diff options
author | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2015-12-15 14:52:16 -0300 |
---|---|---|
committer | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2015-12-15 14:52:16 -0300 |
commit | 8d91c1e411f55d7ea91b1183a2e9f8088fb4d5be (patch) | |
tree | e9891aa6c295060d065adffd610c4f49ecf884f3 /tools/testing/selftests | |
parent | a71852147516bc1cb5b0b3cbd13639bfd4022dc8 (diff) |
Linux-libre 4.3.2-gnu
Diffstat (limited to 'tools/testing/selftests')
51 files changed, 2888 insertions, 171 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 3af31afa0..8922c2155 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -7,6 +7,7 @@ TARGETS += ftrace TARGETS += futex TARGETS += kcmp TARGETS += kdbus +TARGETS += membarrier TARGETS += memfd TARGETS += memory-hotplug TARGETS += mount @@ -16,6 +17,7 @@ TARGETS += powerpc TARGETS += ptrace TARGETS += seccomp TARGETS += size +TARGETS += static_keys TARGETS += sysctl ifneq (1, $(quicktest)) TARGETS += timers @@ -23,6 +25,7 @@ endif TARGETS += user TARGETS += vm TARGETS += x86 +TARGETS += zram #Please keep the TARGETS list alphabetically sorted # Run "make quicktest=1 run_tests" or # "make quicktest=1 kselftest from top level Makefile @@ -72,7 +75,6 @@ ifdef INSTALL_PATH @# Ask all targets to install their files mkdir -p $(INSTALL_PATH) for TARGET in $(TARGETS); do \ - mkdir -p $(INSTALL_PATH)/$$TARGET ; \ make -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ done; diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index 182235640..d27108b4f 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -1,22 +1,12 @@ # Taken from perf makefile uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/) -ifeq ($(ARCH),i386) - ARCH := x86 -endif -ifeq ($(ARCH),x86_64) - ARCH := x86 -endif +ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) - -all: ifeq ($(ARCH),x86) - gcc breakpoint_test.c -o breakpoint_test -else - echo "Not an x86 target, can't build breakpoints selftests" +TEST_PROGS := breakpoint_test endif -TEST_PROGS := breakpoint_test +all: include ../lib.mk diff --git a/tools/testing/selftests/capabilities/.gitignore b/tools/testing/selftests/capabilities/.gitignore new file mode 100644 index 000000000..b732dd0d4 --- /dev/null +++ b/tools/testing/selftests/capabilities/.gitignore @@ -0,0 +1,2 @@ +test_execve +validate_cap diff --git a/tools/testing/selftests/capabilities/Makefile b/tools/testing/selftests/capabilities/Makefile new file mode 100644 index 000000000..8c8f0c1f0 --- /dev/null +++ b/tools/testing/selftests/capabilities/Makefile @@ -0,0 +1,18 @@ +all: + +include ../lib.mk + +.PHONY: all clean + +TARGETS := validate_cap test_execve +TEST_PROGS := test_execve + +CFLAGS := -O2 -g -std=gnu99 -Wall -lcap-ng + +all: $(TARGETS) + +clean: + $(RM) $(TARGETS) + +$(TARGETS): %: %.c + $(CC) -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c new file mode 100644 index 000000000..10a21a958 --- /dev/null +++ b/tools/testing/selftests/capabilities/test_execve.c @@ -0,0 +1,427 @@ +#define _GNU_SOURCE + +#include <cap-ng.h> +#include <err.h> +#include <linux/capability.h> +#include <stdbool.h> +#include <string.h> +#include <stdio.h> +#include <fcntl.h> +#include <errno.h> +#include <stdarg.h> +#include <sched.h> +#include <sys/mount.h> +#include <limits.h> +#include <libgen.h> +#include <malloc.h> +#include <sys/wait.h> +#include <sys/prctl.h> +#include <sys/stat.h> + +#ifndef PR_CAP_AMBIENT +#define PR_CAP_AMBIENT 47 +# define PR_CAP_AMBIENT_IS_SET 1 +# define PR_CAP_AMBIENT_RAISE 2 +# define PR_CAP_AMBIENT_LOWER 3 +# define PR_CAP_AMBIENT_CLEAR_ALL 4 +#endif + +static int nerrs; + +static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap) +{ + char buf[4096]; + int fd; + ssize_t written; + int buf_len; + + buf_len = vsnprintf(buf, sizeof(buf), fmt, ap); + if (buf_len < 0) { + err(1, "vsnprintf failed"); + } + if (buf_len >= sizeof(buf)) { + errx(1, "vsnprintf output truncated"); + } + + fd = open(filename, O_WRONLY); + if (fd < 0) { + if ((errno == ENOENT) && enoent_ok) + return; + err(1, "open of %s failed", filename); + } + written = write(fd, buf, buf_len); + if (written != buf_len) { + if (written >= 0) { + errx(1, "short write to %s", filename); + } else { + err(1, "write to %s failed", filename); + } + } + if (close(fd) != 0) { + err(1, "close of %s failed", filename); + } +} + +static void maybe_write_file(char *filename, char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vmaybe_write_file(true, filename, fmt, ap); + va_end(ap); +} + +static void write_file(char *filename, char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vmaybe_write_file(false, filename, fmt, ap); + va_end(ap); +} + +static bool create_and_enter_ns(uid_t inner_uid) +{ + uid_t outer_uid; + gid_t outer_gid; + int i; + bool have_outer_privilege; + + outer_uid = getuid(); + outer_gid = getgid(); + + /* + * TODO: If we're already root, we could skip creating the userns. + */ + + if (unshare(CLONE_NEWNS) == 0) { + printf("[NOTE]\tUsing global UIDs for tests\n"); + if (prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0) != 0) + err(1, "PR_SET_KEEPCAPS"); + if (setresuid(inner_uid, inner_uid, -1) != 0) + err(1, "setresuid"); + + // Re-enable effective caps + capng_get_caps_process(); + for (i = 0; i < CAP_LAST_CAP; i++) + if (capng_have_capability(CAPNG_PERMITTED, i)) + capng_update(CAPNG_ADD, CAPNG_EFFECTIVE, i); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + + have_outer_privilege = true; + } else if (unshare(CLONE_NEWUSER | CLONE_NEWNS) == 0) { + printf("[NOTE]\tUsing a user namespace for tests\n"); + maybe_write_file("/proc/self/setgroups", "deny"); + write_file("/proc/self/uid_map", "%d %d 1", inner_uid, outer_uid); + write_file("/proc/self/gid_map", "0 %d 1", outer_gid); + + have_outer_privilege = false; + } else { + errx(1, "must be root or be able to create a userns"); + } + + if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL) != 0) + err(1, "remount everything private"); + + return have_outer_privilege; +} + +static void chdir_to_tmpfs(void) +{ + char cwd[PATH_MAX]; + if (getcwd(cwd, sizeof(cwd)) != cwd) + err(1, "getcwd"); + + if (mount("private_tmp", ".", "tmpfs", 0, "mode=0777") != 0) + err(1, "mount private tmpfs"); + + if (chdir(cwd) != 0) + err(1, "chdir to private tmpfs"); + + if (umount2(".", MNT_DETACH) != 0) + err(1, "detach private tmpfs"); +} + +static void copy_fromat_to(int fromfd, const char *fromname, const char *toname) +{ + int from = openat(fromfd, fromname, O_RDONLY); + if (from == -1) + err(1, "open copy source"); + + int to = open(toname, O_CREAT | O_WRONLY | O_EXCL, 0700); + + while (true) { + char buf[4096]; + ssize_t sz = read(from, buf, sizeof(buf)); + if (sz == 0) + break; + if (sz < 0) + err(1, "read"); + + if (write(to, buf, sz) != sz) + err(1, "write"); /* no short writes on tmpfs */ + } + + close(from); + close(to); +} + +static bool fork_wait(void) +{ + pid_t child = fork(); + if (child == 0) { + nerrs = 0; + return true; + } else if (child > 0) { + int status; + if (waitpid(child, &status, 0) != child || + !WIFEXITED(status)) { + printf("[FAIL]\tChild died\n"); + nerrs++; + } else if (WEXITSTATUS(status) != 0) { + printf("[FAIL]\tChild failed\n"); + nerrs++; + } else { + printf("[OK]\tChild succeeded\n"); + } + + return false; + } else { + err(1, "fork"); + } +} + +static void exec_other_validate_cap(const char *name, + bool eff, bool perm, bool inh, bool ambient) +{ + execl(name, name, (eff ? "1" : "0"), + (perm ? "1" : "0"), (inh ? "1" : "0"), (ambient ? "1" : "0"), + NULL); + err(1, "execl"); +} + +static void exec_validate_cap(bool eff, bool perm, bool inh, bool ambient) +{ + exec_other_validate_cap("./validate_cap", eff, perm, inh, ambient); +} + +static int do_tests(int uid, const char *our_path) +{ + bool have_outer_privilege = create_and_enter_ns(uid); + + int ourpath_fd = open(our_path, O_RDONLY | O_DIRECTORY); + if (ourpath_fd == -1) + err(1, "open '%s'", our_path); + + chdir_to_tmpfs(); + + copy_fromat_to(ourpath_fd, "validate_cap", "validate_cap"); + + if (have_outer_privilege) { + uid_t gid = getegid(); + + copy_fromat_to(ourpath_fd, "validate_cap", + "validate_cap_suidroot"); + if (chown("validate_cap_suidroot", 0, -1) != 0) + err(1, "chown"); + if (chmod("validate_cap_suidroot", S_ISUID | 0700) != 0) + err(1, "chmod"); + + copy_fromat_to(ourpath_fd, "validate_cap", + "validate_cap_suidnonroot"); + if (chown("validate_cap_suidnonroot", uid + 1, -1) != 0) + err(1, "chown"); + if (chmod("validate_cap_suidnonroot", S_ISUID | 0700) != 0) + err(1, "chmod"); + + copy_fromat_to(ourpath_fd, "validate_cap", + "validate_cap_sgidroot"); + if (chown("validate_cap_sgidroot", -1, 0) != 0) + err(1, "chown"); + if (chmod("validate_cap_sgidroot", S_ISGID | 0710) != 0) + err(1, "chmod"); + + copy_fromat_to(ourpath_fd, "validate_cap", + "validate_cap_sgidnonroot"); + if (chown("validate_cap_sgidnonroot", -1, gid + 1) != 0) + err(1, "chown"); + if (chmod("validate_cap_sgidnonroot", S_ISGID | 0710) != 0) + err(1, "chmod"); +} + + capng_get_caps_process(); + + /* Make sure that i starts out clear */ + capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + + if (uid == 0) { + printf("[RUN]\tRoot => ep\n"); + if (fork_wait()) + exec_validate_cap(true, true, false, false); + } else { + printf("[RUN]\tNon-root => no caps\n"); + if (fork_wait()) + exec_validate_cap(false, false, false, false); + } + + printf("[OK]\tCheck cap_ambient manipulation rules\n"); + + /* We should not be able to add ambient caps yet. */ + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != -1 || errno != EPERM) { + if (errno == EINVAL) + printf("[FAIL]\tPR_CAP_AMBIENT_RAISE isn't supported\n"); + else + printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have failed eith EPERM on a non-inheritable cap\n"); + return 1; + } + printf("[OK]\tPR_CAP_AMBIENT_RAISE failed on non-inheritable cap\n"); + + capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_RAW); + capng_update(CAPNG_DROP, CAPNG_PERMITTED, CAP_NET_RAW); + capng_update(CAPNG_DROP, CAPNG_EFFECTIVE, CAP_NET_RAW); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_RAW, 0, 0, 0) != -1 || errno != EPERM) { + printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have failed on a non-permitted cap\n"); + return 1; + } + printf("[OK]\tPR_CAP_AMBIENT_RAISE failed on non-permitted cap\n"); + + capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { + printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have succeeded\n"); + return 1; + } + printf("[OK]\tPR_CAP_AMBIENT_RAISE worked\n"); + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 1) { + printf("[FAIL]\tPR_CAP_AMBIENT_IS_SET is broken\n"); + return 1; + } + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_CLEAR_ALL, 0, 0, 0, 0) != 0) + err(1, "PR_CAP_AMBIENT_CLEAR_ALL"); + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { + printf("[FAIL]\tPR_CAP_AMBIENT_CLEAR_ALL didn't work\n"); + return 1; + } + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) + err(1, "PR_CAP_AMBIENT_RAISE"); + + capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { + printf("[FAIL]\tDropping I should have dropped A\n"); + return 1; + } + + printf("[OK]\tBasic manipulation appears to work\n"); + + capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + if (uid == 0) { + printf("[RUN]\tRoot +i => eip\n"); + if (fork_wait()) + exec_validate_cap(true, true, true, false); + } else { + printf("[RUN]\tNon-root +i => i\n"); + if (fork_wait()) + exec_validate_cap(false, false, true, false); + } + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) + err(1, "PR_CAP_AMBIENT_RAISE"); + + printf("[RUN]\tUID %d +ia => eipa\n", uid); + if (fork_wait()) + exec_validate_cap(true, true, true, true); + + /* The remaining tests need real privilege */ + + if (!have_outer_privilege) { + printf("[SKIP]\tSUID/SGID tests (needs privilege)\n"); + goto done; + } + + if (uid == 0) { + printf("[RUN]\tRoot +ia, suidroot => eipa\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_suidroot", + true, true, true, true); + + printf("[RUN]\tRoot +ia, suidnonroot => ip\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_suidnonroot", + false, true, true, false); + + printf("[RUN]\tRoot +ia, sgidroot => eipa\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_sgidroot", + true, true, true, true); + + if (fork_wait()) { + printf("[RUN]\tRoot, gid != 0, +ia, sgidroot => eip\n"); + if (setresgid(1, 1, 1) != 0) + err(1, "setresgid"); + exec_other_validate_cap("./validate_cap_sgidroot", + true, true, true, false); + } + + printf("[RUN]\tRoot +ia, sgidnonroot => eip\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_sgidnonroot", + true, true, true, false); + } else { + printf("[RUN]\tNon-root +ia, sgidnonroot => i\n"); + exec_other_validate_cap("./validate_cap_sgidnonroot", + false, false, true, false); + + if (fork_wait()) { + printf("[RUN]\tNon-root +ia, sgidroot => i\n"); + if (setresgid(1, 1, 1) != 0) + err(1, "setresgid"); + exec_other_validate_cap("./validate_cap_sgidroot", + false, false, true, false); + } + } + +done: + return nerrs ? 