { + ksft_print_msg("%s VL %d returned %d, did not round down\n", + data->name, vl, new_vl); + errors++; + + continue; + } + } + + ksft_test_result(errors == 0, "%s prctl() set all VLs, %d errors\n", + data->name, errors); +} + typedef void (*test_type)(struct vec_data *); static const test_type tests[] = { @@ -561,10 +628,12 @@ static const test_type tests[] = { proc_write_max, prctl_get, + prctl_set_same, prctl_set, prctl_set_no_child, prctl_set_for_child, prctl_set_onexec, + prctl_set_all_vqs, }; int main(void) diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 6836510a522f..22722abc9dfa 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -266,16 +266,19 @@ int test_init(struct tdescr *td) td->feats_supported |= FEAT_SSBS; if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; - if (feats_ok(td)) + if (feats_ok(td)) { fprintf(stderr, "Required Features: [%s] supported\n", feats_to_string(td->feats_required & td->feats_supported)); - else + } else { fprintf(stderr, "Required Features: [%s] NOT supported\n", feats_to_string(td->feats_required & ~td->feats_supported)); + td->result = KSFT_SKIP; + return 0; + } } /* Perform test specific additional initialization */ diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 866531c08e4f..799b88152e9e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -375,7 +375,8 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_BPF_PROGS_DIR)/%.c \ $(TRUNNER_BPF_PROGS_DIR)/*.h \ $$(INCLUDE_DIR)/vmlinux.h \ - $(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT) + $(wildcard $(BPFDIR)/bpf_*.h) \ + | $(TRUNNER_OUTPUT) $$(BPFOBJ) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS)) diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 033051717ba5..f3daa44a8266 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -12,27 +12,36 @@ #include <unistd.h> #include <ftw.h> - #include "cgroup_helpers.h" /* * To avoid relying on the system setup, when setup_cgroup_env is called - * we create a new mount namespace, and cgroup namespace. The cgroup2 - * root is mounted at CGROUP_MOUNT_PATH - * - * Unfortunately, most people don't have cgroupv2 enabled at this point in time. - * It's easier to create our own mount namespace and manage it ourselves. + * we create a new mount namespace, and cgroup namespace. The cgroupv2 + * root is mounted at CGROUP_MOUNT_PATH. Unfortunately, most people don't + * have cgroupv2 enabled at this point in time. It's easier to create our + * own mount namespace and manage it ourselves. We assume /mnt exists. * - * We assume /mnt exists. + * Related cgroupv1 helpers are named *classid*(), since we only use the + * net_cls controller for tagging net_cls.classid. We assume the default + * mount under /sys/fs/cgroup/net_cls, which should be the case for the + * vast majority of users. */ #define WALK_FD_LIMIT 16 + #define CGROUP_MOUNT_PATH "/mnt" +#define CGROUP_MOUNT_DFLT "/sys/fs/cgroup" +#define NETCLS_MOUNT_PATH CGROUP_MOUNT_DFLT "/net_cls" #define CGROUP_WORK_DIR "/cgroup-test-work-dir" + #define format_cgroup_path(buf, path) \ snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \ CGROUP_WORK_DIR, path) +#define format_classid_path(buf) \ + snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH, \ + CGROUP_WORK_DIR) + /** * enable_all_controllers() - Enable all available cgroup v2 controllers * @@ -139,8 +148,7 @@ static int nftwfunc(const char *filename, const struct stat *statptr, return 0; } - -static int join_cgroup_from_top(char *cgroup_path) +static int join_cgroup_from_top(const char *cgroup_path) { char cgroup_procs_path[PATH_MAX + 1]; pid_t pid = getpid(); @@ -313,3 +321,114 @@ int cgroup_setup_and_join(const char *path) { } return cg_fd; } + +/** + * setup_classid_environment() - Setup the cgroupv1 net_cls environment + * + * After calling this function, cleanup_classid_environment should be called + * once testing is complete. + * + * This function will print an error to stderr and return 1 if it is unable + * to setup the cgroup environment. If setup is successful, 0 is returned. + */ +int setup_classid_environment(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + + if (mount("tmpfs", CGROUP_MOUNT_DFLT, "tmpfs", 0, NULL) && + errno != EBUSY) { + log_err("mount cgroup base"); + return 1; + } + + if (mkdir(NETCLS_MOUNT_PATH, 0777) && errno != EEXIST) { + log_err("mkdir cgroup net_cls"); + return 1; + } + + if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") && + errno != EBUSY) { + log_err("mount cgroup net_cls"); + return 1; + } + + cleanup_classid_environment(); + + if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) { + log_err("mkdir cgroup work dir"); + return 1; + } + + return 0; +} + +/** + * set_classid() - Set a cgroupv1 net_cls classid + * @id: the numeric classid + * + * Writes the passed classid into the cgroup work dir's net_cls.classid + * file in order to later on trigger socket tagging. + * + * On success, it returns 0, otherwise on failure it returns 1. If there + * is a failure, it prints the error to stderr. + */ +int set_classid(unsigned int id) +{ + char cgroup_workdir[PATH_MAX - 42]; + char cgroup_classid_path[PATH_MAX + 1]; + int fd, rc = 0; + + format_classid_path(cgroup_workdir); + snprintf(cgroup_classid_path, sizeof(cgroup_classid_path), + "%s/net_cls.classid", cgroup_workdir); + + fd = open(cgroup_classid_path, O_WRONLY); + if (fd < 0) { + log_err("Opening cgroup classid: %s", cgroup_classid_path); + return 1; + } + + if (dprintf(fd, "%u\n", id) < 0) { + log_err("Setting cgroup classid"); + rc = 1; + } + + close(fd); + return rc; +} + +/** + * join_classid() - Join a cgroupv1 net_cls classid + * + * This function expects the cgroup work dir to be already created, as we + * join it here. This causes the process sockets to be tagged with the given + * net_cls classid. + * + * On success, it returns 0, otherwise on failure it returns 1. + */ +int join_classid(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + return join_cgroup_from_top(cgroup_workdir); +} + +/** + * cleanup_classid_environment() - Cleanup the cgroupv1 net_cls environment + * + * At call time, it moves the calling process to the root cgroup, and then + * runs the deletion process. + * + * On failure, it will print an error to stderr, and try to continue. + */ +void cleanup_classid_environment(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + join_cgroup_from_top(NETCLS_MOUNT_PATH); + nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT); +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 5fe3d88e4f0d..629da3854b3e 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_HELPERS_H #define __CGROUP_HELPERS_H + #include <errno.h> #include <string.h> @@ -8,12 +9,21 @@ #define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) - +/* cgroupv2 related */ int cgroup_setup_and_join(const char *path); int create_and_get_cgroup(const char *path); +unsigned long long get_cgroup_id(const char *path); + int join_cgroup(const char *path); + int setup_cgroup_environment(void); void cleanup_cgroup_environment(void); -unsigned long long get_cgroup_id(const char *path); -#endif +/* cgroupv1 related */ +int set_classid(unsigned int id); +int join_classid(void); + +int setup_classid_environment(void); +void cleanup_classid_environment(void); + +#endif /* __CGROUP_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 7e9f6375757a..6db1af8fdee7 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -208,11 +208,26 @@ error_close: static int connect_fd_to_addr(int fd, const struct sockaddr_storage *addr, - socklen_t addrlen) + socklen_t addrlen, const bool must_fail) { - if (connect(fd, (const struct sockaddr *)addr, addrlen)) { - log_err("Failed to connect to server"); - return -1; + int ret; + + errno = 0; + ret = connect(fd, (const struct sockaddr *)addr, addrlen); + if (must_fail) { + if (!ret) { + log_err("Unexpected success to connect to server"); + return -1; + } + if (errno != EPERM) { + log_err("Unexpected error from connect to server"); + return -1; + } + } else { + if (ret) { + log_err("Failed to connect to server"); + return -1; + } } return 0; @@ -257,7 +272,7 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts) strlen(opts->cc) + 1)) goto error_close; - if (connect_fd_to_addr(fd, &addr, addrlen)) + if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail)) goto error_close; return fd; @@ -289,7 +304,7 @@ int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms) return -1; } - if (connect_fd_to_addr(client_fd, &addr, len)) + if (connect_fd_to_addr(client_fd, &addr, len, false)) return -1; return 0; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index da7e132657d5..d198181a5648 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -20,6 +20,7 @@ typedef __u16 __sum16; struct network_helper_opts { const char *cc; int timeout_ms; + bool must_fail; }; /* ipv4 test vector */ diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c new file mode 100644 index 000000000000..ab3b9bc5e6d1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "connect4_dropper.skel.h" + +#include "cgroup_helpers.h" +#include "network_helpers.h" + +static int run_test(int cgroup_fd, int server_fd, bool classid) +{ + struct network_helper_opts opts = { + .must_fail = true, + }; + struct connect4_dropper *skel; + int fd, err = 0; + + skel = connect4_dropper__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return -1; + + skel->links.connect_v4_dropper = + bpf_program__attach_cgroup(skel->progs.connect_v4_dropper, + cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.connect_v4_dropper, "prog_attach")) { + err = -1; + goto out; + } + + if (classid && !ASSERT_OK(join_classid(), "join_classid")) { + err = -1; + goto out; + } + + fd = connect_to_fd_opts(server_fd, &opts); + if (fd < 0) + err = -1; + else + close(fd); +out: + connect4_dropper__destroy(skel); + return err; +} + +void test_cgroup_v1v2(void) +{ + struct network_helper_opts opts = {}; + int server_fd, client_fd, cgroup_fd; + static const int port = 60123; + + /* Step 1: Check base connectivity works without any BPF. */ + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + if (!ASSERT_GE(server_fd, 0, "server_fd")) + return; + client_fd = connect_to_fd_opts(server_fd, &opts); + if (!ASSERT_GE(client_fd, 0, "client_fd")) { + close(server_fd); + return; + } + close(client_fd); + close(server_fd); + + /* Step 2: Check BPF policy prog attached to cgroups drops connectivity. */ + cgroup_fd = test__join_cgroup("/connect_dropper"); + if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd")) + return; + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + if (!ASSERT_GE(server_fd, 0, "server_fd")) { + close(cgroup_fd); + return; + } + ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only"); + setup_classid_environment(); + set_classid(42); + ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2"); + cleanup_classid_environment(); + close(server_fd); + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 5c5979046523..d88bb65b74cc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -949,7 +949,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, int err, n; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1002,17 +1001,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, goto close_peer1; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_peer1: xclose(p1); @@ -1571,7 +1564,6 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1606,17 +1598,11 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); @@ -1748,7 +1734,6 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; u32 key; char b; @@ -1781,17 +1766,11 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1841,7 +1820,6 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1876,17 +1854,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1932,7 +1904,6 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, int sfd[2]; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1963,17 +1934,11 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c index 53f0e0fa1a53..37c20b5ffa70 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c +++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE #include <test_progs.h> -#include <linux/ptrace.h> #include "test_task_pt_regs.skel.h" void test_task_pt_regs(void) diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c new file mode 100644 index 000000000000..b565d997810a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define VERDICT_REJECT 0 +#define VERDICT_PROCEED 1 + +SEC("cgroup/connect4") +int connect_v4_dropper(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_STREAM) + return VERDICT_PROCEED; + if (ctx->user_port == bpf_htons(60123)) + return VERDICT_REJECT; + return VERDICT_PROCEED; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c index 6c059f1cfa1b..e6cb09259408 100644 --- a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c +++ b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c @@ -1,12 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/ptrace.h> -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -struct pt_regs current_regs = {}; -struct pt_regs ctx_regs = {}; +#define PT_REGS_SIZE sizeof(struct pt_regs) + +/* + * The kernel struct pt_regs isn't exported in its entirety to userspace. + * Pass it as an array to task_pt_regs.c + */ +char current_regs[PT_REGS_SIZE] = {}; +char ctx_regs[PT_REGS_SIZE] = {}; int uprobe_res = 0; SEC("uprobe/trigger_func") @@ -17,8 +22,10 @@ int handle_uprobe(struct pt_regs *ctx) current = bpf_get_current_task_btf(); regs = (struct pt_regs *) bpf_task_pt_regs(current); - __builtin_memcpy(¤t_regs, regs, sizeof(*regs)); - __builtin_memcpy(&ctx_regs, ctx, sizeof(*ctx)); + if (bpf_probe_read_kernel(current_regs, PT_REGS_SIZE, regs)) + return 0; + if (bpf_probe_read_kernel(ctx_regs, PT_REGS_SIZE, ctx)) + return 0; /* Prove that uprobe was run */ uprobe_res = 1; diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index 59ea56945e6c..b497bb85b667 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -112,6 +112,14 @@ setup() ip netns add "${NS2}" ip netns add "${NS3}" + # rp_filter gets confused by what these tests are doing, so disable it + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip link add veth1 type veth peer name veth2 ip link add veth3 type veth peer name veth4 ip link add veth5 type veth peer name veth6 @@ -236,11 +244,6 @@ setup() ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF} ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF} - # rp_filter gets confused by what these tests are doing, so disable it - ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 - TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX) sleep 1 # reduce flakiness diff --git a/tools/testing/selftests/drivers/dma-buf/udmabuf.c b/tools/testing/selftests/drivers/dma-buf/udmabuf.c index 4de902ea14d8..de1c4e6de0b2 100644 --- a/tools/testing/selftests/drivers/dma-buf/udmabuf.c +++ b/tools/testing/selftests/drivers/dma-buf/udmabuf.