diff options
Diffstat (limited to 'tools/testing/selftests')
71 files changed, 2619 insertions, 557 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1195bd85af38..017ce2a7ae36 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -6,6 +6,7 @@ TARGETS += breakpoints TARGETS += capabilities TARGETS += cgroup TARGETS += clone3 +TARGETS += core TARGETS += cpufreq TARGETS += cpu-hotplug TARGETS += drivers/dma-buf @@ -15,6 +16,7 @@ TARGETS += filesystems TARGETS += filesystems/binderfs TARGETS += filesystems/epoll TARGETS += firmware +TARGETS += fpu TARGETS += ftrace TARGETS += futex TARGETS += gpio diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index f7ee8fa377ad..6ccecbd39476 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -5,10 +5,60 @@ #include "test_btf_map_in_map.skel.h" +static int duration; + +static __u32 bpf_map_id(struct bpf_map *map) +{ + struct bpf_map_info info; + __u32 info_len = sizeof(info); + int err; + + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len); + if (err) + return 0; + return info.id; +} + +/* + * Trigger synchronize_rcu() in kernel. + * + * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu() + * if looking up an existing non-NULL element or updating the map with a valid + * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map, + * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then + * cleanup. At the end, at least one synchronize_rcu() would be called. + */ +static int kern_sync_rcu(void) +{ + int inner_map_fd, outer_map_fd, err, zero = 0; + + inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0); + if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno)) + return -1; + + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, + sizeof(int), inner_map_fd, 1, 0); + if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) { + close(inner_map_fd); + return -1; + } + + err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0); + if (err) + err = -errno; + CHECK(err, "outer_map_update", "failed %d\n", err); + close(inner_map_fd); + close(outer_map_fd); + return err; +} + void test_btf_map_in_map(void) { - int duration = 0, err, key = 0, val; - struct test_btf_map_in_map* skel; + int err, key = 0, val, i; + struct test_btf_map_in_map *skel; + int outer_arr_fd, outer_hash_fd; + int fd, map1_fd, map2_fd, map1_id, map2_id; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -18,32 +68,78 @@ void test_btf_map_in_map(void) if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) goto cleanup; + map1_fd = bpf_map__fd(skel->maps.inner_map1); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + outer_arr_fd = bpf_map__fd(skel->maps.outer_arr); + outer_hash_fd = bpf_map__fd(skel->maps.outer_hash); + /* inner1 = input, inner2 = input + 1 */ - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0); skel->bss->input = 1; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2); /* inner1 = input + 1, inner2 = input */ - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0); + bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0); skel->bss->input = 3; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3); + for (i = 0; i < 5; i++) { + val = i % 2 ? map1_fd : map2_fd; + err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + } + + map1_id = bpf_map_id(skel->maps.inner_map1); + map2_id = bpf_map_id(skel->maps.inner_map2); + CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); + CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); + + test_btf_map_in_map__destroy(skel); + skel = NULL; + + /* we need to either wait for or force synchronize_rcu(), before + * checking for "still exists" condition, otherwise map could still be + * resolvable by ID, causing false positives. + * + * Older kernels (5.8 and earlier) freed map only after two + * synchronize_rcu()s, so trigger two, to be entirely sure. + */ + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + + fd = bpf_map_get_fd_by_id(map1_id); + if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { + close(fd); + goto cleanup; + } + fd = bpf_map_get_fd_by_id(map2_id); + if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { + close(fd); + goto cleanup; + } + cleanup: test_btf_map_in_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 8294ae3ffb3c..43c9cda199b8 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -318,6 +318,9 @@ class DebugfsDir: continue if os.path.isfile(p): + # We need to init trap_flow_action_cookie before read it + if f == "trap_flow_action_cookie": + cmd('echo deadbeef > %s/%s' % (path, f)) _, out = cmd('cat %s/%s' % (path, f)) dfs[f] = out.strip() elif os.path.isdir(p): diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 99f8f582c02b..c5e805980409 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -112,6 +112,7 @@ "perfevent for cgroup sockopt", .insns = { __PERF_EVENT_INSNS__ }, .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .fixup_map_event_output = { 4 }, .result = ACCEPT, .retval = 1, diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index b3ead29c6089..2cf6f10ab7c4 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -47,7 +47,7 @@ void child(int cpu) _exit(0); } -bool run_test(int cpu) +int run_test(int cpu) { int status; pid_t pid = fork(); @@ -55,7 +55,7 @@ bool run_test(int cpu) if (pid < 0) { ksft_print_msg("fork() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (pid == 0) child(cpu); @@ -63,67 +63,68 @@ bool run_test(int cpu) wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFSTOPPED(status)) { ksft_print_msg("child did not stop: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WSTOPSIG(status) != SIGSTOP) { ksft_print_msg("child did not stop with SIGSTOP: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (ptrace(PTRACE_SINGLESTEP, pid, NULL, NULL) < 0) { if (errno == EIO) { - ksft_exit_skip( + ksft_print_msg( "ptrace(PTRACE_SINGLESTEP) not supported on this architecture: %s\n", strerror(errno)); + return KSFT_SKIP; } ksft_print_msg("ptrace(PTRACE_SINGLESTEP) failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: $s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WIFEXITED(status)) { ksft_print_msg("child did not single-step: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFSTOPPED(status)) { ksft_print_msg("child did not stop: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WSTOPSIG(status) != SIGTRAP) { ksft_print_msg("child did not stop with SIGTRAP: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) { ksft_print_msg("ptrace(PTRACE_CONT) failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFEXITED(status)) { ksft_print_msg("child did not exit after PTRACE_CONT: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } - return true; + return KSFT_PASS; } void suspend(void) @@ -183,32 +184,38 @@ int main(int argc, char **argv) } } + err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus); + if (err < 0) + ksft_exit_fail_msg("sched_getaffinity() failed\n"); + for (cpu = 0; cpu < CPU_SETSIZE; cpu++) { if (!CPU_ISSET(cpu, &available_cpus)) continue; tests++; } - ksft_set_plan(tests); if (do_suspend) suspend(); - err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus); - if (err < 0) - ksft_exit_fail_msg("sched_getaffinity() failed\n"); - + ksft_set_plan(tests); for (cpu = 0; cpu < CPU_SETSIZE; cpu++) { - bool test_success; + int test_success; if (!CPU_ISSET(cpu, &available_cpus)) continue; test_success = run_test(cpu); - if (test_success) { + switch (test_success) { + case KSFT_PASS: ksft_test_result_pass("CPU %d\n", cpu); - } else { + break; + case KSFT_SKIP: + ksft_test_result_skip("CPU %d\n", cpu); + break; + case KSFT_FAIL: ksft_test_result_fail("CPU %d\n", cpu); succeeded = false; + break; } } diff --git a/tools/testing/selftests/clone3/.gitignore b/tools/testing/selftests/clone3/.gitignore index a81085742d40..83c0f6246055 100644 --- a/tools/testing/selftests/clone3/.gitignore +++ b/tools/testing/selftests/clone3/.gitignore @@ -2,3 +2,4 @@ clone3 clone3_clear_sighand clone3_set_tid +clone3_cap_checkpoint_restore diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile index cf976c732906..ef7564cb7abe 100644 --- a/tools/testing/selftests/clone3/Makefile +++ b/tools/testing/selftests/clone3/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g -I../../../../usr/include/ +LDLIBS += -lcap -TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid +TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid \ + clone3_cap_checkpoint_restore include ../lib.mk diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index f14c269a5a18..b7e6dec36173 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -131,9 +131,9 @@ int main(int argc, char *argv[]) uid_t uid = getuid(); - test_clone3_supported(); ksft_print_header(); ksft_set_plan(17); + test_clone3_supported(); /* Just a simple clone3() should return 0.*/ test_clone3(0, 0, 0, CLONE3_ARGS_NO_TEST); diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c new file mode 100644 index 000000000000..9562425aa0a9 --- /dev/null +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Based on Christian Brauner's clone3() example. + * These tests are assuming to be running in the host's + * PID namespace. + */ + +/* capabilities related code based on selftests/bpf/test_verifier.c */ + +#define _GNU_SOURCE +#include <errno.h> +#include <linux/types.h> +#include <linux/sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <sys/capability.h> +#include <sys/prctl.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/un.h> +#include <sys/wait.h> +#include <unistd.h> +#include <sched.h> + +#include "../kselftest_harness.h" +#include "clone3_selftests.h" + +#ifndef MAX_PID_NS_LEVEL +#define MAX_PID_NS_LEVEL 32 +#endif + +static void child_exit(int ret) +{ + fflush(stdout); + fflush(stderr); + _exit(ret); +} + +static int call_clone3_set_tid(struct __test_metadata *_metadata, + pid_t *set_tid, size_t set_tid_size) +{ + int status; + pid_t pid = -1; + + struct clone_args args = { + .exit_signal = SIGCHLD, + .set_tid = ptr_to_u64(set_tid), + .set_tid_size = set_tid_size, + }; + + pid = sys_clone3(&args, sizeof(struct clone_args)); + if (pid < 0) { + TH_LOG("%s - Failed to create new process", strerror(errno)); + return -errno; + } + + if (pid == 0) { + int ret; + char tmp = 0; + + TH_LOG("I am the child, my PID is %d (expected %d)", getpid(), set_tid[0]); + + if (set_tid[0] != getpid()) + child_exit(EXIT_FAILURE); + child_exit(EXIT_SUCCESS); + } + + TH_LOG("I am the parent (%d). My child's pid is %d", getpid(), pid); + + if (waitpid(pid, &status, 0) < 0) { + TH_LOG("Child returned %s", strerror(errno)); + return -errno; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static int test_clone3_set_tid(struct __test_metadata *_metadata, + pid_t *set_tid, size_t set_tid_size) +{ + int ret; + + TH_LOG("[%d] Trying clone3() with CLONE_SET_TID to %d", getpid(), set_tid[0]); + ret = call_clone3_set_tid(_metadata, set_tid, set_tid_size); + TH_LOG("[%d] clone3() with CLONE_SET_TID %d says:%d", getpid(), set_tid[0], ret); + return ret; +} + +struct libcap { + struct __user_cap_header_struct hdr; + struct __user_cap_data_struct data[2]; +}; + +static int set_capability(void) +{ + cap_value_t cap_values[] = { CAP_SETUID, CAP_SETGID }; + struct libcap *cap; + int ret = -1; + cap_t caps; + + caps = cap_get_proc(); + if (!caps) { + perror("cap_get_proc"); + return -1; + } + + /* Drop all capabilities */ + if (cap_clear(caps)) { + perror("cap_clear"); + goto out; + } + + cap_set_flag(caps, CAP_EFFECTIVE, 2, cap_values, CAP_SET); + cap_set_flag(caps, CAP_PERMITTED, 2, cap_values, CAP_SET); + + cap = (struct libcap *) caps; + + /* 40 -> CAP_CHECKPOINT_RESTORE */ + cap->data[1].effective |= 1 << (40 - 32); + cap->data[1].permitted |= 1 << (40 - 32); + + if (cap_set_proc(caps)) { + perror("cap_set_proc"); + goto out; + } + ret = 0; +out: + if (cap_free(caps)) + perror("cap_free"); + return ret; +} + +TEST(clone3_cap_checkpoint_restore) +{ + pid_t pid; + int status; + int ret = 0; + pid_t set_tid[1]; + + test_clone3_supported(); + + EXPECT_EQ(getuid(), 0) + XFAIL(return, "Skipping all tests as non-root\n"); + + memset(&set_tid, 0, sizeof(set_tid)); + + /* Find the current active PID */ + pid = fork(); + if (pid == 0) { + TH_LOG("Child has PID %d", getpid()); + child_exit(EXIT_SUCCESS); + } + ASSERT_GT(waitpid(pid, &status, 0), 0) + TH_LOG("Waiting for child %d failed", pid); + + /* After the child has finished, its PID should be free. */ + set_tid[0] = pid; + + ASSERT_EQ(set_capability(), 0) + TH_LOG("Could not set CAP_CHECKPOINT_RESTORE"); + + ASSERT_EQ(prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0), 0); + + EXPECT_EQ(setgid(65534), 0) + TH_LOG("Failed to setgid(65534)"); + ASSERT_EQ(setuid(65534), 0); + + set_tid[0] = pid; + /* This would fail without CAP_CHECKPOINT_RESTORE */ + ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), -EPERM); + ASSERT_EQ(set_capability(), 0) + TH_LOG("Could not set CAP_CHECKPOINT_RESTORE"); + /* This should work as we have CAP_CHECKPOINT_RESTORE as non-root */ + ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c index 9e1af8aa7698..db5fc9c5edcf 100644 --- a/tools/testing/selftests/clone3/clone3_clear_sighand.c +++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c @@ -119,9 +119,8 @@ static void test_clone3_clear_sighand(void) int main(int argc, char **argv) { ksft_print_header(); - test_clone3_supported(); - ksft_set_plan(1); + test_clone3_supported(); test_clone3_clear_sighand(); diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c index 25beb22f35b5..5831c1082d6d 100644 --- a/tools/testing/selftests/clone3/clone3_set_tid.c +++ b/tools/testing/selftests/clone3/clone3_set_tid.c @@ -157,8 +157,8 @@ int main(int argc, char *argv[]) pid_t set_tid[MAX_PID_NS_LEVEL * 2]; ksft_print_header(); - test_clone3_supported(); ksft_set_plan(29); + test_clone3_supported(); if (pipe(pipe_1) < 0 || pipe(pipe_2) < 0) ksft_exit_fail_msg("pipe() failed\n"); diff --git a/tools/testing/selftests/core/.gitignore b/tools/testing/selftests/core/.gitignore new file mode 100644 index 000000000000..6e6712ce5817 --- /dev/null +++ b/tools/testing/selftests/core/.gitignore @@ -0,0 +1 @@ +close_range_test diff --git a/tools/testing/selftests/core/Makefile b/tools/testing/selftests/core/Makefile new file mode 100644 index 000000000000..f6f2d6f473c6 --- /dev/null +++ b/tools/testing/selftests/core/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +CFLAGS += -g -I../../../../usr/include/ + +TEST_GEN_PROGS := close_range_test + +include ../lib.mk + diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c new file mode 100644 index 000000000000..c99b98b0d461 --- /dev/null +++ b/tools/testing/selftests/core/close_range_test.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/kernel.h> +#include <limits.