From a7f0765edfd53aed09cb7b0e15863688b39447de Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 23 Sep 2009 15:56:44 -0700 Subject: ptrace: __ptrace_detach: do __wake_up_parent() if we reap the tracee The bug is old, it wasn't cause by recent changes. Test case: static void *tfunc(void *arg) { int pid = (long)arg; assert(ptrace(PTRACE_ATTACH, pid, NULL, NULL) == 0); kill(pid, SIGKILL); sleep(1); return NULL; } int main(void) { pthread_t th; long pid = fork(); if (!pid) pause(); signal(SIGCHLD, SIG_IGN); assert(pthread_create(&th, NULL, tfunc, (void*)pid) == 0); int r = waitpid(-1, NULL, __WNOTHREAD); printf("waitpid: %d %m\n", r); return 0; } Before the patch this program hangs, after this patch waitpid() correctly fails with errno == -ECHILD. The problem is, __ptrace_detach() reaps the EXIT_ZOMBIE tracee if its ->real_parent is our sub-thread and we ignore SIGCHLD. But in this case we should wake up other threads which can sleep in do_wait(). Signed-off-by: Oleg Nesterov Cc: Roland McGrath Cc: Vitaly Mayatskikh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'kernel/signal.c') diff --git a/kernel/signal.c b/kernel/signal.c index 64c5deeaca5d..534ea81cde47 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1382,15 +1382,6 @@ ret: return ret; } -/* - * Wake up any threads in the parent blocked in wait* syscalls. - */ -static inline void __wake_up_parent(struct task_struct *p, - struct task_struct *parent) -{ - wake_up_interruptible_sync(&parent->signal->wait_chldexit); -} - /* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. -- cgit v1.2.3 From ae6d2ed7bb3877ff35b9569402025f40ea2e1803 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 23 Sep 2009 15:56:53 -0700 Subject: signals: tracehook_notify_jctl change This changes tracehook_notify_jctl() so it's called with the siglock held, and changes its argument and return value definition. These clean-ups make it a better fit for what new tracing hooks need to check. Tracing needs the siglock here, held from the time TASK_STOPPED was set, to avoid potential SIGCONT races if it wants to allow any blocking in its tracing hooks. This also folds the finish_stop() function into its caller do_signal_stop(). The function is short, called only once and only unconditionally. It aids readability to fold it in. [oleg@redhat.com: do not call tracehook_notify_jctl() in TASK_STOPPED state] [oleg@redhat.com: introduce tracehook_finish_jctl() helper] Signed-off-by: Roland McGrath Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 97 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 47 insertions(+), 50 deletions(-) (limited to 'kernel/signal.c') diff --git a/kernel/signal.c b/kernel/signal.c index 534ea81cde47..5d3b3f8f219b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -705,7 +705,7 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) if (why) { /* - * The first thread which returns from finish_stop() + * The first thread which returns from do_signal_stop() * will take ->siglock, notice SIGNAL_CLD_MASK, and * notify its parent. See get_signal_to_deliver(). */ @@ -1664,29 +1664,6 @@ void ptrace_notify(int exit_code) spin_unlock_irq(¤t->sighand->siglock); } -static void -finish_stop(int stop_count) -{ - /* - * If there are no other threads in the group, or if there is - * a group stop in progress and we are the last to stop, - * report to the parent. When ptraced, every thread reports itself. - */ - if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) { - read_lock(&tasklist_lock); - do_notify_parent_cldstop(current, CLD_STOPPED); - read_unlock(&tasklist_lock); - } - - do { - schedule(); - } while (try_to_freeze()); - /* - * Now we don't run again until continued. - */ - current->exit_code = 0; -} - /* * This performs the stopping for SIGSTOP and other stop signals. * We have to stop all threads in the thread group. @@ -1696,15 +1673,9 @@ finish_stop(int stop_count) static int do_signal_stop(int signr) { struct