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> #include <errno.h> -#include <linux/fcntl.h> +#include <fcntl.h> #include <malloc.h> #include <sys/ioctl.h> diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index beee0d5646a6..f7d84549cc3e 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -1,6 +1,6 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Copyright 2020 NXP Semiconductors +# Copyright 2020 NXP WAIT_TIME=1 NUM_NETIFS=4 diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 8ec1922e974e..c3311c8c4089 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -428,7 +428,7 @@ for t in $TEST_CASES; do exit 1 fi done -(cd $TRACING_DIR; initialize_ftrace) # for cleanup +(cd $TRACING_DIR; finish_ftrace) # for cleanup prlog "" prlog "# of passed: " `echo $PASSED_CASES | wc -w` diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc index 5f5b2ba3e557..60c02b482be8 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc @@ -11,8 +11,8 @@ SYSTEM="syscalls" EVENT="sys_enter_openat" FIELD="filename" EPROBE="eprobe_open" - -echo "e:$EPROBE $SYSTEM/$EVENT file=+0(\$filename):ustring" >> dynamic_events +OPTIONS="file=+0(\$filename):ustring" +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events grep -q "$EPROBE" dynamic_events test -d events/eprobes/$EPROBE @@ -37,4 +37,54 @@ echo "-:$EPROBE" >> dynamic_events ! grep -q "$EPROBE" dynamic_events ! test -d events/eprobes/$EPROBE +# test various ways to remove the probe (already tested with just event name) + +# With group name +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With group name and system/event +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With just event name and system/event +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:$EPROBE $SYSTEM/$EVENT" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With just event name and system/event and options +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With group name and system/event and options +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# Finally make sure what is in the dynamic_events file clears it too +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +LINE=`sed -e '/$EPROBE/s/^e/-/' < dynamic_events` +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 000fd05e84b1..5f6cbec847fc 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -124,10 +124,22 @@ initialize_ftrace() { # Reset ftrace to initial-state [ -f uprobe_events ] && echo > uprobe_events [ -f synthetic_events ] && echo > synthetic_events [ -f snapshot ] && echo 0 > snapshot + +# Stop tracing while reading the trace file by default, to prevent +# the test results while checking it and to avoid taking a long time +# to check the result. + [ -f options/pause-on-trace ] && echo 1 > options/pause-on-trace + clear_trace enable_tracing } +finish_ftrace() { + initialize_ftrace +# And recover it to default. + [ -f options/pause-on-trace ] && echo 0 > options/pause-on-trace +} + check_requires() { # Check required files and tracers for i in "$@" ; do r=${i%:README} diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 0e78b49d0f2f..fbcbdb6963b3 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -8,3 +8,4 @@ futex_wait_uninitialized_heap futex_wait_wouldblock futex_wait futex_requeue +futex_waitv diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index bd1fec59e010..5cc38de9d8ea 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -17,7 +17,8 @@ TEST_GEN_FILES := \ futex_wait_uninitialized_heap \ futex_wait_private_mapped_file \ futex_wait \ - futex_requeue + futex_requeue \ + futex_waitv TEST_PROGS := run.sh diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index 1f8f6daaf1e7..3651ce17beeb 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -17,6 +17,7 @@ #include <pthread.h> #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-timeout" @@ -96,6 +97,12 @@ int main(int argc, char *argv[]) struct timespec to; pthread_t thread; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -118,7 +125,7 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(7); + ksft_set_plan(9); ksft_print_msg("%s: Block on a futex and wait for timeout\n", basename(argv[0])); ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns); @@ -175,6 +182,18 @@ int main(int argc, char *argv[]) res = futex_lock_pi(&futex_pi, NULL, 0, FUTEX_CLOCK_REALTIME); test_timeout(res, &ret, "futex_lock_pi invalid timeout flag", ENOSYS); + /* futex_waitv with CLOCK_MONOTONIC */ + if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + test_timeout(res, &ret, "futex_waitv monotonic", ETIMEDOUT); + + /* futex_waitv with CLOCK_REALTIME */ + if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_REALTIME); + test_timeout(res, &ret, "futex_waitv realtime", ETIMEDOUT); + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c index 0ae390ff8164..7d7a6a06cdb7 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c +++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c @@ -22,6 +22,7 @@ #include <string.h> #include <time.h> #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-wouldblock" @@ -42,6 +43,12 @@ int main(int argc, char *argv[]) futex_t f1 = FUTEX_INITIALIZER; int res, ret = RET_PASS; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1+1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -61,18 +68,44 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(1); + ksft_set_plan(2); ksft_print_msg("%s: Test the unexpected futex value in FUTEX_WAIT\n", basename(argv[0])); info("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); res = futex_wait(&f1, f1+1, &to, FUTEX_PRIVATE_FLAG); if (!res || errno != EWOULDBLOCK) { - fail("futex_wait returned: %d %s\n", - res ? errno : res, res ? strerror(errno) : ""); + ksft_test_result_fail("futex_wait returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_wait\n"); } - print_result(TEST_NAME, ret); + if (clock_gettime(CLOCK_MONOTONIC, &to)) { + error("clock_gettime failed\n", errno); + return errno; + } + + to.tv_nsec += timeout_ns; + + if (to.tv_nsec >= 1000000000) { + to.tv_sec++; + to.tv_nsec -= 1000000000; + } + + info("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + if (!res || errno != EWOULDBLOCK) { + ksft_test_result_pass("futex_waitv returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv\n"); + } + + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_waitv.c b/tools/testing/selftests/futex/functional/futex_waitv.c new file mode 100644 index 000000000000..a94337f677e1 --- /dev/null +++ b/tools/testing/selftests/futex/functional/futex_waitv.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * futex_waitv() test by André Almeida <andrealmeid@collabora.com> + * + * Copyright 2021 Collabora Ltd. + */ + +#include <errno.h> +#include <error.h> +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <pthread.h> +#include <stdint.h> +#include <sys/shm.h> +#include "futextest.h" +#include "futex2test.h" +#include "logging.h" + +#define TEST_NAME "futex-wait" +#define WAKE_WAIT_US 10000 +#define NR_FUTEXES 30 +static struct futex_waitv waitv[NR_FUTEXES]; +u_int32_t futexes[NR_FUTEXES] = {0}; + +void usage(char *prog) +{ + printf("Usage: %s\n", prog); + printf(" -c Use color\n"); + printf(" -h Display this help message\n"); + printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n", + VQUIET, VCRITICAL, VINFO); +} + +void *waiterfn(void *arg) +{ + struct timespec to; + int res; + + /* setting absolute timeout for futex2 */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res < 0) { + ksft_test_result_fail("futex_waitv returned: %d %s\n", + errno, strerror(errno)); + } else if (res != NR_FUTEXES - 1) { + ksft_test_result_fail("futex_waitv returned: %d, expecting %d\n", + res, NR_FUTEXES - 1); + } + + return NULL; +} + +int main(int argc, char *argv[]) +{ + pthread_t waiter; + int res, ret = RET_PASS; + struct timespec to; + int c, i; + + while ((c = getopt(argc, argv, "cht:v:")) != -1) { + switch (c) { + case 'c': + log_color(1); + break; + case 'h': + usage(basename(argv[0])); + exit(0); + case 'v': + log_verbosity(atoi(optarg)); + break; + default: + usage(basename(argv[0])); + exit(1); + } + } + + ksft_print_header(); + ksft_set_plan(7); + ksft_print_msg("%s: Test FUTEX_WAITV\n", + basename(argv[0])); + + for (i = 0; i < NR_FUTEXES; i++) { + waitv[i].uaddr = (uintptr_t)&futexes[i]; + waitv[i].flags = FUTEX_32 | FUTEX_PRIVATE_FLAG; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } + + /* Private waitv */ + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); + + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, FUTEX_PRIVATE_FLAG); + if (res != 1) { + ksft_test_result_fail("futex_wake private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv private\n"); + } + + /* Shared waitv */ + for (i = 0; i < NR_FUTEXES; i++) { + int shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666); + + if (shm_id < 0) { + perror("shmget"); + exit(1); + } + + unsigned int *shared_data = shmat(shm_id, NULL, 0); + + *shared_data = 0; + waitv[i].uaddr = (uintptr_t)shared_data; + waitv[i].flags = FUTEX_32; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } + + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); + + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, 0); + if (res != 1) { + ksft_test_result_fail("futex_wake shared returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv shared\n"); + } + + for (i = 0; i < NR_FUTEXES; i++) + shmdt(u64_to_ptr(waitv[i].uaddr)); + + /* Testing a waiter without FUTEX_32 flag */ + waitv[0].flags = FUTEX_PRIVATE_FLAG; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv without FUTEX_32\n"); + } + + /* Testing a waiter with an unaligned address */ + waitv[0].flags = FUTEX_PRIVATE_FLAG | FUTEX_32; + waitv[0].uaddr = 1; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_wake private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv with an unaligned address\n"); + } + + /* Testing a NULL address for waiters.uaddr */ + waitv[0].uaddr = 0x00000000; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv NULL address in waitv.uaddr\n"); + } + + /* Testing a NULL address for *waiters */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv NULL address in *waiters\n"); + } + + /* Testing an invalid clockid */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_TAI); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv invalid clockid\n"); + } + + ksft_print_cnts(); + return ret; +} diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh index 11a9d62290f5..5ccd599da6c3 100755 --- a/tools/testing/selftests/futex/functional/run.sh +++ b/tools/testing/selftests/futex/functional/run.sh @@ -79,3 +79,6 @@ echo echo ./futex_requeue $COLOR + +echo +./futex_waitv $COLOR diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h new file mode 100644 index 000000000000..9d305520e849 --- /dev/null +++ b/tools/testing/selftests/futex/include/futex2test.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Futex2 library addons for futex tests + * + * Copyright 2021 Collabora Ltd. + */ +#include <stdint.h> + +#define u64_to_ptr(x) ((void *)(uintptr_t)(x)) + +/** + * futex_waitv - Wait at multiple futexes, wake on any + * @waiters: Array of waiters + * @nr_waiters: Length of waiters array + * @flags: Operation flags + * @timo: Optional timeout for operation + */ +static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters, + unsigned long flags, struct timespec *timo, clockid_t clockid) +{ + return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, timo, clockid); +} diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 98053d3afbda..b8dbabe24ac2 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -24,6 +24,7 @@ /x86_64/smm_test /x86_64/state_test /x86_64/svm_vmcall_test +/x86_64/svm_int_ctl_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/userspace_msr_exit_test @@ -48,6 +49,7 @@ /kvm_page_table_test /memslot_modification_stress_test /memslot_perf_test +/rseq_test /set_memory_region_test /steal_time /kvm_binary_stats_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 5d05801ab816..d1774f461393 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -56,6 +56,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test @@ -80,6 +81,7 @@ TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test TEST_GEN_PROGS_x86_64 += memslot_perf_test +TEST_GEN_PROGS_x86_64 += rseq_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test @@ -93,6 +95,7 @@ TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += kvm_page_table_test +TEST_GEN_PROGS_aarch64 += rseq_test TEST_GEN_PROGS_aarch64 += set_memory_region_test TEST_GEN_PROGS_aarch64 += steal_time TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test @@ -104,6 +107,7 @@ TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus TEST_GEN_PROGS_s390x += kvm_page_table_test +TEST_GEN_PROGS_s390x += rseq_test TEST_GEN_PROGS_s390x += set_memory_region_test TEST_GEN_PROGS_s390x += kvm_binary_stats_test diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 71e277c7c3f3..5d95113c7b7c 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -371,9 +371,7 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n\n"); - backing_src_help(); + backing_src_help("-s"); puts(""); exit(0); } @@ -381,7 +379,7 @@ static void help(char *name) int main(int argc, char *argv[]) { struct test_params params = { - .backing_src = VM_MEM_SRC_ANONYMOUS, + .backing_src = DEFAULT_VM_MEM_SRC, .