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <unistd.h> + +#include "../kselftest_harness.h" +#include "../clone3/clone3_selftests.h" + +#ifndef __NR_close_range +#define __NR_close_range -1 +#endif + +#ifndef CLOSE_RANGE_UNSHARE +#define CLOSE_RANGE_UNSHARE (1U << 1) +#endif + +static inline int sys_close_range(unsigned int fd, unsigned int max_fd, + unsigned int flags) +{ + return syscall(__NR_close_range, fd, max_fd, flags); +} + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +TEST(close_range) +{ + int i, ret; + int open_fds[101]; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) { + if (errno == ENOSYS) + XFAIL(return, "close_range() syscall not supported"); + } + + EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0)); + + for (i = 0; i <= 50; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + for (i = 51; i <= 100; i++) + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + /* create a couple of gaps */ + close(57); + close(78); + close(81); + close(82); + close(84); + close(90); + + EXPECT_EQ(0, sys_close_range(open_fds[51], open_fds[92], 0)); + + for (i = 51; i <= 92; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + for (i = 93; i <= 100; i++) + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + /* test that the kernel caps and still closes all fds */ + EXPECT_EQ(0, sys_close_range(open_fds[93], open_fds[99], 0)); + + for (i = 93; i <= 99; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + EXPECT_EQ(0, sys_close_range(open_fds[100], open_fds[100], 0)); + + EXPECT_EQ(-1, fcntl(open_fds[100], F_GETFL)); +} + +TEST(close_range_unshare) +{ + int i, ret, status; + pid_t pid; + int open_fds[101]; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = sys_close_range(open_fds[0], open_fds[50], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 0; i <= 50; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + for (i = 51; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) == -1) + exit(EXIT_FAILURE); + + /* create a couple of gaps */ + close(57); + close(78); + close(81); + close(82); + close(84); + close(90); + + ret = sys_close_range(open_fds[51], open_fds[92], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 51; i <= 92; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + for (i = 93; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) == -1) + exit(EXIT_FAILURE); + + /* test that the kernel caps and still closes all fds */ + ret = sys_close_range(open_fds[93], open_fds[99], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 93; i <= 99; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + if (fcntl(open_fds[100], F_GETFL) == -1) + exit(EXIT_FAILURE); + + ret = sys_close_range(open_fds[100], open_fds[100], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + if (fcntl(open_fds[100], F_GETFL) != -1) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST(close_range_unshare_capped) +{ + int i, ret, status; + pid_t pid; + int open_fds[101]; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = sys_close_range(open_fds[0], UINT_MAX, + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 0; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 8a6b507e34a8..1d27f52c61e6 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -21,7 +21,6 @@ #include <linux/android/binder.h> #include <linux/android/binderfs.h> -#include "../../kselftest.h" #include "../../kselftest_harness.h" #define DEFAULT_THREADS 4 @@ -37,37 +36,26 @@ fd = -EBADF; \ } -#define log_exit(format, ...) \ - ({ \ - fprintf(stderr, format "\n", ##__VA_ARGS__); \ - exit(EXIT_FAILURE); \ - }) - -static void change_mountns(void) +static void change_mountns(struct __test_metadata *_metadata) { int ret; ret = unshare(CLONE_NEWNS); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n", - strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unshare mount namespace", + strerror(errno)); + } ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to mount / as private\n", - strerror(errno)); -} - -static void rmdir_protect_errno(const char *dir) -{ - int saved_errno = errno; - (void)rmdir(dir); - errno = saved_errno; + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to mount / as private", + strerror(errno)); + } } -static int __do_binderfs_test(void) +static int __do_binderfs_test(struct __test_metadata *_metadata) { - int fd, ret, saved_errno; + int fd, ret, saved_errno, result = 1; size_t len; ssize_t wret; struct binderfs_device device = { 0 }; @@ -75,113 +63,107 @@ static int __do_binderfs_test(void) char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX", device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME]; - change_mountns(); + change_mountns(_metadata); - if (!mkdtemp(binderfs_mntpt)) - ksft_exit_fail_msg( - "%s - Failed to create binderfs mountpoint\n", + EXPECT_NE(mkdtemp(binderfs_mntpt), NULL) { + TH_LOG("%s - Failed to create binderfs mountpoint", strerror(errno)); + goto out; + } ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); - if (ret < 0) { - if (errno != ENODEV) - ksft_exit_fail_msg("%s - Failed to mount binderfs\n", - strerror(errno)); - - rmdir_protect_errno(binderfs_mntpt); - return 1; + EXPECT_EQ(ret, 0) { + if (errno == ENODEV) + XFAIL(goto out, "binderfs missing"); + TH_LOG("%s - Failed to mount binderfs", strerror(errno)); + goto rmdir; } - /* binderfs mount test passed */ - ksft_inc_pass_cnt(); + /* success: binderfs mounted */ memcpy(device.name, "my-binder", strlen("my-binder")); snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); fd = open(device_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) - ksft_exit_fail_msg( - "%s - Failed to open binder-control device\n", + EXPECT_GE(fd, 0) { + TH_LOG("%s - Failed to open binder-control device", strerror(errno)); + goto umount; + } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to allocate new binder device\n", + EXPECT_GE(ret, 0) { + TH_LOG("%s - Failed to allocate new binder device", strerror(errno)); + goto umount; } - ksft_print_msg( - "Allocated new binder device with major %d, minor %d, and name %s\n", + TH_LOG("Allocated new binder device with major %d, minor %d, and name %s", device.major, device.minor, device.name); - /* binder device allocation test passed */ - ksft_inc_pass_cnt(); + /* success: binder device allocation */ snprintf(device_path, sizeof(device_path), "%s/my-binder", binderfs_mntpt); fd = open(device_path, O_CLOEXEC | O_RDONLY); - if (fd < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("%s - Failed to open my-binder device\n", - strerror(errno)); + EXPECT_GE(fd, 0) { + TH_LOG("%s - Failed to open my-binder device", + strerror(errno)); + goto umount; } ret = ioctl(fd, BINDER_VERSION, &version); saved_errno = errno; close(fd); errno = saved_errno; - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to open perform BINDER_VERSION request\n", + EXPECT_GE(ret, 0) { + TH_LOG("%s - Failed to open perform BINDER_VERSION request", strerror(errno)); + goto umount; } - ksft_print_msg("Detected binder version: %d\n", - version.protocol_version); + TH_LOG("Detected binder version: %d", version.protocol_version); - /* binder transaction with binderfs binder device passed */ - ksft_inc_pass_cnt(); + /* success: binder transaction with binderfs binder device */ ret = unlink(device_path); - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("%s - Failed to delete binder device\n", - strerror(errno)); + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to delete binder device", + strerror(errno)); + goto umount; } - /* binder device removal passed */ - ksft_inc_pass_cnt(); + /* success: binder device removal */ snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); ret = unlink(device_path); - if (!ret) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("Managed to delete binder-control device\n"); - } else if (errno != EPERM) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to delete binder-control device but exited with unexpected error code\n", + EXPECT_NE(ret, 0) { + TH_LOG("Managed to delete binder-control device"); + goto umount; + } + EXPECT_EQ(errno, EPERM) { + TH_LOG("%s - Failed to delete binder-control device but exited with unexpected error code", strerror(errno)); + goto umount; } - /* binder-control device removal failed as expected */ - ksft_inc_xfail_cnt(); + /* success: binder-control device removal failed as expected */ + result = 0; -on_error: +umount: ret = umount2(binderfs_mntpt, MNT_DETACH); - rmdir_protect_errno(binderfs_mntpt); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unmount binderfs\n", - strerror(errno)); - - /* binderfs unmount test passed */ - ksft_inc_pass_cnt(); - return 0; + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to unmount binderfs", strerror(errno)); + } +rmdir: + ret = rmdir(binderfs_mntpt); + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to rmdir binderfs mount", strerror(errno)); + } +out: + return result; } static int wait_for_pid(pid_t pid) @@ -291,7 +273,7 @@ static int write_id_mapping(enum idmap_type type, pid_t pid, const char *buf, return 0; } -static void change_userns(int syncfds[2]) +static void change_userns(struct __test_metadata *_metadata, int syncfds[2]) { int ret; char buf; @@ -299,25 +281,29 @@ static void change_userns(int syncfds[2]) close_prot_errno_disarm(syncfds[1]); ret = unshare(CLONE_NEWUSER); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unshare user namespace\n", - strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unshare user namespace", + strerror(errno)); + } ret = write_nointr(syncfds[0], "1", 1); - if (ret != 1) - ksft_exit_fail_msg("write_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("write_nointr() failed"); + } ret = read_nointr(syncfds[0], &buf, 1); - if (ret != 1) - ksft_exit_fail_msg("read_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("read_nointr() failed"); + } close_prot_errno_disarm(syncfds[0]); - if (setid_userns_root()) - ksft_exit_fail_msg("setid_userns_root() failed"); + ASSERT_EQ(setid_userns_root(), 0) { + TH_LOG("setid_userns_root() failed"); + } } -static void change_idmaps(int syncfds[2], pid_t pid) +static void change_idmaps(struct __test_metadata *_metadata, int syncfds[2], pid_t pid) { int ret; char buf; @@ -326,35 +312,42 @@ static void change_idmaps(int syncfds[2], pid_t pid) close_prot_errno_disarm(syncfds[0]); ret = read_nointr(syncfds[1], &buf, 1); - if (ret != 1) - ksft_exit_fail_msg("read_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("read_nointr() failed"); + } snprintf(id_map, sizeof(id_map), "0 %d 1\n", getuid()); ret = write_id_mapping(UID_MAP, pid, id_map, strlen(id_map)); - if (ret) - ksft_exit_fail_msg("write_id_mapping(UID_MAP) failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("write_id_mapping(UID_MAP) failed"); + } snprintf(id_map, sizeof(id_map), "0 %d 1\n", getgid()); ret = write_id_mapping(GID_MAP, pid, id_map, strlen(id_map)); - if (ret) - ksft_exit_fail_msg("write_id_mapping(GID_MAP) failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("write_id_mapping(GID_MAP) failed"); + } ret = write_nointr(syncfds[1], "1", 1); - if (ret != 1) - ksft_exit_fail_msg("write_nointr() failed"); + ASSERT_EQ(ret, 1) { + TH_LOG("write_nointr() failed"); + } close_prot_errno_disarm(syncfds[1]); } +struct __test_metadata *_thread_metadata; static void *binder_version_thread(void *data) { + struct __test_metadata *_metadata = _thread_metadata; int fd = PTR_TO_INT(data); struct binder_version version = { 0 }; int ret; ret = ioctl(fd, BINDER_VERSION, &version); if (ret < 0) - ksft_print_msg("%s - Failed to open perform BINDER_VERSION request\n", strerror(errno)); + TH_LOG("%s - Failed to open perform BINDER_VERSION request\n", + strerror(errno)); pthread_exit(data); } @@ -377,68 +370,79 @@ TEST(binderfs_stress) device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME]; ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to create socket pair", strerror(errno)); + } pid = fork(); - if (pid < 0) { + ASSERT_GE(pid, 0) { + TH_LOG("%s - Failed to fork", strerror(errno)); close_prot_errno_disarm(syncfds[0]); close_prot_errno_disarm(syncfds[1]); - ksft_exit_fail_msg("%s - Failed to fork", strerror(errno)); } if (pid == 0) { int i, j, k, nthreads; pthread_attr_t attr; pthread_t threads[DEFAULT_THREADS]; - change_userns(syncfds); - change_mountns(); + change_userns(_metadata, syncfds); + change_mountns(_metadata); - if (!mkdtemp(binderfs_mntpt)) - log_exit("%s - Failed to create binderfs mountpoint\n", - strerror(errno)); + ASSERT_NE(mkdtemp(binderfs_mntpt), NULL) { + TH_LOG("%s - Failed to create binderfs mountpoint", + strerror(errno)); + } ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); - if (ret < 0) - log_exit("%s - Failed to mount binderfs\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to mount binderfs", strerror(errno)); + } for (int i = 0; i < ARRAY_SIZE(fds); i++) { snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); fd = open(device_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) - log_exit("%s - Failed to open binder-control device\n", strerror(errno)); + ASSERT_GE(fd, 0) { + TH_LOG("%s - Failed to open binder-control device", + strerror(errno)); + } memset(&device, 0, sizeof(device)); snprintf(device.name, sizeof(device.name), "%d", i); ret = ioctl(fd, BINDER_CTL_ADD, &device); close_prot_errno_disarm(fd); - if (ret < 0) - log_exit("%s - Failed to allocate new binder device\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to allocate new binder device", + strerror(errno)); + } snprintf(device_path, sizeof(device_path), "%s/%d", binderfs_mntpt, i); fds[i] = open(device_path, O_RDONLY | O_CLOEXEC); - if (fds[i] < 0) - log_exit("%s - Failed to open binder device\n", strerror(errno)); + ASSERT_GE(fds[i], 0) { + TH_LOG("%s - Failed to open binder device", strerror(errno)); + } } ret = umount2(binderfs_mntpt, MNT_DETACH); - rmdir_protect_errno(binderfs_mntpt); - if (ret < 0) - log_exit("%s - Failed to unmount binderfs\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unmount binderfs", strerror(errno)); + rmdir(binderfs_mntpt); + } nthreads = get_nprocs_conf(); if (nthreads > DEFAULT_THREADS) nthreads = DEFAULT_THREADS; + _thread_metadata = _metadata; pthread_attr_init(&attr); for (k = 0; k < ARRAY_SIZE(fds); k++) { for (i = 0; i < nthreads; i++) { ret = pthread_create(&threads[i], &attr, binder_version_thread, INT_TO_PTR(fds[k])); if (ret) { - ksft_print_msg("%s - Failed to create thread %d\n", strerror(errno), i); + TH_LOG("%s - Failed to create thread %d", + strerror(errno), i); break; } } @@ -448,7 +452,8 @@ TEST(binderfs_stress) ret = pthread_join(threads[j], &fdptr); if (ret) - ksft_print_msg("%s - Failed to join thread %d for fd %d\n", strerror(errno), j, PTR_TO_INT(fdptr)); + TH_LOG("%s - Failed to join thread %d for fd %d", + strerror(errno), j, PTR_TO_INT(fdptr)); } } pthread_attr_destroy(&attr); @@ -459,11 +464,12 @@ TEST(binderfs_stress) exit(EXIT_SUCCESS); } - change_idmaps(syncfds, pid); + change_idmaps(_metadata, syncfds, pid); ret = wait_for_pid(pid); - if (ret) - ksft_exit_fail_msg("wait_for_pid() failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("wait_for_pid() failed"); + } } TEST(binderfs_test_privileged) @@ -471,7 +477,7 @@ TEST(binderfs_test_privileged) if (geteuid() != 0) XFAIL(return, "Tests are not run as root. Skipping privileged tests"); - if (__do_binderfs_test() == 1) + if (__do_binderfs_test(_metadata)) XFAIL(return, "The Android binderfs filesystem is not available"); } @@ -482,31 +488,33 @@ TEST(binderfs_test_unprivileged) pid_t pid; ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to create socket pair", strerror(errno)); + } pid = fork(); - if (pid < 0) { + ASSERT_GE(pid, 0) { close_prot_errno_disarm(syncfds[0]); close_prot_errno_disarm(syncfds[1]); - ksft_exit_fail_msg("%s - Failed to fork", strerror(errno)); + TH_LOG("%s - Failed to fork", strerror(errno)); } if (pid == 0) { - change_userns(syncfds); - if (__do_binderfs_test() == 1) + change_userns(_metadata, syncfds); + if (__do_binderfs_test(_metadata)) exit(2); exit(EXIT_SUCCESS); } - change_idmaps(syncfds, pid); + change_idmaps(_metadata, syncfds, pid); ret = wait_for_pid(pid); if (ret) { if (ret == 2) XFAIL(return, "The Android binderfs filesystem is not available"); - else - ksft_exit_fail_msg("wait_for_pid() failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("wait_for_pid() failed"); + } } } diff --git a/tools/testing/selftests/firmware/settings b/tools/testing/selftests/firmware/settings new file mode 100644 index 000000000000..085e664ee093 --- /dev/null +++ b/tools/testing/selftests/firmware/settings @@ -0,0 +1,8 @@ +# The async firmware timeout is set to 1 second (but ends up being effectively +# 2 seconds). There are 3 test configs, each done with and without firmware +# present, each with 2 "nowait" functions tested 5 times. Expected time for a +# normal execution should be 2 * 3 * 2 * 2 * 5 = 120 seconds for those alone. +# Additionally, fw_fallback may take 5 seconds for internal timeouts in each +# of the 3 configs, so at least another 15 seconds are needed. Add another +# 10 seconds for each testing config: 120 + 15 + 30 +timeout=165 diff --git a/tools/testing/selftests/fpu/.gitignore b/tools/testing/selftests/fpu/.gitignore new file mode 100644 index 000000000000..d6d12ac1d9c3 --- /dev/null +++ b/tools/testing/selftests/fpu/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0+ +test_fpu diff --git a/tools/testing/selftests/fpu/Makefile b/tools/testing/selftests/fpu/Makefile new file mode 100644 index 000000000000..ea62c176ede7 --- /dev/null +++ b/tools/testing/selftests/fpu/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0+ + +LDLIBS := -lm + +TEST_GEN_PROGS := test_fpu + +TEST_PROGS := run_test_fpu.sh + +include ../lib.mk diff --git a/tools/testing/selftests/fpu/run_test_fpu.sh b/tools/testing/selftests/fpu/run_test_fpu.sh new file mode 100755 index 000000000000..d77be93ec139 --- /dev/null +++ b/tools/testing/selftests/fpu/run_test_fpu.sh @@ -0,0 +1,46 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Load kernel module for FPU tests + +uid=$(id -u) +if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit 1 +fi + +if ! which modprobe > /dev/null 2>&1; then + echo "$0: You need modprobe installed" + exit 4 +fi + +if ! modinfo test_fpu > /dev/null 2>&1; then + echo "$0: You must have the following enabled in your kernel:" + echo "CONFIG_TEST_FPU=m" + exit 4 +fi + +NR_CPUS=$(getconf _NPROCESSORS_ONLN) +if [ ! $NR_CPUS ]; then + NR_CPUS=1 +fi + +modprobe test_fpu + +if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then + mount -t debugfs none /sys/kernel/debug + + if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then + echo "$0: Error mounting debugfs" + exit 4 + fi +fi + +echo "Running 1000 iterations on all CPUs... " +for i in $(seq 1 1000); do + for c in $(seq 1 $NR_CPUS); do + ./test_fpu & + done +done + +rmmod test_fpu diff --git a/tools/testing/selftests/fpu/test_fpu.c b/tools/testing/selftests/fpu/test_fpu.c new file mode 100644 index 000000000000..200238522a9d --- /dev/null +++ b/tools/testing/selftests/fpu/test_fpu.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* This testcase operates with the test_fpu kernel driver. + * It modifies the FPU control register in user mode and calls the kernel + * module to perform floating point operations in the kernel. The control + * register value should be independent between kernel and user mode. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <fenv.h> +#include <unistd.h> +#include <fcntl.h> + +const char *test_fpu_path = "/sys/kernel/debug/selftest_helpers/test_fpu"; + +int main(void) +{ + char dummy[1]; + int fd = open(test_fpu_path, O_RDONLY); + + if (fd < 0) { + printf("[SKIP]\tcan't access %s: %s\n", + test_fpu_path, strerror(errno)); + return 0; + } + + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with default rounding mode failed\n"); + return 1; + } + + fesetround(FE_DOWNWARD); + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with downward rounding mode failed\n"); + return 2; + } + if (fegetround() != FE_DOWNWARD) { + printf("[FAIL]\tusermode rounding mode clobbered\n"); + return 3; + } + + /* Note: the tests up to this point are quite safe and will only return + * an error. But the exception mask setting can cause misbehaving kernel + * to crash. + */ + feclearexcept(FE_ALL_EXCEPT); + feenableexcept(FE_ALL_EXCEPT); + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with fpu exceptions unmasked failed\n"); + return 4; + } + if (fegetexcept() != FE_ALL_EXCEPT) { + printf("[FAIL]\tusermode fpu exception mask clobbered\n"); + return 5; + } + + printf("[OK]\ttest_fpu\n"); + return 0; +} diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index c82aa77958e5..ea2147248ebe 100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -130,7 +130,7 @@ test_reqs() if [[ $KMOD_VERSION -le 19 ]]; then echo "$0: You need at least kmod 20" >&2 echo "kmod <= 19 is buggy, for details see:" >&2 - echo "http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2 + echo "https://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2 exit $ksft_skip fi diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 862eee734553..8d50483fe204 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -1,11 +1,43 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * kselftest.h: kselftest framework return codes to include from - * selftests. + * kselftest.h: low-level kselftest framework to include from + * selftest programs. When possible, please use + * kselftest_harness.h instead. * * Copyright (c) 2014 Shuah Khan <shuahkh@osg.samsung.com> * Copyright (c) 2014 Samsung Electronics Co., Ltd. * + * Using this API consists of first counting how many tests your code + * has to run, and then starting up the reporting: + * + * ksft_print_header(); + * ksft_set_plan(total_number_of_tests); + * + * For each test, report any progress, debugging, etc with: + * + * ksft_print_msg(fmt, ...); + * + * and finally report the pass/fail/skip/xfail state of the test with one of: + * + * ksft_test_result(condition, fmt, ...); + * ksft_test_result_pass(fmt, ...); + * ksft_test_result_fail(fmt, ...); + * ksft_test_result_skip(fmt, ...); + * ksft_test_result_xfail(fmt, ...); + * ksft_test_result_error(fmt, ...); + * + * When all tests are finished, clean up and exit the program with one of: + * + * ksft_exit(condition); + * ksft_exit_pass(); + * ksft_exit_fail(); + * + * If the program wants to report details on why the entire program has + * failed, it can instead exit with a message (this is usually done when + * the program is aborting before finishing all tests): + * + * ksft_exit_fail_msg(fmt, ...); + * */ #ifndef __KSELFTEST_H #define __KSELFTEST_H @@ -74,7 +106,7 @@ static inline void ksft_print_cnts(void) if (ksft_plan != ksft_test_num()) printf("# Planned tests != run tests (%u != %u)\n", ksft_plan, ksft_test_num()); - printf("# Pass %d Fail %d Xfail %d Xpass %d Skip %d Error %d\n", + printf("# Totals: pass:%d fail:%d xfail:%d xpass:%d skip:%d error:%d\n", ksft_cnt.ksft_pass, ksft_cnt.ksft_fail, ksft_cnt.ksft_xfail, ksft_cnt.ksft_xpass, ksft_cnt.ksft_xskip, ksft_cnt.ksft_error); @@ -120,6 +152,32 @@ static inline void ksft_test_result_fail(const char *msg, ...) va_end(args); } +/** + * ksft_test_result() - Report test success based on truth of condition + * + * @condition: if true, report test success, otherwise failure. + */ +#define ksft_test_result(condition, fmt, ...) do { \ + if (!!(condition)) \ + ksft_test_result_pass(fmt, ##__VA_ARGS__);\ + else \ + ksft_test_result_fail(fmt, ##__VA_ARGS__);\ + } while (0) + +static inline void ksft_test_result_xfail(const char *msg, ...) +{ + int saved_errno = errno; + va_list args; + + ksft_cnt.ksft_xfail++; + + va_start(args, msg); + printf("ok %d # XFAIL ", ksft_test_num()); + errno = saved_errno; + vprintf(msg, args); + va_end(args); +} + static inline void ksft_test_result_skip(const char *msg, ...) { int saved_errno = errno; @@ -128,12 +186,13 @@ static inline void ksft_test_result_skip(const char *msg, ...) ksft_cnt.ksft_xskip++; va_start(args, msg); - printf("not ok %d # SKIP ", ksft_test_num()); + printf("ok %d # SKIP ", ksft_test_num()); errno = saved_errno; vprintf(msg, args); va_end(args); } +/* TODO: how does "error" differ from "fail" or "skip"? */ static inline void ksft_test_result_error(const char *msg, ...) { int saved_errno = errno; @@ -156,11 +215,22 @@ static inline int ksft_exit_pass(void) static inline int ksft_exit_fail(void) { - printf("Bail out!\n"); ksft_print_cnts(); exit(KSFT_FAIL); } +/** + * ksft_exit() - Exit selftest based on truth of condition + * + * @condition: if true, exit self test with success, otherwise fail. + */ +#define ksft_exit(condition) do { \ + if (!!(condition)) \ + ksft_exit_pass(); \ + else \ + ksft_exit_fail(); \ + } while (0) + static inline int ksft_exit_fail_msg(const char *msg, ...) { int saved_errno = errno; @@ -190,18 +260,30 @@ static inline int ksft_exit_xpass(void) static inline int ksft_exit_skip(const char *msg, ...) { - if (msg) { - int saved_errno = errno; - va_list args; + int saved_errno = errno; + va_list args; + + va_start(args, msg); - va_start(args, msg); - printf("not ok %d # SKIP ", 1 + ksft_test_num()); + /* + * FIXME: several tests misuse ksft_exit_skip so produce + * something sensible if some tests have already been run + * or a plan has been printed. Those tests should use + * ksft_test_result_skip or ksft_exit_fail_msg instead. + */ + if (ksft_plan || ksft_test_num()) { + ksft_cnt.ksft_xskip++; + printf("ok %d # SKIP ", 1 + ksft_test_num()); + } else { + printf("1..0 # SKIP "); + } + if (msg) { errno = saved_errno; vprintf(msg, args); va_end(args); - } else { - ksft_print_cnts(); } + if (ksft_test_num()) + ksft_print_cnts(); exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 676b3a8b114d..cc9c846585f0 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -53,6 +53,10 @@ run_one() settings="$BASE_DIR/$DIR/settings" if [ -r "$settings" ] ; then while read line ; do + # Skip comments. + if echo "$line" | grep -q '^#'; then + continue + fi field=$(echo "$line" | cut -d= -f1) value=$(echo "$line" | cut -d= -f2-) eval "kselftest_$field"="$value" @@ -77,10 +81,10 @@ run_one() echo "ok $test_num $TEST_HDR_MSG") || (rc=$?; \ if [ $rc -eq $skip_rc ]; then \ - echo "not ok $test_num $TEST_HDR_MSG # SKIP" + echo "ok $test_num $TEST_HDR_MSG # SKIP" elif [ $rc -eq $timeout_rc ]; then \ echo "#" - echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT" + echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT $kselftest_timeout seconds" else echo "not ok $test_num $TEST_HDR_MSG # exit=$rc" fi) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index c9f03ef93338..4f78e4805633 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -50,7 +50,9 @@ #ifndef __KSELFTEST_HARNESS_H #define __KSELFTEST_HARNESS_H +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <asm/types.h> #include <errno.h> #include <stdbool.h> @@ -58,10 +60,13 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/mman.h> #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include "kselftest.h" + #define TEST_TIMEOUT_DEFAULT 30 /* Utilities exposed to the test definitions */ @@ -104,26 +109,28 @@ /* Unconditional logger for internal use. */ #define __TH_LOG(fmt, ...) \ - fprintf(TH_LOG_STREAM, "%s:%d:%s:" fmt "\n", \ + fprintf(TH_LOG_STREAM, "# %s:%d:%s:" fmt "\n", \ __FILE__, __LINE__, _metadata->name, ##__VA_ARGS__) /** - * XFAIL(statement, fmt, ...) + * SKIP(statement, fmt, ...) * - * @statement: statement to run after reporting XFAIL + * @statement: statement to run after reporting SKIP * @fmt: format string * @...: optional arguments * - * This forces a "pass" after reporting a failure with an XFAIL prefix, + * This forces a "pass" after reporting why something is being skipped * and runs "statement", which is usually "return" or "goto skip". */ -#define XFAIL(statement, fmt, ...) do { \ +#define SKIP(statement, fmt, ...) do { \ + snprintf(_metadata->results->reason, \ + sizeof(_metadata->results->reason), fmt, ##__VA_ARGS__); \ if (TH_LOG_ENABLED) { \ - fprintf(TH_LOG_STREAM, "[ XFAIL! ] " fmt "\n", \ - ##__VA_ARGS__); \ + fprintf(TH_LOG_STREAM, "# SKIP %s\n", \ + _metadata->results->reason); \ } \ - /* TODO: find a way to pass xfail to test runner process. */ \ _metadata->passed = 1; \ + _metadata->skip = 1; \ _metadata->trigger = 0; \ statement; \ } while (0) @@ -195,8 +202,9 @@ * * .. code-block:: c * - * FIXTURE_DATA(datatype name) + * FIXTURE_DATA(datatype_name) * + * Almost always, you want just FIXTURE() instead (see below). * This call may be used when the type of the fixture data * is needed. In general, this should not be needed unless * the *self* is being passed to a helper directly. @@ -211,7 +219,7 @@ * * .. code-block:: c * - * FIXTURE(datatype name) { + * FIXTURE(fixture_name) { * type property1; * ... * }; @@ -238,7 +246,7 @@ * * .. code-block:: c * - * FIXTURE_SETUP(fixture name) { implementation } + * FIXTURE_SETUP(fixture_name) { implementation } * * Populates the required "setup" function for a fixture. An instance of the * datatype defined with FIXTURE_DATA() will be exposed as *self* for the @@ -264,7 +272,7 @@ * * .. code-block:: c * - * FIXTURE_TEARDOWN(fixture name) { implementation } + * FIXTURE_TEARDOWN(fixture_name) { implementation } * * Populates the required "teardown" function for a fixture. An instance of the * datatype defined with FIXTURE_DATA() will be exposed as *self* for the @@ -285,7 +293,7 @@ * * .. code-block:: c * - * FIXTURE_VARIANT(datatype name) { + * FIXTURE_VARIANT(fixture_name) { * type property1; * ... * }; @@ -305,8 +313,8 @@ * * .. code-block:: c * - * FIXTURE_ADD(datatype name) { - * .property1 = val1; + * FIXTURE_VARIANT_ADD(fixture_name, variant_name) { + * .property1 = val1, * ... * }; * @@ -672,20 +680,53 @@ __bail(_assert, _metadata->no_print, _metadata->step)) #define __INC_STEP(_metadata) \ - if (_metadata->passed && _metadata->step < 255) \ + /* Keep "step" below 255 (which is used for "SKIP" reporting). */ \ + if (_metadata->passed && _metadata->step < 253) \ _metadata->step++; +#define is_signed_type(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) + #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \ /* Avoid multiple evaluation of the cases */ \ __typeof__(_expected) __exp = (_expected); \ __typeof__(_seen) __seen = (_seen); \ if (_assert) __INC_STEP(_metadata); \ if (!(__exp _t __seen)) { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ - _expected_str, __exp_print, #_t, \ - _seen_str, __seen_print); \ + /* Report with actual signedness to avoid weird output. */ \ + switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \ + case 0: { \ + unsigned long long __exp_print = (uintptr_t)__exp; \ + unsigned long long __seen_print = (uintptr_t)__seen; \ + __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 1: { \ + unsigned long long __exp_print = (uintptr_t)__exp; \ + long long __seen_print = (intptr_t)__seen; \ + __TH_LOG("Expected %s (%llu) %s %s (%lld)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 2: { \ + long long __exp_print = (intptr_t)__exp; \ + unsigned long long __seen_print = (uintptr_t)__seen; \ + __TH_LOG("Expected %s (%lld) %s %s (%llu)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 3: { \ + long long __exp_print = (intptr_t)__exp; \ + long long __seen_print = (intptr_t)__seen; \ + __TH_LOG("Expected %s (%lld) %s %s (%lld)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + } \ _metadata->passed = 0; \ /* Ensure the optional handler is triggered */ \ _metadata->trigger = 1; \ @@ -726,6 +767,10 @@ } \ } +struct __test_results { + char reason[1024]; /* Reason for test result */ +}; + struct __test_metadata; struct __fixture_variant_metadata; @@ -773,11 +818,13 @@ struct __test_metadata { struct __fixture_metadata *fixture; int termsig; int passed; + int skip; /* did SKIP get used? */ int trigger; /* extra handler after the evaluation */ int timeout; /* seconds to wait for test timeout */ bool timed_out; /* did this test timeout instead of exiting? */ __u8 step; bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + struct __test_results *results; struct __test_metadata *prev, *next; }; @@ -813,12 +860,12 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) /* Sanity check handler execution environment. */ if (!t) { fprintf(TH_LOG_STREAM, - "no active test in SIGALRM handler!?