signal_struct *sig = current->signal; - int stop_count; + int notify; - if (sig->group_stop_count > 0) { - /* - * There is a group stop in progress. We don't need to - * start another one. - */ - stop_count = --sig->group_stop_count; - } else { + if (!sig->group_stop_count) { struct task_struct *t; if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) || @@ -1716,7 +1687,7 @@ static int do_signal_stop(int signr) */ sig->group_exit_code = signr; - stop_count = 0; + sig->group_stop_count = 1; for (t = next_thread(current); t != current; t = next_thread(t)) /* * Setting state to TASK_STOPPED for a group @@ -1725,19 +1696,44 @@ static int do_signal_stop(int signr) */ if (!(t->flags & PF_EXITING) && !task_is_stopped_or_traced(t)) { - stop_count++; + sig->group_stop_count++; signal_wake_up(t, 0); } - sig->group_stop_count = stop_count; } + /* + * If there are no other threads in the group, or if there is + * a group stop in progress and we are the last to stop, report + * to the parent. When ptraced, every thread reports itself. + */ + notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0; + notify = tracehook_notify_jctl(notify, CLD_STOPPED); + /* + * tracehook_notify_jctl() can drop and reacquire siglock, so + * we keep ->group_stop_count != 0 before the call. If SIGCONT + * or SIGKILL comes in between ->group_stop_count == 0. + */ + if (sig->group_stop_count) { + if (!--sig->group_stop_count) + sig->flags = SIGNAL_STOP_STOPPED; + current->exit_code = sig->group_exit_code; + __set_current_state(TASK_STOPPED); + } + spin_unlock_irq(¤t->sighand->siglock); - if (stop_count == 0) - sig->flags = SIGNAL_STOP_STOPPED; - current->exit_code = sig->group_exit_code; - __set_current_state(TASK_STOPPED); + if (notify) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current, notify); + read_unlock(&tasklist_lock); + } + + /* Now we don't run again until woken by SIGCONT or SIGKILL */ + do { + schedule(); + } while (try_to_freeze()); + + tracehook_finish_jctl(); + current->exit_code = 0; - spin_unlock_irq(¤t->sighand->siglock); - finish_stop(stop_count); return 1; } @@ -1806,14 +1802,15 @@ relock: int why = (signal->flags & SIGNAL_STOP_CONTINUED) ? CLD_CONTINUED : CLD_STOPPED; signal->flags &= ~SIGNAL_CLD_MASK; - spin_unlock_irq(&sighand->siglock); - if (unlikely(!tracehook_notify_jctl(1, why))) - goto relock; + why = tracehook_notify_jctl(why, CLD_CONTINUED); + spin_unlock_irq(&sighand->siglock); - read_lock(&tasklist_lock); - do_notify_parent_cldstop(current->group_leader, why); - read_unlock(&tasklist_lock); + if (why) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current->group_leader, why); + read_unlock(&tasklist_lock); + } goto relock; } @@ -1978,14 +1975,14 @@ void exit_signals(struct task_struct *tsk) if (unlikely(tsk->signal->group_stop_count) && !--tsk->signal->group_stop_count) { tsk->signal->flags = SIGNAL_STOP_STOPPED; - group_stop = 1; + group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED); } out: spin_unlock_irq(&tsk->sighand->siglock); - if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) { + if (unlikely(group_stop)) { read_lock(&tasklist_lock); - do_notify_parent_cldstop(tsk, CLD_STOPPED); + do_notify_parent_cldstop(tsk, group_stop); read_unlock(&tasklist_lock); } } -- cgit v1.2.3 From 4a30debfb778240a4b1767d4b0c5a5b25ab97160 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 23 Sep 2009 15:57:00 -0700 Subject: signals: introduce do_send_sig_info() helper Introduce do_send_sig_info() and convert group_send_sig_info(), send_sig_info(), do_send_specific() to use this helper. Hopefully it will have more users soon, it allows to specify specific/group behaviour via "bool group" argument. Shaves 80 bytes from .text. Signed-off-by: Oleg Nesterov Cc: Peter Zijlstra Cc: stephane eranian Cc: Ingo Molnar Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 56 +++++++++++++++++++++++++++----------------------------- 1 file changed, 27 