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE, .vcpus = 1, }; diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index e79c1b64977f..1510b21e6306 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -179,7 +179,7 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } - if (!pollfd[0].revents & POLLIN) + if (!(pollfd[0].revents & POLLIN)) continue; r = read(uffd, &msg, sizeof(msg)); @@ -416,7 +416,7 @@ static void help(char *name) { puts(""); printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" - " [-b memory] [-t type] [-v vcpus] [-o]\n", name); + " [-b memory] [-s type] [-v vcpus] [-o]\n", name); guest_modes_help(); printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); @@ -426,8 +426,7 @@ static void help(char *name) printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); - printf(" -t: The type of backing memory to use. Default: anonymous\n"); - backing_src_help(); + backing_src_help("-s"); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -439,14 +438,14 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { - .src_type = VM_MEM_SRC_ANONYMOUS, + .src_type = DEFAULT_VM_MEM_SRC, .partition_vcpu_memory_access = true, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -465,7 +464,7 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; - case 't': + case 's': p.src_type = parse_backing_src_type(optarg); break; case 'v': @@ -485,7 +484,7 @@ int main(int argc, char *argv[]) if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && !backing_src_is_shared(p.src_type)) { - TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -s"); } for_each_guest_mode(run_test, &p); diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 479868570d59..7ffab5bd5ce5 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -118,42 +118,64 @@ static inline void disable_dirty_logging(struct kvm_vm *vm, int slots) toggle_dirty_logging(vm, slots, false); } -static void get_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap, - uint64_t nr_pages) +static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots) { - uint64_t slot_pages = nr_pages / slots; int i; for (i = 0; i < slots; i++) { int slot = PERF_TEST_MEM_SLOT_INDEX + i; - unsigned long *slot_bitmap = bitmap + i * slot_pages; - kvm_vm_get_dirty_log(vm, slot, slot_bitmap); + kvm_vm_get_dirty_log(vm, slot, bitmaps[i]); } } -static void clear_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap, - uint64_t nr_pages) +static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], + int slots, uint64_t pages_per_slot) { - uint64_t slot_pages = nr_pages / slots; int i; for (i = 0; i < slots; i++) { int slot = PERF_TEST_MEM_SLOT_INDEX + i; - unsigned long *slot_bitmap = bitmap + i * slot_pages; - kvm_vm_clear_dirty_log(vm, slot, slot_bitmap, 0, slot_pages); + kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot); } } +static unsigned long **alloc_bitmaps(int slots, uint64_t pages_per_slot) +{ + unsigned long **bitmaps; + int i; + + bitmaps = malloc(slots * sizeof(bitmaps[0])); + TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array."); + + for (i = 0; i < slots; i++) { + bitmaps[i] = bitmap_zalloc(pages_per_slot); + TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap."); + } + + return bitmaps; +} + +static void free_bitmaps(unsigned long *bitmaps[], int slots) +{ + int i; + + for (i = 0; i < slots; i++) + free(bitmaps[i]); + + free(bitmaps); +} + static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; pthread_t *vcpu_threads; struct kvm_vm *vm; - unsigned long *bmap; + unsigned long **bitmaps; uint64_t guest_num_pages; uint64_t host_num_pages; + uint64_t pages_per_slot; int vcpu_id; struct timespec start; struct timespec ts_diff; @@ -171,7 +193,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); host_num_pages = vm_num_host_pages(mode, guest_num_pages); - bmap = bitmap_zalloc(host_num_pages); + pages_per_slot = host_num_pages / p->slots; + + bitmaps = alloc_bitmaps(p->slots, pages_per_slot); if (dirty_log_manual_caps) { cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; @@ -239,7 +263,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) iteration, ts_diff.tv_sec, ts_diff.tv_nsec); clock_gettime(CLOCK_MONOTONIC, &start); - get_dirty_log(vm, p->slots, bmap, host_num_pages); + get_dirty_log(vm, bitmaps, p->slots); ts_diff = timespec_elapsed(start); get_dirty_log_total = timespec_add(get_dirty_log_total, ts_diff); @@ -248,7 +272,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) if (dirty_log_manual_caps) { clock_gettime(CLOCK_MONOTONIC, &start); - clear_dirty_log(vm, p->slots, bmap, host_num_pages); + clear_dirty_log(vm, bitmaps, p->slots, pages_per_slot); ts_diff = timespec_elapsed(start); clear_dirty_log_total = timespec_add(clear_dirty_log_total, ts_diff); @@ -281,7 +305,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); } - free(bmap); + free_bitmaps(bitmaps, p->slots); free(vcpu_threads); perf_test_destroy_vm(vm); } @@ -308,11 +332,9 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n\n"); + backing_src_help("-s"); printf(" -x: Split the memory region into this number of memslots.\n" - " (default: 1)"); - backing_src_help(); + " (default: 1)\n"); puts(""); exit(0); } @@ -324,7 +346,7 @@ int main(int argc, char *argv[]) .iterations = TEST_HOST_LOOP_N, .wr_fract = 1, .partition_vcpu_memory_access = true, - .backing_src = VM_MEM_SRC_ANONYMOUS, + .backing_src = DEFAULT_VM_MEM_SRC, .slots = 1, }; int opt; diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index d79be15dd3d2..f8fddc84c0d3 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -90,18 +90,23 @@ enum vm_mem_backing_src_type { NUM_SRC_TYPES, }; +#define DEFAULT_VM_MEM_SRC VM_MEM_SRC_ANONYMOUS + struct vm_mem_backing_src_alias { const char *name; uint32_t flag; }; +#define MIN_RUN_DELAY_NS 200000UL + bool thp_configured(void); size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); size_t get_backing_src_pagesz(uint32_t i); -void backing_src_help(void); +void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); +long get_run_delay(void); /* * Whether or not the given source type is shared memory (as opposed to diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 242ae8e09a65..05e65ca1c30c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -312,37 +312,37 @@ static inline void set_xmm(int n, unsigned long val) } } -typedef unsigned long v1di __attribute__ ((vector_size (8))); +#define GET_XMM(__xmm) \ +({ \ + unsigned long __val; \ + asm volatile("movq %%"#__xmm", %0" : "=r"(__val)); \ + __val; \ +}) + static inline unsigned long get_xmm(int n) { assert(n >= 0 && n <= 7); - register v1di xmm0 __asm__("%xmm0"); - register v1di xmm1 __asm__("%xmm1"); - register v1di xmm2 __asm__("%xmm2"); - register v1di xmm3 __asm__("%xmm3"); - register v1di xmm4 __asm__("%xmm4"); - register v1di xmm5 __asm__("%xmm5"); - register v1di xmm6 __asm__("%xmm6"); - register v1di xmm7 __asm__("%xmm7"); switch (n) { case 0: - return (unsigned long)xmm0; + return GET_XMM(xmm0); case 1: - return (unsigned long)xmm1; + return GET_XMM(xmm1); case 2: - return (unsigned long)xmm2; + return GET_XMM(xmm2); case 3: - return (unsigned long)xmm3; + return GET_XMM(xmm3); case 4: - return (unsigned long)xmm4; + return GET_XMM(xmm4); case 5: - return (unsigned long)xmm5; + return GET_XMM(xmm5); case 6: - return (unsigned long)xmm6; + return GET_XMM(xmm6); case 7: - return (unsigned long)xmm7; + return GET_XMM(xmm7); } + + /* never reached */ return 0; } diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 0d04a7db7f24..36407cb0ec85 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -456,10 +456,7 @@ static void help(char *name) " (default: 1G)\n"); printf(" -v: specify the number of vCPUs to run\n" " (default: 1)\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n" - " (default: anonymous)\n\n"); - backing_src_help(); + backing_src_help("-s"); puts(""); } @@ -468,7 +465,7 @@ int main(int argc, char *argv[]) int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { .test_mem_size = DEFAULT_TEST_MEM_SIZE, - .src_type = VM_MEM_SRC_ANONYMOUS, + .src_type = DEFAULT_VM_MEM_SRC, }; int opt; diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index af1031fed97f..b72429108993 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -11,6 +11,7 @@ #include <stdlib.h> #include <time.h> #include <sys/stat.h> +#include <sys/syscall.h> #include <linux/mman.h> #include "linux/kernel.h" @@ -129,13 +130,16 @@ size_t get_trans_hugepagesz(void) { size_t size; FILE *f; + int ret; TEST_ASSERT(thp_configured(), "THP is not configured in host kernel"); f = fopen("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", "r"); TEST_ASSERT(f != NULL, "Error in opening transparent_hugepage/hpage_pmd_size"); - fscanf(f, "%ld", &size); + ret = fscanf(f, "%ld", &size); + ret = fscanf(f, "%ld", &size); + TEST_ASSERT(ret < 1, "Error reading transparent_hugepage/hpage_pmd_size"); fclose(f); return size; @@ -279,13 +283,22 @@ size_t get_backing_src_pagesz(uint32_t i) } } -void backing_src_help(void) +static void print_available_backing_src_types(const char *prefix) { int i; - printf("Available backing src types:\n"); + printf("%sAvailable backing src types:\n", prefix); + for (i = 0; i < NUM_SRC_TYPES; i++) - printf("\t%s\n", vm_mem_backing_src_alias(i)->name); + printf("%s %s\n", prefix, vm_mem_backing_src_alias(i)->name); +} + +void backing_src_help(const char *flag) +{ + printf(" %s: specify the type of memory that should be used to\n" + " back the guest data region. (default: %s)\n", + flag, vm_mem_backing_src_alias(DEFAULT_VM_MEM_SRC)->name); + print_available_backing_src_types(" "); } enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) @@ -296,7 +309,23 @@ enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) if (!strcmp(type_name, vm_mem_backing_src_alias(i)->name)) return i; - backing_src_help(); + print_available_backing_src_types(""); TEST_FAIL("Unknown backing src type: %s", type_name); return -1; } + +long get_run_delay(void) +{ + char path[64]; + long val[2]; + FILE *fp; + + sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); + fp = fopen(path, "r"); + /* Return MIN_RUN_DELAY_NS upon failure just to be safe */ + if (fscanf(fp, "%ld %ld ", &val[0], &val[1]) < 2) + val[1] = MIN_RUN_DELAY_NS; + fclose(fp); + + return val[1]; +} diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c new file mode 100644 index 000000000000..4158da0da2bb --- /dev/null +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <errno.h> +#include <fcntl.h> +#include <pthread.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <syscall.h> +#include <sys/ioctl.h> +#include <sys/sysinfo.h> +#include <asm/barrier.h> +#include <linux/atomic.h> +#include <linux/rseq.h> +#include <linux/unistd.h> + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +#define VCPU_ID 0 + +static __thread volatile struct rseq __rseq = { + .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, +}; + +/* + * Use an arbitrary, bogus signature for configuring rseq, this test does not + * actually enter an rseq critical section. + */ +#define RSEQ_SIG 0xdeadbeef + +/* + * Any bug related to task migration is likely to be timing-dependent; perform + * a large number of migrations to reduce the odds of a false negative. + */ +#define NR_TASK_MIGRATIONS 100000 + +static pthread_t migration_thread; +static cpu_set_t possible_mask; +static int min_cpu, max_cpu; +static bool done; + +static atomic_t seq_cnt; + +static void guest_code(void) +{ + for (;;) + GUEST_SYNC(0); +} + +static void sys_rseq(int flags) +{ + int r; + + r = syscall(__NR_rseq, &__rseq, sizeof(__rseq), flags, RSEQ_SIG); + TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno)); +} + +static int next_cpu(int cpu) +{ + /* + * Advance to the next CPU, skipping those that weren't in the original + * affinity set. Sadly, there is no CPU_SET_FOR_EACH, and cpu_set_t's + * data storage is considered as opaque. Note, if this task is pinned + * to a small set of discontigous CPUs, e.g. 2 and 1023, this loop will + * burn a lot cycles and the test will take longer than normal to + * complete. + */ + do { + cpu++; + if (cpu > max_cpu) { + cpu = min_cpu; + TEST_ASSERT(CPU_ISSET(cpu, &possible_mask), + "Min CPU = %d must always be usable", cpu); + break; + } + } while (!CPU_ISSET(cpu, &possible_mask)); + + return cpu; +} + +static void *migration_worker(void *ign) +{ + cpu_set_t allowed_mask; + int r, i, cpu; + + CPU_ZERO(&allowed_mask); + + for (i = 0, cpu = min_cpu; i < NR_TASK_MIGRATIONS; i++, cpu = next_cpu(cpu)) { + CPU_SET(cpu, &allowed_mask); + + /* + * Bump the sequence count twice to allow the reader to detect + * that a migration may have occurred in between rseq and sched + * CPU ID reads. An odd sequence count indicates a migration + * is in-progress, while a completely different count indicates + * a migration occurred since the count was last read. + */ + atomic_inc(&seq_cnt); + + /* + * Ensure the odd count is visible while sched_getcpu() isn't + * stable, i.e. while changing affinity is in-progress. + */ + smp_wmb(); + r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask); + TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)", + errno, strerror(errno)); + smp_wmb(); + atomic_inc(&seq_cnt); + + CPU_CLR(cpu, &allowed_mask); + + /* + * Wait 1-10us before proceeding to the next iteration and more + * specifically, before bumping seq_cnt again. A delay is + * needed on three fronts: + * + * 1. To allow sched_setaffinity() to prompt migration before + * ioctl(KVM_RUN) enters the guest so that TIF_NOTIFY_RESUME + * (or TIF_NEED_RESCHED, which indirectly leads to handling + * NOTIFY_RESUME) is handled in KVM context. + * + * If NOTIFY_RESUME/NEED_RESCHED is set after KVM enters + * the guest, the guest will trigger a IO/MMIO exit all the + * way to userspace and the TIF flags will be handled by + * the generic "exit to userspace" logic, not by KVM. The + * exit to userspace is necessary to give the test a chance + * to check the rseq CPU ID (see #2). + * + * Alternatively, guest_code() could include an instruction + * to trigger an exit that is handled by KVM, but any such + * exit requires architecture specific code. + * + * 