\n"); + "# no active test in SIGALRM handler!?\n"); abort(); } if (sig != SIGALRM || sig != info->si_signo) { fprintf(TH_LOG_STREAM, - "%s: SIGALRM handler caught signal %d!?\n", + "# %s: SIGALRM handler caught signal %d!?\n", t->name, sig != SIGALRM ? sig : info->si_signo); abort(); } @@ -839,7 +886,7 @@ void __wait_for_test(struct __test_metadata *t) if (sigaction(SIGALRM, &action, &saved_action)) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: unable to install SIGALRM handler\n", + "# %s: unable to install SIGALRM handler\n", t->name); return; } @@ -851,7 +898,7 @@ void __wait_for_test(struct __test_metadata *t) if (sigaction(SIGALRM, &saved_action, NULL)) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: unable to uninstall SIGALRM handler\n", + "# %s: unable to uninstall SIGALRM handler\n", t->name); return; } @@ -860,39 +907,51 @@ void __wait_for_test(struct __test_metadata *t) if (t->timed_out) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: Test terminated by timeout\n", t->name); + "# %s: Test terminated by timeout\n", t->name); } else if (WIFEXITED(status)) { - t->passed = t->termsig == -1 ? !WEXITSTATUS(status) : 0; if (t->termsig != -1) { + t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: Test exited normally " - "instead of by signal (code: %d)\n", - t->name, - WEXITSTATUS(status)); - } else if (!t->passed) { - fprintf(TH_LOG_STREAM, - "%s: Test failed at step #%d\n", + "# %s: Test exited normally instead of by signal (code: %d)\n", t->name, WEXITSTATUS(status)); + } else { + switch (WEXITSTATUS(status)) { + /* Success */ + case 0: + t->passed = 1; + break; + /* SKIP */ + case 255: + t->passed = 1; + t->skip = 1; + break; + /* Other failure, assume step report. */ + default: + t->passed = 0; + fprintf(TH_LOG_STREAM, + "# %s: Test failed at step #%d\n", + t->name, + WEXITSTATUS(status)); + } } } else if (WIFSIGNALED(status)) { t->passed = 0; if (WTERMSIG(status) == SIGABRT) { fprintf(TH_LOG_STREAM, - "%s: Test terminated by assertion\n", + "# %s: Test terminated by assertion\n", t->name); } else if (WTERMSIG(status) == t->termsig) { t->passed = 1; } else { fprintf(TH_LOG_STREAM, - "%s: Test terminated unexpectedly " - "by signal %d\n", + "# %s: Test terminated unexpectedly by signal %d\n", t->name, WTERMSIG(status)); } } else { fprintf(TH_LOG_STREAM, - "%s: Test ended in some other way [%u]\n", + "# %s: Test ended in some other way [%u]\n", t->name, status); } @@ -904,25 +963,39 @@ void __run_test(struct __fixture_metadata *f, { /* reset test struct */ t->passed = 1; + t->skip = 0; t->trigger = 0; t->step = 0; t->no_print = 0; + memset(t->results->reason, 0, sizeof(t->results->reason)); - printf("[ RUN ] %s%s%s.%s\n", + ksft_print_msg(" RUN %s%s%s.%s ...\n", f->name, variant->name[0] ? "." : "", variant->name, t->name); t->pid = fork(); if (t->pid < 0) { - printf("ERROR SPAWNING TEST CHILD\n"); + ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { t->fn(t, variant); - /* return the step that failed or 0 */ - _exit(t->passed ? 0 : t->step); + if (t->skip) + _exit(255); + /* Pass is exit 0 */ + if (t->passed) + _exit(0); + /* Something else happened, report the step. */ + _exit(t->step); } else { __wait_for_test(t); } - printf("[ %4s ] %s%s%s.%s\n", (t->passed ? "OK" : "FAIL"), + ksft_print_msg(" %4s %s%s%s.%s\n", t->passed ? "OK" : "FAIL", f->name, variant->name[0] ? "." : "", variant->name, t->name); + + if (t->skip) + ksft_test_result_skip("%s\n", t->results->reason[0] ? + t->results->reason : "unknown"); + else + ksft_test_result(t->passed, "%s%s%s.%s\n", + f->name, variant->name[0] ? "." : "", variant->name, t->name); } static int test_harness_run(int __attribute__((unused)) argc, @@ -931,6 +1004,7 @@ static int test_harness_run(int __attribute__((unused)) argc, struct __fixture_variant_metadata no_variant = { .name = "", }; struct __fixture_variant_metadata *v; struct __fixture_metadata *f; + struct __test_results *results; struct __test_metadata *t; int ret = 0; unsigned int case_count = 0, test_count = 0; @@ -945,14 +1019,20 @@ static int test_harness_run(int __attribute__((unused)) argc, } } - /* TODO(wad) add optional arguments similar to gtest. */ - printf("[==========] Running %u tests from %u test cases.\n", + results = mmap(NULL, sizeof(*results), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + + ksft_print_header(); + ksft_set_plan(test_count); + ksft_print_msg("Starting %u tests from %u test cases.\n", test_count, case_count); for (f = __fixture_list; f; f = f->next) { for (v = f->variant ?: &no_variant; v; v = v->next) { for (t = f->tests; t; t = t->next) { count++; + t->results = results; __run_test(f, v, t); + t->results = NULL; if (t->passed) pass_count++; else @@ -960,9 +1040,14 @@ static int test_harness_run(int __attribute__((unused)) argc, } } } - printf("[==========] %u / %u tests passed.\n", pass_count, count); - printf("[ %s ]\n", (ret ? "FAILED" : "PASSED")); - return ret; + munmap(results, sizeof(*results)); + + ksft_print_msg("%s: %u / %u tests passed.\n", ret ? "FAILED" : "PASSED", + pass_count, count); + ksft_exit(ret == 0); + + /* unreachable */ + return KSFT_FAIL; } static void __attribute__((constructor)) __constructor_order_first(void) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 54cdefdfb49d..d59f3eb67c8f 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -76,10 +76,8 @@ void set_default_state(struct kvm_nested_state *state) void set_default_vmx_state(struct kvm_nested_state *state, int size) { memset(state, 0, size); - state->flags = KVM_STATE_NESTED_GUEST_MODE | - KVM_STATE_NESTED_RUN_PENDING; if (have_evmcs) - state->flags |= KVM_STATE_NESTED_EVMCS; + state->flags = KVM_STATE_NESTED_EVMCS; state->format = 0; state->size = size; state->hdr.vmx.vmxon_pa = 0x1000; @@ -148,6 +146,11 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.smm.flags = 1; test_nested_state_expect_einval(vm, state); + /* Invalid flags are rejected. */ + set_default_vmx_state(state, state_sz); + state->hdr.vmx.flags = ~0; + test_nested_state_expect_einval(vm, state); + /* It is invalid to have vmxon_pa == -1ull and vmcs_pa != -1ull. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; @@ -185,20 +188,41 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE; test_nested_state_expect_einval(vm, state); - /* Size must be large enough to fit kvm_nested_state and vmcs12. */ + /* + * Size must be large enough to fit kvm_nested_state and vmcs12 + * if VMCS12 physical address is set + */ set_default_vmx_state(state, state_sz); state->size = sizeof(*state); + state->flags = 0; + test_nested_state_expect_einval(vm, state); + + set_default_vmx_state(state, state_sz); + state->size = sizeof(*state); + state->flags = 0; + state->hdr.vmx.vmcs12_pa = -1; test_nested_state(vm, state); - /* vmxon_pa cannot be the same address as vmcs_pa. */ + /* + * KVM_SET_NESTED_STATE succeeds with invalid VMCS + * contents but L2 not running. + */ set_default_vmx_state(state, state_sz); - state->hdr.vmx.vmxon_pa = 0; - state->hdr.vmx.vmcs12_pa = 0; + state->flags = 0; + test_nested_state(vm, state); + + /* Invalid flags are rejected, even if no VMCS loaded. */ + set_default_vmx_state(state, state_sz); + state->size = sizeof(*state); + state->flags = 0; + state->hdr.vmx.vmcs12_pa = -1; + state->hdr.vmx.flags = ~0; test_nested_state_expect_einval(vm, state); - /* The revision id for vmcs12 must be VMCS12_REVISION. */ + /* vmxon_pa cannot be the same address as vmcs_pa. */ set_default_vmx_state(state, state_sz); - set_revision_id_for_vmcs12(state, 0); + state->hdr.vmx.vmxon_pa = 0; + state->hdr.vmx.vmcs12_pa = 0; test_nested_state_expect_einval(vm, state); /* diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index b0556c752443..7a17ea815736 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -59,9 +59,8 @@ else all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) endif -.ONESHELL: define RUN_TESTS - @BASE_DIR="$(selfdir)"; \ + BASE_DIR="$(selfdir)"; \ . $(selfdir)/kselftest/runner.sh; \ if [ "X$(summary)" != "X" ]; then \ per_test_logging=1; \ @@ -71,22 +70,21 @@ endef run_tests: all ifdef building_out_of_srctree - @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then - @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT) + @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ + rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ fi - @if [ "X$(TEST_PROGS)" != "X" ]; then - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) - else - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)) + @if [ "X$(TEST_PROGS)" != "X" ]; then \ + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) ; \ + else \ + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)); \ fi else - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) + @$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) endif define INSTALL_SINGLE_RULE $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) - $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) - $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) endef define INSTALL_RULE diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh index ee64ff8df8f4..8383eb89d88a 100755 --- a/tools/testing/selftests/lkdtm/run.sh +++ b/tools/testing/selftests/lkdtm/run.sh @@ -8,6 +8,7 @@ # set -e TRIGGER=/sys/kernel/debug/provoke-crash/DIRECT +CLEAR_ONCE=/sys/kernel/debug/clear_warn_once KSELFTEST_SKIP_TEST=4 # Verify we have LKDTM available in the kernel. @@ -67,6 +68,11 @@ cleanup() { } trap cleanup EXIT +# Reset WARN_ONCE counters so we trip it each time this runs. +if [ -w $CLEAR_ONCE ] ; then + echo 1 > $CLEAR_ONCE +fi + # Save existing dmesg so we can detect new content below dmesg > "$DMESG" diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt index 92ca32143ae5..9d266e79c6a2 100644 --- a/tools/testing/selftests/lkdtm/tests.txt +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -14,6 +14,7 @@ STACK_GUARD_PAGE_LEADING STACK_GUARD_PAGE_TRAILING UNSET_SMEP CR4 bits went missing DOUBLE_FAULT +CORRUPT_PAC UNALIGNED_LOAD_STORE_WRITE #OVERWRITE_ALLOCATION Corrupts memory on failure #WRITE_AFTER_FREE Corrupts memory on failure diff --git a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh index 9dc35a16e415..51df5e305855 100755 --- a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh +++ b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh @@ -144,7 +144,7 @@ setup() cleanup() { - for n in h1 r1 h2 h3 h4 + for n in h0 r1 h1 h2 h3 do ip netns del ${n} 2>/dev/null done diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index eb8e2a23bbb4..43a948feed26 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -252,8 +252,6 @@ check_highest_speed_is_chosen() fi local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1)) - # Remove the first speed, h1 does not advertise this speed. - unset speeds_arr[0] max_speed=${speeds_arr[0]} for current in ${speeds_arr[@]}; do diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh index 15d3489ecd9c..ceb7ad4dbd94 100755 --- a/tools/testing/selftests/net/ip_defrag.sh +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -6,6 +6,8 @@ set +x set -e +modprobe -q nf_defrag_ipv6 + readonly NETNS="ns-$(mktemp -u XXXXXX)" setup() { diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 8c8c7d79c38d..2c522f7a0aec 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off, int fds[2], fds_udp[2][2], ret; fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", - typeflags, PORT_BASE, PORT_BASE + port_off); + typeflags, (uint16_t)PORT_BASE, + (uint16_t)(PORT_BASE + port_off)); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index 422e7761254d..bcb79ba1f214 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -329,8 +329,7 @@ int main(int argc, char **argv) bool all_tests = true; int arg_index = 0; int failures = 0; - int s, t; - char opt; + int s, t, opt; while ((opt = getopt_long(argc, argv, "", long_options, &arg_index)) != -1) { diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index ceaad78e9667..3155fbbf644b 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -121,7 +121,7 @@ static bool do_recv_one(int fdr, struct timed_send *ts) if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); - if (labs(tstop - texpect) > cfg_variance_us) + if (llabs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); return false; diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4555f88252ba..a61b7b3da549 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -344,7 +344,7 @@ int main(int argc, char *argv[]) { struct sockaddr_storage listenaddr, addr; unsigned int max_pacing_rate = 0; - size_t total = 0; + uint64_t total = 0; char *host = NULL; int fd, c, on = 1; char *buffer; @@ -473,12 +473,12 @@ int main(int argc, char *argv[]) zflg = 0; } while (total < FILE_SZ) { - ssize_t wr = FILE_SZ - total; + int64_t wr = FILE_SZ - total; if (wr > chunk_size) wr = chunk_size; /* Note : we just want to fill the pipe with 0 bytes */ - wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + wr = send(fd, buffer, (size_t)wr, zflg ? MSG_ZEROCOPY : 0); if (wr <= 0) break; total += wr; diff --git a/tools/testing/selftests/net/txtimestamp.sh b/tools/testing/selftests/net/txtimestamp.sh index eea6f5193693..31637769f59f 100755 --- a/tools/testing/selftests/net/txtimestamp.sh +++ b/tools/testing/selftests/net/txtimestamp.sh @@ -75,7 +75,7 @@ main() { fi } -if [[ "$(ip netns identify)" == "root" ]]; then +if [[ -z "$(ip netns identify)" ]]; then ./in_netns.sh $0 $@ else main $@ diff --git a/tools/testing/selftests/pid_namespace/regression_enomem.c b/tools/testing/selftests/pid_namespace/regression_enomem.c index 73d532556d17..7d84097ad45c 100644 --- a/tools/testing/selftests/pid_namespace/regression_enomem.c +++ b/tools/testing/selftests/pid_namespace/regression_enomem.c @@ -11,7 +11,6 @@ #include <syscall.h> #include <sys/wait.h> -#include "../kselftest.h" #include "../kselftest_harness.h" #include "../pidfd/pidfd.h" diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 8d728eda783d..a2c80914e3dc 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -22,6 +22,10 @@ #define P_PIDFD 3 #endif +#ifndef CLONE_NEWTIME +#define CLONE_NEWTIME 0x00000080 +#endif + #ifndef CLONE_PIDFD #define CLONE_PIDFD 0x00001000 #endif diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c index 84b65ecccb04..7758c98be015 100644 --- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c @@ -18,7 +18,6 @@ #include <linux/kcmp.h> #include "pidfd.h" -#include "../kselftest.h" #include "../kselftest_harness.h" /* diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 9418108eae13..7dca1aa4672d 