1 : 0; +} + +int main(int argc, char **argv) +{ + char *tmp1, *tmp2, *our_path; + + /* Find our path */ + tmp1 = strdup(argv[0]); + if (!tmp1) + err(1, "strdup"); + tmp2 = dirname(tmp1); + our_path = strdup(tmp2); + if (!our_path) + err(1, "strdup"); + free(tmp1); + + if (fork_wait()) { + printf("[RUN]\t+++ Tests with uid == 0 +++\n"); + return do_tests(0, our_path); + } + + if (fork_wait()) { + printf("[RUN]\t+++ Tests with uid != 0 +++\n"); + return do_tests(1, our_path); + } + + return nerrs ? 1 : 0; +} diff --git a/tools/testing/selftests/capabilities/validate_cap.c b/tools/testing/selftests/capabilities/validate_cap.c new file mode 100644 index 000000000..dd3c45f7b --- /dev/null +++ b/tools/testing/selftests/capabilities/validate_cap.c @@ -0,0 +1,73 @@ +#include <cap-ng.h> +#include <err.h> +#include <linux/capability.h> +#include <stdbool.h> +#include <string.h> +#include <stdio.h> +#include <sys/prctl.h> +#include <sys/auxv.h> + +#ifndef PR_CAP_AMBIENT +#define PR_CAP_AMBIENT 47 +# define PR_CAP_AMBIENT_IS_SET 1 +# define PR_CAP_AMBIENT_RAISE 2 +# define PR_CAP_AMBIENT_LOWER 3 +# define PR_CAP_AMBIENT_CLEAR_ALL 4 +#endif + +#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ >= 19) +# define HAVE_GETAUXVAL +#endif + +static bool bool_arg(char **argv, int i) +{ + if (!strcmp(argv[i], "0")) + return false; + else if (!strcmp(argv[i], "1")) + return true; + else + errx(1, "wrong argv[%d]", i); +} + +int main(int argc, char **argv) +{ + const char *atsec = ""; + + /* + * Be careful just in case a setgid or setcapped copy of this + * helper gets out. + */ + + if (argc != 5) + errx(1, "wrong argc"); + +#ifdef HAVE_GETAUXVAL + if (getauxval(AT_SECURE)) + atsec = " (AT_SECURE is set)"; + else + atsec = " (AT_SECURE is not set)"; +#endif + + capng_get_caps_process(); + + if (capng_have_capability(CAPNG_EFFECTIVE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 1)) { + printf("[FAIL]\tWrong effective state%s\n", atsec); + return 1; + } + if (capng_have_capability(CAPNG_PERMITTED, CAP_NET_BIND_SERVICE) != bool_arg(argv, 2)) { + printf("[FAIL]\tWrong permitted state%s\n", atsec); + return 1; + } + if (capng_have_capability(CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 3)) { + printf("[FAIL]\tWrong inheritable state%s\n", atsec); + return 1; + } + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != bool_arg(argv, 4)) { + printf("[FAIL]\tWrong ambient state%s\n", atsec); + return 1; + } + + printf("[OK]\tCapabilities after execve were correct\n"); + return 0; +} diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index 6b76bfdc8..4e400eb83 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -1,6 +1,6 @@ CFLAGS = -Wall BINARIES = execveat -DEPS = execveat.symlink execveat.denatured script +DEPS = execveat.symlink execveat.denatured script subdir all: $(BINARIES) $(DEPS) subdir: @@ -22,7 +22,5 @@ TEST_FILES := $(DEPS) include ../lib.mk -override EMIT_TESTS := echo "mkdir -p subdir; (./execveat && echo \"selftests: execveat [PASS]\") || echo \"selftests: execveat [FAIL]\"" - clean: rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx* diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh index 3fc6c10c2..c4366dc74 100755 --- a/tools/testing/selftests/firmware/fw_filesystem.sh +++ b/tools/testing/selftests/firmware/fw_filesystem.sh @@ -9,7 +9,15 @@ modprobe test_firmware DIR=/sys/devices/virtual/misc/test_firmware -OLD_TIMEOUT=$(cat /sys/class/firmware/timeout) +# CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/ +# These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that +# as an indicator for CONFIG_FW_LOADER_USER_HELPER. +HAS_FW_LOADER_USER_HELPER=$(if [ -d /sys/class/firmware/ ]; then echo yes; else echo no; fi) + +if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then + OLD_TIMEOUT=$(cat /sys/class/firmware/timeout) +fi + OLD_FWPATH=$(cat /sys/module/firmware_class/parameters/path) FWPATH=$(mktemp -d) @@ -17,7 +25,9 @@ FW="$FWPATH/test-firmware.bin" test_finish() { - echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout + if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then + echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout + fi echo -n "$OLD_PATH" >/sys/module/firmware_class/parameters/path rm -f "$FW" rmdir "$FWPATH" @@ -25,8 +35,11 @@ test_finish() trap "test_finish" EXIT -# Turn down the timeout so failures don't take so long. -echo 1 >/sys/class/firmware/timeout +if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then + # Turn down the timeout so failures don't take so long. + echo 1 >/sys/class/firmware/timeout +fi + # Set the kernel search path. echo -n "$FWPATH" >/sys/module/firmware_class/parameters/path @@ -41,7 +54,9 @@ if diff -q "$FW" /dev/test_firmware >/dev/null ; then echo "$0: firmware was not expected to match" >&2 exit 1 else - echo "$0: timeout works" + if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then + echo "$0: timeout works" + fi fi # This should succeed via kernel load or will fail after 1 second after diff --git a/tools/testing/selftests/firmware/fw_userhelper.sh b/tools/testing/selftests/firmware/fw_userhelper.sh index 6efbade12..b9983f8e0 100755 --- a/tools/testing/selftests/firmware/fw_userhelper.sh +++ b/tools/testing/selftests/firmware/fw_userhelper.sh @@ -9,7 +9,17 @@ modprobe test_firmware DIR=/sys/devices/virtual/misc/test_firmware -OLD_TIMEOUT=$(cat /sys/class/firmware/timeout) +# CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/ +# These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that +# as an indicator for CONFIG_FW_LOADER_USER_HELPER. +HAS_FW_LOADER_USER_HELPER=$(if [ -d /sys/class/firmware/ ]; then echo yes; else echo no; fi) + +if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then + OLD_TIMEOUT=$(cat /sys/class/firmware/timeout) +else + echo "usermode helper disabled so ignoring test" + exit 0 +fi FWPATH=$(mktemp -d) FW="$FWPATH/test-firmware.bin" diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index 0acbeca47..4e6ed13e7 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,7 @@ all: TEST_PROGS := ftracetest -TEST_DIRS := test.d/ +TEST_DIRS := test.d include ../lib.mk diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index ee412bab7..50a93f5f1 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -12,11 +12,11 @@ run_tests: all $(RUN_TESTS) define INSTALL_RULE - mkdir -p $(INSTALL_PATH) - @for TEST_DIR in $(TEST_DIRS); do\ - cp -r $$TEST_DIR $(INSTALL_PATH); \ - done; - install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) + @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ + mkdir -p ${INSTALL_PATH}; \ + echo "rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ + rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ + fi endef install: all diff --git a/tools/testing/selftests/membarrier/.gitignore b/tools/testing/selftests/membarrier/.gitignore new file mode 100644 index 000000000..020c44f49 --- /dev/null +++ b/tools/testing/selftests/membarrier/.gitignore @@ -0,0 +1 @@ +membarrier_test diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile new file mode 100644 index 000000000..a1a970858 --- /dev/null +++ b/tools/testing/selftests/membarrier/Makefile @@ -0,0 +1,10 @@ +CFLAGS += -g -I../../../../usr/include/ + +TEST_PROGS := membarrier_test + +all: $(TEST_PROGS) + +include ../lib.mk + +clean: + $(RM) $(TEST_PROGS) diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c new file mode 100644 index 000000000..535f0fef4 --- /dev/null +++ b/tools/testing/selftests/membarrier/membarrier_test.c @@ -0,0 +1,118 @@ +#define _GNU_SOURCE +#include <linux/membarrier.h> +#include <syscall.h> +#include <stdio.h> +#include <errno.h> +#include <string.h> + +#include "../kselftest.h" + +enum test_membarrier_status { + TEST_MEMBARRIER_PASS = 0, + TEST_MEMBARRIER_FAIL, + TEST_MEMBARRIER_SKIP, +}; + +static int sys_membarrier(int cmd, int flags) +{ + return syscall(__NR_membarrier, cmd, flags); +} + +static enum test_membarrier_status test_membarrier_cmd_fail(void) +{ + int cmd = -1, flags = 0; + + if (sys_membarrier(cmd, flags) != -1) { + printf("membarrier: Wrong command should fail but passed.\n"); + return TEST_MEMBARRIER_FAIL; + } + return TEST_MEMBARRIER_PASS; +} + +static enum test_membarrier_status test_membarrier_flags_fail(void) +{ + int cmd = MEMBARRIER_CMD_QUERY, flags = 1; + + if (sys_membarrier(cmd, flags) != -1) { + printf("membarrier: Wrong flags should fail but passed.\n"); + return TEST_MEMBARRIER_FAIL; + } + return TEST_MEMBARRIER_PASS; +} + +static enum test_membarrier_status test_membarrier_success(void) +{ + int cmd = MEMBARRIER_CMD_SHARED, flags = 0; + + if (sys_membarrier(cmd, flags) != 0) { + printf("membarrier: Executing MEMBARRIER_CMD_SHARED failed. %s.\n", + strerror(errno)); + return TEST_MEMBARRIER_FAIL; + } + + printf("membarrier: MEMBARRIER_CMD_SHARED success.\n"); + return TEST_MEMBARRIER_PASS; +} + +static enum test_membarrier_status test_membarrier(void) +{ + enum test_membarrier_status status; + + status = test_membarrier_cmd_fail(); + if (status) + return status; + status = test_membarrier_flags_fail(); + if (status) + return status; + status = test_membarrier_success(); + if (status) + return status; + return TEST_MEMBARRIER_PASS; +} + +static enum test_membarrier_status test_membarrier_query(void) +{ + int flags = 0, ret; + + printf("membarrier MEMBARRIER_CMD_QUERY "); + ret = sys_membarrier(MEMBARRIER_CMD_QUERY, flags); + if (ret < 0) { + printf("failed. %s.\n", strerror(errno)); + switch (errno) { + case ENOSYS: + /* + * It is valid to build a kernel with + * CONFIG_MEMBARRIER=n. However, this skips the tests. + */ + return TEST_MEMBARRIER_SKIP; + case EINVAL: + default: + return TEST_MEMBARRIER_FAIL; + } + } + if (!(ret & MEMBARRIER_CMD_SHARED)) { + printf("command MEMBARRIER_CMD_SHARED is not supported.\n"); + return TEST_MEMBARRIER_FAIL; + } + printf("syscall available.\n"); + return TEST_MEMBARRIER_PASS; +} + +int main(int argc, char **argv) +{ + switch (test_membarrier_query()) { + case TEST_MEMBARRIER_FAIL: + return ksft_exit_fail(); + case TEST_MEMBARRIER_SKIP: + return ksft_exit_skip(); + } + switch (test_membarrier()) { + case TEST_MEMBARRIER_FAIL: + return ksft_exit_fail(); + case TEST_MEMBARRIER_SKIP: + return ksft_exit_skip(); + } + + printf("membarrier: tests done!