2. To let ioctl(KVM_RUN) make its way back to the test + * before the next round of migration. The test's check on + * the rseq CPU ID must wait for migration to complete in + * order to avoid false positive, thus any kernel rseq bug + * will be missed if the next migration starts before the + * check completes. + * + * 3. To ensure the read-side makes efficient forward progress, + * e.g. if sched_getcpu() involves a syscall. Stalling the + * read-side means the test will spend more time waiting for + * sched_getcpu() to stabilize and less time trying to hit + * the timing-dependent bug. + * + * Because any bug in this area is likely to be timing-dependent, + * run with a range of delays at 1us intervals from 1us to 10us + * as a best effort to avoid tuning the test to the point where + * it can hit _only_ the original bug and not detect future + * regressions. + * + * The original bug can reproduce with a delay up to ~500us on + * x86-64, but starts to require more iterations to reproduce + * as the delay creeps above ~10us, and the average runtime of + * each iteration obviously increases as well. Cap the delay + * at 10us to keep test runtime reasonable while minimizing + * potential coverage loss. + * + * The lower bound for reproducing the bug is likely below 1us, + * e.g. failures occur on x86-64 with nanosleep(0), but at that + * point the overhead of the syscall likely dominates the delay. + * Use usleep() for simplicity and to avoid unnecessary kernel + * dependencies. + */ + usleep((i % 10) + 1); + } + done = true; + return NULL; +} + +static int calc_min_max_cpu(void) +{ + int i, cnt, nproc; + + if (CPU_COUNT(&possible_mask) < 2) + return -EINVAL; + + /* + * CPU_SET doesn't provide a FOR_EACH helper, get the min/max CPU that + * this task is affined to in order to reduce the time spent querying + * unusable CPUs, e.g. if this task is pinned to a small percentage of + * total CPUs. + */ + nproc = get_nprocs_conf(); + min_cpu = -1; + max_cpu = -1; + cnt = 0; + + for (i = 0; i < nproc; i++) { + if (!CPU_ISSET(i, &possible_mask)) + continue; + if (min_cpu == -1) + min_cpu = i; + max_cpu = i; + cnt++; + } + + return (cnt < 2) ? -EINVAL : 0; +} + +int main(int argc, char *argv[]) +{ + int r, i, snapshot; + struct kvm_vm *vm; + u32 cpu, rseq_cpu; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask); + TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, + strerror(errno)); + + if (calc_min_max_cpu()) { + print_skip("Only one usable CPU, task migration not possible"); + exit(KSFT_SKIP); + } + + sys_rseq(0); + + /* + * Create and run a dummy VM that immediately exits to userspace via + * GUEST_SYNC, while concurrently migrating the process by setting its + * CPU affinity. + */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + ucall_init(vm, NULL); + + pthread_create(&migration_thread, NULL, migration_worker, 0); + + for (i = 0; !done; i++) { + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC, + "Guest failed?"); + + /* + * Verify rseq's CPU matches sched's CPU. Ensure migration + * doesn't occur between sched_getcpu() and reading the rseq + * cpu_id by rereading both if the sequence count changes, or + * if the count is odd (migration in-progress). + */ + do { + /* + * Drop bit 0 to force a mismatch if the count is odd, + * i.e. if a migration is in-progress. + */ + snapshot = atomic_read(&seq_cnt) & ~1; + + /* + * Ensure reading sched_getcpu() and rseq.cpu_id + * complete in a single "no migration" window, i.e. are + * not reordered across the seq_cnt reads. + */ + smp_rmb(); + cpu = sched_getcpu(); + rseq_cpu = READ_ONCE(__rseq.cpu_id); + smp_rmb(); + } while (snapshot != atomic_read(&seq_cnt)); + + TEST_ASSERT(rseq_cpu == cpu, + "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu); + } + + /* + * Sanity check that the test was able to enter the guest a reasonable + * number of times, e.g. didn't get stalled too often/long waiting for + * sched_getcpu() to stabilize. A 2:1 migration:KVM_RUN ratio is a + * fairly conservative ratio on x86-64, which can do _more_ KVM_RUNs + * than migrations given the 1us+ delay in the migration task. + */ + TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2), + "Only performed %d KVM_RUNs, task stalled too much?\n", i); + + pthread_join(migration_thread, NULL); + + kvm_vm_free(vm); + + sys_rseq(RSEQ_FLAG_UNREGISTER); + + return 0; +} diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index ecec30865a74..62f2eb9ee3d5 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -10,7 +10,6 @@ #include <sched.h> #include <pthread.h> #include <linux/kernel.h> -#include <sys/syscall.h> #include <asm/kvm.h> #include <asm/kvm_para.h> @@ -20,7 +19,6 @@ #define NR_VCPUS 4 #define ST_GPA_BASE (1 << 30) -#define MIN_RUN_DELAY_NS 200000UL static void *st_gva[NR_VCPUS]; static uint64_t guest_stolen_time[NR_VCPUS]; @@ -118,12 +116,12 @@ struct st_time { uint64_t st_time; }; -static int64_t smccc(uint32_t func, uint32_t arg) +static int64_t smccc(uint32_t func, uint64_t arg) { unsigned long ret; asm volatile( - "mov x0, %1\n" + "mov w0, %w1\n" "mov x1, %2\n" "hvc #0\n" "mov %0, x0\n" @@ -217,20 +215,6 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid) #endif -static long get_run_delay(void) -{ - char path[64]; - long val[2]; - FILE *fp; - - sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); - fp = fopen(path, "r"); - fscanf(fp, "%ld %ld ", &val[0], &val[1]); - fclose(fp); - - return val[1]; -} - static void *do_steal_time(void *arg) { struct timespec ts, stop; diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c index e6480fd5c4bd..8039e1eff938 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -82,7 +82,8 @@ int get_warnings_count(void) FILE *f; f = popen("dmesg | grep \"WARNING:\" | wc -l", "r"); - fscanf(f, "%d", &warnings); + if (fscanf(f, "%d", &warnings) < 1) + warnings = 0; fclose(f); return warnings; diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c new file mode 100644 index 000000000000..df04f56ce859 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_int_ctl_test + * + * Copyright (C) 2021, Red Hat, Inc. + * + * Nested SVM testing: test simultaneous use of V_IRQ from L1 and L0. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "apic.h" + +#define VCPU_ID 0 + +static struct kvm_vm *vm; + +bool vintr_irq_called; +bool intr_irq_called; + +#define VINTR_IRQ_NUMBER 0x20 +#define INTR_IRQ_NUMBER 0x30 + +static void vintr_irq_handler(struct ex_regs *regs) +{ + vintr_irq_called = true; +} + +static void intr_irq_handler(struct ex_regs *regs) +{ + x2apic_write_reg(APIC_EOI, 0x00); + intr_irq_called = true; +} + +static void l2_guest_code(struct svm_test_data *svm) +{ + /* This code raises interrupt INTR_IRQ_NUMBER in the L1's LAPIC, + * and since L1 didn't enable virtual interrupt masking, + * L2 should receive it and not L1. + * + * L2 also has virtual interrupt 'VINTR_IRQ_NUMBER' pending in V_IRQ + * so it should also receive it after the following 'sti'. + */ + x2apic_write_reg(APIC_ICR, + APIC_DEST_SELF | APIC_INT_ASSERT | INTR_IRQ_NUMBER); + + __asm__ __volatile__( + "sti\n" + "nop\n" + ); + + GUEST_ASSERT(vintr_irq_called); + GUEST_ASSERT(intr_irq_called); + + __asm__ __volatile__( + "vmcall\n" + ); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + x2apic_enable(); + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* No virtual interrupt masking */ + vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; + + /* No intercepts for real and virtual interrupts */ + vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR); + + /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */ + vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT); + vmcb->control.int_vector = VINTR_IRQ_NUMBER; + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t svm_gva; + + nested_svm_check_supported(); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler); + vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler); + + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s", (const char *)uc.args[0]); + break; + /* NOT REACHED */ + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 117bf49a3d79..eda0d2a51224 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -14,7 +14,6 @@ #include <stdint.h> #include <time.h> #include <sched.h> -#include <sys/syscall.h> #define VCPU_ID 5 @@ -98,20 +97,6 @@ static void guest_code(void) GUEST_DONE(); } -static long get_run_delay(void) -{ - char path[64]; - long val[2]; - FILE *fp; - - sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); - fp = fopen(path, "r"); - fscanf(fp, "%ld %ld ", &val[0], &val[1]); - fclose(fp); - - return val[1]; -} - static int cmp_timespec(struct timespec *a, struct timespec *b) { if (a->tv_sec > b->tv_sec) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index fa2ac0e56b43..fe7ee2b0f29c 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -48,6 +48,7 @@ ARCH ?= $(SUBARCH) # When local build is done, headers are installed in the default # INSTALL_HDR_PATH usr/include. .PHONY: khdr +.NOTPARALLEL: khdr: ifndef KSFT_KHDR_INSTALL_DONE ifeq (1,$(DEFAULT_INSTALL_HDR_PATH)) diff --git a/tools/testing/selftests/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c index e1bf55dabdf6..162c41e9bcae 100644 --- a/tools/testing/selftests/nci/nci_dev.c +++ b/tools/testing/selftests/nci/nci_dev.c @@ -746,7 +746,7 @@ int read_write_nci_cmd(int nfc_sock, int virtual_fd, const __u8 *cmd, __u32 cmd_ const __u8 *rsp, __u32 rsp_len) { char buf[256]; - unsigned int len; + int len; send(nfc_sock, &cmd[3], cmd_len - 3, 0); len = read(virtual_fd, buf, cmd_len); diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index cfc7f4f97fd1..df341648f818 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,5 +1,2 @@ -##TEST_GEN_FILES := test_unix_oob -TEST_PROGS := test_unix_oob +TEST_GEN_PROGS := test_unix_oob include ../../lib.mk - -all: $(TEST_PROGS) diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c index 0f3e3763f4f8..3dece8b29253 100644 --- a/tools/testing/selftests/net/af_unix/test_unix_oob.c +++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c @@ -271,8 +271,9 @@ main(int argc, char **argv) read_oob(pfd, &oob); if (!signal_recvd || len != 127 || oob != '%' || atmark != 1) { - fprintf(stderr, "Test 3 failed, sigurg %d len %d OOB %c ", - "atmark %d\n", signal_recvd, len, oob, atmark); + fprintf(stderr, + "Test 3 failed, sigurg %d len %d OOB %c atmark %d\n", + signal_recvd, len, oob, atmark); die(1); } diff --git a/tools/testing/selftests/net/altnames.sh b/tools/testing/selftests/net/altnames.sh index 4254ddc3f70b..1ef9e4159bba 100755 --- a/tools/testing/selftests/net/altnames.sh +++ b/tools/testing/selftests/net/altnames.sh @@ -45,7 +45,7 @@ altnames_test() check_err $? "Got unexpected long alternative name from link show JSON" ip link property del $DUMMY_DEV altname $SHORT_NAME - check_err $? "Failed to add short alternative name" + check_err $? "Failed to delete short alternative name" ip -j -p link show $SHORT_NAME &>/dev/null check_fail $? "Unexpected success while trying to do link show with deleted short alternative name" diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 21b646d10b88..86ab429fe7f3 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -43,3 +43,4 @@ CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_MIRRED=m CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y +CONFIG_CRYPTO_SM4=y diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 13350cd5c8ac..3313566ce906 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -289,6 +289,12 @@ set_sysctl() run_cmd sysctl -q -w $* } +# get sysctl values in NS-A +get_sysctl() +{ + ${NSA_CMD} sysctl -n $* +} + ################################################################################ # Setup for tests @@ -439,10 +445,13 @@ cleanup() ip -netns ${NSA} link set dev ${NSA_DEV} down ip -netns ${NSA} link del dev ${NSA_DEV} + ip netns pids ${NSA} | xargs kill 2>/dev/null ip netns del ${NSA} fi + ip netns pids ${NSB} | xargs kill 2>/dev/null ip netns del ${NSB} + ip netns pids ${NSC} | xargs kill 2>/dev/null ip netns del ${NSC} >/dev/null 2>&1 } @@ -1003,6 +1012,60 @@ ipv4_tcp_md5() run_cmd nettest -s -I ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET} log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + test_ipv4_md5_vrf__vrf_server__no_bind_ifindex + test_ipv4_md5_vrf__global_server__bind_ifindex0 +} + +test_ipv4_md5_vrf__vrf_server__no_bind_ifindex() +{ + log_start + show_hint "Simulates applications using VRF without TCP_MD5SIG_FLAG_IFINDEX" + run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: VRF-bound server, unbound key accepts connection" + + log_start + show_hint "Binding both the socket and the key is not required but it works" + run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: VRF-bound server, bound key accepts connection" +} + +test_ipv4_md5_vrf__global_server__bind_ifindex0() +{ + # This particular test needs tcp_l3mdev_accept=1 for Global server to accept VRF connections + local old_tcp_l3mdev_accept + old_tcp_l3mdev_accept=$(get_sysctl net.ipv4.tcp_l3mdev_accept) + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 2 "MD5: VRF: Global server, Key bound to ifindex=0 rejects VRF connection" + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key bound to ifindex=0 accepts non-VRF connection" + log_start + + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts VRF connection" + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts non-VRF connection" + + # restore value + set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept" } ipv4_tcp_novrf() diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index d97bd6889446..72ee644d47bf 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -9,6 +9,7 @@ TEST_PROGS = bridge_igmp.sh \ gre_inner_v4_multipath.sh \ gre_inner_v6_multipath.sh \ gre_multipath.sh \ + ip6_forward_instats_vrf.sh \ ip6gre_inner_v4_multipath.sh \ ip6gre_inner_v6_multipath.sh \ ipip_flat_gre_key.sh \ diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b802c14d2950..e5e2fbeca22e 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -39,3 +39,5 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# IPv6 