diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 9e7704e44f6d..1db9bbcfb84e 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -473,3 +473,4 @@ 541 common fsconfig sys_fsconfig 542 common fsmount sys_fsmount 543 common fspick sys_fspick +544 common pidfd_open sys_pidfd_open diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index aaf479a9e92d..81e6e1817c45 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -447,3 +447,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 2a23614198f1..ede7b88d4f15 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 434 +#define __NR_compat_syscalls 435 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index aa995920bd34..52415923e08f 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -875,6 +875,8 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index e01df3f2f80d..ecc44926737b 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -354,3 +354,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7e3d0734b2f3..9a3eb2558568 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -433,3 +433,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 26339e417695..ad706f83c755 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -439,3 +439,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 0e2dd68ade57..97035e19ad03 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -372,3 +372,4 @@ 431 n32 fsconfig sys_fsconfig 432 n32 fsmount sys_fsmount 433 n32 fspick sys_fspick +434 n32 pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 5eebfa0d155c..d7292722d3b0 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -348,3 +348,4 @@ 431 n64 fsconfig sys_fsconfig 432 n64 fsmount sys_fsmount 433 n64 fspick sys_fspick +434 n64 pidfd_open sys_pidfd_open diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3cc1374e02d0..dba084c92f14 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -421,3 +421,4 @@ 431 o32 fsconfig sys_fsconfig 432 o32 fsmount sys_fsmount 433 o32 fspick sys_fspick +434 o32 pidfd_open sys_pidfd_open diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index c9e377d59232..5022b9e179c2 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -430,3 +430,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 103655d84b4b..f2c3bda2d39f 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -515,3 +515,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index e822b2964a83..6ebacfeaf853 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -436,3 +436,4 @@ 431 common fsconfig sys_fsconfig sys_fsconfig 432 common fsmount sys_fsmount sys_fsmount 433 common fspick sys_fspick sys_fspick +434 common pidfd_open sys_pidfd_open sys_pidfd_open diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 016a727d4357..834c9c7d79fa 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -436,3 +436,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index e047480b1605..c58e71f21129 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -479,3 +479,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ad968b7bac72..43e4429a5272 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -438,3 +438,4 @@ 431 i386 fsconfig sys_fsconfig __ia32_sys_fsconfig 432 i386 fsmount sys_fsmount __ia32_sys_fsmount 433 i386 fspick sys_fspick __ia32_sys_fspick +434 i386 pidfd_open sys_pidfd_open __ia32_sys_pidfd_open diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index b4e6f9e6204a..1bee0a77fdd3 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -355,6 +355,7 @@ 431 common fsconfig __x64_sys_fsconfig 432 common fsmount __x64_sys_fsmount 433 common fspick __x64_sys_fspick +434 common pidfd_open __x64_sys_pidfd_open # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 5fa0ee1c8e00..782b81945ccc 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -404,3 +404,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open diff --git a/include/linux/pid.h b/include/linux/pid.h index 3c8ef5a199ca..1484db6ca8d1 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -3,6 +3,7 @@ #define _LINUX_PID_H #include +#include enum pid_type { @@ -60,6 +61,8 @@ struct pid unsigned int level; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; + /* wait queue for pidfd notifications */ + wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[1]; }; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index