\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 0e3b41eb8..eebac29ac 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -1,8 +1,8 @@ -CFLAGS = -O2 +CFLAGS += -O2 +LDLIBS = -lrt -lpthread -lpopt +TEST_PROGS := mq_open_tests mq_perf_tests -all: - $(CC) $(CFLAGS) mq_open_tests.c -o mq_open_tests -lrt - $(CC) $(CFLAGS) -o mq_perf_tests mq_perf_tests.c -lrt -lpthread -lpopt +all: $(TEST_PROGS) include ../lib.mk @@ -11,8 +11,6 @@ override define RUN_TESTS @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" endef -TEST_PROGS := mq_open_tests mq_perf_tests - override define EMIT_TESTS echo "./mq_open_tests /test1 || echo \"selftests: mq_open_tests [FAIL]\"" echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\"" diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 08c2a36ef..412459369 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -19,6 +19,8 @@ * - PACKET_FANOUT_LB * - PACKET_FANOUT_CPU * - PACKET_FANOUT_ROLLOVER + * - PACKET_FANOUT_CBPF + * - PACKET_FANOUT_EBPF * * Todo: * - functionality: PACKET_FANOUT_FLAG_DEFRAG @@ -44,7 +46,9 @@ #include <arpa/inet.h> #include <errno.h> #include <fcntl.h> +#include <linux/unistd.h> /* for __NR_bpf */ #include <linux/filter.h> +#include <linux/bpf.h> #include <linux/if_packet.h> #include <net/ethernet.h> #include <netinet/ip.h> @@ -91,6 +95,51 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets) return fd; } +static void sock_fanout_set_ebpf(int fd) +{ + const int len_off = __builtin_offsetof(struct __sk_buff, len); + struct bpf_insn prog[] = { + { BPF_ALU64 | BPF_MOV | BPF_X, 6, 1, 0, 0 }, + { BPF_LDX | BPF_W | BPF_MEM, 0, 6, len_off, 0 }, + { BPF_JMP | BPF_JGE | BPF_K, 0, 0, 1, DATA_LEN }, + { BPF_JMP | BPF_JA | BPF_K, 0, 0, 4, 0 }, + { BPF_LD | BPF_B | BPF_ABS, 0, 0, 0, 0x50 }, + { BPF_JMP | BPF_JEQ | BPF_K, 0, 0, 2, DATA_CHAR }, + { BPF_JMP | BPF_JEQ | BPF_K, 0, 0, 1, DATA_CHAR_1 }, + { BPF_ALU | BPF_MOV | BPF_K, 0, 0, 0, 0 }, + { BPF_JMP | BPF_EXIT, 0, 0, 0, 0 } + }; + char log_buf[512]; + union bpf_attr attr; + int pfd; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = (unsigned long) prog; + attr.insn_cnt = sizeof(prog) / sizeof(prog[0]); + attr.license = (unsigned long) "GPL"; + attr.log_buf = (unsigned long) log_buf, + attr.log_size = sizeof(log_buf), + attr.log_level = 1, + + pfd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + if (pfd < 0) { + perror("bpf"); + fprintf(stderr, "bpf verifier:\n%s\n", log_buf); + exit(1); + } + + if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &pfd, sizeof(pfd))) { + perror("fanout data ebpf"); + exit(1); + } + + if (close(pfd)) { + perror("close ebpf"); + exit(1); + } +} + static char *sock_fanout_open_ring(int fd) { struct tpacket_req req = { @@ -115,8 +164,8 @@ static char *sock_fanout_open_ring(int fd) ring = mmap(0, req.tp_block_size * req.tp_block_nr, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - if (!ring) { - fprintf(stderr, "packetsock ring mmap\n"); + if (ring == MAP_FAILED) { + perror("packetsock ring mmap"); exit(1); } @@ -209,6 +258,7 @@ static int test_datapath(uint16_t typeflags, int port_off, { const int expect0[] = { 0, 0 }; char *rings[2]; + uint8_t type = typeflags & 0xFF; int fds[2], fds_udp[2][2], ret; fprintf(stderr, "test: datapath 0x%hx\n", typeflags); @@ -219,6 +269,11 @@ static int test_datapath(uint16_t typeflags, int port_off, fprintf(stderr, "ERROR: failed open\n"); exit(1); } + if (type == PACKET_FANOUT_CBPF) + sock_setfilter(fds[0], SOL_PACKET, PACKET_FANOUT_DATA); + else if (type == PACKET_FANOUT_EBPF) + sock_fanout_set_ebpf(fds[0]); + rings[0] = sock_fanout_open_ring(fds[0]); rings[1] = sock_fanout_open_ring(fds[1]); pair_udp_open(fds_udp[0], PORT_BASE); @@ -227,11 +282,11 @@ static int test_datapath(uint16_t typeflags, int port_off, /* Send data, but not enough to overflow a queue */ pair_udp_send(fds_udp[0], 15); - pair_udp_send(fds_udp[1], 5); + pair_udp_send_char(fds_udp[1], 5, DATA_CHAR_1); ret = sock_fanout_read(fds, rings, expect1); /* Send more data, overflow the queue */ - pair_udp_send(fds_udp[0], 15); + pair_udp_send_char(fds_udp[0], 15, DATA_CHAR_1); /* TODO: ensure consistent order between expect1 and expect2 */ ret |= sock_fanout_read(fds, rings, expect2); @@ -275,6 +330,7 @@ int main(int argc, char **argv) const int expect_rb[2][2] = { { 15, 5 }, { 20, 15 } }; const int expect_cpu0[2][2] = { { 20, 0 }, { 20, 0 } }; const int expect_cpu1[2][2] = { { 0, 20 }, { 0, 20 } }; + const int expect_bpf[2][2] = { { 15, 5 }, { 15, 20 } }; int port_off = 2, tries = 5, ret; test_control_single(); @@ -296,6 +352,11 @@ int main(int argc, char **argv) ret |= test_datapath(PACKET_FANOUT_ROLLOVER, port_off, expect_rb[0], expect_rb[1]); + ret |= test_datapath(PACKET_FANOUT_CBPF, + port_off, expect_bpf[0], expect_bpf[1]); + ret |= test_datapath(PACKET_FANOUT_EBPF, + port_off, expect_bpf[0], expect_bpf[1]); + set_cpuaffinity(0); ret |= test_datapath(PACKET_FANOUT_CPU, port_off, expect_cpu0[0], expect_cpu0[1]); diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h index 37da54ac8..24bc7ec1b 100644 --- a/tools/testing/selftests/net/psock_lib.h +++ b/tools/testing/selftests/net/psock_lib.h @@ -30,6 +30,7 @@ #define DATA_LEN 100 #define DATA_CHAR 'a' +#define DATA_CHAR_1 'b' #define PORT_BASE 8000 @@ -37,29 +38,36 @@ # define __maybe_unused __attribute__ ((__unused__)) #endif -static __maybe_unused void pair_udp_setfilter(int fd) +static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum) { struct sock_filter bpf_filter[] = { { 0x80, 0, 0, 0x00000000 }, /* LD pktlen */ - { 0x35, 0, 5, DATA_LEN }, /* JGE DATA_LEN [f goto nomatch]*/ + { 0x35, 0, 4, DATA_LEN }, /* JGE DATA_LEN [f goto nomatch]*/ { 0x30, 0, 0, 0x00000050 }, /* LD ip[80] */ - { 0x15, 0, 3, DATA_CHAR }, /* JEQ DATA_CHAR [f goto nomatch]*/ - { 0x30, 0, 0, 0x00000051 }, /* LD ip[81] */ - { 0x15, 0, 1, DATA_CHAR }, /* JEQ DATA_CHAR [f goto nomatch]*/ + { 0x15, 1, 0, DATA_CHAR }, /* JEQ DATA_CHAR [t goto match]*/ + { 0x15, 0, 1, DATA_CHAR_1}, /* JEQ DATA_CHAR_1 [t goto match]*/ { 0x06, 0, 0, 0x00000060 }, /* RET match */ { 0x06, 0, 0, 0x00000000 }, /* RET no match */ }; struct sock_fprog bpf_prog; + if (lvl == SOL_PACKET && optnum == PACKET_FANOUT_DATA) + bpf_filter[5].code = 0x16; /* RET A */ + bpf_prog.filter = bpf_filter; bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); - if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog, + if (setsockopt(fd, lvl, optnum, &bpf_prog, sizeof(bpf_prog))) { perror("setsockopt SO_ATTACH_FILTER"); exit(1); } } +static __maybe_unused void pair_udp_setfilter(int fd) +{ + sock_setfilter(fd, SOL_SOCKET, SO_ATTACH_FILTER); +} + static __maybe_unused void pair_udp_open(int fds[], uint16_t port) { struct sockaddr_in saddr, daddr; @@ -96,11 +104,11 @@ static __maybe_unused void pair_udp_open(int fds[], uint16_t port) } } -static __maybe_unused void pair_udp_send(int fds[], int num) +static __maybe_unused void pair_udp_send_char(int fds[], int num, char payload) { char buf[DATA_LEN], rbuf[DATA_LEN]; - memset(buf, DATA_CHAR, sizeof(buf)); + memset(buf, payload, sizeof(buf)); while (num--) { /* Should really handle EINTR and EAGAIN */ if (write(fds[0], buf, sizeof(buf)) != sizeof(buf)) { @@ -118,6 +126,11 @@ static __maybe_unused void pair_udp_send(int fds[], int num) } } +static __maybe_unused void pair_udp_send(int fds[], int num) +{ + return pair_udp_send_char(fds, num, DATA_CHAR); +} + static __maybe_unused void pair_udp_close(int fds[]) { close(fds[0]); diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 41cc3ed66..ee179e223 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -2,8 +2,9 @@ noarg: $(MAKE) -C ../ TEST_PROGS := hugetlb_vs_thp_test subpage_prot +TEST_FILES := tempfile -all: $(TEST_PROGS) tempfile +all: $(TEST_PROGS) $(TEST_FILES) $(TEST_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c index d1b647509..6cae06117 100644 --- a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c +++ b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c @@ -25,10 +25,19 @@ #define FIXUP_SECTION ".ex_fixup" +static inline unsigned long __fls(unsigned long x); + #include "word-at-a-time.h" #include "utils.h" +static inline unsigned long __fls(unsigned long x) +{ + int lz; + + asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (x)); + return sizeof(unsigned long) - 1 - lz; +} static int page_size; static char *mem_region; diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 index 2cc0e60eb..bafe94cbd 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 @@ -5,6 +5,6 @@ CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y CONFIG_DEBUG_LOCK_ALLOC=y -CONFIG_PROVE_LOCKING=n -#CHECK#CONFIG_PROVE_RCU=n +CONFIG_PROVE_LOCKING=y +#CHECK#CONFIG_PROVE_RCU=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 8e9137f66..f572b873c 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -13,7 +13,6 @@ CONFIG_MAXSMP=y CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index aeea6a204..ef6a22c44 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -17,7 +17,6 @@ CONFIG_RCU_FANOUT_LEAF=3 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T index 2ac9e68ea..917d2517b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T @@ -17,6 +17,5 @@ CONFIG_RCU_FANOUT_LEAF=3 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index 72aa7d87e..7a17c503b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -13,7 +13,6 @@ CONFIG_RCU_FANOUT=2 CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=y CONFIG_RCU_KTHREAD_PRIO=2 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 3f5112751..39a2c6d7d 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -17,6 +17,5 @@ CONFIG_RCU_FANOUT=4 CONFIG_RCU_FANOUT_LEAF=4 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index c04dfea6f..1257d3227 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -17,6 +17,5 @@ CONFIG_RCU_NOCB_CPU_NONE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index f51d2c73a..d3e456b74 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -18,6 +18,5 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index f422af4ff..3956b4131 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -17,6 +17,5 @@ CONFIG_RCU_FANOUT=2 CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index a24d2ca30..bb9b0c1a2 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -19,7 +19,6 @@ CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T index b2b8cea69..2ad13f0d2 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T @@ -17,6 +17,5 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 index aa4ed08d9..6710e749d 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 @@ -13,7 +13,6 @@ CONFIG_SUSPEND=n CONFIG_HIBERNATION=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n #CHECK#CONFIG_RCU_EXPERT=n diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index b24c0004f..657f3a035 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -16,7 +16,6 @@ CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not. CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING. CONFIG_RCU_BOOST -- one of PREEMPT_RCU. CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing. -CONFIG_RCU_CPU_STALL_INFO -- Now default, avoid at least twice. CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others. CONFIG_RCU_FANOUT_LEAF -- Do one non-default. CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL. diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index c5abe7fd7..770f47adf 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -14,6 +14,7 @@ #include <linux/filter.h> #include <sys/prctl.h> #include <sys/ptrace.h> +#include <sys/types.h> #include <sys/user.h> #include <linux/prctl.h> #include <linux/ptrace.h> @@ -82,7 +83,13 @@ struct seccomp_data { }; #endif +#if __BYTE_ORDER == __LITTLE_ENDIAN #define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n])) +#elif __BYTE_ORDER == __BIG_ENDIAN +#define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]) + sizeof(__u32)) +#else +#error "wut? Unknown __BYTE_ORDER?!" +#endif #define SIBLING_EXIT_UNKILLED 0xbadbeef #define SIBLING_EXIT_FAILURE 0xbadface @@ -1199,6 +1206,14 @@ TEST_F(TRACE_poke, getpid_runs_normally) # define ARCH_REGS struct user_pt_regs # define SYSCALL_NUM regs[8] # define SYSCALL_RET regs[0] +#elif defined(__powerpc__) +# define ARCH_REGS struct pt_regs +# define SYSCALL_NUM gpr[0] +# define SYSCALL_RET gpr[3] +#elif defined(__s390__) +# define ARCH_REGS s390_regs +# define SYSCALL_NUM gprs[2] +# define SYSCALL_RET gprs[2] #else # error "Do not know how to find your architecture's registers and syscalls" #endif @@ -1232,7 +1247,8 @@ void change_syscall(struct __test_metadata *_metadata, ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov); EXPECT_EQ(0, ret); -#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) +#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) || \ + defined(__powerpc__) || defined(__s390__) { regs.SYSCALL_NUM = syscall; } @@ -1270,17 +1286,21 @@ void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg); EXPECT_EQ(0, ret); + /* Validate