traceroute utility name. +TROUTE6=traceroute6 diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh new file mode 100755 index 000000000000..9f5b3e2e5e95 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -0,0 +1,172 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test ipv6 stats on the incoming if when forwarding with VRF + +ALL_TESTS=" + ipv6_ping + ipv6_in_too_big_err + ipv6_in_hdr_err + ipv6_in_addr_err + ipv6_in_discard +" + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 2001:1:1::2/64 + ip -6 route add vrf v$h1 2001:1:2::/64 via 2001:1:1::1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 2001:1:2::/64 via 2001:1:1::1 + simple_if_fini $h1 2001:1:1::2/64 +} + +router_create() +{ + vrf_create router + __simple_if_init $rtr1 router 2001:1:1::1/64 + __simple_if_init $rtr2 router 2001:1:2::1/64 + mtu_set $rtr2 1280 +} + +router_destroy() +{ + mtu_restore $rtr2 + __simple_if_fini $rtr2 2001:1:2::1/64 + __simple_if_fini $rtr1 2001:1:1::1/64 + vrf_destroy router +} + +h2_create() +{ + simple_if_init $h2 2001:1:2::2/64 + ip -6 route add vrf v$h2 2001:1:1::/64 via 2001:1:2::1 + mtu_set $h2 1280 +} + +h2_destroy() +{ + mtu_restore $h2 + ip -6 route del vrf v$h2 2001:1:1::/64 via 2001:1:2::1 + simple_if_fini $h2 2001:1:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rtr1=${NETIFS[p2]} + + rtr2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + router_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + router_destroy + h1_destroy + vrf_cleanup +} + +ipv6_in_too_big_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) + local vrf_name=$(master_name_get $h1) + + # Send too big packets + ip vrf exec $vrf_name \ + $PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + + local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InTooBigErrors" +} + +ipv6_in_hdr_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InHdrErrors) + local vrf_name=$(master_name_get $h1) + + # Send packets with hop limit 1, easiest with traceroute6 as some ping6 + # doesn't allow hop limit to be specified + ip vrf exec $vrf_name \ + $TROUTE6 2001:1:2::2 &> /dev/null + + local t1=$(ipv6_stats_get $rtr1 Ip6InHdrErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InHdrErrors" +} + +ipv6_in_addr_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) + local vrf_name=$(master_name_get $h1) + + # Disable forwarding temporary while sending the packet + sysctl -qw net.ipv6.conf.all.forwarding=0 + ip vrf exec $vrf_name \ + $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + sysctl -qw net.ipv6.conf.all.forwarding=1 + + local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InAddrErrors" +} + +ipv6_in_discard() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InDiscards) + local vrf_name=$(master_name_get $h1) + + # Add a policy to discard + ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block + ip vrf exec $vrf_name \ + $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + ip xfrm policy del dst 2001:1:2::2/128 dir fwd + + local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InDiscards" +} +ipv6_ping() +{ + RET=0 + + ping6_test $h1 2001:1:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index e7fc5c35b569..92087d423bcf 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -751,6 +751,14 @@ qdisc_parent_stats_get() | jq '.[] | select(.parent == "'"$parent"'") | '"$selector" } +ipv6_stats_get() +{ + local dev=$1; shift + local stat=$1; shift + + cat /proc/net/dev_snmp6/$dev | grep "^$stat" | cut -f2 +} + humanize() { local speed=$1; shift diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index 3caf72bb9c6a..a2489ec398fe 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -468,10 +468,26 @@ out_bits() for i in {0..22} do ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ - prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 - - run_test "out_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \ - db01::2 db01::1 veth0 ${bit2type[$i]} 123 + prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ + dev veth0 &>/dev/null + + local cmd_res=$? + local descr="${desc/<n>/$i}" + + if [[ $i -ge 12 && $i -le 21 ]] + then + if [ $cmd_res != 0 ] + then + npassed=$((npassed+1)) + log_test_passed "$descr" + else + nfailed=$((nfailed+1)) + log_test_failed "$descr" + fi + else + run_test "out_bit$i" "$descr" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 ${bit2type[$i]} 123 + fi done bit2size[22]=$tmp @@ -544,7 +560,7 @@ in_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) - for i in {0..22} + for i in {0..11} {22..22} do ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index d376cb2c383c..8f6997d35816 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -94,16 +94,6 @@ enum { TEST_OUT_BIT9, TEST_OUT_BIT10, TEST_OUT_BIT11, - TEST_OUT_BIT12, - TEST_OUT_BIT13, - TEST_OUT_BIT14, - TEST_OUT_BIT15, - TEST_OUT_BIT16, - TEST_OUT_BIT17, - TEST_OUT_BIT18, - TEST_OUT_BIT19, - TEST_OUT_BIT20, - TEST_OUT_BIT21, TEST_OUT_BIT22, TEST_OUT_FULL_SUPP_TRACE, @@ -125,16 +115,6 @@ enum { TEST_IN_BIT9, TEST_IN_BIT10, TEST_IN_BIT11, - TEST_IN_BIT12, - TEST_IN_BIT13, - TEST_IN_BIT14, - TEST_IN_BIT15, - TEST_IN_BIT16, - TEST_IN_BIT17, - TEST_IN_BIT18, - TEST_IN_BIT19, - TEST_IN_BIT20, - TEST_IN_BIT21, TEST_IN_BIT22, TEST_IN_FULL_SUPP_TRACE, @@ -199,30 +179,6 @@ static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, ioam6h->nodelen != 2 || ioam6h->remlen; - case TEST_OUT_BIT12: - case TEST_IN_BIT12: - case TEST_OUT_BIT13: - case TEST_IN_BIT13: - case TEST_OUT_BIT14: - case TEST_IN_BIT14: - case TEST_OUT_BIT15: - case TEST_IN_BIT15: - case TEST_OUT_BIT16: - case TEST_IN_BIT16: - case TEST_OUT_BIT17: - case TEST_IN_BIT17: - case TEST_OUT_BIT18: - case TEST_IN_BIT18: - case TEST_OUT_BIT19: - case TEST_IN_BIT19: - case TEST_OUT_BIT20: - case TEST_IN_BIT20: - case TEST_OUT_BIT21: - case TEST_IN_BIT21: - return ioam6h->overflow || - ioam6h->nodelen || - ioam6h->remlen != 1; - case TEST_OUT_BIT22: case TEST_IN_BIT22: return ioam6h->overflow || @@ -326,6 +282,66 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, *p += sizeof(__u32); } + if (ioam6h->type.bit12) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit13) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit14) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit15) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit16) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit17) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit18) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit19) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit20) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit21) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + if (ioam6h->type.bit22) { len = cnf.sc_data ? strlen(cnf.sc_data) : 0; aligned = cnf.sc_data ? __ALIGN_KERNEL(len, 4) : 0; @@ -455,26 +471,6 @@ static int str2id(const char *tname) return TEST_OUT_BIT10; if (!strcmp("out_bit11", tname)) return TEST_OUT_BIT11; - if (!strcmp("out_bit12", tname)) - return TEST_OUT_BIT12; - if (!strcmp("out_bit13", tname)) - return TEST_OUT_BIT13; - if (!strcmp("out_bit14", tname)) - return TEST_OUT_BIT14; - if (!strcmp("out_bit15", tname)) - return TEST_OUT_BIT15; - if (!strcmp("out_bit16", tname)) - return TEST_OUT_BIT16; - if (!strcmp("out_bit17", tname)) - return TEST_OUT_BIT17; - if (!strcmp("out_bit18", tname)) - return TEST_OUT_BIT18; - if (!strcmp("out_bit19", tname)) - return TEST_OUT_BIT19; - if (!strcmp("out_bit20", tname)) - return TEST_OUT_BIT20; - if (!strcmp("out_bit21", tname)) - return TEST_OUT_BIT21; if (!strcmp("out_bit22", tname)) return TEST_OUT_BIT22; if (!strcmp("out_full_supp_trace", tname)) @@ -509,26 +505,6 @@ static int str2id(const char *tname) return TEST_IN_BIT10; if (!strcmp("in_bit11", tname)) return TEST_IN_BIT11; - if (!strcmp("in_bit12", tname)) - return TEST_IN_BIT12; - if (!strcmp("in_bit13", tname)) - return TEST_IN_BIT13; - if (!strcmp("in_bit14", tname)) - return TEST_IN_BIT14; - if (!strcmp("in_bit15", tname)) - return TEST_IN_BIT15; - if (!strcmp("in_bit16", tname)) - return TEST_IN_BIT16; - if (!strcmp("in_bit17", tname)) - return TEST_IN_BIT17; - if (!strcmp("in_bit18", tname)) - return TEST_IN_BIT18; - if (!strcmp("in_bit19", tname)) - return TEST_IN_BIT19; - if (!strcmp("in_bit20", tname)) - return TEST_IN_BIT20; - if (!strcmp("in_bit21", tname)) - return TEST_IN_BIT21; if (!strcmp("in_bit22", tname)) return TEST_IN_BIT22; if (!strcmp("in_full_supp_trace", tname)) @@ -606,16 +582,6 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { [TEST_OUT_BIT9] = check_ioam_header_and_data, [TEST_OUT_BIT10] = check_ioam_header_and_data, [TEST_OUT_BIT11] = check_ioam_header_and_data, - [TEST_OUT_BIT12] = check_ioam_header, - [TEST_OUT_BIT13] = check_ioam_header, - [TEST_OUT_BIT14] = check_ioam_header, - [TEST_OUT_BIT15] = check_ioam_header, - [TEST_OUT_BIT16] = check_ioam_header, - [TEST_OUT_BIT17] = check_ioam_header, - [TEST_OUT_BIT18] = check_ioam_header, - [TEST_OUT_BIT19] = check_ioam_header, - [TEST_OUT_BIT20] = check_ioam_header, - [TEST_OUT_BIT21] = check_ioam_header, [TEST_OUT_BIT22] = check_ioam_header_and_data, [TEST_OUT_FULL_SUPP_TRACE] = check_ioam_header_and_data, [TEST_IN_UNDEF_NS] = check_ioam_header, @@ -633,16 +599,6 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { [TEST_IN_BIT9] = check_ioam_header_and_data, [TEST_IN_BIT10] = check_ioam_header_and_data, [TEST_IN_BIT11] = check_ioam_header_and_data, - [TEST_IN_BIT12] = check_ioam_header, - [TEST_IN_BIT13] = check_ioam_header, - [TEST_IN_BIT14] = check_ioam_header, - [TEST_IN_BIT15] = check_ioam_header, - [TEST_IN_BIT16] = check_ioam_header, - [TEST_IN_BIT17] = check_ioam_header, - [TEST_IN_BIT18] = check_ioam_header, - [TEST_IN_BIT19] = check_ioam_header, - [TEST_IN_BIT20] = check_ioam_header, - [TEST_IN_BIT21] = check_ioam_header, [TEST_IN_BIT22] = check_ioam_header_and_data, [TEST_IN_FULL_SUPP_TRACE] = check_ioam_header_and_data, [TEST_FWD_FULL_SUPP_TRACE] = check_ioam_header_and_data, diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index bd6288302094..b599003eb5ba 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -28,6 +28,7 @@ #include <unistd.h> #include <time.h> #include <errno.h> +#include <getopt.h> #include <linux/xfrm.h> #include <linux/ipsec.h> @@ -101,6 +102,8 @@ struct sock_args { struct sockaddr_in6 v6; } md5_prefix; unsigned int prefix_len; + /* 0: default, -1: force off, +1: force on */ + int bind_key_ifindex; /* expected addresses and device index for connection */ const char *expected_dev; @@ -271,11 +274,14 @@ static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args } memcpy(&md5sig.tcpm_addr, addr, alen); - if (args->ifindex) { + if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) { opt = TCP_MD5SIG_EXT; md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX; md5sig.tcpm_ifindex = args->ifindex; + log_msg("TCP_MD5SIG_FLAG_IFINDEX set tcpm_ifindex=%d\n", md5sig.tcpm_ifindex); + } else { + log_msg("TCP_MD5SIG_FLAG_IFINDEX off\n", md5sig.tcpm_ifindex); } rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig)); @@ -1822,6 +1828,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) } #define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" +#define OPT_FORCE_BIND_KEY_IFINDEX 1001 +#define OPT_NO_BIND_KEY_IFINDEX 1002 + +static struct option long_opts[] = { + {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX}, + {"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX}, + {0, 0, 0, 0} +}; static void print_usage(char *prog) { @@ -1858,6 +1872,10 @@ static void print_usage(char *prog) " -M password use MD5 sum protection\n" " -X password MD5 password for client mode\n" " -m prefix/len prefix and length to use for MD5 key\n" + " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n" + " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n" + " (default: only if -I is passed)\n" + "\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" "\n" @@ -1893,7 +1911,7 @@ int main(int argc, char *argv[]) * process input args */ - while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) { + while ((rc = getopt_long(argc, argv, GETOPT_STR, long_opts, NULL)) != -1) { switch (rc) { case 'B': both_mode = 1; @@ -1966,6 +1984,12 @@ int main(int argc, char *argv[]) case 'M': args.password = optarg; break; + case OPT_FORCE_BIND_KEY_IFINDEX: + args.bind_key_ifindex = 1; + break; + case OPT_NO_BIND_KEY_IFINDEX: + args.bind_key_ifindex = -1; + break; case 'X': args.client_pw = optarg; break; diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 427d94816f2d..d4ffebb989f8 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -199,7 +199,6 @@ fi # test basic connectivity if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then echo "ERROR: ns1 cannot reach ns2" 1>&2 - bash exit 1 fi diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index d7e07f4c3d7f..da1c1e4b6c86 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -741,6 +741,149 @@ EOF return $lret } +# test port shadowing. +# create two listening services, one on router (ns0), one +# on client (ns2), which is masqueraded from ns1 point of view. +# ns2 sends udp packet coming from service port to ns1, on a highport. +# Later, if n1 uses same highport to connect to ns0:service, packet +# might be port-forwarded to ns2 instead. + +# second argument tells if we expect the 'fake-entry' to take effect +# (CLIENT) or not (ROUTER). +test_port_shadow() +{ + local test=$1 + local expect=$2 + local daddrc="10.0.1.99" + local daddrs="10.0.1.1" + local result="" + local logmsg="" + + echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & + nc_r=$! + + echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & + nc_c=$! + + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + + # ns1 tries to connect to ns0:1405. With default settings this should connect + # to client, it matches the conntrack entry created above. + + result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + + if [ "$result" = "$expect" ] ;then + echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" + else + echo "ERROR: portshadow test $test: got reply from \"$result\", not $expect as intended" + ret=1 + fi + + kill $nc_r $nc_c 2>/dev/null + + # flush udp entries for next test round, if any + ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 +} + +# This prevents port shadow of router service via packet filter, +# packets claiming to originate from service port from internal +# network are dropped. +test_port_shadow_filter() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family filter { + chain forward { + type filter hook forward priority 0; policy accept; + meta iif veth1 udp sport 1405 drop + } +} +EOF + test_port_shadow "port-filter" "ROUTER" + + ip netns exec "$ns0" nft delete table $family filter +} + +# This prevents port shadow of router service via notrack. +test_port_shadow_notrack() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family raw { + chain prerouting { + type filter hook prerouting priority -300; policy accept; + meta iif veth0 udp dport 1405 notrack + udp dport 1405 notrack + } + chain output { + type filter hook output priority -300; policy accept; + udp sport 1405 notrack + } +} +EOF + test_port_shadow "port-notrack" "ROUTER" + + ip netns exec "$ns0" nft delete table $family raw +} + +# This prevents port shadow of router service via sport remap. +test_port_shadow_pat() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family pat { + chain postrouting { + type nat hook postrouting priority -1; policy accept; + meta iif veth1 udp sport <= 1405 masquerade to : 1406-65535 random + } +} +EOF + test_port_shadow "pat" "ROUTER" + + ip netns exec "$ns0" nft delete table $family pat +} + +test_port_shadowing() +{ + local family="ip" + + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + meta oif veth0 masquerade + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add $family masquerade hook" + return $ksft_skip + fi + + # test default behaviour. Packet from ns1 to ns0 is redirected to ns2. + test_port_shadow "default" "CLIENT" + + # test packet filter based mitigation: prevent forwarding of + # packets claiming to come from the service port. + test_port_shadow_filter "$family" + + # test conntrack based mitigation: connections going or coming + # from router:service bypass connection tracking. + test_port_shadow_notrack "$family" + + # test nat based mitigation: fowarded packets coming from service port + # are masqueraded with random highport. + test_port_shadow_pat "$family" + + ip netns exec "$ns0" nft delete table $family nat +} # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do @@ -861,6 +1004,8 @@ reset_counters $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet +test_port_shadowing + if [ $ret -ne 0 ];then echo -n "FAIL: " nft --version diff --git a/tools/testing/selftests/netfilter/nft_nat_zones.sh b/tools/testing/selftests/netfilter/nft_nat_zones.sh new file mode 100755 index 000000000000..b9ab37380f33 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_nat_zones.sh @@ -0,0 +1,309 @@ +#!/bin/bash +# +# Test connection tracking zone and NAT source port reallocation support. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# Don't increase too much, 2000 clients should work +# just fine but script can then take several minutes with +# KASAN/debug builds. +maxclients=100 + +have_iperf=1 +ret=0 + +# client1---. +# veth1-. +# | +# NAT Gateway --veth0--> Server +# | | +# veth2-' | +# client2---' | +# .... | +# clientX----vethX---' + +# All clients share identical IP address. +# NAT Gateway uses policy routing and conntrack zones to isolate client +# namespaces. Each client connects to Server, each with colliding tuples: +# clientsaddr:10000 -> serveraddr:dport +# NAT Gateway is supposed to do port reallocation for each of the +# connections. + +sfx=$(mktemp -u "XXXXXXXX") +gw="ns-gw-$sfx" +cl1="ns-cl1-$sfx" +cl2="ns-cl2-$sfx" +srv="ns-srv-$sfx" + +v4gc1=$(sysctl -n net.ipv4.neigh.default.gc_thresh1 2>/dev/null) +v4gc2=$(sysctl -n net.ipv4.neigh.default.gc_thresh2 2>/dev/null) +v4gc3=$(sysctl -n net.ipv4.neigh.default.gc_thresh3 2>/dev/null) +v6gc1=$(sysctl -n net.ipv6.neigh.default.gc_thresh1 2>/dev/null) +v6gc2=$(sysctl -n net.ipv6.neigh.default.gc_thresh2 2>/dev/null) +v6gc3=$(sysctl -n net.ipv6.neigh.default.gc_thresh3 2>/dev/null) + +cleanup() +{ + ip netns del $gw + ip netns del $srv + for i in $(seq 1 $maxclients); do + ip netns del ns-cl$i-$sfx 2>/dev/null + done + + sysctl -q net.ipv4.neigh.default.gc_thresh1=$v4gc1 2>/dev/null + sysctl -q net.ipv4.neigh.default.gc_thresh2=$v4gc2 2>/dev/null + sysctl -q net.ipv4.neigh.default.gc_thresh3=$v4gc3 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh1=$v6gc1 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh2=$v6gc2 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh3=$v6gc3 2>/dev/null +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +conntrack -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without conntrack tool" + exit $ksft_skip +fi + +iperf3 -v >/dev/null 2>&1 +if [ $? -ne 0 ];then + have_iperf=0 +fi + +ip netns add "$gw" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $gw" + exit $ksft_skip +fi +ip -net "$gw" link set lo up + +trap cleanup EXIT + +ip netns add "$srv" +if [ $? -ne 0 ];then + echo "SKIP: Could not create server netns $srv" + exit $ksft_skip +fi + +ip link add veth0 netns "$gw" type veth peer name eth0 netns "$srv" +ip -net "$gw" link set veth0 up +ip -net "$srv" link set lo up +ip -net "$srv" link set eth0 up + +sysctl -q net.ipv6.neigh.default.gc_thresh1=512 2>/dev/null +sysctl -q net.ipv6.neigh.default.gc_thresh2=1024 2>/dev/null +sysctl -q net.ipv6.neigh.default.gc_thresh3=4096 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh1=512 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh2=1024 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh3=4096 2>/dev/null + +for i in $(seq 1 $maxclients);do + cl="ns-cl$i-$sfx" + + ip netns add "$cl" + if [ $? -ne 0 ];then + echo "SKIP: Could not create client netns $cl" + exit $ksft_skip + fi + ip link add veth$i netns "$gw" type veth peer name eth0 netns "$cl" > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip + fi +done + +for i in $(seq 1 $maxclients);do + cl="ns-cl$i-$sfx" + echo netns exec "$cl" ip link set lo up + echo netns exec "$cl" ip link set eth0 up + echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2 + echo netns exec "$gw" ip link set veth$i up + echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.arp_ignore=2 + echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.rp_filter=0 + + # clients have same IP addresses. + echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0 + echo netns exec "$cl" ip addr add dead:1::3/64 dev eth0 + echo netns exec "$cl" ip route add default via 10.1.0.2 dev eth0 + echo netns exec "$cl" ip route add default via dead:1::2 dev eth0 + + # NB: same addresses on client-facing interfaces. + echo netns exec "$gw" ip addr add 10.1.0.2/24 dev veth$i + echo netns exec "$gw" ip addr add dead:1::2/64 dev veth$i + + # gw: policy routing + echo netns exec "$gw" ip route add 10.1.0.0/24 dev veth$i table $((1000+i)) + echo netns exec "$gw" ip route add dead:1::0/64 dev veth$i table $((1000+i)) + echo netns exec "$gw" ip route add 10.3.0.0/24 dev veth0 table $((1000+i)) + echo netns exec "$gw" ip route add dead:3::0/64 dev veth0 table $((1000+i)) + echo netns exec "$gw" ip rule add fwmark $i lookup $((1000+i)) +done | ip -batch /dev/stdin + +ip -net "$gw" addr add 10.3.0.1/24 dev veth0 +ip -net "$gw" addr add dead:3::1/64 dev veth0 + +ip -net "$srv" addr add 10.3.0.99/24 dev eth0 +ip -net "$srv" addr add dead:3::99/64 dev eth0 + +ip netns exec $gw nft -f /dev/stdin<<EOF +table inet raw { + map iiftomark { + type ifname : mark + } + + map iiftozone { + typeof iifname : ct zone + } + + set inicmp { + flags dynamic + type ipv4_addr . ifname . ipv4_addr + } + set inflows { + flags dynamic + type ipv4_addr . inet_service . ifname . ipv4_addr . inet_service + } + + set inflows6 { + flags dynamic + type ipv6_addr . inet_service . ifname . ipv6_addr . inet_service + } + + chain prerouting { + type filter hook prerouting priority -64000; policy accept; + ct original zone set meta iifname map @iiftozone + meta mark set meta iifname map @iiftomark + + tcp flags & (syn|ack) == ack add @inflows { ip saddr . tcp sport . meta iifname . ip daddr . tcp dport counter } + add @inflows6 { ip6 saddr . tcp sport . meta iifname . ip6 daddr . tcp dport counter } + ip protocol icmp add @inicmp { ip saddr . meta iifname . ip daddr counter } + } + + chain nat_postrouting { + type nat hook postrouting priority 0; policy accept; + ct mark set meta mark meta oifname veth0 masquerade + } + + chain mangle_prerouting { + type filter hook prerouting priority -100; policy accept; + ct direction reply meta mark set ct mark + } +} +EOF + +( echo add element inet raw iiftomark \{ + for i in $(seq 1 $((maxclients-1))); do + echo \"veth$i\" : $i, + done + echo \"veth$maxclients\" : $maxclients \} + echo add element inet raw iiftozone \{ + for i in $(seq 1 $((maxclients-1))); do + echo \"veth$i\" : $i, + done + echo \"veth$maxclients\" : $maxclients \} +) | ip netns exec $gw nft -f /dev/stdin + +ip netns exec "$gw" sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null + +# useful for debugging: allows to use 'ping' from clients to gateway. +ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv6.fwmark_reflect=1 > /dev/null + +for i in $(seq 1 $maxclients); do + cl="ns-cl$i-$sfx" + ip netns exec $cl ping -i 0.5 -q -c 3 10.3.0.99 > /dev/null 2>&1 & + if [ $? -ne 0 ]; then + echo FAIL: Ping failure from $cl 1>&2 + ret=1 + break + fi +done + +wait + +for i in $(seq 1 $maxclients); do + ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" | grep -q "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 counter packets 3 bytes 252 }" + if [ $? -ne 0 ];then + ret=1 + echo "FAIL: counter icmp mismatch for veth$i" 1>&2 + ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" 1>&2 + break + fi +done + +ip netns exec $gw nft get element inet raw inicmp "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 }" | grep -q "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }" +if [ $? -ne 0 ];then + ret=1 + echo "FAIL: counter icmp mismatch for veth0: { 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }" + ip netns exec $gw nft get element inet raw inicmp "{ 10.3.99 . \"veth0\" . 10.3.0.1 }" 1>&2 +fi + +if [ $ret -eq 0 ]; then + echo "PASS: ping test from all $maxclients namespaces" +fi + +if [ $have_iperf -eq 0 ];then + echo "SKIP: iperf3 not installed" + if [ $ret -ne 0 ];then + exit $ret + fi + exit $ksft_skip +fi + +ip netns exec $srv iperf3 -s > /dev/null 2>&1 & +iperfpid=$! +sleep 1 + +for i in $(seq 1 $maxclients); do + if [ $ret -ne 0 ]; then + break + fi + cl="ns-cl$i-$sfx" + ip netns exec $cl iperf3 -c 10.3.0.99 --cport 10000 -n 1 > /dev/null + if [ $? -ne 0 ]; then + echo FAIL: Failure to connect for $cl 1>&2 + ip netns exec $gw conntrack -S 1>&2 + ret=1 + fi +done +if [ $ret -eq 0 ];then + echo "PASS: iperf3 connections for all $maxclients net namespaces" +fi + +kill $iperfpid +wait + +for i in $(seq 1 $maxclients); do + ip netns exec $gw nft get element inet raw inflows "{ 10.1.0.3 . 10000 . \"veth$i\" . 10.3.0.99 . 5201 }" > /dev/null + if [ $? -ne 0 ];then + ret=1 + echo "FAIL: can't find expected tcp entry for veth$i" 1>&2 + break + fi +done +if [ $ret -eq 0 ];then + echo "PASS: Found client connection for all $maxclients net namespaces" +fi + +ip netns exec $gw nft get element inet raw inflows "{ 10.3.0.99 . 5201 . \"veth0\" . 10.3.0.1 . 10000 }" > /dev/null +if [ $? -ne 0 ];then + ret=1 + echo "FAIL: cannot find return entry on veth0" 1>&2 +fi + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh new file mode 100755 index 000000000000..ac646376eb01 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -0,0 +1,156 @@ +#!/bin/bash + +# Test insertion speed for packets with identical addresses/ports +# that are all placed in distinct conntrack zones. + +sfx=$(mktemp -u "XXXXXXXX") +ns="ns-$sfx" + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +zones=20000 +have_ct_tool=0 +ret=0 + +cleanup() +{ + ip netns del $ns +} + +ip netns add $ns +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $gw" + exit $ksft_skip +fi + +trap cleanup EXIT + +conntrack -V > /dev/null 2>&1 +if [ $? -eq 0 ];then + have_ct_tool=1 +fi + +ip -net "$ns" link set lo up + +test_zones() { + local max_zones=$1 + +ip netns exec $ns sysctl -q net.netfilter.nf_conntrack_udp_timeout=3600 +ip netns exec $ns nft -f /dev/stdin<<EOF +flush ruleset +table inet raw { + map rndzone { + typeof numgen inc mod $max_zones : ct zone + } + + chain output { + type filter hook output priority -64000; policy accept; + udp dport 12345 ct zone set numgen inc mod 65536 map @rndzone + } +} +EOF + ( + echo "add element inet raw rndzone {" + for i in $(seq 1 $max_zones);do + echo -n "$i : $i" + if [ $i -lt $max_zones ]; then + echo "," + else + echo "}" + fi + done + ) | ip netns exec $ns nft -f /dev/stdin + + local i=0 + local j=0 + local outerstart=$(date +%s%3N) + local stop=$outerstart + + while [ $i -lt $max_zones ]; do + local start=$(date +%s%3N) + i=$((i + 10000)) + j=$((j + 1)) + dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null + if [ $? -ne 0 ] ;then + ret=1 + break + fi + + stop=$(date +%s%3N) + local duration=$((stop-start)) + echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)" + done + + if [ $have_ct_tool -eq 1 ]; then + local count=$(ip netns exec "$ns" conntrack -C) + local duration=$((stop-outerstart)) + + if [ $count -eq $max_zones ]; then + echo "PASS: inserted $count entries from packet path in $duration ms total" + else + ip netns exec $ns conntrack -S 1>&2 + echo "FAIL: inserted $count entries from packet path in $duration ms total, expected $max_zones entries" + ret=1 + fi + fi + + if [ $ret -ne 0 ];then + echo "FAIL: insert $max_zones entries from packet path" 1>&2 + fi +} + +test_conntrack_tool() { + local max_zones=$1 + + ip netns exec $ns conntrack -F >/dev/null 2>/dev/null + + local outerstart=$(date +%s%3N) + local start=$(date +%s%3N) + local stop=$start + local i=0 + while [ $i -lt $max_zones ]; do + i=$((i + 1)) + ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \ + --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i >/dev/null 2>&1 + if [ $? -ne 0 ];then + ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \ + --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i > /dev/null + echo "FAIL: conntrack -I returned an error" + ret=1 + break + fi + + if [ $((i%10000)) -eq 0 ];then + stop=$(date +%s%3N) + + local duration=$((stop-start)) + echo "PASS: added 10000 entries in $duration ms (now $i total)" + start=$stop + fi + done + + local count=$(ip netns exec "$ns" conntrack -C) + local duration=$((stop-outerstart)) + + if [ $count -eq $max_zones ]; then + echo "PASS: inserted $count entries via ctnetlink in $duration ms" + else + ip netns exec $ns conntrack -S 1>&2 + echo "FAIL: inserted $count entries via ctnetlink in $duration ms, expected $max_zones entries ($duration ms)" + ret=1 + fi +} + +test_zones $zones + +if [ $have_ct_tool -eq 1 ];then + test_conntrack_tool $zones +else + echo "SKIP: Could not run ctnetlink insertion test without conntrack tool" + if [ $ret -eq 0 ];then + exit $ksft_skip + fi +fi + +exit $ret diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S index bd1ca25febe4..aed632d29fff 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S +++ b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#include <ppc-asm.h> +#include <basic_asm.h> #include <asm/unistd.h> .text @@ -26,3 +26,38 @@ FUNC_START(getppid_tm_suspended) 1: li r3, -1 blr + + +.macro scv level + .long (0x44000001 | (\level) << 5) +.endm + +FUNC_START(getppid_scv_tm_active) + PUSH_BASIC_STACK(0) + tbegin. + beq 1f + li r0, __NR_getppid + scv 0 + tend. + POP_BASIC_STACK(0) + blr +1: + li r3, -1 + POP_BASIC_STACK(0) + blr + +FUNC_START(getppid_scv_tm_suspended) + PUSH_BASIC_STACK(0) + tbegin. + beq 1f + li r0, __NR_getppid + tsuspend. + scv 0 + tresume. + tend. + POP_BASIC_STACK(0) + blr +1: + li r3, -1 + POP_BASIC_STACK(0) + blr diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c index 467a6b3134b2..b763354c2eb4 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall.c +++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c @@ -19,23 +19,36 @@ #include "utils.h" #include "tm.h" +#ifndef PPC_FEATURE2_SCV +#define PPC_FEATURE2_SCV 0x00100000 /* scv syscall */ +#endif + extern int getppid_tm_active(void); extern int getppid_tm_suspended(void); +extern int getppid_scv_tm_active(void); +extern int getppid_scv_tm_suspended(void); unsigned retries = 0; #define TEST_DURATION 10 /* seconds */ -pid_t getppid_tm(bool suspend) +pid_t getppid_tm(bool scv, bool suspend) { int i; pid_t pid; for (i = 0; i < TM_RETRIES; i++) { - if (suspend) - pid = getppid_tm_suspended(); - else - pid = getppid_tm_active(); + if (suspend) { + if (scv) + pid = getppid_scv_tm_suspended(); + else + pid = getppid_tm_suspended(); + } else { + if (scv) + pid = getppid_scv_tm_active(); + else + pid = getppid_tm_active(); + } if (pid >= 0) return pid; @@ -82,15 +95,24 @@ int tm_syscall(void) * Test a syscall within a suspended transaction and verify * that it succeeds. */ - FAIL_IF(getppid_tm(true) == -1); /* Should succeed. */ + FAIL_IF(getppid_tm(false, true) == -1); /* Should succeed. */ /* * Test a syscall within an active transaction and verify that * it fails with the correct failure code. */ - FAIL_IF(getppid_tm(false) != -1); /* Should fail... */ + FAIL_IF(getppid_tm(false, false) != -1); /* Should fail... */ FAIL_IF(!failure_is_persistent()); /* ...persistently... */ FAIL_IF(!failure_is_syscall()); /* ...with code syscall. */ + + /* Now do it all again with scv if it is available. */ + if (have_hwcap2(PPC_FEATURE2_SCV)) { + FAIL_IF(getppid_tm(true, true) == -1); /* Should succeed. */ + FAIL_IF(getppid_tm(true, false) != -1); /* Should fail... */ + FAIL_IF(!failure_is_persistent()); /* ...persistently... */ + FAIL_IF(!failure_is_syscall()); /* ...with code syscall. */ + } + gettimeofday(&now, 0); } diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 7db9cf822dc7..8109b17dc764 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -62,6 +62,17 @@ enum pid_type {PIDTYPE_PID = 0, PIDTYPE_TGID, PIDTYPE_PGID}; const int THREAD_CLONE_FLAGS = CLONE_THREAD | CLONE_SIGHAND | CLONE_FS | CLONE_VM | CLONE_FILES; +struct child_args { + int num_threads; + int pfd[2]; + int cpid; + int thr_tids[MAX_THREADS]; +}; + +static struct child_args procs[MAX_PROCESSES]; +static int num_processes = 2; +static int need_cleanup = 0; + static int _prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { @@ -78,8 +89,14 @@ static int _prctl(int option, unsigned long arg2, unsigned long arg3, unsigned l #define handle_error(msg) __handle_error(__FILE__, __LINE__, msg) static void __handle_error(char *fn, int ln, char *msg) { + int pidx; printf("(%s:%d) - ", fn, ln); perror(msg); + if (need_cleanup) { + for (pidx = 0; pidx < num_processes; ++pidx) + kill(procs[pidx].cpid, 15); + need_cleanup = 0; + } exit(EXIT_FAILURE); } @@ -106,13 +123,6 @@ static unsigned long get_cs_cookie(int pid) return cookie; } -struct child_args { - int num_threads; - int pfd[2]; - int cpid; - int thr_tids[MAX_THREADS]; -}; - static int child_func_thread(void __attribute__((unused))*arg) { while (1) @@ -212,10 +222,7 @@ void _validate(int line, int val, char *msg) int main(int argc, char *argv[]) { - struct child_args procs[MAX_PROCESSES]; - int keypress = 0; - int num_processes = 2; int num_threads = 3; int delay = 0; int res = 0; @@ -262,6 +269,7 @@ int main(int argc, char *argv[]) printf("\n## Create a thread/process/process group hiearchy\n"); create_processes(num_processes, num_threads, procs); + need_cleanup = 1; disp_processes(num_processes, procs); validate(get_cs_cookie(0) == 0); diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c index 1af16d2c2a0a..52497b7b9f1d 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -341,7 +341,7 @@ void split_file_backed_thp(void) } /* write something to the file, so a file-backed THP can be allocated */ - num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc)); + num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1); close(fd); if (num_written < 1) { diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 10ab56c2484a..60aa1a4fc69b 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -414,9 +414,6 @@ static void uffd_test_ctx_init_ext(uint64_t *features) uffd_test_ops->allocate_area((void **)&area_src); uffd_test_ops->allocate_area((void **)&area_dst); - uffd_test_ops->release_pages(area_src); - uffd_test_ops->release_pages(area_dst); - userfaultfd_open(features); count_verify = malloc(nr_pages * sizeof(unsigned long long)); @@ -437,6 +434,26 @@ static void uffd_test_ctx_init_ext(uint64_t *features) *(area_count(area_src, nr) + 1) = 1; } + /* + * After initialization of area_src, we must explicitly release pages + * for area_dst to make sure it's fully empty. Otherwise we could have + * some area_dst pages be errornously initialized with zero pages, + * hence we could hit memory corruption later in the test. + * + * One example is when THP is globally enabled, above allocate_area() + * calls could have the two areas merged into a single VMA (as they + * will have the same VMA flags so they're mergeable). When we + * initialize the area_src above, it's possible that some part of + * area_dst could have been faulted in via one huge THP that will be + * shared between area_src and area_dst. It could cause some of the + * area_dst won't be trapped by missing userfaults. + * + * This release_pages() will guarantee even if that happened, we'll + * proactively split the thp and drop any accidentally initialized + * pages within area_dst. + */ + uffd_test_ops->release_pages(area_dst); + pipefd = malloc(sizeof(int) * nr_cpus * 2); if (!pipefd) err("pipefd"); diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index b4142cd1c5c2..8a1f62ab3c8e 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -18,7 +18,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \ - corrupt_xstate_header + corrupt_xstate_header amx # Some selftests require 32bit support enabled also on 64bit systems TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c new file mode 100644 index 000000000000..3615ef4a48bb --- /dev/null +++ b/tools/testing/selftests/x86/amx.c @@ -0,0 +1,851 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <err.h> +#include <errno.h> +#include <pthread.h> +#include <setjmp.h> +#include <stdio.h> +#include <string.h> +#include <stdbool.h> +#include <unistd.h> +#include <x86intrin.h> + +#include <sys/auxv.h> +#include <sys/mman.h> +#include <sys/shm.h> +#include <sys/syscall.h> +#include <sys/wait.h> + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +#define XSAVE_HDR_OFFSET 512 +#define XSAVE_HDR_SIZE 64 + +struct xsave_buffer { + union { + struct { + char legacy[XSAVE_HDR_OFFSET]; + char header[XSAVE_HDR_SIZE]; + char extended[0]; + }; + char bytes[0]; + }; +}; + +static inline uint64_t xgetbv(uint32_t index) +{ + uint32_t eax, edx; + + asm volatile("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((uint64_t)edx << 32); +} + +static inline void cpuid(uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx) +{ + asm volatile("cpuid;" + : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline void xsave(struct xsave_buffer *xbuf, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xsave (%%rdi)" + : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi) + : "memory"); +} + +static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xrstor (%%rdi)" + : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi)); +} + +/* err() exits and will not return */ +#define fatal_error(msg, ...) err(1, "[FAIL]\t" msg, ##__VA_ARGS__) + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + fatal_error("sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + fatal_error("sigaction"); +} + +#define XFEATURE_XTILECFG 17 +#define XFEATURE_XTILEDATA 18 +#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) +#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) + +#define CPUID_LEAF1_ECX_XSAVE_MASK (1 << 26) +#define CPUID_LEAF1_ECX_OSXSAVE_MASK (1 << 27) +static inline void check_cpuid_xsave(void) +{ + uint32_t eax, ebx, ecx, edx; + + /* + * CPUID.1:ECX.XSAVE[bit 26] enumerates general + * support for the XSAVE feature set, including + * XGETBV. + */ + eax = 1; + ecx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + if (!(ecx & CPUID_LEAF1_ECX_XSAVE_MASK)) + fatal_error("cpuid: no CPU xsave support"); + if (!(ecx & CPUID_LEAF1_ECX_OSXSAVE_MASK)) + fatal_error("cpuid: no OS xsave support"); +} + +static uint32_t xbuf_size; + +static struct { + uint32_t xbuf_offset; + uint32_t size; +} xtiledata; + +#define CPUID_LEAF_XSTATE 0xd +#define CPUID_SUBLEAF_XSTATE_USER 0x0 +#define TILE_CPUID 0x1d +#define TILE_PALETTE_ID 0x1 + +static void check_cpuid_xtiledata(void) +{ + uint32_t eax, ebx, ecx, edx; + + eax = CPUID_LEAF_XSTATE; + ecx = CPUID_SUBLEAF_XSTATE_USER; + cpuid(&eax, &ebx, &ecx, &edx); + + /* + * EBX enumerates the size (in bytes) required by the XSAVE + * instruction for an XSAVE area containing all the user state + * components corresponding to bits currently set in XCR0. + * + * Stash that off so it can be used to allocate buffers later. + */ + xbuf_size = ebx; + + eax = CPUID_LEAF_XSTATE; + ecx = XFEATURE_XTILEDATA; + + cpuid(&eax, &ebx, &ecx, &edx); + /* + * eax: XTILEDATA state component size + * ebx: XTILEDATA state component offset in user buffer + */ + if (!eax || !ebx) + fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d", + eax, ebx); + + xtiledata.size = eax; + xtiledata.xbuf_offset = ebx; +} + +/* The helpers for managing XSAVE buffer and tile states: */ + +struct xsave_buffer *alloc_xbuf(void) +{ + struct xsave_buffer *xbuf; + + /* XSAVE buffer should be 64B-aligned. */ + xbuf = aligned_alloc(64, xbuf_size); + if (!xbuf) + fatal_error("aligned_alloc()"); + return xbuf; +} + +static inline void clear_xstate_header(struct xsave_buffer *buffer) +{ + memset(&buffer->header, 0, sizeof(buffer->header)); +} + +static inline uint64_t get_xstatebv(struct xsave_buffer *buffer) +{ + /* XSTATE_BV is at the beginning of the header: */ + return *(uint64_t *)&buffer->header; +} + +static inline void set_xstatebv(struct xsave_buffer *buffer, uint64_t bv) +{ + /* XSTATE_BV is at the beginning of the header: */ + *(uint64_t *)(&buffer->header) = bv; +} + +static void set_rand_tiledata(struct xsave_buffer *xbuf) +{ + int *ptr = (int *)&xbuf->bytes[xtiledata.xbuf_offset]; + int data; + int i; + + /* + * Ensure that 'data' is never 0. This ensures that + * the registers are never in their initial configuration + * and thus never tracked as being in the init state. + */ + data = rand() | 1; + + for (i = 0; i < xtiledata.size / sizeof(int); i++, ptr++) + *ptr = data; +} + +struct xsave_buffer *stashed_xsave; + +static void init_stashed_xsave(void) +{ + stashed_xsave = alloc_xbuf(); + if (!stashed_xsave) + fatal_error("failed to allocate stashed_xsave\n"); + clear_xstate_header(stashed_xsave); +} + +static void free_stashed_xsave(void) +{ + free(stashed_xsave); +} + +/* See 'struct _fpx_sw_bytes' at sigcontext.h */ +#define SW_BYTES_OFFSET 464 +/* N.B. The struct's field name varies so read from the offset. */ +#define SW_BYTES_BV_OFFSET (SW_BYTES_OFFSET + 8) + +static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *buffer) +{ + return (struct _fpx_sw_bytes *)(buffer + SW_BYTES_OFFSET); +} + +static inline uint64_t get_fpx_sw_bytes_features(void *buffer) +{ + return *(uint64_t *)(buffer + SW_BYTES_BV_OFFSET); +} + +/* Work around printf() being unsafe in signals: */ +#define SIGNAL_BUF_LEN 1000 +char signal_message_buffer[SIGNAL_BUF_LEN]; +void sig_print(char *msg) +{ + int left = SIGNAL_BUF_LEN - strlen(signal_message_buffer) - 1; + + strncat(signal_message_buffer, msg, left); +} + +static volatile bool noperm_signaled; +static int noperm_errs; +/* + * Signal handler for when AMX is used but + * permission has not been obtained. + */ +static void handle_noperm(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t *)ctx_void; + void *xbuf = ctx->uc_mcontext.fpregs; + struct _fpx_sw_bytes *sw_bytes; + uint64_t features; + + /* Reset the signal message buffer: */ + signal_message_buffer[0] = '\0'; + sig_print("\tAt SIGILL handler,\n"); + + if (si->si_code != ILL_ILLOPC) { + noperm_errs++; + sig_print("[FAIL]\tInvalid signal code.