bc4bbbb9ed9a..699aed6674a0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -927,6 +927,7 @@ asmlinkage long sys_clock_adjtime32(clockid_t which_clock, struct old_timex32 __user *tx); asmlinkage long sys_syncfs(int fd); asmlinkage long sys_setns(int fd, int nstype); +asmlinkage long sys_pidfd_open(pid_t pid, unsigned int flags); asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, unsigned int vlen, unsigned flags); asmlinkage long sys_process_vm_readv(pid_t pid, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index a87904daf103..e5684a4512c0 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -844,9 +844,11 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open) #undef __NR_syscalls -#define __NR_syscalls 434 +#define __NR_syscalls 435 /* * 32 bit systems traditionally used different diff --git a/kernel/fork.c b/kernel/fork.c index 847dd147b068..187c02ce534c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1711,8 +1711,34 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) } #endif +/* + * Poll support for process exit notification. + */ +static unsigned int pidfd_poll(struct file *file, struct poll_table_struct *pts) +{ + struct task_struct *task; + struct pid *pid = file->private_data; + int poll_flags = 0; + + poll_wait(file, &pid->wait_pidfd, pts); + + rcu_read_lock(); + task = pid_task(pid, PIDTYPE_PID); + /* + * Inform pollers only when the whole thread group exits. + * If the thread group leader exits before all other threads in the + * group, then poll(2) should block, similar to the wait(2) family. + */ + if (!task || (task->exit_state && thread_group_empty(task))) + poll_flags = POLLIN | POLLRDNORM; + rcu_read_unlock(); + + return poll_flags; +} + const struct file_operations pidfd_fops = { .release = pidfd_release, + .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif diff --git a/kernel/pid.c b/kernel/pid.c index e5cad0c7d5dd..16263b526560 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -38,6 +38,8 @@ #include #include #include +#include +#include #include #include @@ -214,6 +216,8 @@ struct pid *alloc_pid(struct pid_namespace *ns) for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); + init_waitqueue_head(&pid->wait_pidfd); + upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) @@ -451,6 +455,73 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) return idr_get_next(&ns->idr, &nr); } +/** + * pidfd_create() - Create a new pid file descriptor. + * + * @pid: struct pid that the pidfd will reference + * + * This creates a new pid file descriptor with the O_CLOEXEC flag set. + * + * Note, that this function can only be called after the fd table has + * been unshared to avoid leaking the pidfd to the new process. + * + * Return: On success, a cloexec pidfd is returned. + * On error, a negative errno number will be returned. + */ +static int pidfd_create(struct pid *pid) +{ + int fd; + + fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), + O_RDWR | O_CLOEXEC); + if (fd < 0) + put_pid(pid); + + return fd; +} + +/** + * pidfd_open() - Open new pid file descriptor. + * + * @pid: pid for which to retrieve a pidfd + * @flags: flags to pass + * + * This creates a new pid file descriptor with the O_CLOEXEC flag set for + * the process identified by @pid. Currently, the process identified by + * @pid must be a thread-group leader. This restriction currently exists + * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot + * be used with CLONE_THREAD) and pidfd polling (only supports thread group + * leaders). + * + * Return: On success, a cloexec pidfd is returned. + * On error, a negative errno number will be returned. + */ +SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) +{ + int fd, ret; + struct pid *p; + + if (flags) + return -EINVAL; + + if (pid <= 0) + return -EINVAL; + + p = find_get_pid(pid); + if (!p) + return -ESRCH; + + ret = 0; + rcu_read_lock(); + if (!pid_task(p, PIDTYPE_TGID)) + ret = -EINVAL; + rcu_read_unlock(); + + fd = ret ?: pidfd_create(p); + put_pid(p); + return fd; +} + void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ diff --git a/kernel/signal.c b/kernel/signal.c index 91cb8ca41954..dabe100d2091 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1881,6 +1881,14 @@ ret: return ret; } +static void