insertions(+), 29 deletions(-) (limited to 'kernel/signal.c') diff --git a/kernel/signal.c b/kernel/signal.c index 5d3b3f8f219b..c6d7a24a86a1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -971,6 +971,20 @@ specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t) return send_signal(sig, info, t, 0); } +int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, + bool group) +{ + unsigned long flags; + int ret = -ESRCH; + + if (lock_task_sighand(p, &flags)) { + ret = send_signal(sig, info, p, group); + unlock_task_sighand(p, &flags); + } + + return ret; +} + /* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. @@ -1068,18 +1082,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long */ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { - unsigned long flags; - int ret; - - ret = check_kill_permission(sig, info, p); + int ret = check_kill_permission(sig, info, p); - if (!ret && sig) { - ret = -ESRCH; - if (lock_task_sighand(p, &flags)) { - ret = __group_send_sig_info(sig, info, p); - unlock_task_sighand(p, &flags); - } - } + if (!ret && sig) + ret = do_send_sig_info(sig, info, p, true); return ret; } @@ -1224,15 +1230,9 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) * These are for backward compatibility with the rest of the kernel source. */ -/* - * The caller must ensure the task can't exit. - */ int send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { - int ret; - unsigned long flags; - /* * Make sure legacy kernel users don't send in bad values * (normal paths check this in check_kill_permission). @@ -1240,10 +1240,7 @@ send_sig_info(int sig, struct siginfo *info, struct task_struct *p) if (!valid_signal(sig)) return -EINVAL; - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = specific_send_sig_info(sig, info, p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - return ret; + return do_send_sig_info(sig, info, p, false); } #define __si_special(priv) \ @@ -2278,7 +2275,6 @@ static int do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) { struct task_struct *p; - unsigned long flags; int error = -ESRCH; rcu_read_lock(); @@ -2288,14 +2284,16 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) /* * The null signal is a permissions and process existence * probe. No signal is actually delivered. - * - * If lock_task_sighand() fails we pretend the task dies - * after receiving the signal. The window is tiny, and the - * signal is private anyway. */ - if (!error && sig && lock_task_sighand(p, &flags)) { - error = specific_send_sig_info(sig, info, p); - unlock_task_sighand(p, &flags); + if (!error && sig) { + error = do_send_sig_info(sig, info, p, false); + /* + * If lock_task_sighand() failed we pretend the task + * dies after receiving the signal. The window is tiny, + * and the signal is private anyway. + */ + if (unlikely(error == -ESRCH)) + error = 0; } } rcu_read_unlock(); -- cgit v1.2.3 From d9588725e52650e82989707f8fd2feb67ad2dc8e Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 23 Sep 2009 15:57:04 -0700 Subject: signals: inline __fatal_signal_pending __fatal_signal_pending inlines to one instruction on x86, probably two instructions on other machines. It takes two longer x86 instructions just to call it and test its return value, not to mention the function itself. On my random x86_64 config, this saved 70 bytes of text (59 of those being __fatal_signal_pending itself). Signed-off-by: Roland McGrath Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel/signal.c') diff --git a/kernel/signal.c b/kernel/signal.c index c6d7a24a86a1..6705320784fd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1050,12 +1050,6 @@ void zap_other_threads(struct task_struct *p) } } -int __fatal_signal_pending(struct task_struct *tsk) -{ - return sigismember(&tsk->pending.signal, SIGKILL); -} -EXPORT_SYMBOL(__fatal_signal_pending); - struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags) { struct sighand_struct *sighand; -- cgit v1.2.3