\n"); + } else { + sig_print("[OK]\tValid signal code (ILL_ILLOPC).\n"); + } + + sw_bytes = get_fpx_sw_bytes(xbuf); + /* + * Without permission, the signal XSAVE buffer should not + * have room for AMX register state (aka. xtiledata). + * Check that the size does not overlap with where xtiledata + * will reside. + * + * This also implies that no state components *PAST* + * XTILEDATA (features >=19) can be present in the buffer. + */ + if (sw_bytes->xstate_size <= xtiledata.xbuf_offset) { + sig_print("[OK]\tValid xstate size\n"); + } else { + noperm_errs++; + sig_print("[FAIL]\tInvalid xstate size\n"); + } + + features = get_fpx_sw_bytes_features(xbuf); + /* + * Without permission, the XTILEDATA feature + * bit should not be set. + */ + if ((features & XFEATURE_MASK_XTILEDATA) == 0) { + sig_print("[OK]\tValid xstate mask\n"); + } else { + noperm_errs++; + sig_print("[FAIL]\tInvalid xstate mask\n"); + } + + noperm_signaled = true; + ctx->uc_mcontext.gregs[REG_RIP] += 3; /* Skip the faulting XRSTOR */ +} + +/* Return true if XRSTOR is successful; otherwise, false. */ +static inline bool xrstor_safe(struct xsave_buffer *xbuf, uint64_t mask) +{ + noperm_signaled = false; + xrstor(xbuf, mask); + + /* Print any messages produced by the signal code: */ + printf("%s", signal_message_buffer); + /* + * Reset the buffer to make sure any future printing + * only outputs new messages: + */ + signal_message_buffer[0] = '\0'; + + if (noperm_errs) + fatal_error("saw %d errors in noperm signal handler\n", noperm_errs); + + return !noperm_signaled; +} + +/* + * Use XRSTOR to populate the XTILEDATA registers with + * random data. + * + * Return true if successful; otherwise, false. + */ +static inline bool load_rand_tiledata(struct xsave_buffer *xbuf) +{ + clear_xstate_header(xbuf); + set_xstatebv(xbuf, XFEATURE_MASK_XTILEDATA); + set_rand_tiledata(xbuf); + return xrstor_safe(xbuf, XFEATURE_MASK_XTILEDATA); +} + +/* Return XTILEDATA to its initial configuration. */ +static inline void init_xtiledata(void) +{ + clear_xstate_header(stashed_xsave); + xrstor_safe(stashed_xsave, XFEATURE_MASK_XTILEDATA); +} + +enum expected_result { FAIL_EXPECTED, SUCCESS_EXPECTED }; + +/* arch_prctl() and sigaltstack() test */ + +#define ARCH_GET_XCOMP_PERM 0x1022 +#define ARCH_REQ_XCOMP_PERM 0x1023 + +static void req_xtiledata_perm(void) +{ + syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA); +} + +static void validate_req_xcomp_perm(enum expected_result exp) +{ + unsigned long bitmask; + long rc; + + rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA); + if (exp == FAIL_EXPECTED) { + if (rc) { + printf("[OK]\tARCH_REQ_XCOMP_PERM saw expected failure..\n"); + return; + } + + fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected success.\n"); + } else if (rc) { + fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected failure.\n"); + } + + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask); + if (rc) { + fatal_error("prctl(ARCH_GET_XCOMP_PERM) error: %ld", rc); + } else if (bitmask & XFEATURE_MASK_XTILE) { + printf("\tARCH_REQ_XCOMP_PERM is successful.\n"); + } +} + +static void validate_xcomp_perm(enum expected_result exp) +{ + bool load_success = load_rand_tiledata(stashed_xsave); + + if (exp == FAIL_EXPECTED) { + if (load_success) { + noperm_errs++; + printf("[FAIL]\tLoad tiledata succeeded.\n"); + } else { + printf("[OK]\tLoad tiledata failed.\n"); + } + } else if (exp == SUCCESS_EXPECTED) { + if (load_success) { + printf("[OK]\tLoad tiledata succeeded.\n"); + } else { + noperm_errs++; + printf("[FAIL]\tLoad tiledata failed.\n"); + } + } +} + +#ifndef AT_MINSIGSTKSZ +# define AT_MINSIGSTKSZ 51 +#endif + +static void *alloc_altstack(unsigned int size) +{ + void *altstack; + + altstack = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + + if (altstack == MAP_FAILED) + fatal_error("mmap() for altstack"); + + return altstack; +} + +static void setup_altstack(void *addr, unsigned long size, enum expected_result exp) +{ + stack_t ss; + int rc; + + memset(&ss, 0, sizeof(ss)); + ss.ss_size = size; + ss.ss_sp = addr; + + rc = sigaltstack(&ss, NULL); + + if (exp == FAIL_EXPECTED) { + if (rc) { + printf("[OK]\tsigaltstack() failed.\n"); + } else { + fatal_error("sigaltstack() succeeded unexpectedly.\n"); + } + } else if (rc) { + fatal_error("sigaltstack()"); + } +} + +static void test_dynamic_sigaltstack(void) +{ + unsigned int small_size, enough_size; + unsigned long minsigstksz; + void *altstack; + + minsigstksz = getauxval(AT_MINSIGSTKSZ); + printf("\tAT_MINSIGSTKSZ = %lu\n", minsigstksz); + /* + * getauxval() itself can return 0 for failure or + * success. But, in this case, AT_MINSIGSTKSZ + * will always return a >=0 value if implemented. + * Just check for 0. + */ + if (minsigstksz == 0) { + printf("no support for AT_MINSIGSTKSZ, skipping sigaltstack tests\n"); + return; + } + + enough_size = minsigstksz * 2; + + altstack = alloc_altstack(enough_size); + printf("\tAllocate memory for altstack (%u bytes).\n", enough_size); + + /* + * Try setup_altstack() with a size which can not fit + * XTILEDATA. ARCH_REQ_XCOMP_PERM should fail. + */ + small_size = minsigstksz - xtiledata.size; + printf("\tAfter sigaltstack() with small size (%u bytes).\n", small_size); + setup_altstack(altstack, small_size, SUCCESS_EXPECTED); + validate_req_xcomp_perm(FAIL_EXPECTED); + + /* + * Try setup_altstack() with a size derived from + * AT_MINSIGSTKSZ. It should be more than large enough + * and thus ARCH_REQ_XCOMP_PERM should succeed. + */ + printf("\tAfter sigaltstack() with enough size (%u bytes).\n", enough_size); + setup_altstack(altstack, enough_size, SUCCESS_EXPECTED); + validate_req_xcomp_perm(SUCCESS_EXPECTED); + + /* + * Try to coerce setup_altstack() to again accept a + * too-small altstack. This ensures that big-enough + * sigaltstacks can not shrink to a too-small value + * once XTILEDATA permission is established. + */ + printf("\tThen, sigaltstack() with small size (%u bytes).\n", small_size); + setup_altstack(altstack, small_size, FAIL_EXPECTED); +} + +static void test_dynamic_state(void) +{ + pid_t parent, child, grandchild; + + parent = fork(); + if (parent < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (parent > 0) { + int status; + /* fork() succeeded. Now in the parent. */ + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("arch_prctl test parent exit"); + return; + } + /* fork() succeeded. Now in the child . */ + + printf("[RUN]\tCheck ARCH_REQ_XCOMP_PERM around process fork() and sigaltack() test.\n"); + + printf("\tFork a child.\n"); + child = fork(); + if (child < 0) { + fatal_error("fork"); + } else if (child > 0) { + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("arch_prctl test child exit"); + _exit(0); + } + + /* + * The permission request should fail without an + * XTILEDATA-compatible signal stack + */ + printf("\tTest XCOMP_PERM at child.\n"); + validate_xcomp_perm(FAIL_EXPECTED); + + /* + * Set up an XTILEDATA-compatible signal stack and + * also obtain permission to populate XTILEDATA. + */ + printf("\tTest dynamic sigaltstack at child:\n"); + test_dynamic_sigaltstack(); + + /* Ensure that XTILEDATA can be populated. */ + printf("\tTest XCOMP_PERM again at child.\n"); + validate_xcomp_perm(SUCCESS_EXPECTED); + + printf("\tFork a grandchild.\n"); + grandchild = fork(); + if (grandchild < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (!grandchild) { + /* fork() succeeded. Now in the (grand)child. */ + printf("\tTest XCOMP_PERM at grandchild.\n"); + + /* + * Ensure that the grandchild inherited + * permission and a compatible sigaltstack: + */ + validate_xcomp_perm(SUCCESS_EXPECTED); + } else { + int status; + /* fork() succeeded. Now in the parent. */ + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test grandchild"); + } + + _exit(0); +} + +/* + * Save current register state and compare it to @xbuf1.' + * + * Returns false if @xbuf1 matches the registers. + * Returns true if @xbuf1 differs from the registers. + */ +static inline bool __validate_tiledata_regs(struct xsave_buffer *xbuf1) +{ + struct xsave_buffer *xbuf2; + int ret; + + xbuf2 = alloc_xbuf(); + if (!xbuf2) + fatal_error("failed to allocate XSAVE buffer\n"); + + xsave(xbuf2, XFEATURE_MASK_XTILEDATA); + ret = memcmp(&xbuf1->bytes[xtiledata.xbuf_offset], + &xbuf2->bytes[xtiledata.xbuf_offset], + xtiledata.size); + + free(xbuf2); + + if (ret == 0) + return false; + return true; +} + +static inline void validate_tiledata_regs_same(struct xsave_buffer *xbuf) +{ + int ret = __validate_tiledata_regs(xbuf); + + if (ret != 0) + fatal_error("TILEDATA registers changed"); +} + +static inline void validate_tiledata_regs_changed(struct xsave_buffer *xbuf) +{ + int ret = __validate_tiledata_regs(xbuf); + + if (ret == 0) + fatal_error("TILEDATA registers did not change"); +} + +/* tiledata inheritance test */ + +static void test_fork(void) +{ + pid_t child, grandchild; + + child = fork(); + if (child < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (child > 0) { + /* fork() succeeded. Now in the parent. */ + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test child"); + return; + } + /* fork() succeeded. Now in the child. */ + printf("[RUN]\tCheck tile data inheritance.\n\tBefore fork(), load tiledata\n"); + + load_rand_tiledata(stashed_xsave); + + grandchild = fork(); + if (grandchild < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (grandchild > 0) { + /* fork() succeeded. Still in the first child. */ + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test grand child"); + _exit(0); + } + /* fork() succeeded. Now in the (grand)child. */ + + /* + * TILEDATA registers are not preserved across fork(). + * Ensure that their value has changed: + */ + validate_tiledata_regs_changed(stashed_xsave); + + _exit(0); +} + +/* Context switching test */ + +static struct _ctxtswtest_cfg { + unsigned int iterations; + unsigned int num_threads; +} ctxtswtest_config; + +struct futex_info { + pthread_t thread; + int nr; + pthread_mutex_t mutex; + struct futex_info *next; +}; + +static void *check_tiledata(void *info) +{ + struct futex_info *finfo = (struct futex_info *)info; + struct xsave_buffer *xbuf; + int i; + + xbuf = alloc_xbuf(); + if (!xbuf) + fatal_error("unable to allocate XSAVE buffer"); + + /* + * Load random data into 'xbuf' and then restore + * it to the tile registers themselves. + */ + load_rand_tiledata(xbuf); + for (i = 0; i < ctxtswtest_config.iterations; i++) { + pthread_mutex_lock(&finfo->mutex); + + /* + * Ensure the register values have not + * diverged from those recorded in 'xbuf'. + */ + validate_tiledata_regs_same(xbuf); + + /* Load new, random values into xbuf and registers */ + load_rand_tiledata(xbuf); + + /* + * The last thread's last unlock will be for + * thread 0's mutex. However, thread 0 will + * have already exited the loop and the mutex + * will already be unlocked. + * + * Because this is not an ERRORCHECK mutex, + * that inconsistency will be silently ignored. + */ + pthread_mutex_unlock(&finfo->next->mutex); + } + + free(xbuf); + /* + * Return this thread's finfo, which is + * a unique value for this thread. + */ + return finfo; +} + +static int create_threads(int num, struct futex_info *finfo) +{ + int i; + + for (i = 0; i < num; i++) { + int next_nr; + + finfo[i].nr = i; + /* + * Thread 'i' will wait on this mutex to + * be unlocked. Lock it immediately after + * initialization: + */ + pthread_mutex_init(&finfo[i].mutex, NULL); + pthread_mutex_lock(&finfo[i].mutex); + + next_nr = (i + 1) % num; + finfo[i].next = &finfo[next_nr]; + + if (pthread_create(&finfo[i].thread, NULL, check_tiledata, &finfo[i])) + fatal_error("pthread_create()"); + } + return 0; +} + +static void affinitize_cpu0(void) +{ + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + fatal_error("sched_setaffinity to CPU 0"); +} + +static void test_context_switch(void) +{ + struct futex_info *finfo; + int i; + + /* Affinitize to one CPU to force context switches */ + affinitize_cpu0(); + + req_xtiledata_perm(); + + printf("[RUN]\tCheck tiledata context switches, %d iterations, %d threads.\n", + ctxtswtest_config.iterations, + ctxtswtest_config.num_threads); + + + finfo = malloc(sizeof(*finfo) * ctxtswtest_config.num_threads); + if (!finfo) + fatal_error("malloc()"); + + create_threads(ctxtswtest_config.num_threads, finfo); + + /* + * This thread wakes up thread 0 + * Thread 0 will wake up 1 + * Thread 1 will wake up 2 + * ... + * the last thread will wake up 0 + * + * ... this will repeat for the configured + * number of iterations. + */ + pthread_mutex_unlock(&finfo[0].mutex); + + /* Wait for all the threads to finish: */ + for (i = 0; i < ctxtswtest_config.num_threads; i++) { + void *thread_retval; + int rc; + + rc = pthread_join(finfo[i].thread, &thread_retval); + + if (rc) + fatal_error("pthread_join() failed for thread %d err: %d\n", + i, rc); + + if (thread_retval != &finfo[i]) + fatal_error("unexpected thread retval for thread %d: %p\n", + i, thread_retval); + + } + + printf("[OK]\tNo incorrect case was found.\n"); + + free(finfo); +} + +int main(void) +{ + /* Check hardware availability at first */ + check_cpuid_xsave(); + check_cpuid_xtiledata(); + + init_stashed_xsave(); + sethandler(SIGILL, handle_noperm, 0); + + test_dynamic_state(); + + /* Request permission for the following tests */ + req_xtiledata_perm(); + + test_fork(); + + ctxtswtest_config.iterations = 10; + ctxtswtest_config.num_threads = 5; + test_context_switch(); + + clearhandler(SIGILL); + free_stashed_xsave(); + + return 0; +} diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c index cec6f5a738e1..fa927ad16f8a 100644 --- a/tools/testing/vsock/vsock_diag_test.c +++ b/tools/testing/vsock/vsock_diag_test.c @@ -332,8 +332,6 @@ static void test_no_sockets(const struct test_opts *opts) read_vsock_stat(&sockets); check_no_sockets(&sockets); - - free_sock_stat(&sockets); } static void test_listen_socket_server(const struct test_opts *opts) |