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -20,7 +20,6 @@ #include "pidfd.h" #include "../clone3/clone3_selftests.h" -#include "../kselftest.h" #include "../kselftest_harness.h" enum { @@ -32,6 +31,7 @@ enum { PIDFD_NS_NET, PIDFD_NS_CGROUP, PIDFD_NS_PIDCLD, + PIDFD_NS_TIME, PIDFD_NS_MAX }; @@ -47,6 +47,7 @@ const struct ns_info { [PIDFD_NS_NET] = { "net", CLONE_NEWNET, }, [PIDFD_NS_CGROUP] = { "cgroup", CLONE_NEWCGROUP, }, [PIDFD_NS_PIDCLD] = { "pid_for_children", 0, }, + [PIDFD_NS_TIME] = { "time", CLONE_NEWTIME, }, }; FIXTURE(current_nsset) @@ -83,9 +84,49 @@ pid_t create_child(int *pidfd, unsigned flags) return sys_clone3(&args, sizeof(struct clone_args)); } +static bool switch_timens(void) +{ + int fd, ret; + + if (unshare(CLONE_NEWTIME)) + return false; + + fd = open("/proc/self/ns/time_for_children", O_RDONLY | O_CLOEXEC); + if (fd < 0) + return false; + + ret = setns(fd, CLONE_NEWTIME); + close(fd); + return ret == 0; +} + +static ssize_t read_nointr(int fd, void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = read(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + FIXTURE_SETUP(current_nsset) { int i, proc_fd, ret; + int ipc_sockets[2]; + char c; for (i = 0; i < PIDFD_NS_MAX; i++) { self->nsfds[i] = -EBADF; @@ -130,6 +171,9 @@ FIXTURE_SETUP(current_nsset) TH_LOG("%m - Failed to open pidfd for process %d", self->pid); } + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + /* Create tasks that will be stopped. */ self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWUSER | CLONE_NEWNS | @@ -139,10 +183,27 @@ FIXTURE_SETUP(current_nsset) EXPECT_GE(self->child_pid1, 0); if (self->child_pid1 == 0) { + close(ipc_sockets[0]); + + if (!switch_timens()) + _exit(EXIT_FAILURE); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + pause(); _exit(EXIT_SUCCESS); } + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWNS | CLONE_NEWCGROUP | CLONE_NEWIPC | @@ -151,10 +212,24 @@ FIXTURE_SETUP(current_nsset) EXPECT_GE(self->child_pid2, 0); if (self->child_pid2 == 0) { + close(ipc_sockets[0]); + + if (!switch_timens()) + _exit(EXIT_FAILURE); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + pause(); _exit(EXIT_SUCCESS); } + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + for (i = 0; i < PIDFD_NS_MAX; i++) { char p[100]; diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 7aff2d3b42c0..c585aaa2acd8 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -8,6 +8,7 @@ #include <sched.h> #include <signal.h> #include <stdio.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <syscall.h> @@ -27,6 +28,8 @@ #define MAX_EVENTS 5 +static bool have_pidfd_send_signal; + static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) { size_t stack_size = 1024; @@ -56,6 +59,13 @@ static int test_pidfd_send_signal_simple_success(void) int pidfd, ret; const char *test_name = "pidfd_send_signal send SIGUSR1"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + pidfd = open("/proc/self", O_DIRECTORY | O_CLOEXEC); if (pidfd < 0) ksft_exit_fail_msg( @@ -86,6 +96,13 @@ static int test_pidfd_send_signal_exited_fail(void) pid_t pid; const char *test_name = "pidfd_send_signal signal exited process"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + pid = fork(); if (pid < 0) ksft_exit_fail_msg("%s test: Failed to create new process\n", @@ -137,16 +154,34 @@ static int test_pidfd_send_signal_recycled_pid_fail(void) pid_t pid1; const char *test_name = "pidfd_send_signal signal recycled pid"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + ret = unshare(CLONE_NEWPID); - if (ret < 0) + if (ret < 0) { + if (errno == EPERM) { + ksft_test_result_skip("%s test: Unsharing pid namespace not permitted\n", + test_name); + return 0; + } ksft_exit_fail_msg("%s test: Failed to unshare pid namespace\n", test_name); + } ret = unshare(CLONE_NEWNS); - if (ret < 0) - ksft_exit_fail_msg( - "%s test: Failed to unshare mount namespace\n", - test_name); + if (ret < 0) { + if (errno == EPERM) { + ksft_test_result_skip("%s test: Unsharing mount namespace not permitted\n", + test_name); + return 0; + } + ksft_exit_fail_msg("%s test: Failed to unshare mount namespace\n", + test_name); + } ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); if (ret < 0) @@ -325,15 +360,17 @@ static int test_pidfd_send_signal_syscall_support(void) ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0); if (ret < 0) { - if (errno == ENOSYS) - ksft_exit_skip( + if (errno == ENOSYS) { + ksft_test_result_skip( "%s test: pidfd_send_signal() syscall not supported\n", test_name); - + return 0; + } ksft_exit_fail_msg("%s test: Failed to send signal\n", test_name); } + have_pidfd_send_signal = true; close(pidfd); ksft_test_result_pass( "%s test: pidfd_send_signal() syscall is supported. Tests can be executed\n", @@ -521,7 +558,7 @@ static void test_pidfd_poll_leader_exit(int use_waitpid) int main(int argc, char **argv) { ksft_print_header(); - ksft_set_plan(4); + ksft_set_plan(8); test_pidfd_poll_exec(0); test_pidfd_poll_exec(1); diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 93e80a42249a..d6e5ce084b1c 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -32,11 +32,11 @@ if test -z "$TORTURE_TRUST_MAKE" then make clean > $resdir/Make.clean 2>&1 fi -make $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 +make $TORTURE_KMAKE_ARG $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 mv .config .config.sav sh $T/upd.sh < .config.sav > .config cp .config .config.new -yes '' | make oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err +yes '' | make $TORTURE_KMAKE_ARG oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err # verify new config matches specification. configcheck.sh .config $c diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh new file mode 100755 index 000000000000..0e4c0b2eb7f0 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Scan standard input for error messages, dumping any found to standard +# output. +# +# Usage: console-badness.sh +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | +grep -v 'ODEBUG: ' | +grep -v 'This means that this is a DEBUG kernel and it is' | +grep -v 'Warning: unable to open an initial console' diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 12810229fddc..51f3464b96d3 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -215,9 +215,6 @@ identify_qemu_args () { then echo -device spapr-vlan,netdev=net0,mac=$TORTURE_QEMU_MAC echo -netdev bridge,br=br0,id=net0 - elif test -n "$TORTURE_QEMU_INTERACTIVE" - then - echo -net nic -net user fi ;; esac @@ -234,7 +231,7 @@ identify_qemu_args () { # Returns the number of virtual CPUs available to the aggregate of the # guest OSes. identify_qemu_vcpus () { - lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' + lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' -e 's/[ ]*//g' } # print_bug @@ -275,3 +272,21 @@ specify_qemu_cpus () { esac fi } + +# specify_qemu_net qemu-args +# +# Appends a string containing "-net none" to qemu-args, unless the incoming +# qemu-args already contains "-smp" or unless the TORTURE_QEMU_INTERACTIVE +# environment variable is set, in which case the string that is be added is +# instead "-net nic -net user". +specify_qemu_net () { + if echo $1 | grep -q -e -net + then + echo $1 + elif test -n "$TORTURE_QEMU_INTERACTIVE" + then + echo $1 -net nic -net user + else + echo $1 -net none + fi +} diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh index 30cb5b27d32e..188b864bc4bf 100755 --- a/tools/testing/selftests/rcutorture/bin/jitter.sh +++ b/tools/testing/selftests/rcutorture/bin/jitter.sh @@ -46,6 +46,12 @@ do exit 0; fi + # Check for stop request. + if test -f "$TORTURE_STOPFILE" + then + exit 1; + fi + # Set affinity to randomly selected online CPU if cpus=`grep 1 /sys/devices/system/cpu/*/online 2>&1 | sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//'` diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 18d6518504ee..115e1822b26f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -9,6 +9,12 @@ # # Authors: Paul E. McKenney <paulmck@linux.ibm.com> +if test -f "$TORTURE_STOPFILE" +then + echo "kvm-build.sh early exit due to run STOP request" + exit 1 +fi + config_template=${1} if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh new file mode 100755 index 000000000000..6e65c134e5f1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh @@ -0,0 +1,108 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Run a group of kvm.sh tests on the specified commits. This currently +# unconditionally does three-minute runs on each scenario in CFLIST, +# taking advantage of all available CPUs and trusting the "make" utility. +# In the short term, adjustments can be made by editing this script and +# CFLIST. If some adjustments appear to have ongoing value, this script +# might grow some command-line arguments. +# +# Usage: kvm-check-branches.sh commit1 commit2..commit3 commit4 ... +# +# This script considers its arguments one at a time. If more elaborate +# specification of commits is needed, please use "git rev-list" to +# produce something that this simple script can understand. The reason +# for retaining the simplicity is that it allows the user to more easily +# see which commit came from which branch. +# +# This script creates a yyyy.mm.dd-hh.mm.ss-group entry in the "res" +# directory. The calls to kvm.sh create the usual entries, but this script +# moves them under the yyyy.mm.dd-hh.mm.ss-group entry, each in its own +# directory numbered in run order, that is, "0001", "0002", and so on. +# For successful runs, the large build artifacts are removed. Doing this +# reduces the disk space required by about two orders of magnitude for +# successful runs. +# +# Copyright (C) Facebook, 2020 +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +if ! git status > /dev/null 2>&1 +then + echo '!!!' This script needs to run in a git archive. 1>&2 + echo '!!!' Giving up. 1>&2 + exit 1 +fi + +# Remember where we started so that we can get back and the end. +curcommit="`git status | head -1 | awk '{ print $NF }'`" + +nfail=0 +ntry=0 +resdir="tools/testing/selftests/rcutorture/res" +ds="`date +%Y.%m.%d-%H.%M.%S`-group" +if ! test -e $resdir +then + mkdir $resdir || : +fi +mkdir $resdir/$ds +echo Results directory: $resdir/$ds + +KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM +PATH=${KVM}/bin:$PATH; export PATH +. functions.sh +cpus="`identify_qemu_vcpus`" +echo Using up to $cpus CPUs. + +# Each pass through this loop does one command-line argument. +for gitbr in $@ +do + echo ' --- git branch ' $gitbr + + # Each pass through this loop tests one commit. + for i in `git rev-list "$gitbr"` + do + ntry=`expr $ntry + 1` + idir=`awk -v ntry="$ntry" 'END { printf "%04d", ntry; }' < /dev/null` + echo ' --- commit ' $i from branch $gitbr + date + mkdir $resdir/$ds/$idir + echo $gitbr > $resdir/$ds/$idir/gitbr + echo $i >> $resdir/$ds/$idir/gitbr + + # Test the specified commit. + git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1 + echo git checkout return code: $? "(Commit $ntry: $i)" + kvm.sh --cpus $cpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1 + ret=$? + echo kvm.sh return code $ret for commit $i from branch $gitbr + + # Move the build products to their resting place. + runresdir="`grep -m 1 '^Results directory:' < $resdir/$ds/$idir/kvm.sh.out | sed -e 's/^Results directory://'`" + mv $runresdir $resdir/$ds/$idir + rrd="`echo $runresdir | sed -e 's,^.*/,,'`" + echo Run results: $resdir/$ds/$idir/$rrd + if test "$ret" -ne 0 + then + # Failure, so leave all evidence intact. + nfail=`expr $nfail + 1` + else + # Success, so remove large files to save about 1GB. + ( cd $resdir/$ds/$idir/$rrd; rm -f */vmlinux */bzImage */System.map */Module.symvers ) + fi + done +done +date + +# Go back to the original commit. +git checkout "$curcommit" + +if test $nfail -ne 0 +then + echo '!!! ' $nfail failures in $ntry 'runs!!!' + exit 1 +else + echo No failures in $ntry runs. + exit 0 +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh new file mode 100755 index 000000000000..35a463dddffe --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh @@ -0,0 +1,71 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Analyze a given results directory for refscale performance measurements. +# +# Usage: kvm-recheck-refscale.sh resdir +# +# Copyright (C) IBM Corporation, 2016 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +i="$1" +if test -d "$i" -a -r "$i" +then + : +else + echo Unreadable results directory: $i + exit 1 +fi +PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH +. functions.sh + +configfile=`echo $i | sed -e 's/^.*\///'` + +sed -e 's/^\[[^]]*]//' < $i/console.log | tr -d '\015' | +awk -v configfile="$configfile" ' +/^[ ]*Runs Time\(ns\) *$/ { + if (dataphase + 0 == 0) { + dataphase = 1; + # print configfile, $0; + } + next; +} + +/[^ ]*[0-9][0-9]* [0-9][0-9]*\.[0-9][0-9]*$/ { + if (dataphase == 1) { + # print $0; + readertimes[++n] = $2; + sum += $2; + } + next; +} + +{ + if (dataphase == 1) + dataphase == 2; + next; +} + +END { + print configfile " results:"; + newNR = asort(readertimes); + if (newNR <= 0) { + print "No refscale records found???" + exit; + } + medianidx = int(newNR / 2); + if (newNR == medianidx * 2) + medianvalue = (readertimes[medianidx - 1] + readertimes[medianidx]) / 2; + else + medianvalue = readertimes[medianidx]; + points = "Points:"; + for (i = 1; i <= newNR; i++) + points = points " " readertimes[i]; + print points; + print "Average reader duration: " sum / newNR " nanoseconds"; + print "Minimum reader duration: " readertimes[1]; + print "Median reader duration: " medianvalue; + print "Maximum reader duration: " readertimes[newNR]; + print "Computed from refscale printk output."; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 736f04749b90..840a4679a0d7 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -31,6 +31,7 @@ do head -1 $resdir/log fi TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" + configfile=`echo $i | sed -e 's,^.*/,,'` rm -f $i/console.log.