From e64646946ed32902fd597fa6e514b1da84642de3 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 20 May 2016 17:00:20 -0700 Subject: exit_thread: accept a task parameter to be exited We need to call exit_thread from copy_process in a fail path. So make it accept task_struct as a parameter. [v2] * s390: exit_thread_runtime_instr doesn't make sense to be called for non-current tasks. * arm: fix the comment in vfp_thread_copy * change 'me' to 'tsk' for task_struct * now we can change only archs that actually have exit_thread [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jiri Slaby Cc: "David S. Miller" Cc: "H. Peter Anvin" Cc: "James E.J. Bottomley" Cc: Aurelien Jacquiot Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Chen Liqin Cc: Chris Metcalf Cc: Chris Zankel Cc: David Howells Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James Hogan Cc: Jeff Dike Cc: Jesper Nilsson Cc: Jiri Slaby Cc: Jonas Bonn Cc: Koichi Yasutake Cc: Lennox Wu Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mikael Starvik Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Rich Felker Cc: Richard Henderson Cc: Richard Kuo Cc: Richard Weinberger Cc: Russell King Cc: Steven Miao Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index fd90195667e1..75b34fe835b2 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -746,7 +746,7 @@ void do_exit(long code) disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); - exit_thread(); + exit_thread(tsk); /* * Flush inherited counters to the parent - before the parent -- cgit v1.2.3 From bf959931ddb88c4e4366e96dd22e68fa0db9527c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 23 May 2016 16:23:50 -0700 Subject: wait/ptrace: assume __WALL if the child is traced The following program (simplified version of generated by syzkaller) #include #include #include #include #include void *thread_func(void *arg) { ptrace(PTRACE_TRACEME, 0,0,0); return 0; } int main(void) { pthread_t thread; if (fork()) return 0; while (getppid() != 1) ; pthread_create(&thread, NULL, thread_func, NULL); pthread_join(thread, NULL); return 0; } creates an unreapable zombie if /sbin/init doesn't use __WALL. This is not a kernel bug, at least in a sense that everything works as expected: debugger should reap a traced sub-thread before it can reap the leader, but without __WALL/__WCLONE do_wait() ignores sub-threads. Unfortunately, it seems that /sbin/init in most (all?) distributions doesn't use it and we have to change the kernel to avoid the problem. Note also that most init's use sys_waitid() which doesn't allow __WALL, so the necessary user-space fix is not that trivial. This patch just adds the "ptrace" check into eligible_child(). To some degree this matches the "tsk->ptrace" in exit_notify(), ->exit_signal is mostly ignored when the tracee reports to debugger. Or WSTOPPED, the tracer doesn't need to set this flag to wait for the stopped tracee. This obviously means the user-visible change: __WCLONE and __WALL no longer have any meaning for debugger. And I can only hope that this won't break something, but at least strace/gdb won't suffer. We could make a more conservative change. Say, we can take __WCLONE into account, or !thread_group_leader(). But it would be nice to not complicate these historical/confusing checks. Signed-off-by: Oleg Nesterov Reported-by: Dmitry Vyukov Cc: Denys Vlasenko Cc: Jan Kratochvil Cc: "Michael Kerrisk (man-pages)" Cc: Pedro Alves Cc: Roland McGrath Cc: Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 75b34fe835b2..44fbe6edd7fe 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -918,17 +918,28 @@ static int eligible_pid(struct wait_opts *wo, struct task_struct *p) task_pid_type(p, wo->wo_type) == wo->wo_pid; } -static int eligible_child(struct wait_opts *wo, struct task_struct *p) +static int +eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) { if (!eligible_pid(wo, p)) return 0; - /* Wait for all children (clone and not) if __WALL is set; - * otherwise, wait for clone children *only* if __WCLONE is - * set; otherwise, wait for non-clone children *only*. (Note: - * A "clone" child here is one that reports to its parent - * using a signal other than SIGCHLD.) */ - if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) - && !(wo->wo_flags & __WALL)) + + /* + * Wait for all children (clone and not) if __WALL is set or + * if it is traced by us. + */ + if (ptrace || (wo->wo_flags & __WALL)) + return 1; + + /* + * Otherwise, wait for clone children *only* if __WCLONE is set; + * otherwise, wait for non-clone children *only*. + * + * Note: a "clone" child here is one that reports to its parent + * using a signal other than SIGCHLD, or a non-leader thread which + * we can only see if it is traced by us. + */ + if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) return 0; return 1; @@ -1300,7 +1311,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, if (unlikely(exit_state == EXIT_DEAD)) return 0; - ret = eligible_child(wo, p); + ret = eligible_child(wo, ptrace, p); if (!ret) return ret; -- cgit v1.2.3 From 91c4e8ea8f05916df0c8a6f383508ac7c9e10dba Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 23 May 2016 16:23:53 -0700 Subject: wait: allow sys_waitid() to accept __WNOTHREAD/__WCLONE/__WALL I see no reason why waitid() can't support other linux-specific flags allowed in sys_wait4(). In particular this change can help if we reconsider the previous change ("wait/ptrace: assume __WALL if the child is traced") which adds the "automagical" __WALL for debugger. Signed-off-by: Oleg Nesterov Cc: Dmitry Vyukov Cc: Denys Vlasenko Cc: Jan Kratochvil Cc: "Michael Kerrisk (man-pages)" Cc: Pedro Alves Cc: Roland McGrath Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 44fbe6edd7fe..9e6e1356e6bb 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1535,7 +1535,8 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, enum pid_type type; long ret; - if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED)) + if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| + __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) return -EINVAL; -- cgit v1.2.3