do_notify_pidfd(struct task_struct *task) +{ + struct pid *pid; + + pid = task_pid(task); + wake_up_all(&pid->wait_pidfd); +} + /* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. @@ -1904,6 +1912,9 @@ bool do_notify_parent(struct task_struct *tsk, int sig) BUG_ON(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); + /* Wake up all pidfd waiters */ + do_notify_pidfd(tsk); + if (sig != SIGCHLD) { /* * This is only possible if parent == real_parent. diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 822a1e63d045..16d84d117bc0 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -1 +1,2 @@ +pidfd_open_test pidfd_test diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index 443fedbd6231..720b2d884b3c 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ +CFLAGS += -g -I../../../../usr/include/ -lpthread -TEST_GEN_PROGS := pidfd_test +TEST_GEN_PROGS := pidfd_test pidfd_open_test include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h new file mode 100644 index 000000000000..8452e910463f --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PIDFD_H +#define __PIDFD_H + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" + +/* + * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c + * That means, when it wraps around any pid < 300 will be skipped. + * So we need to use a pid > 300 in order to test recycling. + */ +#define PID_RECYCLE 1000 + +/* + * Define a few custom error codes for the child process to clearly indicate + * what is happening. This way we can tell the difference between a system + * error, a test error, etc. + */ +#define PIDFD_PASS 0 +#define PIDFD_FAIL 1 +#define PIDFD_ERROR 2 +#define PIDFD_SKIP 3 +#define PIDFD_XFAIL 4 + +int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + + +#endif /* __PIDFD_H */ diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c new file mode 100644 index 000000000000..0377133dd6dc --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_open_test.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "pidfd.h" +#include "../kselftest.h" + +static inline int sys_pidfd_open(pid_t pid, unsigned int flags) +{ + return syscall(__NR_pidfd_open, pid, flags); +} + +static int safe_int(const char *numstr, int *converted) +{ + char *err = NULL; + long sli; + + errno = 0; + sli = strtol(numstr, &err, 0); + if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN)) + return -ERANGE; + + if (errno != 0 && sli == 0) + return -EINVAL; + + if (err == numstr || *err != '\0') + return -EINVAL; + + if (sli > INT_MAX || sli < INT_MIN) + return -ERANGE; + + *converted = (int)sli; + return 0; +} + +static int char_left_gc(const char *buffer, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (buffer[i] == ' ' || + buffer[i] == '\t') + continue; + + return i; + } + + return 0; +} + +static int char_right_gc(const char *buffer, size_t len) +{ + int i; + + for (i = len - 1; i >= 0; i--) { + if (buffer[i] == ' ' || + buffer[i] == '\t' || + buffer[i] == '\n' || + buffer[i] == '\0') + continue; + + return i + 1; + } + + return 0; +} + +static char *trim_whitespace_in_place(char *buffer) +{ + buffer += char_left_gc(buffer, strlen(buffer)); + buffer[char_right_gc(buffer, strlen(buffer))] = '\0'; + return buffer; +} + +static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) +{ + int ret; + char path[512]; + FILE *f; + size_t n = 0; + pid_t result = -1; + char *line = NULL; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd); + + f = fopen(path, "re"); + if (!f) + return -1; + + while (getline(&line, &n, f) != -1) { + char *numstr; + + if (strncmp(line, key, keylen)) + continue; + + numstr = trim_whitespace_in_place(line + 4); + ret = safe_int(numstr, &result); + if (ret < 0) + goto out; + + break; + } + +out: + free(line); + fclose(f); + return result; +} + +int main(int argc, char **argv) +{ + int pidfd = -1, ret = 1; + pid_t pid; + + ksft_set_plan(3); + + pidfd = sys_pidfd_open(-1, 0); + if (pidfd >= 0) { + ksft_print_msg( + "%s - succeeded to open pidfd for invalid pid -1\n", + strerror(errno)); + goto on_error; + } + ksft_test_result_pass("do not allow invalid pid test: passed\n"); + + pidfd = sys_pidfd_open(getpid(), 1); + if (pidfd >= 0) { + ksft_print_msg( + "%s - succeeded to open pidfd with invalid flag value specified\n", + strerror(errno)); + goto