and take action on expected syscalls. */ switch (msg) { case 0x1002: /* change getpid to getppid. */ + EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee)); change_syscall(_metadata, tracee, __NR_getppid); break; case 0x1003: /* skip gettid. */ + EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee)); change_syscall(_metadata, tracee, -1); break; case 0x1004: /* do nothing (allow getppid) */ + EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee)); break; default: EXPECT_EQ(0, msg) { @@ -1396,6 +1416,10 @@ TEST_F(TRACE_syscall, syscall_dropped) # define __NR_seccomp 383 # elif defined(__aarch64__) # define __NR_seccomp 277 +# elif defined(__powerpc__) +# define __NR_seccomp 358 +# elif defined(__s390__) +# define __NR_seccomp 348 # else # warning "seccomp syscall number unknown for this architecture" # define __NR_seccomp 0xffff @@ -1440,6 +1464,9 @@ TEST(seccomp_syscall) /* Reject insane operation. */ ret = seccomp(-1, 0, &prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } EXPECT_EQ(EINVAL, errno) { TH_LOG("Did not reject crazy op value!"); } @@ -1488,6 +1515,9 @@ TEST(seccomp_syscall_mode_lock) } ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } EXPECT_EQ(0, ret) { TH_LOG("Could not install filter!"); } @@ -1522,6 +1552,9 @@ TEST(TSYNC_first) ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, &prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } EXPECT_EQ(0, ret) { TH_LOG("Could not install initial filter with TSYNC!"); } @@ -1681,6 +1714,9 @@ TEST_F(TSYNC, siblings_fail_prctl) /* Check prctl failure detection by requesting sib 0 diverge. */ ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("setting filter failed"); } @@ -1718,6 +1754,9 @@ TEST_F(TSYNC, two_siblings_with_ancestor) } ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!"); } @@ -1792,6 +1831,9 @@ TEST_F(TSYNC, two_siblings_with_no_filter) ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, &self->apply_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("Could install filter on all threads!"); } @@ -1820,6 +1862,9 @@ TEST_F(TSYNC, two_siblings_with_one_divergence) } ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!"); } @@ -1877,6 +1922,9 @@ TEST_F(TSYNC, two_siblings_not_under_filter) } ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!"); } diff --git a/tools/testing/selftests/seccomp/test_harness.h b/tools/testing/selftests/seccomp/test_harness.h index 977a6afc4..fb2841601 100644 --- a/tools/testing/selftests/seccomp/test_harness.h +++ b/tools/testing/selftests/seccomp/test_harness.h @@ -370,11 +370,8 @@ __typeof__(_expected) __exp = (_expected); \ __typeof__(_seen) __seen = (_seen); \ if (!(__exp _t __seen)) { \ - unsigned long long __exp_print = 0; \ - unsigned long long __seen_print = 0; \ - /* Avoid casting complaints the scariest way we can. */ \ - memcpy(&__exp_print, &__exp, sizeof(__exp)); \ - memcpy(&__seen_print, &__seen, sizeof(__seen)); \ + unsigned long long __exp_print = (unsigned long long)__exp; \ + unsigned long long __seen_print = (unsigned long long)__seen; \ __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ #_expected, __exp_print, #_t, \ #_seen, __seen_print); \ diff --git a/tools/testing/selftests/static_keys/Makefile b/tools/testing/selftests/static_keys/Makefile new file mode 100644 index 000000000..9cdadf37f --- /dev/null +++ b/tools/testing/selftests/static_keys/Makefile @@ -0,0 +1,8 @@ +# Makefile for static keys selftests + +# No binaries, but make sure arg-less "make" doesn't trigger "run_tests" +all: + +TEST_PROGS := test_static_keys.sh + +include ../lib.mk diff --git a/tools/testing/selftests/static_keys/test_static_keys.sh b/tools/testing/selftests/static_keys/test_static_keys.sh new file mode 100644 index 000000000..1261e3fa1 --- /dev/null +++ b/tools/testing/selftests/static_keys/test_static_keys.sh @@ -0,0 +1,16 @@ +#!/bin/sh +# Runs static keys kernel module tests + +if /sbin/modprobe -q test_static_key_base; then + if /sbin/modprobe -q test_static_keys; then + echo "static_key: ok" + /sbin/modprobe -q -r test_static_keys + /sbin/modprobe -q -r test_static_key_base + else + echo "static_keys: [FAIL]" + /sbin/modprobe -q -r test_static_key_base + fi +else + echo "static_key: [FAIL]" + exit 1 +fi diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 231b9a031..3c53cac15 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,17 +1,22 @@ # Makefile for vm selftests -CFLAGS = -Wall +CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) BINARIES = compaction_test BINARIES += hugepage-mmap BINARIES += hugepage-shm -BINARIES += hugetlbfstest BINARIES += map_hugetlb BINARIES += thuge-gen BINARIES += transhuge-stress +BINARIES += userfaultfd all: $(BINARIES) %: %.c $(CC) $(CFLAGS) -o $@ $^ -lrt +userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h + $(CC) $(CFLAGS) -O2 -o $@ $< -lpthread + +../../../../usr/include/linux/kernel.h: + make -C ../../../.. headers_install TEST_PROGS := run_vmtests TEST_FILES := $(BINARIES) diff --git a/tools/testing/selftests/vm/hugetlbfstest.c b/tools/testing/selftests/vm/hugetlbfstest.c deleted file mode 100644 index 02e1072ec..000000000 --- a/tools/testing/selftests/vm/hugetlbfstest.c +++ /dev/null @@ -1,86 +0,0 @@ -#define _GNU_SOURCE -#include <assert.h> -#include <fcntl.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/mman.h> -#include <sys/stat.h> -#include <sys/types.h> -#include <unistd.h> - -typedef unsigned long long u64; - -static size_t length = 1 << 24; - -static u64 read_rss(void) -{ - char buf[4096], *s = buf; - int i, fd; - u64 rss; - - fd = open("/proc/self/statm", O_RDONLY); - assert(fd > 2); - memset(buf, 0, sizeof(buf)); - read(fd, buf, sizeof(buf) - 1); - for (i = 0; i < 1; i++) - s = strchr(s, ' ') + 1; - rss = strtoull(s, NULL, 10); - return rss << 12; /* assumes 4k pagesize */ -} - -static void do_mmap(int fd, int extra_flags, int unmap) -{ - int *p; - int flags = MAP_PRIVATE | MAP_POPULATE | extra_flags; - u64 before, after; - int ret; - - before = read_rss(); - p = mmap(NULL, length, PROT_READ | PROT_WRITE, flags, fd, 0); - assert(p != MAP_FAILED || - !"mmap returned an unexpected error"); - after = read_rss(); - assert(llabs(after - before - length) < 0x40000 || - !"rss didn't grow as expected"); - if (!unmap) - return; - ret = munmap(p, length); - assert(!ret || !"munmap returned an unexpected error"); - after = read_rss(); - assert(llabs(after - before) < 0x40000 || - !"rss didn't shrink as expected"); -} - -static int open_file(const char *path) -{ - int fd, err; - - unlink(path); - fd = open(path, O_CREAT | O_RDWR | O_TRUNC | O_EXCL - | O_LARGEFILE | O_CLOEXEC, 0600); - assert(fd > 2); - unlink(path); - err = ftruncate(fd, length); - assert(!err); - return fd; -} - -int main(void) -{ - int hugefd, fd; - - fd = open_file("/dev/shm/hugetlbhog"); - hugefd = open_file("/hugepages/hugetlbhog"); - - system("echo 100 > /proc/sys/vm/nr_hugepages"); - do_mmap(-1, MAP_ANONYMOUS, 1); - do_mmap(fd, 0, 1); - do_mmap(-1, MAP_ANONYMOUS | MAP_HUGETLB, 1); - do_mmap(hugefd, 0, 1); - do_mmap(hugefd, MAP_HUGETLB, 1); - /* Leak the last one to test do_exit() */ - do_mmap(-1, MAP_ANONYMOUS | MAP_HUGETLB, 0); - printf("oll korrekt.\n"); - return 0; -} diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index 49ece11ff..9179ce8df 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -75,10 +75,14 @@ else echo "[PASS]" fi +echo "NOTE: The above hugetlb tests provide minimal coverage. Use" +echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" +echo " hugetlb regression testing." + echo "--------------------" -echo "running hugetlbfstest" +echo "running userfaultfd" echo "--------------------" -./hugetlbfstest +./userfaultfd 128 32 if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c new file mode 100644 index 000000000..d77ed41b2 --- /dev/null +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -0,0 +1,645 @@ +/* + * Stress userfaultfd syscall. + * + * Copyright (C) 2015 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * This test allocates two virtual areas and bounces the physical + * memory across the two virtual areas (from area_src to area_dst) + * using userfaultfd. + * + * There are three threads running per CPU: + * + * 1) one per-CPU thread takes a per-page pthread_mutex in a random + * page of the area_dst (while the physical page may still be in + * area_src), and increments a per-page counter in the same page, + * and checks its value against a verification region. + * + * 2) another per-CPU thread handles the userfaults generated by + * thread 1 above. userfaultfd blocking reads or poll() modes are + * exercised interleaved. + * + * 3) one last per-CPU thread transfers the memory in the background + * at maximum bandwidth (if not already transferred by thread + * 2). Each cpu thread takes cares of transferring a portion of the + * area. + * + * When all threads of type 3 completed the transfer, one bounce is + * complete. area_src and area_dst are then swapped. All threads are + * respawned and so the bounce is immediately restarted in the + * opposite direction. + * + * per-CPU threads 1 by triggering userfaults inside + * pthread_mutex_lock will also verify the atomicity of the memory + * transfer (UFFDIO_COPY). + * + * The program takes two parameters: the amounts of physical memory in + * megabytes (MiB) of the area and the number of bounces to execute. + * + * # 100MiB 99999 bounces + * ./userfaultfd 100 99999 + * + * # 1GiB 99 bounces + * ./userfaultfd 1000 99 + * + * # 10MiB-~6GiB 999 bounces, continue forever unless an error triggers + * while ./userfaultfd $[RANDOM % 6000 + 10] 999; do true; done + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <errno.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <time.h> +#include <signal.h> +#include <poll.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <sys/ioctl.h> +#include <pthread.h> +#include <linux/userfaultfd.h> + +#ifdef __NR_userfaultfd + +static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; + +#define BOUNCE_RANDOM (1<<0) +#define BOUNCE_RACINGFAULTS (1<<1) +#define BOUNCE_VERIFY (1<<2) +#define BOUNCE_POLL (1<<3) +static int bounces; + +static unsigned long long *count_verify; +static int uffd, finished, *pipefd; +static char *area_src, *area_dst; +static char *zeropage; +pthread_attr_t attr; + +/* pthread_mutex_t starts at page offset 0 */ +#define area_mutex(___area, ___nr) \ + ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) +/* + * count is placed in the page after pthread_mutex_t naturally aligned + * to avoid non alignment faults on non-x86 archs. + */ +#define area_count(___area, ___nr) \ + ((volatile unsigned long long *) ((unsigned long) \ + ((___area) + (___nr)*page_size + \ + sizeof(pthread_mutex_t) + \ + sizeof(unsigned long long) - 1) & \ + ~(unsigned long)(sizeof(unsigned long long) \ + - 1))) + +static int my_bcmp(char *str1, char *str2, size_t n) +{ + unsigned long i; + for (i = 0; i < n; i++) + if (str1[i] != str2[i]) + return 1; + return 0; +} + +static void *locking_thread(void *arg) +{ + unsigned long cpu = (unsigned long) arg; + struct random_data rand; + unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */ + int32_t rand_nr; + unsigned long long count; + char randstate[64]; + unsigned int seed; + time_t start; + + if (bounces & BOUNCE_RANDOM) { + seed = (unsigned int) time(NULL) - bounces; + if (!(bounces & BOUNCE_RACINGFAULTS)) + seed += cpu; + bzero(&rand, sizeof(rand)); + bzero(&randstate, sizeof(randstate)); + if (initstate_r(seed, randstate, sizeof(randstate), &rand)) + fprintf(stderr, "srandom_r error\n"), exit(1); + } else { + page_nr = -bounces; + if (!