diff options
| -rw-r--r-- | include/linux/sched.h | 47 | ||||
| -rw-r--r-- | kernel/signal.c | 10 |
2 files changed, 51 insertions, 6 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index 8cd523202a3b..c0c5876c52c0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -635,11 +635,13 @@ struct signal_struct { #endif #ifdef CONFIG_CGROUPS /* - * The group_rwsem prevents threads from forking with - * CLONE_THREAD while held for writing. Use this for fork-sensitive - * threadgroup-wide operations. It's taken for reading in fork.c in - * copy_process(). - * Currently only needed write-side by cgroups. + * group_rwsem prevents new tasks from entering the threadgroup and + * member tasks from exiting,a more specifically, setting of + * PF_EXITING. fork and exit paths are protected with this rwsem + * using threadgroup_change_begin/end(). Users which require + * threadgroup to remain stable should use threadgroup_[un]lock() + * which also takes care of exec path. Currently, cgroup is the + * only user. */ struct rw_semaphore group_rwsem; #endif @@ -2371,7 +2373,6 @@ static inline void unlock_task_sighand(struct task_struct *tsk, spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); } -/* See the declaration of group_rwsem in signal_struct. */ #ifdef CONFIG_CGROUPS static inline void threadgroup_change_begin(struct task_struct *tsk) { @@ -2381,13 +2382,47 @@ static inline void threadgroup_change_end(struct task_struct *tsk) { up_read(&tsk->signal->group_rwsem); } + +/** + * threadgroup_lock - lock threadgroup + * @tsk: member task of the threadgroup to lock + * + * Lock the threadgroup @tsk belongs to. No new task is allowed to enter + * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or + * perform exec. This is useful for cases where the threadgroup needs to + * stay stable across blockable operations. + * + * fork and exit paths explicitly call threadgroup_change_{begin|end}() for + * synchronization. While held, no new task will be added to threadgroup + * and no existing live task will have its PF_EXITING set. + * + * During exec, a task goes and puts its thread group through unusual + * changes. After de-threading, exclusive access is assumed to resources + * which are usually shared by tasks in the same group - e.g. sighand may + * be replaced with a new one. Also, the exec'ing task takes over group + * leader role including its pid. Exclude these changes while locked by + * grabbing cred_guard_mutex which is used to synchronize exec path. + */ static inline void threadgroup_lock(struct task_struct *tsk) { + /* + * exec uses exit for de-threading nesting group_rwsem inside + * cred_guard_mutex. Grab cred_guard_mutex first. + */ + mutex_lock(&tsk->signal->cred_guard_mutex); down_write(&tsk->signal->group_rwsem); } + +/** + * threadgroup_unlock - unlock threadgroup + * @tsk: member task of the threadgroup to unlock + * + * Reverse threadgroup_lock(). + */ static inline void threadgroup_unlock(struct task_struct *tsk) { up_write(&tsk->signal->group_rwsem); + mutex_unlock(&tsk->signal->cred_guard_mutex); } #else static inline void threadgroup_change_begin(struct task_struct *tsk) {} diff --git a/kernel/signal.c b/kernel/signal.c index b3f78d09a105..399c184bf0ae 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2359,8 +2359,15 @@ void exit_signals(struct task_struct *tsk) int group_stop = 0; sigset_t unblocked; + /* + * @tsk is about to have PF_EXITING set - lock out users which + * expect stable threadgroup. + */ + threadgroup_change_begin(tsk); + if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) { tsk->flags |= PF_EXITING; + threadgroup_change_end(tsk); return; } @@ -2370,6 +2377,9 @@ void exit_signals(struct task_struct *tsk) * see wants_signal(), do_signal_stop(). */ tsk->flags |= PF_EXITING; + + threadgroup_change_end(tsk); + if (!signal_pending(tsk)) goto out; |