on_error; + } + ksft_test_result_pass("do not allow invalid flag test: passed\n"); + + pidfd = sys_pidfd_open(getpid(), 0); + if (pidfd < 0) { + ksft_print_msg("%s - failed to open pidfd\n", strerror(errno)); + goto on_error; + } + ksft_test_result_pass("open a new pidfd test: passed\n"); + + pid = get_pid_from_fdinfo_file(pidfd, "Pid:", sizeof("Pid:") - 1); + ksft_print_msg("pidfd %d refers to process with pid %d\n", pidfd, pid); + + ret = 0; + +on_error: + if (pidfd >= 0) + close(pidfd); + + return !ret ? ksft_exit_pass() : ksft_exit_fail(); +} diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 104c75a33882..7eaa8a3de262 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -4,22 +4,49 @@ #include #include #include +#include #include #include #include #include #include #include +#include +#include #include #include +#include #include +#include "pidfd.h" #include "../kselftest.h" #ifndef __NR_pidfd_send_signal #define __NR_pidfd_send_signal -1 #endif +#define str(s) _str(s) +#define _str(s) #s +#define CHILD_THREAD_MIN_WAIT 3 /* seconds */ + +#define MAX_EVENTS 5 + +#ifndef CLONE_PIDFD +#define CLONE_PIDFD 0x00001000 +#endif + +static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) +{ + size_t stack_size = 1024; + char *stack[1024] = { 0 }; + +#ifdef __ia64__ + return __clone2(fn, stack, stack_size, flags | SIGCHLD, NULL, pidfd); +#else + return clone(fn, stack + stack_size, flags | SIGCHLD, NULL, pidfd); +#endif +} + static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags) { @@ -66,28 +93,6 @@ static int test_pidfd_send_signal_simple_success(void) return 0; } -static int wait_for_pid(pid_t pid) -{ - int status, ret; - -again: - ret = waitpid(pid, &status, 0); - if (ret == -1) { - if (errno == EINTR) - goto again; - - return -1; - } - - if (ret != pid) - goto again; - - if (!WIFEXITED(status)) - return -1; - - return WEXITSTATUS(status); -} - static int test_pidfd_send_signal_exited_fail(void) { int pidfd, ret, saved_errno; @@ -132,13 +137,6 @@ static int test_pidfd_send_signal_exited_fail(void) return 0; } -/* - * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c - * That means, when it wraps around any pid < 300 will be skipped. - * So we need to use a pid > 300 in order to test recycling. - */ -#define PID_RECYCLE 1000 - /* * Maximum number of cycles we allow. This is equivalent to PID_MAX_DEFAULT. * If users set a higher limit or we have cycled PIDFD_MAX_DEFAULT number of @@ -147,17 +145,6 @@ static int test_pidfd_send_signal_exited_fail(void) */ #define PIDFD_MAX_DEFAULT 0x8000 -/* - * Define a few custom error codes for the child process to clearly indicate - * what is happening. This way we can tell the difference between a system - * error, a test error, etc. - */ -#define PIDFD_PASS 0 -#define PIDFD_FAIL 1 -#define PIDFD_ERROR 2 -#define PIDFD_SKIP 3 -#define PIDFD_XFAIL 4 - static int test_pidfd_send_signal_recycled_pid_fail(void) { int i, ret; @@ -372,11 +359,192 @@ static int test_pidfd_send_signal_syscall_support(void) return 0; } +static void *test_pidfd_poll_exec_thread(void *priv) +{ + ksft_print_msg("Child Thread: starting. pid %d tid %d ; and sleeping\n", + getpid(), syscall(SYS_gettid)); + ksft_print_msg("Child Thread: doing exec of sleep\n"); + + execl("/bin/sleep", "sleep", str(CHILD_THREAD_MIN_WAIT), (char *)NULL); + + ksft_print_msg("Child Thread: DONE. pid %d tid %d\n", + getpid(), syscall(SYS_gettid)); + return NULL; +} + +static void poll_pidfd(const char *test_name, int pidfd) +{ + int c; + int epoll_fd = epoll_create1(EPOLL_CLOEXEC); + struct epoll_event event, events[MAX_EVENTS]; + + if (epoll_fd == -1) + ksft_exit_fail_msg("%s test: Failed to create epoll file descriptor " + "(errno %d)\n", + test_name, errno); + + event.events = EPOLLIN; + event.data.fd = pidfd; + + if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, pidfd, &event)) { + ksft_exit_fail_msg("%s test: Failed to add epoll file descriptor " + "(errno %d)\n", + test_name, errno); + } + + c = epoll_wait(epoll_fd, events, MAX_EVENTS, 5000); + if (c != 1 || !