(bounces & BOUNCE_RACINGFAULTS)) + page_nr += cpu * nr_pages_per_cpu; + } + + while (!finished) { + if (bounces & BOUNCE_RANDOM) { + if (random_r(&rand, &rand_nr)) + fprintf(stderr, "random_r 1 error\n"), exit(1); + page_nr = rand_nr; + if (sizeof(page_nr) > sizeof(rand_nr)) { + if (random_r(&rand, &rand_nr)) + fprintf(stderr, "random_r 2 error\n"), exit(1); + page_nr |= (((unsigned long) rand_nr) << 16) << + 16; + } + } else + page_nr += 1; + page_nr %= nr_pages; + + start = time(NULL); + if (bounces & BOUNCE_VERIFY) { + count = *area_count(area_dst, page_nr); + if (!count) + fprintf(stderr, + "page_nr %lu wrong count %Lu %Lu\n", + page_nr, count, + count_verify[page_nr]), exit(1); + + + /* + * We can't use bcmp (or memcmp) because that + * returns 0 erroneously if the memory is + * changing under it (even if the end of the + * page is never changing and always + * different). + */ +#if 1 + if (!my_bcmp(area_dst + page_nr * page_size, zeropage, + page_size)) + fprintf(stderr, + "my_bcmp page_nr %lu wrong count %Lu %Lu\n", + page_nr, count, + count_verify[page_nr]), exit(1); +#else + unsigned long loops; + + loops = 0; + /* uncomment the below line to test with mutex */ + /* pthread_mutex_lock(area_mutex(area_dst, page_nr)); */ + while (!bcmp(area_dst + page_nr * page_size, zeropage, + page_size)) { + loops += 1; + if (loops > 10) + break; + } + /* uncomment below line to test with mutex */ + /* pthread_mutex_unlock(area_mutex(area_dst, page_nr)); */ + if (loops) { + fprintf(stderr, + "page_nr %lu all zero thread %lu %p %lu\n", + page_nr, cpu, area_dst + page_nr * page_size, + loops); + if (loops > 10) + exit(1); + } +#endif + } + + pthread_mutex_lock(area_mutex(area_dst, page_nr)); + count = *area_count(area_dst, page_nr); + if (count != count_verify[page_nr]) { + fprintf(stderr, + "page_nr %lu memory corruption %Lu %Lu\n", + page_nr, count, + count_verify[page_nr]), exit(1); + } + count++; + *area_count(area_dst, page_nr) = count_verify[page_nr] = count; + pthread_mutex_unlock(area_mutex(area_dst, page_nr)); + + if (time(NULL) - start > 1) + fprintf(stderr, + "userfault too slow %ld " + "possible false positive with overcommit\n", + time(NULL) - start); + } + + return NULL; +} + +static int copy_page(unsigned long offset) +{ + struct uffdio_copy uffdio_copy; + + if (offset >= nr_pages * page_size) + fprintf(stderr, "unexpected offset %lu\n", + offset), exit(1); + uffdio_copy.dst = (unsigned long) area_dst + offset; + uffdio_copy.src = (unsigned long) area_src + offset; + uffdio_copy.len = page_size; + uffdio_copy.mode = 0; + uffdio_copy.copy = 0; + if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy)) { + /* real retval in ufdio_copy.copy */ + if (uffdio_copy.copy != -EEXIST) + fprintf(stderr, "UFFDIO_COPY error %Ld\n", + uffdio_copy.copy), exit(1); + } else if (uffdio_copy.copy != page_size) { + fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n", + uffdio_copy.copy), exit(1); + } else + return 1; + return 0; +} + +static void *uffd_poll_thread(void *arg) +{ + unsigned long cpu = (unsigned long) arg; + struct pollfd pollfd[2]; + struct uffd_msg msg; + int ret; + unsigned long offset; + char tmp_chr; + unsigned long userfaults = 0; + + pollfd[0].fd = uffd; + pollfd[0].events = POLLIN; + pollfd[1].fd = pipefd[cpu*2]; + pollfd[1].events = POLLIN; + + for (;;) { + ret = poll(pollfd, 2, -1); + if (!ret) + fprintf(stderr, "poll error %d\n", ret), exit(1); + if (ret < 0) + perror("poll"), exit(1); + if (pollfd[1].revents & POLLIN) { + if (read(pollfd[1].fd, &tmp_chr, 1) != 1) + fprintf(stderr, "read pipefd error\n"), + exit(1); + break; + } + if (!(pollfd[0].revents & POLLIN)) + fprintf(stderr, "pollfd[0].revents %d\n", + pollfd[0].revents), exit(1); + ret = read(uffd, &msg, sizeof(msg)); + if (ret < 0) { + if (errno == EAGAIN) + continue; + perror("nonblocking read error"), exit(1); + } + if (msg.event != UFFD_EVENT_PAGEFAULT) + fprintf(stderr, "unexpected msg event %u\n", + msg.event), exit(1); + if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + fprintf(stderr, "unexpected write fault\n"), exit(1); + offset = (char *)(unsigned long)msg.arg.pagefault.address - + area_dst; + offset &= ~(page_size-1); + if (copy_page(offset)) + userfaults++; + } + return (void *)userfaults; +} + +pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; + +static void *uffd_read_thread(void *arg) +{ + unsigned long *this_cpu_userfaults; + struct uffd_msg msg; + unsigned long offset; + int ret; + + this_cpu_userfaults = (unsigned long *) arg; + *this_cpu_userfaults = 0; + + pthread_mutex_unlock(&uffd_read_mutex); + /* from here cancellation is ok */ + + for (;;) { + ret = read(uffd, &msg, sizeof(msg)); + if (ret != sizeof(msg)) { + if (ret < 0) + perror("blocking read error"), exit(1); + else + fprintf(stderr, "short read\n"), exit(1); + } + if (msg.event != UFFD_EVENT_PAGEFAULT) + fprintf(stderr, "unexpected msg event %u\n", + msg.event), exit(1); + if (bounces & BOUNCE_VERIFY && + msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + fprintf(stderr, "unexpected write fault\n"), exit(1); + offset = (char *)(unsigned long)msg.arg.pagefault.address - + area_dst; + offset &= ~(page_size-1); + if (copy_page(offset)) + (*this_cpu_userfaults)++; + } + return (void *)NULL; +} + +static void *background_thread(void *arg) +{ + unsigned long cpu = (unsigned long) arg; + unsigned long page_nr; + + for (page_nr = cpu * nr_pages_per_cpu; + page_nr < (cpu+1) * nr_pages_per_cpu; + page_nr++) + copy_page(page_nr * page_size); + + return NULL; +} + +static int stress(unsigned long *userfaults) +{ + unsigned long cpu; + pthread_t locking_threads[nr_cpus]; + pthread_t uffd_threads[nr_cpus]; + pthread_t background_threads[nr_cpus]; + void **_userfaults = (void **) userfaults; + + finished = 0; + for (cpu = 0; cpu < nr_cpus; cpu++) { + if (pthread_create(&locking_threads[cpu], &attr, + locking_thread, (void *)cpu)) + return 1; + if (bounces & BOUNCE_POLL) { + if (pthread_create(&uffd_threads[cpu], &attr, + uffd_poll_thread, (void *)cpu)) + return 1; + } else { + if (pthread_create(&uffd_threads[cpu], &attr, + uffd_read_thread, + &_userfaults[cpu])) + return 1; + pthread_mutex_lock(&uffd_read_mutex); + } + if (pthread_create(&background_threads[cpu], &attr, + background_thread, (void *)cpu)) + return 1; + } + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pthread_join(background_threads[cpu], NULL)) + return 1; + + /* + * Be strict and immediately zap area_src, the whole area has + * been transferred already by the background treads. The + * area_src could then be faulted in in a racy way by still + * running uffdio_threads reading zeropages after we zapped + * area_src (but they're guaranteed to get -EEXIST from + * UFFDIO_COPY without writing zero pages into area_dst + * because the background threads already completed). + */ + if (madvise(area_src, nr_pages * page_size, MADV_DONTNEED)) { + perror("madvise"); + return 1; + } + + for (cpu = 0; cpu < nr_cpus; cpu++) { + char c; + if (bounces & BOUNCE_POLL) { + if (write(pipefd[cpu*2+1], &c, 1) != 1) { + fprintf(stderr, "pipefd write error\n"); + return 1; + } + if (pthread_join(uffd_threads[cpu], &_userfaults[cpu])) + return 1; + } else { + if (pthread_cancel(uffd_threads[cpu])) + return 1; + if (pthread_join(uffd_threads[cpu], NULL)) + return 1; + } + } + + finished = 1; + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pthread_join(locking_threads[cpu], NULL)) + return 1; + + return 0; +} + +static int userfaultfd_stress(void) +{ + void *area; + char *tmp_area; + unsigned long nr; + struct uffdio_register uffdio_register; + struct uffdio_api uffdio_api; + unsigned long cpu; + int uffd_flags, err; + unsigned long userfaults[nr_cpus]; + + if (posix_memalign(&area, page_size, nr_pages * page_size)) { + fprintf(stderr, "out of memory\n"); + return 1; + } + area_src = area; + if (posix_memalign(&area, page_size, nr_pages * page_size)) { + fprintf(stderr, "out of memory\n"); + return 1; + } + area_dst = area; + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd < 0) { + fprintf(stderr, + "userfaultfd syscall not available in this kernel\n"); + return 1; + } + uffd_flags = fcntl(uffd, F_GETFD, NULL); + + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) { + fprintf(stderr, "UFFDIO_API\n"); + return 1; + } + if (uffdio_api.api != UFFD_API) { + fprintf(stderr, "UFFDIO_API error %Lu\n", uffdio_api.api); + return 1; + } + + count_verify = malloc(nr_pages * sizeof(unsigned long long)); + if (!count_verify) { + perror("count_verify"); + return 1; + } + + for (nr = 0; nr < nr_pages; nr++) { + *area_mutex(area_src, nr) = (pthread_mutex_t) + PTHREAD_MUTEX_INITIALIZER; + count_verify[nr] = *area_count(area_src, nr) = 1; + /* + * In the transition between 255 to 256, powerpc will + * read out of order in my_bcmp and see both bytes as + * zero, so leave a placeholder below always non-zero + * after the count, to avoid my_bcmp to trigger false + * positives. + */ + *(area_count(area_src, nr) + 1) = 1; + } + + pipefd = malloc(sizeof(int) * nr_cpus * 2); + if (!pipefd) { + perror("pipefd"); + return 1; + } + for (cpu = 0; cpu < nr_cpus; cpu++) { + if (pipe2(&pipefd[cpu*2], O_CLOEXEC | O_NONBLOCK)) { + perror("pipe"); + return 1; + } + } + + if (posix_memalign(&area, page_size, page_size)) { + fprintf(stderr, "out of memory\n"); + return 1; + } + zeropage = area; + bzero(zeropage, page_size); + + pthread_mutex_lock(&uffd_read_mutex); + + pthread_attr_init(&attr); + pthread_attr_setstacksize(&attr, 16*1024*1024); + + err = 0; + while (bounces--) { + unsigned long expected_ioctls; + + printf("bounces: %d, mode:", bounces); + if (bounces & BOUNCE_RANDOM) + printf(" rnd"); + if (bounces & BOUNCE_RACINGFAULTS) + printf(" racing"); + if (bounces & BOUNCE_VERIFY) + printf(" ver"); + if (bounces & BOUNCE_POLL) + printf(" poll"); + printf(", "); + fflush(stdout); + + if (bounces & BOUNCE_POLL) + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + else + fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK); + + /* register */ + uffdio_register.range.start = (unsigned long) area_dst; + uffdio_register.range.len = nr_pages * page_size; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { + fprintf(stderr, "register failure\n"); + return 1; + } + expected_ioctls = (1 << _UFFDIO_WAKE) | + (1 << _UFFDIO_COPY) | + (1 << _UFFDIO_ZEROPAGE); + if ((uffdio_register.ioctls & expected_ioctls) != + expected_ioctls) { + fprintf(stderr, + "unexpected missing ioctl for anon memory\n"); + return 1; + } + + /* + * The madvise done previously isn't enough: some + * uffd_thread could have read userfaults (one of + * those already resolved by the background thread) + * and it may be in the process of calling + * UFFDIO_COPY. UFFDIO_COPY will read the zapped + * area_src and it would map a zero page in it (of + * course such a UFFDIO_COPY is perfectly safe as it'd + * return -EEXIST). The problem comes at the next + * bounce though: that racing UFFDIO_COPY would + * generate zeropages in the area_src, so invalidating + * the previous MADV_DONTNEED. Without this additional + * MADV_DONTNEED those zeropages leftovers in the + * area_src would lead to -EEXIST failure during the + * next bounce, effectively leaving a zeropage in the + * area_dst. + * + * Try to comment this out madvise to see the memory + * corruption being caught pretty quick. + * + * khugepaged is also inhibited to collapse THP after + * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's + * required to MADV_DONTNEED here. + */ + if (madvise(area_dst, nr_pages * page_size, MADV_DONTNEED)) { + perror("madvise 2"); + return 1; + } + + /* bounce pass */ + if (stress(userfaults)) + return 1; + + /* unregister */ + if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) { + fprintf(stderr, "register failure\n"); + return 1; + } + + /* verification */ + if (bounces & BOUNCE_VERIFY) { + for (nr = 0; nr < nr_pages; nr++) { + if (*area_count(area_dst, nr) != count_verify[nr]) { + fprintf(stderr, + "error area_count %Lu %Lu %lu\n", + *area_count(area_src, nr), + count_verify[nr], + nr); + err = 1; + bounces = 0; + } + } + } + + /* prepare next bounce */ + tmp_area = area_src; + area_src = area_dst; + area_dst = tmp_area; + + printf("userfaults:"); + for (cpu = 0; cpu < nr_cpus; cpu++) + printf(" %lu", userfaults[cpu]); + printf("\n"); + } + + return err; +} + +int main(int argc, char **argv) +{ + if (argc < 3) + fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + page_size = sysconf(_SC_PAGE_SIZE); + if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 + > page_size) + fprintf(stderr, "Impossible to run this test\n"), exit(2); + nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size / + nr_cpus; + if (!nr_pages_per_cpu) { + fprintf(stderr, "invalid MiB\n"); + fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); + } + bounces = atoi(argv[2]); + if (bounces <= 0) { + fprintf(stderr, "invalid bounces\n"); + fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); + } + nr_pages = nr_pages_per_cpu * nr_cpus; + printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", + nr_pages, nr_pages_per_cpu); + return userfaultfd_stress(); +} + +#else /* __NR_userfaultfd */ + +#warning "missing __NR_userfaultfd definition" + +int main(void) +{ + printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n"); + return 0; +} + +#endif /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index caa60d56d..29089b24d 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -4,8 +4,8 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean -TARGETS_C_BOTHBITS := sigreturn single_step_syscall sysret_ss_attrs -TARGETS_C_32BIT_ONLY := entry_from_vm86 +TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt +TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32) diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c index 5c38a1876..d075ea0e5 100644 --- a/tools/testing/selftests/x86/entry_from_vm86.c +++ b/tools/testing/selftests/x86/entry_from_vm86.c @@ -28,6 +28,55 @@ static unsigned long load_addr = 0x10000; static int nerrs = 0; +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static sig_atomic_t got_signal; + +static void sighandler(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (ctx->uc_mcontext.gregs[REG_EFL] & X86_EFLAGS_VM || + (ctx->uc_mcontext.gregs[REG_CS] & 3) != 3) { + printf("[FAIL]\tSignal frame should not reflect vm86 mode\n"); + nerrs++; + } + + const char *signame; + if (sig == SIGSEGV) + signame = "SIGSEGV"; + else if (sig == SIGILL) + signame = "SIGILL"; + else + signame = "unexpected signal"; + + printf("[INFO]\t%s: FLAGS = 0x%lx, CS = 0x%hx\n", signame, + (unsigned long)ctx->uc_mcontext.gregs[REG_EFL], + (unsigned short)ctx->uc_mcontext.gregs[REG_CS]); + + got_signal = 1; +} + asm ( ".pushsection .rodata\n\t" ".type vmcode_bound, @object\n\t" @@ -38,6 +87,14 @@ asm ( "int3\n\t" "vmcode_sysenter:\n\t" "sysenter\n\t" + "vmcode_syscall:\n\t" + "syscall\n\t" + "vmcode_sti:\n\t" + "sti\n\t" + "vmcode_int3:\n\t" + "int3\n\t" + "vmcode_int80:\n\t" + "int $0x80\n\t" ".size vmcode, . - vmcode\n\t" "end_vmcode:\n\t" ".code32\n\t" @@ -45,9 +102,12 @@ asm ( ); extern unsigned char vmcode[], end_vmcode[]; -extern unsigned char vmcode_bound[], vmcode_sysenter[]; +extern unsigned char vmcode_bound[], vmcode_sysenter[], vmcode_syscall[], + vmcode_sti[], vmcode_int3[], vmcode_int80[]; -static void do_test(struct vm86plus_struct *v86, unsigned long eip, +/* Returns false if the test was skipped. */ +static bool do_test(struct vm86plus_struct *v86, unsigned long eip, + unsigned int rettype, unsigned int retarg, const char *text) { long ret; @@ -56,9 +116,10 @@ static void do_test(struct vm86plus_struct *v86, unsigned long eip, v86->regs.eip = eip; ret = vm86(VM86_ENTER, v86); - if (ret == -1 && errno == ENOSYS) { - printf("[SKIP]\tvm86 not supported\n"); - return; + if (ret == -1 && (errno == ENOSYS || errno == EPERM)) { + printf("[SKIP]\tvm86 %s\n", + errno == ENOSYS ? "not supported" : "not allowed"); + return false; } if (VM86_TYPE(ret) == VM86_INTx) { @@ -73,13 +134,30 @@ static void do_test(struct vm86plus_struct *v86, unsigned long eip, else sprintf(trapname, "%d", trapno); - printf("[OK]\tExited vm86 mode due to #%s\n", trapname); + printf("[INFO]\tExited vm86 mode due to #%s\n", trapname); } else if (VM86_TYPE(ret) == VM86_UNKNOWN) { - printf("[OK]\tExited vm86 mode due to unhandled GP fault\n"); + printf("[INFO]\tExited vm86 mode due to unhandled GP fault\n"); + } else if (VM86_TYPE(ret) == VM86_TRAP) { + printf("[INFO]\tExited vm86 mode due to a trap (arg=%ld)\n", + VM86_ARG(ret)); + } else if (VM86_TYPE(ret) == VM86_SIGNAL) { + printf("[INFO]\tExited vm86 mode due to a signal\n"); + } else if (VM86_TYPE(ret) == VM86_STI) { + printf("[INFO]\tExited vm86 mode due to STI\n"); } else { - printf("[OK]\tExited vm86 mode due to type %ld, arg %ld\n", + printf("[INFO]\tExited vm86 mode due to type %ld, arg %ld\n", VM86_TYPE(ret), VM86_ARG(ret)); } + + if (rettype == -1 || + (VM86_TYPE(ret) == rettype && VM86_ARG(ret) == retarg)) { + printf("[OK]\tReturned correctly\n"); + } else { + printf("[FAIL]\tIncorrect return reason\n"); + nerrs++; + } + + return true; } int main(void) @@ -105,10 +183,56 @@ int main(void) assert((v86.regs.cs & 3) == 0); /* Looks like RPL = 0 */ /* #BR -- should deliver SIG??? */ - do_test(&v86, vmcode_bound - vmcode, "#BR"); + do_test(&v86, vmcode_bound - vmcode, VM86_INTx, 5, "#BR"); + + /* + * SYSENTER -- should cause #GP or #UD depending on CPU. + * Expected return type -1 means that we shouldn't validate + * the vm86 return value. This will avoid problems on non-SEP + * CPUs. + */ + sethandler(SIGILL, sighandler, 0); + do_test(&v86, vmcode_sysenter - vmcode, -1, 0, "SYSENTER"); + clearhandler(SIGILL); + + /* + * SYSCALL would be a disaster in VM86 mode. Fortunately, + * there is no kernel that both enables SYSCALL and sets + * EFER.SCE, so it's #UD on all systems. But vm86 is + * buggy (or has a "feature"), so the SIGILL will actually + * be delivered. + */ + sethandler(SIGILL, sighandler, 0); + do_test(&v86, vmcode_syscall - vmcode, VM86_SIGNAL, 0, "SYSCALL"); + clearhandler(SIGILL); + + /* STI with VIP set */ + v86.regs.eflags |= X86_EFLAGS_VIP; + v86.regs.eflags &= ~X86_EFLAGS_IF; + do_test(&v86, vmcode_sti - vmcode, VM86_STI, 0, "STI with VIP set"); + + /* INT3 -- should cause #BP */ + do_test(&v86, vmcode_int3 - vmcode, VM86_TRAP, 3, "INT3"); + + /* INT80 -- should exit with "INTx 0x80" */ + v86.regs.eax = (unsigned int)-1; + do_test(&v86, vmcode_int80 - vmcode, VM86_INTx, 0x80, "int80"); + + /* Execute a null pointer */ + v86.regs.cs = 0; + v86.regs.ss = 0; + sethandler(SIGSEGV, sighandler, 0); + got_signal = 0; + if (do_test(&v86, 0, VM86_SIGNAL, 0, "Execute null pointer") && + !got_signal) { + printf("[FAIL]\tDid not receive SIGSEGV\n"); + nerrs++; + } + clearhandler(SIGSEGV); - /* SYSENTER -- should cause #GP or #UD depending on CPU */ - do_test(&v86, vmcode_sysenter - vmcode, "SYSENTER"); + /* Make sure nothing explodes if we fork. */ + if (fork() > 0) + return 0; return (nerrs == 0 ? 0 : 1); } diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c new file mode 100644 index 000000000..31a3035cd --- /dev/null +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -0,0 +1,576 @@ +/* + * ldt_gdt.c - Test cases for LDT and GDT access + * Copyright (c) 2015 Andrew Lutomirski + */ + +#define _GNU_SOURCE +#include <err.h> +#include <stdio.h> +#include <stdint.h> +#include <signal.h> +#include <setjmp.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <sys/syscall.h> +#include <asm/ldt.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <stdbool.h> +#include <pthread.h> +#include <sched.h> +#include <linux/futex.h> + +#define AR_ACCESSED (1<<8) + +#define AR_TYPE_RODATA (0 * (1<<9)) +#define AR_TYPE_RWDATA (1 * (1<<9)) +#define AR_TYPE_RODATA_EXPDOWN (2 * (1<<9)) +#define AR_TYPE_RWDATA_EXPDOWN (3 * (1<<9)) +#define AR_TYPE_XOCODE (4 * (1<<9)) +#define AR_TYPE_XRCODE (5 * (1<<9)) +#define AR_TYPE_XOCODE_CONF (6 * (1<<9)) +#define AR_TYPE_XRCODE_CONF (7 * (1<<9)) + +#define AR_DPL3 (3 * (1<<13)) + +#define AR_S (1 << 12) +#define AR_P (1 << 15) +#define AR_AVL (1 << 20) +#define AR_L (1 << 21) +#define AR_DB (1 << 22) +#define AR_G (1 << 23) + +static int nerrs; + +static void check_invalid_segment(uint16_t index, int ldt) +{ + uint32_t has_limit = 0, has_ar = 0, limit, ar; + uint32_t selector = (index << 3) | (ldt << 2) | 3; + + asm ("lsl %[selector], %[limit]\n\t" + "jnz 1f\n\t" + "movl $1, %[has_limit]\n\t" + "1:" + : [limit] "=r" (limit), [has_limit] "+rm" (has_limit) + : [selector] "r" (selector)); + asm ("larl %[selector], %[ar]\n\t" + "jnz 1f\n\t" + "movl $1, %[has_ar]\n\t" + "1:" + : [ar] "=r" (ar), [has_ar] "+rm" (has_ar) + : [selector] "r" (selector)); + + if (has_limit || has_ar) { + printf("[FAIL]\t%s entry %hu is valid but should be invalid\n", + (ldt ? "LDT" : "GDT"), index); + nerrs++; + } else { + printf("[OK]\t%s entry %hu is invalid\n", + (ldt ? "LDT" : "GDT"), index); + } +} + +static void check_valid_segment(uint16_t index, int ldt, + uint32_t expected_ar, uint32_t expected_limit, + bool verbose) +{ + uint32_t has_limit = 0, has_ar = 0, limit, ar; + uint32_t selector = (index << 3) | (ldt << 2) | 3; + + asm ("lsl %[selector], %[limit]\n\t" + "jnz 1f\n\t" + "movl $1, %[has_limit]\n\t" + "1:" + : [limit] "=r" (limit), [has_limit] "+rm" (has_limit) + : [selector] "r" (selector)); + asm ("larl %[selector], %[ar]\n\t" + "jnz 1f\n\t" + "movl $1, %[has_ar]\n\t" + "1:" + : [ar] "=r" (ar), [has_ar] "+rm" (has_ar) + : [selector] "r" (selector)); + + if (!has_limit || !has_ar) { + printf("[FAIL]\t%s entry %hu is invalid but should be valid\n", + (ldt ? "LDT" : "GDT"), index); + nerrs++; + return; + } + + if (ar != expected_ar) { + printf("[FAIL]\t%s entry %hu has AR 0x%08X but expected 0x%08X\n", + (ldt ? "LDT" : "GDT"), index, ar, expected_ar); + nerrs++; + } else if (limit != expected_limit) { + printf("[FAIL]\t%s entry %hu has limit 0x%08X but expected 0x%08X\n", + (ldt ? "LDT" : "GDT"), index, limit, expected_limit); + nerrs++; + } else if (verbose) { + printf("[OK]\t%s entry %hu has AR 0x%08X and limit 0x%08X\n", + (ldt ? "LDT" : "GDT"), index, ar, limit); + } +} + +static bool install_valid_mode(const struct user_desc *desc, uint32_t ar, + bool oldmode) +{ + int ret = syscall(SYS_modify_ldt, oldmode ? 1 : 0x11, + desc, sizeof(*desc)); + if (ret < -1) + errno = -ret; + if (ret == 0) { + uint32_t limit = desc->limit; + if (desc->limit_in_pages) + limit = (limit << 12) + 4095; + check_valid_segment(desc->entry_number, 1, ar, limit, true); + return true; + } else if (errno == ENOSYS) { + printf("[OK]\tmodify_ldt returned -ENOSYS\n"); + return false; + } else { + if (desc->seg_32bit) { + printf("[FAIL]\tUnexpected modify_ldt failure %d\n", + errno); + nerrs++; + return false; + } else { + printf("[OK]\tmodify_ldt rejected 16 bit segment\n"); + return false; + } + } +} + +static bool install_valid(const struct user_desc *desc, uint32_t ar) +{ + return install_valid_mode(desc, ar, false); +} + +static void install_invalid(const struct user_desc *desc, bool oldmode) +{ + int ret = syscall(SYS_modify_ldt, oldmode ? 