*.diags kvm-recheck-${TORTURE_SUITE}.sh $i if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137 @@ -43,7 +44,8 @@ do then echo QEMU killed fi - configcheck.sh $i/.config $i/ConfigFragment + configcheck.sh $i/.config $i/ConfigFragment > $T 2>&1 + cat $T if test -r $i/Make.oldconfig.err then cat $i/Make.oldconfig.err @@ -55,15 +57,15 @@ do cat $i/Warnings fi else - if test -f "$i/qemu-cmd" - then - print_bug qemu failed - echo " $i" - elif test -f "$i/buildonly" + if test -f "$i/buildonly" then echo Build-only run, no boot/test configcheck.sh $i/.config $i/ConfigFragment parse-build.sh $i/Make.out $configfile + elif test -f "$i/qemu-cmd" + then + print_bug qemu failed + echo " $i" else print_bug Build failed echo " $i" @@ -72,7 +74,11 @@ do done if test -f "$rd/kcsan.sum" then - if test -s "$rd/kcsan.sum" + if grep -q CONFIG_KCSAN=y $T + then + echo "Compiler or architecture does not support KCSAN!" + echo Did you forget to switch your compiler with '--kmake-arg CC=<cc-that-supports-kcsan>'? + elif test -s "$rd/kcsan.sum" then echo KCSAN summary in $rd/kcsan.sum else diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 6ff611c630d1..e07779a62634 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -124,7 +124,6 @@ seconds=$4 qemu_args=$5 boot_args=$6 -cd $KVM kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null` if test -z "$TORTURE_BUILDONLY" then @@ -141,6 +140,7 @@ then cpu_count=$TORTURE_ALLOTED_CPUS fi qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`" +qemu_args="`specify_qemu_net "$qemu_args"`" # Generate architecture-specific and interaction-specific qemu arguments qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`" @@ -152,6 +152,7 @@ qemu_append="`identify_qemu_append "$QEMU"`" boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`" +echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd if test -n "$TORTURE_BUILDONLY" then @@ -159,9 +160,16 @@ then touch $resdir/buildonly exit 0 fi + +# Decorate qemu-cmd with redirection, backgrounding, and PID capture +sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd +echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd + +# In case qemu refuses to run... echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log -echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd -( $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append "$qemu_append $boot_args" > $resdir/qemu-output 2>&1 & echo $! > $resdir/qemu_pid; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & + +# Attempt to run qemu +( . $T/qemu-cmd; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & commandcompleted=0 sleep 10 # Give qemu's pid a chance to reach the file if test -s "$resdir/qemu_pid" @@ -181,7 +189,7 @@ do kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1 then - if test $kruntime -ge $seconds + if test $kruntime -ge $seconds -o -f "$TORTURE_STOPFILE" then break; fi @@ -210,10 +218,19 @@ then fi if test $commandcompleted -eq 0 -a -n "$qemu_pid" then - echo Grace period for qemu job at pid $qemu_pid + if ! test -f "$TORTURE_STOPFILE" + then + echo Grace period for qemu job at pid $qemu_pid + fi oldline="`tail $resdir/console.log`" while : do + if test -f "$TORTURE_STOPFILE" + then + echo "PID $qemu_pid killed due to run STOP request" >> $resdir/Warnings 2>&1 + kill -KILL $qemu_pid + break + fi kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if kill -0 $qemu_pid > /dev/null 2>&1 then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-transform.sh b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh new file mode 100755 index 000000000000..c45a953ef393 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh @@ -0,0 +1,51 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Transform a qemu-cmd file to allow reuse. +# +# Usage: kvm-transform.sh bzImage console.log < qemu-cmd-in > qemu-cmd-out +# +# bzImage: Kernel and initrd from the same prior kvm.sh run. +# console.log: File into which to place console output. +# +# The original qemu-cmd file is provided on standard input. +# The transformed qemu-cmd file is on standard output. +# The transformation assumes that the qemu command is confined to a +# single line. It also assumes no whitespace in filenames. +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +image="$1" +if test -z "$image" +then + echo Need kernel image file. + exit 1 +fi +consolelog="$2" +if test -z "$consolelog" +then + echo "Need console log file name." + exit 1 +fi + +awk -v image="$image" -v consolelog="$consolelog" ' +{ + line = ""; + for (i = 1; i <= NF; i++) { + if (line == "") + line = $i; + else + line = line " " $i; + if ($i == "-serial") { + i++; + line = line " file:" consolelog; + } + if ($i == "-kernel") { + i++; + line = line " " image; + } + } + print line; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index c279cf9cb010..e655983b7429 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -73,6 +73,10 @@ usage () { while test $# -gt 0 do case "$1" in + --allcpus) + cpus=$TORTURE_ALLOTED_CPUS + max_cpus=$TORTURE_ALLOTED_CPUS + ;; --bootargs|--bootarg) checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--' TORTURE_BOOTARGS="$2" @@ -180,13 +184,14 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\)$' '^--' TORTURE_SUITE=$2 shift - if test "$TORTURE_SUITE" = rcuperf + if test "$TORTURE_SUITE" = rcuperf || test "$TORTURE_SUITE" = refscale then - # If you really want jitter for rcuperf, specify - # it after specifying rcuperf. (But why?) + # If you really want jitter for refscale or + # rcuperf, specify it after specifying the rcuperf + # or the refscale. (But why jitter in these cases?) jitter=0 fi ;; @@ -333,6 +338,8 @@ then mkdir -p "$resdir" || : fi mkdir $resdir/$ds +TORTURE_RESDIR="$resdir/$ds"; export TORTURE_RESDIR +TORTURE_STOPFILE="$resdir/$ds/STOP"; export TORTURE_STOPFILE echo Results directory: $resdir/$ds echo $scriptname $args touch $resdir/$ds/log @@ -497,3 +504,7 @@ fi # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier # Function-graph tracing: ftrace=function_graph ftrace_graph_filter=sched_setaffinity,migration_cpu_stop # Also --kconfig "CONFIG_FUNCTION_TRACER=y CONFIG_FUNCTION_GRAPH_TRACER=y" +# Control buffer size: --bootargs trace_buf_size=3k +# Get trace-buffer dumps on all oopses: --bootargs ftrace_dump_on_oops +# Ditto, but dump only the oopsing CPU: --bootargs ftrace_dump_on_oops=orig_cpu +# Heavy-handed way to also dump on warnings: --bootargs panic_on_warn diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4bf62d7b1cbc..71a9f43a3918 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -33,8 +33,8 @@ then fi cat /dev/null > $file.diags -# Check for proper termination, except that rcuperf runs don't indicate this. -if test "$TORTURE_SUITE" != rcuperf +# Check for proper termination, except for rcuperf and refscale. +if test "$TORTURE_SUITE" != rcuperf && test "$TORTURE_SUITE" != refscale then # check for abject failure @@ -44,11 +44,23 @@ then tail -1 | awk ' { - for (i=NF-8;i<=NF;i++) + normalexit = 1; + for (i=NF-8;i<=NF;i++) { + if (i <= 0 || i !~ /^[0-9]*$/) { + bangstring = $0; + gsub(/^\[[^]]*] /, "", bangstring); + print bangstring; + normalexit = 0; + exit 0; + } sum+=$i; + } } - END { print sum }'` - print_bug $title FAILURE, $nerrs instances + END { + if (normalexit) + print sum " instances" + }'` + print_bug $title FAILURE, $nerrs exit fi @@ -104,10 +116,7 @@ then fi fi | tee -a $file.diags -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | -grep -v 'ODEBUG: ' | -grep -v 'This means that this is a DEBUG kernel and it is' | -grep -v 'Warning: unable to open an initial console' > $T.diags +console-badness.sh < $file > $T.diags if test -s $T.diags then print_warning "Assertion failure in $file $title" diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFLIST b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST new file mode 100644 index 000000000000..4d62eb4a39f9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST @@ -0,0 +1,2 @@ +NOPREEMPT +PREEMPT diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon new file mode 100644 index 000000000000..a98b58b54bb1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon @@ -0,0 +1,2 @@ +CONFIG_RCU_REF_SCALE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT new file mode 100644 index 000000000000..1cd25b7314e3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_PREEMPT_RCU=n +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT new file mode 100644 index 000000000000..d10bc694f42c --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh new file mode 100644 index 000000000000..321e82641287 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Torture-suite-dependent shell functions for the rest of the scripts. +# +# Copyright (C) IBM Corporation, 2015 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 refscale.shutdown=1 \ + refscale.verbose=1 +} diff --git a/tools/testing/selftests/seccomp/config b/tools/testing/selftests/seccomp/config index db1e11b08c8a..64c19d8eba79 100644 --- a/tools/testing/selftests/seccomp/config +++ b/tools/testing/selftests/seccomp/config @@ -1,2 +1,3 @@ CONFIG_SECCOMP=y CONFIG_SECCOMP_FILTER=y +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index 5838c8697ec3..91f5a89cadac 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -18,9 +18,9 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) { - pid_t pid, ret; - unsigned long long i; struct timespec start, finish; + unsigned long long i; + pid_t pid, ret; pid = getpid(); assert(clock_gettime(clk_id, &start) == 0); @@ -31,30 +31,43 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) assert(clock_gettime(clk_id, &finish) == 0); i = finish.tv_sec - start.tv_sec; - i *= 1000000000; + i *= 1000000000ULL; i += finish.tv_nsec - start.tv_nsec; - printf("%lu.%09lu - %lu.%09lu = %llu\n", + printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n", finish.tv_sec, finish.tv_nsec, start.tv_sec, start.tv_nsec, - i); + i, (double)i / 1000000000.0); return i; } unsigned long long calibrate(void) { - unsigned long long i; - - printf("Calibrating reasonable sample size...\n"); + struct timespec start, finish; + unsigned long long i, samples, step = 9973; + pid_t pid, ret; + int seconds = 15; - for (i = 5; ; i++) { - unsigned long long samples = 1 << i; + printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds); - /* Find something that takes more than 5 seconds to run. */ - if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5) - return samples; - } + samples = 0; + pid = getpid(); + assert(clock_gettime(CLOCK_MONOTONIC, &start) == 0); + do { + for (i = 0; i < step; i++) { + ret = syscall(__NR_getpid); + assert(pid == ret); + } + assert(clock_gettime(CLOCK_MONOTONIC, &finish) == 0); + + samples += step; + i = finish.tv_sec - start.tv_sec; + i *= 1000000000ULL; + i += finish.tv_nsec - start.tv_nsec; + } while (i < 1000000000ULL); + + return samples * seconds; } int main(int argc, char *argv[]) @@ -68,32 +81,55 @@ int main(int argc, char *argv[]) }; long ret; unsigned long long samples; - unsigned long long native, filtered; + unsigned long long native, filter1, filter2; + + printf("Current BPF sysctl settings:\n"); + system("sysctl net.core.bpf_jit_enable"); + system("sysctl net.core.bpf_jit_harden"); if (argc > 1) samples = strtoull(argv[1], NULL, 0); else samples = calibrate(); - printf("Benchmarking %llu samples...\n", samples); + printf("Benchmarking %llu syscalls...\n", samples); + /* Native call */ native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; printf("getpid native: %llu ns\n", native); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); assert(ret == 0); + /* One filter */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); assert(ret == 0); - filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW: %llu ns\n", filtered); + filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW 1 filter: %llu ns\n", filter1); + + if (filter1 == native) + printf("No overhead measured!? Try running again with more samples.\n"); + + /* Two filters */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + assert(ret == 0); + + filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW 2 filters: %llu ns\n", filter2); + + /* Calculations */ + printf("Estimated total seccomp overhead for 1 filter: %llu ns\n", + filter1 - native); + + printf("Estimated total seccomp overhead for 2 filters: %llu ns\n", + filter2 - native); - printf("Estimated seccomp overhead per syscall: %llu ns\n", - filtered - native); + printf("Estimated seccomp per-filter overhead: %llu ns\n", + filter2 - filter1); - if (filtered == native) - printf("Trying running again with more samples.\n"); + printf("Estimated seccomp entry overhead: %llu ns\n", + filter1 - native - (filter2 - filter1)); return 0; } diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 252140a52553..5267b9fb7c0f 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -45,12 +45,19 @@ #include <sys/socket.h> #include <sys/ioctl.h> #include <linux/kcmp.h> +#include <sys/resource.h> #include <unistd.h> #include <sys/syscall.h> #include <poll.h> #include "../kselftest_harness.h" +#include "../clone3/clone3_selftests.h" + +/* Attempt to de-conflict with the selftests tree. */ +#ifndef SKIP +#define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) +#endif #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 @@ -167,7 +174,9 @@ struct seccomp_metadata { #ifndef SECCOMP_FILTER_FLAG_NEW_LISTENER #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) +#endif +#ifndef SECCOMP_RET_USER_NOTIF #define SECCOMP_RET_USER_NOTIF 0x7fc00000U #define SECCOMP_IOC_MAGIC '!' @@ -180,7 +189,7 @@ struct seccomp_metadata { #define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ struct seccomp_notif_resp) -#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) struct seccomp_notif { __u64 id; @@ -203,6 +212,39 @@ struct seccomp_notif_sizes { }; #endif +#ifndef SECCOMP_IOCTL_NOTIF_ADDFD +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) + +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ + +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; +#endif + +struct seccomp_notif_addfd_small { + __u64 id; + char weird[4]; +}; +#define SECCOMP_IOCTL_NOTIF_ADDFD_SMALL \ + SECCOMP_IOW(3, struct seccomp_notif_addfd_small) + +struct seccomp_notif_addfd_big { + union { + struct seccomp_notif_addfd addfd; + char buf[sizeof(struct seccomp_notif_addfd) + 8]; + }; +}; +#define SECCOMP_IOCTL_NOTIF_ADDFD_BIG \ + SECCOMP_IOWR(3, struct seccomp_notif_addfd_big) + #ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY #define PTRACE_EVENTMSG_SYSCALL_ENTRY 1 #define PTRACE_EVENTMSG_SYSCALL_EXIT 2 @@ -236,6 +278,40 @@ int seccomp(unsigned int op, unsigned int flags, void *args) #define SIBLING_EXIT_FAILURE 0xbadface #define SIBLING_EXIT_NEWPRIVS 0xbadfeed +static int __filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2) +{ +#ifdef __NR_kcmp + errno = 0; + return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2); +#else + errno = ENOSYS; + return -1; +#endif +} + +/* Have TH_LOG report actual location filecmp() is used. */ +#define filecmp(pid1, pid2, fd1, fd2) ({ \ + int _ret; \ + \ + _ret = __filecmp(pid1, pid2, fd1, fd2); \ + if (_ret != 0) { \ + if (_ret < 0 && errno == ENOSYS) { \ + TH_LOG("kcmp() syscall missing (test is less accurate)");\ + _ret = 0; \ + } \ + } \ + _ret; }) + +TEST(kcmp) +{ + int ret; + + ret = __filecmp(getpid(), getpid(), 1, 1); + EXPECT_EQ(ret, 0); + if (ret != 0 && errno == ENOSYS) + SKIP(return, "Kernel does not support kcmp() (missing CONFIG_CHECKPOINT_RESTORE?)"); +} + TEST(mode_strict_support) { long ret; @@ -1470,6 +1546,7 @@ pid_t setup_trace_fixture(struct __test_metadata *_metadata, return tracer_pid; } + void teardown_trace_fixture(struct __test_metadata *_metadata, pid_t tracer) { @@ -1750,7 +1827,7 @@ void change_syscall(struct __test_metadata *_metadata, EXPECT_EQ(0, ret); } -void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, +void tracer_seccomp(struct __test_metadata *_metadata, pid_t tracee, int status, void *args) { int ret; @@ -1827,6 +1904,24 @@ FIXTURE(TRACE_syscall) { pid_t tracer, mytid, mypid, parent; }; +FIXTURE_VARIANT(TRACE_syscall) { + /* + * All of the SECCOMP_RET_TRACE behaviors can be tested with either + * SECCOMP_RET_TRACE+PTRACE_CONT or plain ptrace()+PTRACE_SYSCALL. + * This indicates if we should use SECCOMP_RET_TRACE (false), or + * ptrace (true). + */ + bool use_ptrace; +}; + +FIXTURE_VARIANT_ADD(TRACE_syscall, ptrace) { + .use_ptrace = true, +}; + +FIXTURE_VARIANT_ADD(TRACE_syscall, seccomp) { + .use_ptrace = false, +}; + FIXTURE_SETUP(TRACE_syscall) { struct sock_filter filter[] = { @@ -1842,12 +1937,11 @@ FIXTURE_SETUP(TRACE_syscall) BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; - - memset(&self->prog, 0, sizeof(self->prog)); - self->prog.filter = malloc(sizeof(filter)); - ASSERT_NE(NULL, self->prog.filter); - memcpy(self->prog.filter, filter, sizeof(filter)); - self->prog.len = (unsigned short)ARRAY_SIZE(filter); + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; /* Prepare some testable syscall results. */ self->mytid = syscall(__NR_gettid); @@ -1865,60 +1959,48 @@ FIXTURE_SETUP(TRACE_syscall) ASSERT_NE(self->parent, self->mypid); /* Launch tracer. */ - self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL, - false); -} + self->tracer = setup_trace_fixture(_metadata, + variant->use_ptrace ? tracer_ptrace + : tracer_seccomp, + NULL, variant->use_ptrace); -FIXTURE_TEARDOWN(TRACE_syscall) -{ - teardown_trace_fixture(_metadata, self->tracer); - if (self->prog.filter) - free(self->prog.filter); -} + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); -TEST_F(TRACE_syscall, ptrace_syscall_redirected) -{ - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); + if (variant->use_ptrace) + return; - /* Tracer will redirect getpid to getppid. */ - EXPECT_NE(self->mypid, syscall(__NR_getpid)); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); } -TEST_F(TRACE_syscall, ptrace_syscall_errno) +FIXTURE_TEARDOWN(TRACE_syscall) { - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - /* Tracer should skip the open syscall, resulting in ESRCH. */ - EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); } -TEST_F(TRACE_syscall, ptrace_syscall_faked) +TEST(negative_ENOSYS) { - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); + /* + * There should be no difference between an "internal" skip + * and userspace asking for syscall "-1". + */ + errno = 0; + EXPECT_EQ(-1, syscall(-1)); + EXPECT_EQ(errno, ENOSYS); + /* And no difference for "still not valid but not -1". */ + errno = 0; + EXPECT_EQ(-1, syscall(-101)); + EXPECT_EQ(errno, ENOSYS); +} - /* Tracer should skip the gettid syscall, resulting fake pid. */ - EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); +TEST_F(TRACE_syscall, negative_ENOSYS) +{ + negative_ENOSYS(_metadata); } TEST_F(TRACE_syscall, syscall_allowed) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - /* getppid works as expected (no changes). */ EXPECT_EQ(self->parent, syscall(__NR_getppid)); EXPECT_NE(self->mypid, syscall(__NR_getppid)); @@ -1926,14 +2008,6 @@ TEST_F(TRACE_syscall, syscall_allowed) TEST_F(TRACE_syscall, syscall_redirected) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - /* getpid has been redirected to getppid as expected. */ EXPECT_EQ(self->parent, syscall(__NR_getpid)); EXPECT_NE(self->mypid, syscall(__NR_getpid)); @@ -1941,33 +2015,17 @@ TEST_F(TRACE_syscall, syscall_redirected) TEST_F(TRACE_syscall, syscall_errno) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* openat has been skipped and an errno return. */ + /* Tracer should skip the open syscall, resulting in ESRCH. */ EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); } TEST_F(TRACE_syscall, syscall_faked) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* gettid has been skipped and an altered return value stored. */ + /* Tracer skips the gettid syscall and store altered return value. */ EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); } -TEST_F(TRACE_syscall, skip_after_RET_TRACE) +TEST_F(TRACE_syscall, skip_after) { struct sock_filter filter[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, @@ -1982,14 +2040,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) }; long ret; - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install fixture filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "errno on getppid" filter. */ + /* Install additional "errno on getppid" filter. */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); ASSERT_EQ(0, ret); @@ -1999,69 +2050,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) EXPECT_EQ(EPERM, errno); } -TEST_F_SIGNAL(TRACE_syscall, kill_after_RET_TRACE, SIGSYS) -{ - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install fixture filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "death on getppid" filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Tracer will redirect getpid to getppid, and we should die. */ - EXPECT_NE(self->mypid, syscall(__NR_getpid)); -} - -TEST_F(TRACE_syscall, skip_after_ptrace) -{ - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; - long ret; - - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "errno on getppid" filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Tracer will redirect getpid to getppid, and we should see EPERM. */ - EXPECT_EQ(-1, syscall(__NR_getpid)); - EXPECT_EQ(EPERM, errno); -} - -TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) +TEST_F_SIGNAL(TRACE_syscall, kill_after, SIGSYS) { struct sock_filter filter[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, @@ -2076,15 +2065,7 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) }; long ret; - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "death on getppid" filter. */ + /* Install additional "death on getppid" filter. */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); ASSERT_EQ(0, ret); @@ -3069,7 +3050,7 @@ TEST(get_metadata) /* Only real root can get metadata. */ if (geteuid()) { - XFAIL(return, "get_metadata requires real root"); + SKIP(return, "get_metadata requires real root"); return; } @@ -3112,7 +3093,7 @@ TEST(get_metadata) ret = ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md); EXPECT_EQ(sizeof(md), ret) { if (errno == EINVAL) - XFAIL(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)"); + SKIP(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)"); } EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG); @@ -3128,7 +3109,7 @@ skip: ASSERT_EQ(0, kill(pid, SIGKILL)); } -static int user_trap_syscall(int nr, unsigned int flags) +static int user_notif_syscall(int nr, unsigned int flags) { struct sock_filter filter[] = { BPF_STMT(BPF_LD+BPF_W+BPF_ABS, @@ -3174,7 +3155,7 @@ TEST(user_notification_basic) /* Check that we get -ENOSYS with no listener attached */ if (pid == 0) { - if (user_trap_syscall(__NR_getppid, 0) < 0) + if (user_notif_syscall(__NR_getppid, 0) < 0) exit(1); ret = syscall(__NR_getppid); exit(ret >= 0 || errno != ENOSYS); @@ -3191,13 +3172,13 @@ TEST(user_notification_basic) EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0); /* Check that the basic notification machinery works */ - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* Installing a second listener in the chain should EBUSY */ - EXPECT_EQ(user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER), + EXPECT_EQ(user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER), -1); EXPECT_EQ(errno, EBUSY); @@ -3258,15 +3239,20 @@ TEST(user_notification_with_tsync) int ret; unsigned int flags; + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + /* these were exclusive */ flags = SECCOMP_FILTER_FLAG_NEW_LISTENER | SECCOMP_FILTER_FLAG_TSYNC; - ASSERT_EQ(-1, user_trap_syscall(__NR_getppid, flags)); + ASSERT_EQ(-1, user_notif_syscall(__NR_getppid, flags)); ASSERT_EQ(EINVAL, errno); /* but now they're not */ flags |= SECCOMP_FILTER_FLAG_TSYNC_ESRCH; - ret = user_trap_syscall(__NR_getppid, flags); + ret = user_notif_syscall(__NR_getppid, flags); close(ret); ASSERT_LE(0, ret); } @@ -3284,8 +3270,8 @@ TEST(user_notification_kill_in_middle) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* @@ -3338,8 +3324,8 @@ TEST(user_notification_signal) ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0); - listener = user_trap_syscall(__NR_gettid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_gettid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3408,8 +3394,8 @@ TEST(user_notification_closed_listener) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* @@ -3440,10 +3426,13 @@ TEST(user_notification_child_pid_ns) struct seccomp_notif req = {}; struct seccomp_notif_resp resp = {}; - ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0) { + if (errno == EINVAL) + SKIP(return, "kernel missing CLONE_NEWUSER support"); + }; - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3482,8 +3471,8 @@ TEST(user_notification_sibling_pid_ns) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3505,7 +3494,10 @@ TEST(user_notification_sibling_pid_ns) } /* Create the sibling ns, and sibling in it. */ - ASSERT_EQ(unshare(CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWPID), 0) { + if (errno == EPERM) + SKIP(return, "CLONE_NEWPID requires CAP_SYS_ADMIN"); + } ASSERT_EQ(errno, 0); pid2 = fork(); @@ -3547,8 +3539,8 @@ TEST(user_notification_fault_recv) ASSERT_EQ(unshare(CLONE_NEWUSER), 0); - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3585,16 +3577,6 @@ TEST(seccomp_get_notif_sizes) EXPECT_EQ(sizes.seccomp_notif_resp, sizeof(struct seccomp_notif_resp)); } -static int filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2) -{ -#ifdef __NR_kcmp - return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2); -#else - errno = ENOSYS; - return -1; -#endif -} - TEST(user_notification_continue) { pid_t pid; @@ -3609,7 +3591,7 @@ TEST(user_notification_continue) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3619,20 +3601,14 @@ TEST(user_notification_continue) int dup_fd, pipe_fds[2]; pid_t self; - ret = pipe(pipe_fds); - if (ret < 0) - exit(1); + ASSERT_GE(pipe(pipe_fds), 0); dup_fd = dup(pipe_fds[0]); - if (dup_fd < 0) - exit(1); + ASSERT_GE(dup_fd, 0); + EXPECT_NE(pipe_fds[0], dup_fd); self = getpid(); - - ret = filecmp(self, self, pipe_fds[0], dup_fd); - if (ret) - exit(2); - + ASSERT_EQ(filecmp(self, self, pipe_fds[0], dup_fd), 0); exit(0); } @@ -3673,7 +3649,7 @@ TEST(user_notification_continue) resp.val = 0; EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0) { if (errno == EINVAL) - XFAIL(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE"); + SKIP(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE"); } skip: @@ -3681,15 +3657,342 @@ skip: EXPECT_EQ(true, WIFEXITED(status)); EXPECT_EQ(0, WEXITSTATUS(status)) { if (WEXITSTATUS(status) == 2) { - XFAIL(return, "Kernel does not support kcmp() syscall"); + SKIP(return, "Kernel does not support kcmp() syscall"); return; } } } +TEST(user_notification_filter_empty) +{ + pid_t pid; + long ret; + int status; + struct pollfd pollfd; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int listener; + + listener = user_notif_syscall(__NR_mknod, SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + _exit(EXIT_FAILURE); + + if (dup2(listener, 200) != 200) + _exit(EXIT_FAILURE); + + close(listener); + + _exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * The seccomp filter has become unused so we should be notified once + * the kernel gets around to cleaning up task struct. + */ + pollfd.fd = 200; + pollfd.events = POLLHUP; + + EXPECT_GT(poll(&pollfd, 1, 2000), 0); + EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); +} + +static void *do_thread(void *data) +{ + return NULL; +} + +TEST(user_notification_filter_empty_threaded) +{ + pid_t pid; + long ret; + int status; + struct pollfd pollfd; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + pid_t pid1, pid2; + int listener, status; + pthread_t thread; + + listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + _exit(EXIT_FAILURE); + + if (dup2(listener, 200) != 200) + _exit(EXIT_FAILURE); + + close(listener); + + pid1 = fork(); + if (pid1 < 0) + _exit(EXIT_FAILURE); + + if (pid1 == 0) + _exit(EXIT_SUCCESS); + + pid2 = fork(); + if (pid2 < 0) + _exit(EXIT_FAILURE); + + if (pid2 == 0) + _exit(EXIT_SUCCESS); + + if (pthread_create(&thread, NULL, do_thread, NULL) || + pthread_join(thread, NULL)) + _exit(EXIT_FAILURE); + + if (pthread_create(&thread, NULL, do_thread, NULL) || + pthread_join(thread, NULL)) + _exit(EXIT_FAILURE); + + if (waitpid(pid1, &status, 0) != pid1 || !WIFEXITED(status) || + WEXITSTATUS(status)) + _exit(EXIT_FAILURE); + + if (waitpid(pid2, &status, 0) != pid2 || !WIFEXITED(status) || + WEXITSTATUS(status)) + _exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * The seccomp filter has become unused so we should be notified once + * the kernel gets around to cleaning up task struct. + */ + pollfd.fd = 200; + pollfd.events = POLLHUP; + + EXPECT_GT(poll(&pollfd, 1, 2000), 0); + EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); +} + +TEST(user_notification_addfd) +{ + pid_t pid; + long ret; + int status, listener, memfd, fd; + struct seccomp_notif_addfd addfd = {}; + struct seccomp_notif_addfd_small small = {}; + struct seccomp_notif_addfd_big big = {}; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + /* 100 ms */ + struct timespec delay = { .tv_nsec = 100000000 }; + + memfd = memfd_create("test", 0); + ASSERT_GE(memfd, 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Check that the basic notification machinery works */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + if (syscall(__NR_getppid) != USER_NOTIF_MAGIC) + exit(1); + exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC); + } + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + addfd.srcfd = memfd; + addfd.newfd = 0; + addfd.id = req.id; + addfd.flags = 0x0; + + /* Verify bad newfd_flags cannot be set */ + addfd.newfd_flags = ~O_CLOEXEC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.newfd_flags = O_CLOEXEC; + + /* Verify bad flags cannot be set */ + addfd.flags = 0xff; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.flags = 0; + + /* Verify that remote_fd cannot be set without setting flags */ + addfd.newfd = 1; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.newfd = 0; + + /* Verify small size cannot be set */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_SMALL, &small), -1); + EXPECT_EQ(errno, EINVAL); + + /* Verify we can't send bits filled in unknown buffer area */ + memset(&big, 0xAA, sizeof(big)); + big.addfd = addfd; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big), -1); + EXPECT_EQ(errno, E2BIG); + + + /* Verify we can set an arbitrary remote fd */ + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); + /* + * The child has fds 0(stdin), 1(stdout), 2(stderr), 3(memfd), + * 4(listener), so the newly allocated fd should be 5. + */ + EXPECT_EQ(fd, 5); + EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); + + /* Verify we can set an arbitrary remote fd with large size */ + memset(&big, 0x0, sizeof(big)); + big.addfd = addfd; + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big); + EXPECT_EQ(fd, 6); + + /* Verify we can set a specific remote fd */ + addfd.newfd = 42; + addfd.flags = SECCOMP_ADDFD_FLAG_SETFD; + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); + EXPECT_EQ(fd, 42); + EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); + + /* Resume syscall */ + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* + * This sets the ID of the ADD FD to the last request plus 1. The + * notification ID increments 1 per notification. + */ + addfd.id = req.id + 1; + + /* This spins until the underlying notification is generated */ + while (ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd) != -1 && + errno != -EINPROGRESS) + nanosleep(&delay, NULL); + + memset(&req, 0, sizeof(req)); + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + ASSERT_EQ(addfd.id, req.id); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* Wait for child to finish. */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + close(memfd); +} + +TEST(user_notification_addfd_rlimit) +{ + pid_t pid; + long ret; + int status, listener, memfd; + struct seccomp_notif_addfd addfd = {}; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + const struct rlimit lim = { + .rlim_cur = 0, + .rlim_max = 0, + }; + + memfd = memfd_create("test", 0); + ASSERT_GE(memfd, 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Check that the basic notification machinery works */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) + exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC); + + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + ASSERT_EQ(prlimit(pid, RLIMIT_NOFILE, &lim, NULL), 0); + + addfd.srcfd = memfd; + addfd.newfd_flags = O_CLOEXEC; + addfd.newfd = 0; + addfd.id = req.id; + addfd.flags = 0; + + /* Should probably spot check /proc/sys/fs/file-nr */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EMFILE); + + addfd.newfd = 100; + addfd.flags = SECCOMP_ADDFD_FLAG_SETFD; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EBADF); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* Wait for child to finish. */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + close(memfd); +} + /* * TODO: - * - add microbenchmarks * - expand NNP testing * - better arch-specific TRACE and TRAP handlers. * - endianness checking when appropriate @@ -3697,7 +4000,6 @@ skip: * - arch value testing (x86 modes especially) * - verify that FILTER_FLAG_LOG filters generate log messages * - verify that RET_LOG generates log messages - * - ... */ TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/seccomp/settings b/tools/testing/selftests/seccomp/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/seccomp/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index ad0f8df2ca0a..8934a3766d20 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -71,7 +71,7 @@ void my_usr1(int sig, siginfo_t *si, void *u) swapcontext(&sc, &uc); ksft_print_msg("%s\n", p->msg); if (!p->flag) { - ksft_exit_skip("[RUN]\tAborting\n"); + ksft_exit_fail_msg("[RUN]\tAborting\n"); exit(EXIT_FAILURE); } } @@ -144,7 +144,7 @@ int main(void) err = sigaltstack(&stk, NULL); if (err) { if (errno == EINVAL) { - ksft_exit_skip( + ksft_test_result_skip( "[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n"); /* * If test cases for the !SS_AUTODISARM variant were diff --git a/tools/testing/selftests/sync/sync_test.c b/tools/testing/selftests/sync/sync_test.c index 3824b66f41a0..414a617db993 100644 --- a/tools/testing/selftests/sync/sync_test.c +++ b/tools/testing/selftests/sync/sync_test.c @@ -86,9 +86,9 @@ int main(void) int err; ksft_print_header(); - ksft_set_plan(3 + 7); sync_api_supported(); + ksft_set_plan(3 + 7); ksft_print_msg("[RUN]\tTesting sync framework\n"); diff --git a/tools/testing/selftests/uevent/uevent_filtering.c b/tools/testing/selftests/uevent/uevent_filtering.c index f83391aa42cf..5cebfb356345 100644 --- a/tools/testing/selftests/uevent/uevent_filtering.c +++ b/tools/testing/selftests/uevent/uevent_filtering.c @@ -19,7 +19,6 @@ #include <sys/wait.h> #include <unistd.h> -#include "../kselftest.h" #include "../kselftest_harness.h" #define __DEV_FULL "/sys/devices/virtual/mem/full/uevent" diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 79db22604019..91d38a29956b 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -881,8 +881,9 @@ TEST_F(hmm, migrate) } /* - * Migrate anonymous memory to device private memory and fault it back to system - * memory. + * Migrate anonymous memory to device private memory and fault some of it back + * to system memory, then try migrating the resulting mix of system and device + * private memory to the device. */ TEST_F(hmm, migrate_fault) { @@ -924,8 +925,17 @@ TEST_F(hmm, migrate_fault) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - /* Fault pages back to system memory and check them. */ - for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + /* Fault half the pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i) + ASSERT_EQ(ptr[i], i); + + /* Migrate memory to the device again. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); hmm_buffer_free(buffer); @@ -1292,6 +1302,82 @@ TEST_F(hmm2, snapshot) } /* + * Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that + * should be mapped by a large page table entry. + */ +TEST_F(hmm, compound) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + int *ptr; + unsigned char *m; + int ret; + long pagesizes[4]; + int n, idx; + unsigned long i; + + /* Skip test if we can't allocate a hugetlbfs page. */ + + n = gethugepagesizes(pagesizes, 4); + if (n <= 0) + return; + for (idx = 0; --n > 0; ) { + if (pagesizes[n] < pagesizes[idx]) + idx = n; + } + size = ALIGN(TWOMEG, pagesizes[idx]); + npages = size >> self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->ptr = get_hugepage_region(size, GHR_STRICT); + if (buffer->ptr == NULL) { + free(buffer); + return; + } + + buffer->size = size; + buffer->mirror = malloc(npages); + ASSERT_NE(buffer->mirror, NULL); + + /* Initialize the pages the device will snapshot in buffer->ptr. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Simulate a device snapshotting CPU pagetables. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device saw. */ + m = buffer->mirror; + for (i = 0; i < npages; ++i) + ASSERT_EQ(m[i], HMM_DMIRROR_PROT_WRITE | + HMM_DMIRROR_PROT_PMD); + + /* Make the region read-only. */ + ret = mprotect(buffer->ptr, size, PROT_READ); + ASSERT_EQ(ret, 0); + + /* Simulate a device snapshotting CPU pagetables. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device saw. */ + m = buffer->mirror; + for (i = 0; i < npages; ++i) + ASSERT_EQ(m[i], HMM_DMIRROR_PROT_READ | + HMM_DMIRROR_PROT_PMD); + + free_hugepage_region(buffer->ptr); + buffer->ptr = NULL; + hmm_buffer_free(buffer); +} + +/* * Test two devices reading the same memory (double mapped). */ TEST_F(hmm2, double_map) diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index fc19addcb5c8..fdbb602ecf32 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Tests Memory Protection Keys (see Documentation/vm/protection-keys.txt) + * Tests Memory Protection Keys (see Documentation/core-api/protection-keys.rst) * * There are examples in here of: * * how to set protection keys on memory diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index d2796ea98c5a..6703c7906b71 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vdso test_vsyscall mov_ss_trap \ - syscall_arg_fault + syscall_arg_fault fsgsbase_restore TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c index 15a329da59fa..998319553523 100644 --- a/tools/testing/selftests/x86/fsgsbase.c +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -285,7 +285,8 @@ static unsigned short load_gs(void) /* 32-bit set_thread_area */ long ret; asm volatile ("int $0x80" - : "=a" (ret) : "a" (243), "b" (low_desc) + : "=a" (ret), "+m" (*low_desc) + : "a" (243), "b" (low_desc) : "r8", "r9", "r10", "r11"); memcpy(&desc, low_desc, sizeof(desc)); munmap(low_desc, sizeof(desc)); @@ -489,11 +490,28 @@ static void test_ptrace_write_gsbase(void) * selector value is changed or not by the GSBASE write in * a ptracer. */ - if (gs == 0 && base == 0xFF) { - printf("[OK]\tGS was reset as expected\n"); - } else { + if (gs != *shared_scratch) { nerrs++; - printf("[FAIL]\tGS=0x%lx, GSBASE=0x%lx (should be 0, 0xFF)\n", gs, base); + printf("[FAIL]\tGS changed to %lx\n", gs); + + /* + * On older kernels, poking a nonzero value into the + * base would zero the selector. On newer kernels, + * this behavior has changed -- poking the base + * changes only the base and, if FSGSBASE is not + * available, this may have no effect once the tracee + * is resumed. + */ + if (gs == 0) + printf("\tNote: this is expected behavior on older kernels.\n"); + } else if (have_fsgsbase && (base != 0xFF)) { + nerrs++; + printf("[FAIL]\tGSBASE changed to %lx\n", base); + } else { + printf("[OK]\tGS remained 0x%hx", *shared_scratch); + if (have_fsgsbase) + printf(" and GSBASE changed to 0xFF"); + printf("\n"); } } diff --git a/tools/testing/selftests/x86/fsgsbase_restore.c b/tools/testing/selftests/x86/fsgsbase_restore.c new file mode 100644 index 000000000000..6fffadc51579 --- /dev/null +++ b/tools/testing/selftests/x86/fsgsbase_restore.c @@ -0,0 +1,245 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * fsgsbase_restore.c, test ptrace vs fsgsbase + * Copyright (c) 2020 Andy Lutomirski + * + * This test case simulates a tracer redirecting tracee execution to + * a function and then restoring tracee state using PTRACE_GETREGS and + * PTRACE_SETREGS. This is similar to what gdb does when doing + * 'p func()'. The catch is that this test has the called function + * modify a segment register. This makes sure that ptrace correctly + * restores segment state when using PTRACE_SETREGS. + * + * This is not part of fsgsbase.c, because that test is 64-bit only. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <err.h> +#include <sys/user.h> +#include <asm/prctl.h> +#include <sys/prctl.h> +#include <asm/ldt.h> +#include <sys/mman.h> +#include <stddef.h> +#include <sys/ptrace.h> +#include <sys/wait.h> +#include <stdint.h> + +#define EXPECTED_VALUE 0x1337f00d + +#ifdef __x86_64__ +# define SEG "%gs" +#else +# define SEG "%fs" +#endif + +static unsigned int dereference_seg_base(void) +{ + int ret; + asm volatile ("mov %" SEG ":(0), %0" : "=rm" (ret)); + return ret; +} + +static void init_seg(void) +{ + unsigned int *target = mmap( + NULL, sizeof(unsigned int), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0); + if (target == MAP_FAILED) + err(1, "mmap"); + + *target = EXPECTED_VALUE; + + printf("\tsegment base address = 0x%lx\n", (unsigned long)target); + + struct user_desc desc = { + .entry_number = 0, + .base_addr = (unsigned int)(uintptr_t)target, + .limit = sizeof(unsigned int) - 1, + .seg_32bit = 1, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 0, + .useable = 0 + }; + if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) { + printf("\tusing LDT slot 0\n"); + asm volatile ("mov %0, %" SEG :: "rm" ((unsigned short)0x7)); + } else { + /* No modify_ldt for us (configured out, perhaps) */ + + struct user_desc *low_desc = mmap( + NULL, sizeof(desc), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0); + memcpy(low_desc, &desc, sizeof(desc)); + + low_desc->entry_number = -1; + + /* 32-bit set_thread_area */ + long ret; + asm volatile ("int $0x80" + : "=a" (ret), "+m" (*low_desc) + : "a" (243), "b" (low_desc) +#ifdef __x86_64__ + : "r8", "r9", "r10", "r11" +#endif + ); + memcpy(&desc, low_desc, sizeof(desc)); + munmap(low_desc, sizeof(desc)); + + if (ret != 0) { + printf("[NOTE]\tcould not create a segment -- can't test anything\n"); + exit(0); + } + printf("\tusing GDT slot %d\n", desc.entry_number); + + unsigned short sel = (unsigned short)((desc.entry_number << 3) | 0x3); + asm volatile ("mov %0, %" SEG :: "rm" (sel)); + } +} + +static void tracee_zap_segment(void) +{ + /* + * The tracer will redirect execution here. This is meant to + * work like gdb's 'p func()' feature. The tricky bit is that + * we modify a segment register in order to make sure that ptrace + * can correctly restore segment registers. + */ + printf("\tTracee: in tracee_zap_segment()\n"); + + /* + * Write a nonzero selector with base zero to the segment register. + * Using a null selector would defeat the test on AMD pre-Zen2 + * CPUs, as such CPUs don't clear the base when loading a null + * selector. + */ + unsigned short sel; + asm volatile ("mov %%ss, %0\n\t" + "mov %0, %" SEG + : "=rm" (sel)); + + pid_t pid = getpid(), tid = syscall(SYS_gettid); + + printf("\tTracee is going back to sleep\n"); + syscall(SYS_tgkill, pid, tid, SIGSTOP); + + /* Should not get here. */ + while (true) { + printf("[FAIL]\tTracee hit unreachable code\n"); + pause(); + } +} + +int main() +{ + printf("\tSetting up a segment\n"); + init_seg(); + + unsigned int val = dereference_seg_base(); + if (val != EXPECTED_VALUE) { + printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE); + return 1; + } + printf("[OK]\tThe segment points to the right place.\n"); + + pid_t chld = fork(); + if (chld < 0) + err(1, "fork"); + + if (chld == 0) { + prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0, 0); + + if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0) + err(1, "PTRACE_TRACEME"); + + pid_t pid = getpid(), tid = syscall(SYS_gettid); + + printf("\tTracee will take a nap until signaled\n"); + syscall(SYS_tgkill, pid, tid, SIGSTOP); + + printf("\tTracee was resumed. Will re-check segment.\n"); + + val = dereference_seg_base(); + if (val != EXPECTED_VALUE) { + printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE); + exit(1); + } + + printf("[OK]\tThe segment points to the right place.\n"); + exit(0); + } + + int status; + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status)) + err(1, "waitpid"); + + struct user_regs_struct regs; + + if (ptrace(PTRACE_GETREGS, chld, NULL, ®s) != 0) + err(1, "PTRACE_GETREGS"); + +#ifdef __x86_64__ + printf("\tChild GS=0x%lx, GSBASE=0x%lx\n", (unsigned long)regs.gs, (unsigned long)regs.gs_base); +#else + printf("\tChild FS=0x%lx\n", (unsigned long)regs.xfs); +#endif + + struct user_regs_struct regs2 = regs; +#ifdef __x86_64__ + regs2.rip = (unsigned long)tracee_zap_segment; + regs2.rsp -= 128; /* Don't clobber the redzone. */ +#else + regs2.eip = (unsigned long)tracee_zap_segment; +#endif + + printf("\tTracer: redirecting tracee to tracee_zap_segment()\n"); + if (ptrace(PTRACE_SETREGS, chld, NULL, ®s2) != 0) + err(1, "PTRACE_GETREGS"); + if (ptrace(PTRACE_CONT, chld, NULL, NULL) != 0) + err(1, "PTRACE_GETREGS"); + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status)) + err(1, "waitpid"); + + printf("\tTracer: restoring tracee state\n"); + if (ptrace(PTRACE_SETREGS, chld, NULL, ®s) != 0) + err(1, "PTRACE_GETREGS"); + if (ptrace(PTRACE_DETACH, chld, NULL, NULL) != 0) + err(1, "PTRACE_GETREGS"); + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld) + err(1, "waitpid"); + + if (WIFSIGNALED(status)) { + printf("[FAIL]\tTracee crashed\n"); + return 1; + } + + if (!WIFEXITED(status)) { + printf("[FAIL]\tTracee stopped for an unexpected reason: %d\n", status); + return 1; + } + + int exitcode = WEXITSTATUS(status); + if (exitcode != 0) { + printf("[FAIL]\tTracee reported failure\n"); + return 1; + } + + printf("[OK]\tAll is well.\n"); + return 0; +} diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c index 5b7abebbcbb9..bff474b5efc6 100644 --- a/tools/testing/selftests/x86/syscall_arg_fault.c +++ b/tools/testing/selftests/x86/syscall_arg_fault.c @@ -53,6 +53,7 @@ static void sigsegv_or_sigbus(int sig, siginfo_t *info, void *ctx_void) if (ax != -EFAULT && ax != -ENOSYS) { printf("[FAIL]\tAX had the wrong value: 0x%lx\n", (unsigned long)ax); + printf("\tIP = 0x%lx\n", (unsigned long)ctx->uc_mcontext.gregs[REG_IP]); n_errs++; } else { printf("[OK]\tSeems okay\n"); @@ -207,5 +208,30 @@ int main() } set_eflags(get_eflags() & ~X86_EFLAGS_TF); +#ifdef __x86_64__ + printf("[RUN]\tSYSENTER with TF, invalid state, and GSBASE < 0\n"); + + if (sigsetjmp(jmpbuf, 1) == 0) { + sigtrap_consecutive_syscalls = 0; + + asm volatile ("wrgsbase %%rax\n\t" + :: "a" (0xffffffffffff0000UL)); + + set_eflags(get_eflags() | X86_EFLAGS_TF); + asm volatile ( + "movl $-1, %%eax\n\t" + "movl $-1, %%ebx\n\t" + "movl $-1, %%ecx\n\t" + "movl $-1, %%edx\n\t" + "movl $-1, %%esi\n\t" + "movl $-1, %%edi\n\t" + "movl $-1, %%ebp\n\t" + "movl $-1, %%esp\n\t" + "sysenter" + : : : "memory", "flags"); + } + set_eflags(get_eflags() & ~X86_EFLAGS_TF); +#endif + return 0; } |