(events[0].events & EPOLLIN)) + ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) ", + "(errno %d)\n", + test_name, c, events[0].events, errno); + + close(epoll_fd); + return; + +} + +static int child_poll_exec_test(void *args) +{ + pthread_t t1; + + ksft_print_msg("Child (pidfd): starting. pid %d tid %d\n", getpid(), + syscall(SYS_gettid)); + pthread_create(&t1, NULL, test_pidfd_poll_exec_thread, NULL); + /* + * Exec in the non-leader thread will destroy the leader immediately. + * If the wait in the parent returns too soon, the test fails. + */ + while (1) + sleep(1); +} + +static void test_pidfd_poll_exec(int use_waitpid) +{ + int pid, pidfd = 0; + int status, ret; + pthread_t t1; + time_t prog_start = time(NULL); + const char *test_name = "pidfd_poll check for premature notification on child thread exec"; + + ksft_print_msg("Parent: pid: %d\n", getpid()); + pid = pidfd_clone(CLONE_PIDFD, &pidfd, child_poll_exec_test); + if (pid < 0) + ksft_exit_fail_msg("%s test: pidfd_clone failed (ret %d, errno %d)\n", + test_name, pid, errno); + + ksft_print_msg("Parent: Waiting for Child (%d) to complete.\n", pid); + + if (use_waitpid) { + ret = waitpid(pid, &status, 0); + if (ret == -1) + ksft_print_msg("Parent: error\n"); + + if (ret == pid) + ksft_print_msg("Parent: Child process waited for.\n"); + } else { + poll_pidfd(test_name, pidfd); + } + + time_t prog_time = time(NULL) - prog_start; + + ksft_print_msg("Time waited for child: %lu\n", prog_time); + + close(pidfd); + + if (prog_time < CHILD_THREAD_MIN_WAIT || prog_time > CHILD_THREAD_MIN_WAIT + 2) + ksft_exit_fail_msg("%s test: Failed\n", test_name); + else + ksft_test_result_pass("%s test: Passed\n", test_name); +} + +static void *test_pidfd_poll_leader_exit_thread(void *priv) +{ + ksft_print_msg("Child Thread: starting. pid %d tid %d ; and sleeping\n", + getpid(), syscall(SYS_gettid)); + sleep(CHILD_THREAD_MIN_WAIT); + ksft_print_msg("Child Thread: DONE. pid %d tid %d\n", getpid(), syscall(SYS_gettid)); + return NULL; +} + +static time_t *child_exit_secs; +static int child_poll_leader_exit_test(void *args) +{ + pthread_t t1, t2; + + ksft_print_msg("Child: starting. pid %d tid %d\n", getpid(), syscall(SYS_gettid)); + pthread_create(&t1, NULL, test_pidfd_poll_leader_exit_thread, NULL); + pthread_create(&t2, NULL, test_pidfd_poll_leader_exit_thread, NULL); + + /* + * glibc exit calls exit_group syscall, so explicity call exit only + * so that only the group leader exits, leaving the threads alone. + */ + *child_exit_secs = time(NULL); + syscall(SYS_exit, 0); +} + +static void test_pidfd_poll_leader_exit(int use_waitpid) +{ + int pid, pidfd = 0; + int status, ret; + time_t prog_start = time(NULL); + const char *test_name = "pidfd_poll check for premature notification on non-empty" + "group leader exit"; + + child_exit_secs = mmap(NULL, sizeof *child_exit_secs, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + + if (child_exit_secs == MAP_FAILED) + ksft_exit_fail_msg("%s test: mmap failed (errno %d)\n", + test_name, errno); + + ksft_print_msg("Parent: pid: %d\n", getpid()); + pid = pidfd_clone(CLONE_PIDFD, &pidfd, child_poll_leader_exit_test); + if (pid < 0) + ksft_exit_fail_msg("%s test: pidfd_clone failed (ret %d, errno %d)\n", + test_name, pid, errno); + + ksft_print_msg("Parent: Waiting for Child (%d) to complete.\n", pid); + + if (use_waitpid) { + ret = waitpid(pid, &status, 0); + if (ret == -1) + ksft_print_msg("Parent: error\n"); + } else { + /* + * This sleep tests for the case where if the child exits, and is in + * EXIT_ZOMBIE, but the thread group leader is non-empty, then the poll + * doesn't prematurely return even though there are active threads + */ + sleep(1); + poll_pidfd(test_name, pidfd); + } + + if (ret == pid) + ksft_print_msg("Parent: Child process waited for.\n"); + + time_t since_child_exit = time(NULL) - *child_exit_secs; + + ksft_print_msg("Time since child exit: %lu\n", since_child_exit); + + close(pidfd); + + if (since_child_exit < CHILD_THREAD_MIN_WAIT || + since_child_exit > CHILD_THREAD_MIN_WAIT + 2) + ksft_exit_fail_msg("%s test: Failed\n", test_name); + else + ksft_test_result_pass("%s test: Passed\n", test_name); +} + int main(int argc, char **argv) { ksft_print_header(); ksft_set_plan(4); + test_pidfd_poll_exec(0); + test_pidfd_poll_exec(1); + test_pidfd_poll_leader_exit(0); + test_pidfd_poll_leader_exit(1); test_pidfd_send_signal_syscall_support(); test_pidfd_send_signal_simple_success(); test_pidfd_send_signal_exited_fail();