1 : 0x11, + desc, sizeof(*desc)); + if (ret < -1) + errno = -ret; + if (ret == 0) { + check_invalid_segment(desc->entry_number, 1); + } else if (errno == ENOSYS) { + printf("[OK]\tmodify_ldt returned -ENOSYS\n"); + } else { + if (desc->seg_32bit) { + printf("[FAIL]\tUnexpected modify_ldt failure %d\n", + errno); + nerrs++; + } else { + printf("[OK]\tmodify_ldt rejected 16 bit segment\n"); + } + } +} + +static int safe_modify_ldt(int func, struct user_desc *ptr, + unsigned long bytecount) +{ + int ret = syscall(SYS_modify_ldt, 0x11, ptr, bytecount); + if (ret < -1) + errno = -ret; + return ret; +} + +static void fail_install(struct user_desc *desc) +{ + if (safe_modify_ldt(0x11, desc, sizeof(*desc)) == 0) { + printf("[FAIL]\tmodify_ldt accepted a bad descriptor\n"); + nerrs++; + } else if (errno == ENOSYS) { + printf("[OK]\tmodify_ldt returned -ENOSYS\n"); + } else { + printf("[OK]\tmodify_ldt failure %d\n", errno); + } +} + +static void do_simple_tests(void) +{ + struct user_desc desc = { + .entry_number = 0, + .base_addr = 0, + .limit = 10, + .seg_32bit = 1, + .contents = 2, /* Code, not conforming */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 0, + .useable = 0 + }; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB); + + desc.limit_in_pages = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | + AR_S | AR_P | AR_DB | AR_G); + + check_invalid_segment(1, 1); + + desc.entry_number = 2; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | + AR_S | AR_P | AR_DB | AR_G); + + check_invalid_segment(1, 1); + + desc.base_addr = 0xf0000000; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | + AR_S | AR_P | AR_DB | AR_G); + + desc.useable = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | + AR_S | AR_P | AR_DB | AR_G | AR_AVL); + + desc.seg_not_present = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | + AR_S | AR_DB | AR_G | AR_AVL); + + desc.seg_32bit = 0; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | + AR_S | AR_G | AR_AVL); + + desc.seg_32bit = 1; + desc.contents = 0; + install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | + AR_S | AR_DB | AR_G | AR_AVL); + + desc.read_exec_only = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | + AR_S | AR_DB | AR_G | AR_AVL); + + desc.contents = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA_EXPDOWN | + AR_S | AR_DB | AR_G | AR_AVL); + + desc.read_exec_only = 0; + desc.limit_in_pages = 0; + install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA_EXPDOWN | + AR_S | AR_DB | AR_AVL); + + desc.contents = 3; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE_CONF | + AR_S | AR_DB | AR_AVL); + + desc.read_exec_only = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_XOCODE_CONF | + AR_S | AR_DB | AR_AVL); + + desc.read_exec_only = 0; + desc.contents = 2; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | + AR_S | AR_DB | AR_AVL); + + desc.read_exec_only = 1; + +#ifdef __x86_64__ + desc.lm = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_XOCODE | + AR_S | AR_DB | AR_AVL); + desc.lm = 0; +#endif + + bool entry1_okay = install_valid(&desc, AR_DPL3 | AR_TYPE_XOCODE | + AR_S | AR_DB | AR_AVL); + + if (entry1_okay) { + printf("[RUN]\tTest fork\n"); + pid_t child = fork(); + if (child == 0) { + nerrs = 0; + check_valid_segment(desc.entry_number, 1, + AR_DPL3 | AR_TYPE_XOCODE | + AR_S | AR_DB | AR_AVL, desc.limit, + true); + check_invalid_segment(1, 1); + exit(nerrs ? 1 : 0); + } else { + int status; + if (waitpid(child, &status, 0) != child || + !WIFEXITED(status)) { + printf("[FAIL]\tChild died\n"); + nerrs++; + } else if (WEXITSTATUS(status) != 0) { + printf("[FAIL]\tChild failed\n"); + nerrs++; + } else { + printf("[OK]\tChild succeeded\n"); + } + } + + printf("[RUN]\tTest size\n"); + int i; + for (i = 0; i < 8192; i++) { + desc.entry_number = i; + desc.limit = i; + if (safe_modify_ldt(0x11, &desc, sizeof(desc)) != 0) { + printf("[FAIL]\tFailed to install entry %d\n", i); + nerrs++; + break; + } + } + for (int j = 0; j < i; j++) { + check_valid_segment(j, 1, AR_DPL3 | AR_TYPE_XOCODE | + AR_S | AR_DB | AR_AVL, j, false); + } + printf("[DONE]\tSize test\n"); + } else { + printf("[SKIP]\tSkipping fork and size tests because we have no LDT\n"); + } + + /* Test entry_number too high. */ + desc.entry_number = 8192; + fail_install(&desc); + + /* Test deletion and actions mistakeable for deletion. */ + memset(&desc, 0, sizeof(desc)); + install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S | AR_P); + + desc.seg_not_present = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S); + + desc.seg_not_present = 0; + desc.read_exec_only = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | AR_S | AR_P); + + desc.read_exec_only = 0; + desc.seg_not_present = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S); + + desc.read_exec_only = 1; + desc.limit = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | AR_S); + + desc.limit = 0; + desc.base_addr = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | AR_S); + + desc.base_addr = 0; + install_invalid(&desc, false); + + desc.seg_not_present = 0; + desc.read_exec_only = 0; + desc.seg_32bit = 1; + install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S | AR_P | AR_DB); + install_invalid(&desc, true); +} + +/* + * 0: thread is idle + * 1: thread armed + * 2: thread should clear LDT entry 0 + * 3: thread should exit + */ +static volatile unsigned int ftx; + +static void *threadproc(void *ctx) +{ + cpu_set_t cpuset; + CPU_ZERO(&cpuset); + CPU_SET(1, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + err(1, "sched_setaffinity to CPU 1"); /* should never fail */ + + while (1) { + syscall(SYS_futex, &ftx, FUTEX_WAIT, 0, NULL, NULL, 0); + while (ftx != 2) { + if (ftx >= 3) + return NULL; + } + + /* clear LDT entry 0 */ + const struct user_desc desc = {}; + if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) != 0) + err(1, "modify_ldt"); + + /* If ftx == 2, set it to zero. If ftx == 100, quit. */ + unsigned int x = -2; + asm volatile ("lock xaddl %[x], %[ftx]" : + [x] "+r" (x), [ftx] "+m" (ftx)); + if (x != 2) + return NULL; + } +} + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); + +} + +static jmp_buf jmpbuf; + +static void sigsegv(int sig, siginfo_t *info, void *ctx_void) +{ + siglongjmp(jmpbuf, 1); +} + +static void do_multicpu_tests(void) +{ + cpu_set_t cpuset; + pthread_t thread; + int failures = 0, iters = 5, i; + unsigned short orig_ss; + + CPU_ZERO(&cpuset); + CPU_SET(1, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) { + printf("[SKIP]\tCannot set affinity to CPU 1\n"); + return; + } + + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) { + printf("[SKIP]\tCannot set affinity to CPU 0\n"); + return; + } + + sethandler(SIGSEGV, sigsegv, 0); +#ifdef __i386__ + /* True 32-bit kernels send SIGILL instead of SIGSEGV on IRET faults. */ + sethandler(SIGILL, sigsegv, 0); +#endif + + printf("[RUN]\tCross-CPU LDT invalidation\n"); + + if (pthread_create(&thread, 0, threadproc, 0) != 0) + err(1, "pthread_create"); + + asm volatile ("mov %%ss, %0" : "=rm" (orig_ss)); + + for (i = 0; i < 5; i++) { + if (sigsetjmp(jmpbuf, 1) != 0) + continue; + + /* Make sure the thread is ready after the last test. */ + while (ftx != 0) + ; + + struct user_desc desc = { + .entry_number = 0, + .base_addr = 0, + .limit = 0xfffff, + .seg_32bit = 1, + .contents = 0, /* Data */ + .read_exec_only = 0, + .limit_in_pages = 1, + .seg_not_present = 0, + .useable = 0 + }; + + if (safe_modify_ldt(0x11, &desc, sizeof(desc)) != 0) { + if (errno != ENOSYS) + err(1, "modify_ldt"); + printf("[SKIP]\tmodify_ldt unavailable\n"); + break; + } + + /* Arm the thread. */ + ftx = 1; + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + + asm volatile ("mov %0, %%ss" : : "r" (0x7)); + + /* Go! */ + ftx = 2; + + while (ftx != 0) + ; + + /* + * On success, modify_ldt will segfault us synchronously, + * and we'll escape via siglongjmp. + */ + + failures++; + asm volatile ("mov %0, %%ss" : : "rm" (orig_ss)); + }; + + ftx = 100; /* Kill the thread. */ + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + + if (pthread_join(thread, NULL) != 0) + err(1, "pthread_join"); + + if (failures) { + printf("[FAIL]\t%d of %d iterations failed\n", failures, iters); + nerrs++; + } else { + printf("[OK]\tAll %d iterations succeeded\n", iters); + } +} + +static int finish_exec_test(void) +{ + /* + * In a sensible world, this would be check_invalid_segment(0, 1); + * For better or for worse, though, the LDT is inherited across exec. + * We can probably change this safely, but for now we test it. + */ + check_valid_segment(0, 1, + AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB, + 42, true); + + return nerrs ? 1 : 0; +} + +static void do_exec_test(void) +{ + printf("[RUN]\tTest exec\n"); + + struct user_desc desc = { + .entry_number = 0, + .base_addr = 0, + .limit = 42, + .seg_32bit = 1, + .contents = 2, /* Code, not conforming */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 0, + .useable = 0 + }; + install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB); + + pid_t child = fork(); + if (child == 0) { + execl("/proc/self/exe", "ldt_gdt_test_exec", NULL); + printf("[FAIL]\tCould not exec self\n"); + exit(1); /* exec failed */ + } else { + int status; + if (waitpid(child, &status, 0) != child || + !WIFEXITED(status)) { + printf("[FAIL]\tChild died\n"); + nerrs++; + } else if (WEXITSTATUS(status) != 0) { + printf("[FAIL]\tChild failed\n"); + nerrs++; + } else { + printf("[OK]\tChild succeeded\n"); + } + } +} + +int main(int argc, char **argv) +{ + if (argc == 1 && !strcmp(argv[0], "ldt_gdt_test_exec")) + return finish_exec_test(); + + do_simple_tests(); + + do_multicpu_tests(); + + do_exec_test(); + + return nerrs ? 1 : 0; +} diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c new file mode 100644 index 000000000..7db4fc9fa --- /dev/null +++ b/tools/testing/selftests/x86/syscall_arg_fault.c @@ -0,0 +1,130 @@ +/* + * syscall_arg_fault.c - tests faults 32-bit fast syscall stack args + * Copyright (c) 2015 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#define _GNU_SOURCE + +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <sys/signal.h> +#include <sys/ucontext.h> +#include <err.h> +#include <setjmp.h> +#include <errno.h> + +/* Our sigaltstack scratch space. */ +static unsigned char altstack_data[SIGSTKSZ]; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static volatile sig_atomic_t sig_traps; +static sigjmp_buf jmpbuf; + +static volatile sig_atomic_t n_errs; + +static void sigsegv(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (ctx->uc_mcontext.gregs[REG_EAX] != -EFAULT) { + printf("[FAIL]\tAX had the wrong value: 0x%x\n", + ctx->uc_mcontext.gregs[REG_EAX]); + n_errs++; + } else { + printf("[OK]\tSeems okay\n"); + } + + siglongjmp(jmpbuf, 1); +} + +static void sigill(int sig, siginfo_t *info, void *ctx_void) +{ + printf("[SKIP]\tIllegal instruction\n"); + siglongjmp(jmpbuf, 1); +} + +int main() +{ + stack_t stack = { + .ss_sp = altstack_data, + .ss_size = SIGSTKSZ, + }; + if (sigaltstack(&stack, NULL) != 0) + err(1, "sigaltstack"); + + sethandler(SIGSEGV, sigsegv, SA_ONSTACK); + sethandler(SIGILL, sigill, SA_ONSTACK); + + /* + * Exercise another nasty special case. The 32-bit SYSCALL + * and SYSENTER instructions (even in compat mode) each + * clobber one register. A Linux system call has a syscall + * number and six arguments, and the user stack pointer + * needs to live in some register on return. That means + * that we need eight registers, but SYSCALL and SYSENTER + * only preserve seven registers. As a result, one argument + * ends up on the stack. The stack is user memory, which + * means that the kernel can fail to read it. + * + * The 32-bit fast system calls don't have a defined ABI: + * we're supposed to invoke them through the vDSO. So we'll + * fudge it: we set all regs to invalid pointer values and + * invoke the entry instruction. The return will fail no + * matter what, and we completely lose our program state, + * but we can fix it up with a signal handler. + */ + + printf("[RUN]\tSYSENTER with invalid state\n"); + if (sigsetjmp(jmpbuf, 1) == 0) { + 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"); + } + + printf("[RUN]\tSYSCALL with invalid state\n"); + if (sigsetjmp(jmpbuf, 1) == 0) { + 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" + "syscall\n\t" + "pushl $0" /* make sure we segfault cleanly */ + : : : "memory", "flags"); + } + + return 0; +} diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c new file mode 100644 index 000000000..60c06af46 --- /dev/null +++ b/tools/testing/selftests/x86/syscall_nt.c @@ -0,0 +1,54 @@ +/* + * syscall_nt.c - checks syscalls with NT set + * Copyright (c) 2014-2015 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * Some obscure user-space code requires the ability to make system calls + * with FLAGS.NT set. Make sure it works. + */ + +#include <stdio.h> +#include <unistd.h> +#include <sys/syscall.h> +#include <asm/processor-flags.h> + +#ifdef __x86_64__ +# define WIDTH "q" +#else +# define WIDTH "l" +#endif + +static unsigned long get_eflags(void) +{ + unsigned long eflags; + asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags)); + return eflags; +} + +static void set_eflags(unsigned long eflags) +{ + asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH + : : "rm" (eflags) : "flags"); +} + +int main() +{ + printf("[RUN]\tSet NT and issue a syscall\n"); + set_eflags(get_eflags() | X86_EFLAGS_NT); + syscall(SYS_getpid); + if (get_eflags() & X86_EFLAGS_NT) { + printf("[OK]\tThe syscall worked and NT is still set\n"); + return 0; + } else { + printf("[FAIL]\tThe syscall worked but NT was cleared\n"); + return 1; + } +} diff --git a/tools/testing/selftests/zram/Makefile b/tools/testing/selftests/zram/Makefile new file mode 100644 index 000000000..29d80346e --- /dev/null +++ b/tools/testing/selftests/zram/Makefile @@ -0,0 +1,9 @@ +all: + +TEST_PROGS := zram.sh +TEST_FILES := zram01.sh zram02.sh zram_lib.sh + +include ../lib.mk + +clean: + $(RM) err.log diff --git a/tools/testing/selftests/zram/README b/tools/testing/selftests/zram/README new file mode 100644 index 000000000..eb17917c8 --- /dev/null +++ b/tools/testing/selftests/zram/README @@ -0,0 +1,40 @@ +zram: Compressed RAM based block devices +---------------------------------------- +* Introduction + +The zram module creates RAM based block devices named /dev/zram<id> +(<id> = 0, 1, ...). Pages written to these disks are compressed and stored +in memory itself. These disks allow very fast I/O and compression provides +good amounts of memory savings. Some of the usecases include /tmp storage, +use as swap disks, various caches under /var and maybe many more :) + +Statistics for individual zram devices are exported through sysfs nodes at +/sys/block/zram<id>/ + +Kconfig required: +CONFIG_ZRAM=y +CONFIG_ZRAM_LZ4_COMPRESS=y +CONFIG_ZPOOL=y +CONFIG_ZSMALLOC=y + +ZRAM Testcases +-------------- +zram_lib.sh: create library with initialization/cleanup functions +zram.sh: For sanity check of CONFIG_ZRAM and to run zram01 and zram02 + +Two functional tests: zram01 and zram02: +zram01.sh: creates general purpose ram disks with ext4 filesystems +zram02.sh: creates block device for swap + +Commands required for testing: + - bc + - dd + - free + - awk + - mkswap + - swapon + - swapoff + - mkfs/ mkfs.ext4 + +For more information please refer: +kernel-source-tree/Documentation/blockdev/zram.txt diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh new file mode 100755 index 000000000..683a292e3 --- /dev/null +++ b/tools/testing/selftests/zram/zram.sh @@ -0,0 +1,27 @@ +#!/bin/bash +TCID="zram.sh" + +. ./zram_lib.sh + +run_zram () { +echo "--------------------" +echo "running zram tests" +echo "--------------------" +./zram01.sh +echo "" +./zram02.sh +} + +check_prereqs + +# check zram module exists +MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko +if [ -f $MODULE_PATH ]; then + run_zram +elif [ -b /dev/zram0 ]; then + run_zram +else + echo "$TCID : No zram.ko module or /dev/zram0 device file not found" + echo "$TCID : CONFIG_ZRAM is not set" + exit 1 +fi diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh new file mode 100755 index 000000000..b9566a647 --- /dev/null +++ b/tools/testing/selftests/zram/zram01.sh @@ -0,0 +1,99 @@ +#!/bin/bash +# Copyright (c) 2015 Oracle and/or its affiliates. All Rights Reserved. +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License as +# published by the Free Software Foundation; either version 2 of +# the License, or (at your option) any later version. +# +# This program is distributed in the hope that it would be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# Test creates several zram devices with different filesystems on them. +# It fills each device with zeros and checks that compression works. +# +# Author: Alexey Kodanev <alexey.kodanev@oracle.com> +# Modified: Naresh Kamboju <naresh.kamboju@linaro.org> + +TCID="zram01" +ERR_CODE=0 + +. ./zram_lib.sh + +# Test will create the following number of zram devices: +dev_num=1 +# This is a list of parameters for zram devices. +# Number of items must be equal to 'dev_num' parameter. +zram_max_streams="2" + +# The zram sysfs node 'disksize' value can be either in bytes, +# or you can use mem suffixes. But in some old kernels, mem +# suffixes are not supported, for example, in RHEL6.6GA's kernel +# layer, it uses strict_strtoull() to parse disksize which does +# not support mem suffixes, in some newer kernels, they use +# memparse() which supports mem suffixes. So here we just use +# bytes to make sure everything works correctly. +zram_sizes="2097152" # 2MB +zram_mem_limits="2M" +zram_filesystems="ext4" +zram_algs="lzo" + +zram_fill_fs() +{ + local mem_free0=$(free -m | awk 'NR==2 {print $4}') + + for i in $(seq 0 $(($dev_num - 1))); do + echo "fill zram$i..." + local b=0 + while [ true ]; do + dd conv=notrunc if=/dev/zero of=zram${i}/file \ + oflag=append count=1 bs=1024 status=none \ + > /dev/null 2>&1 || break + b=$(($b + 1)) + done + echo "zram$i can be filled with '$b' KB" + done + + local mem_free1=$(free -m | awk 'NR==2 {print $4}') + local used_mem=$(($mem_free0 - $mem_free1)) + + local total_size=0 + for sm in $zram_sizes; do + local s=$(echo $sm | sed 's/M//') + total_size=$(($total_size + $s)) + done + + echo "zram used ${used_mem}M, zram disk sizes ${total_size}M" + + local v=$((100 * $total_size / $used_mem)) + + if [ "$v" -lt 100 ]; then + echo "FAIL compression ratio: 0.$v:1" + ERR_CODE=-1 + zram_cleanup + return + fi + + echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" +} + +check_prereqs +zram_load +zram_max_streams +zram_compress_alg +zram_set_disksizes +zram_set_memlimit +zram_makefs +zram_mount + +zram_fill_fs +zram_cleanup +zram_unload + +if [ $ERR_CODE -ne 0 ]; then + echo "$TCID : [FAIL]" +else + echo "$TCID : [PASS]" +fi diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh new file mode 100755 index 000000000..74569b883 --- /dev/null +++ b/tools/testing/selftests/zram/zram02.sh @@ -0,0 +1,54 @@ +#!/bin/bash +# Copyright (c) 2015 Oracle and/or its affiliates. All Rights Reserved. +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License as +# published by the Free Software Foundation; either version 2 of +# the License, or (at your option) any later version. +# +# This program is distributed in the hope that it would be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# Test checks that we can create swap zram device. +# +# Author: Alexey Kodanev <alexey.kodanev@oracle.com> +# Modified: Naresh Kamboju <naresh.kamboju@linaro.org> + +TCID="zram02" +ERR_CODE=0 + +. ./zram_lib.sh + +# Test will create the following number of zram devices: +dev_num=1 +# This is a list of parameters for zram devices. +# Number of items must be equal to 'dev_num' parameter. +zram_max_streams="2" + +# The zram sysfs node 'disksize' value can be either in bytes, +# or you can use mem suffixes. But in some old kernels, mem +# suffixes are not supported, for example, in RHEL6.6GA's kernel +# layer, it uses strict_strtoull() to parse disksize which does +# not support mem suffixes, in some newer kernels, they use +# memparse() which supports mem suffixes. So here we just use +# bytes to make sure everything works correctly. +zram_sizes="1048576" # 1M +zram_mem_limits="1M" + +check_prereqs +zram_load +zram_max_streams +zram_set_disksizes +zram_set_memlimit +zram_makeswap +zram_swapoff +zram_cleanup +zram_unload + +if [ $ERR_CODE -ne 0 ]; then + echo "$TCID : [FAIL]" +else + echo "$TCID : [PASS]" +fi diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh new file mode 100755 index 000000000..f6a9c73e7 --- /dev/null +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -0,0 +1,233 @@ +#!/bin/sh +# Copyright (c) 2015 Oracle and/or its affiliates. All Rights Reserved. +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License as +# published by the Free Software Foundation; either version 2 of +# the License, or (at your option) any later version. +# +# This program is distributed in the hope that it would be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# Author: Alexey Kodanev <alexey.kodanev@oracle.com> +# Modified: Naresh Kamboju <naresh.kamboju@linaro.org> + +MODULE=0 +dev_makeswap=-1 +dev_mounted=-1 + +trap INT + +check_prereqs() +{ + local msg="skip all tests:" + local uid=$(id -u) + + if [ $uid -ne 0 ]; then + echo $msg must be run as root >&2 + exit 0 + fi +} + +zram_cleanup() +{ + echo "zram cleanup" + local i= + for i in $(seq 0 $dev_makeswap); do + swapoff /dev/zram$i + done + + for i in $(seq 0 $dev_mounted); do + umount /dev/zram$i + done + + for i in $(seq 0 $(($dev_num - 1))); do + echo 1 > /sys/block/zram${i}/reset + rm -rf zram$i + done + +} + +zram_unload() +{ + if [ $MODULE -ne 0 ] ; then + echo "zram rmmod zram" + rmmod zram > /dev/null 2>&1 + fi +} + +zram_load() +{ + # check zram module exists + MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko + if [ -f $MODULE_PATH ]; then + MODULE=1 + echo "create '$dev_num' zram device(s)" + modprobe zram num_devices=$dev_num + if [ $? -ne 0 ]; then + echo "failed to insert zram module" + exit 1 + fi + + dev_num_created=$(ls /dev/zram* | wc -w) + + if [ "$dev_num_created" -ne "$dev_num" ]; then + echo "unexpected num of devices: $dev_num_created" + ERR_CODE=-1 + else + echo "zram load module successful" + fi + elif [ -b /dev/zram0 ]; then + echo "/dev/zram0 device file found: OK" + else + echo "ERROR: No zram.ko module or no /dev/zram0 device found" + echo "$TCID : CONFIG_ZRAM is not set" + exit 1 + fi +} + +zram_max_streams() +{ + echo "set max_comp_streams to zram device(s)" + + local i=0 + for max_s in $zram_max_streams; do + local sys_path="/sys/block/zram${i}/max_comp_streams" + echo $max_s > $sys_path || \ + echo "FAIL failed to set '$max_s' to $sys_path" + sleep 1 + local max_streams=$(cat $sys_path) + + [ "$max_s" -ne "$max_streams" ] && \ + echo "FAIL can't set max_streams '$max_s', get $max_stream" + + i=$(($i + 1)) + echo "$sys_path = '$max_streams' ($i/$dev_num)" + done + + echo "zram max streams: OK" +} + +zram_compress_alg() +{ + echo "test that we can set compression algorithm" + + local algs=$(cat /sys/block/zram0/comp_algorithm) + echo "supported algs: $algs" + local i=0 + for alg in $zram_algs; do + local sys_path="/sys/block/zram${i}/comp_algorithm" + echo "$alg" > $sys_path || \ + echo "FAIL can't set '$alg' to $sys_path" + i=$(($i + 1)) + echo "$sys_path = '$alg' ($i/$dev_num)" + done + + echo "zram set compression algorithm: OK" +} + +zram_set_disksizes() +{ + echo "set disk size to zram device(s)" + local i=0 + for ds in $zram_sizes; do + local sys_path="/sys/block/zram${i}/disksize" + echo "$ds" > $sys_path || \ + echo "FAIL can't set '$ds' to $sys_path" + + i=$(($i + 1)) + echo "$sys_path = '$ds' ($i/$dev_num)" + done + + echo "zram set disksizes: OK" +} + +zram_set_memlimit() +{ + echo "set memory limit to zram device(s)" + + local i=0 + for ds in $zram_mem_limits; do + local sys_path="/sys/block/zram${i}/mem_limit" + echo "$ds" > $sys_path || \ + echo "FAIL can't set '$ds' to $sys_path" + + i=$(($i + 1)) + echo "$sys_path = '$ds' ($i/$dev_num)" + done + + echo "zram set memory limit: OK" +} + +zram_makeswap() +{ + echo "make swap with zram device(s)" + local i=0 + for i in $(seq 0 $(($dev_num - 1))); do + mkswap /dev/zram$i > err.log 2>&1 + if [ $? -ne 0 ]; then + cat err.log + echo "FAIL mkswap /dev/zram$1 failed" + fi + + swapon /dev/zram$i > err.log 2>&1 + if [ $? -ne 0 ]; then + cat err.log + echo "FAIL swapon /dev/zram$1 failed" + fi + + echo "done with /dev/zram$i" + dev_makeswap=$i + done + + echo "zram making zram mkswap and swapon: OK" +} + +zram_swapoff() +{ + local i= + for i in $(seq 0 $dev_makeswap); do + swapoff /dev/zram$i > err.log 2>&1 + if [ $? -ne 0 ]; then + cat err.log + echo "FAIL swapoff /dev/zram$i failed" + fi + done + dev_makeswap=-1 + + echo "zram swapoff: OK" +} + +zram_makefs() +{ + local i=0 + for fs in $zram_filesystems; do + # if requested fs not supported default it to ext2 + which mkfs.$fs > /dev/null 2>&1 || fs=ext2 + + echo "make $fs filesystem on /dev/zram$i" + mkfs.$fs /dev/zram$i > err.log 2>&1 + if [ $? -ne 0 ]; then + cat err.log + echo "FAIL failed to make $fs on /dev/zram$i" + fi + i=$(($i + 1)) + echo "zram mkfs.$fs: OK" + done +} + +zram_mount() +{ + local i=0 + for i in $(seq 0 $(($dev_num - 1))); do + echo "mount /dev/zram$i" + mkdir zram$i + mount /dev/zram$i zram$i > /dev/null || \ + echo "FAIL mount /dev/zram$i failed" + dev_mounted=$i + done + + echo "zram mount of zram device(s): OK" +} |