From df4011e050b4e80165a317424e6b3367dfa7697c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 30 Apr 2013 15:28:20 -0700 Subject: exec: do not abuse ->cred_guard_mutex in threadgroup_lock() commit e56fb2874015370e3b7f8d85051f6dce26051df9 upstream. threadgroup_lock() takes signal->cred_guard_mutex to ensure that thread_group_leader() is stable. This doesn't look nice, the scope of this lock in do_execve() is huge. And as Dave pointed out this can lead to deadlock, we have the following dependencies: do_execve: cred_guard_mutex -> i_mutex cgroup_mount: i_mutex -> cgroup_mutex attach_task_by_pid: cgroup_mutex -> cred_guard_mutex Change de_thread() to take threadgroup_change_begin() around the switch-the-leader code and change threadgroup_lock() to avoid ->cred_guard_mutex. Note that de_thread() can't sleep with ->group_rwsem held, this can obviously deadlock with the exiting leader if the writer is active, so it does threadgroup_change_end() before schedule(). Reported-by: Dave Jones Acked-by: Tejun Heo Acked-by: Li Zefan Signed-off-by: Oleg Nesterov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds [ zhj: adjust context ] Signed-off-by: Zhao Hongjiang Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3dd0efbb70f2..28681fd191ab 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2466,27 +2466,18 @@ static inline void threadgroup_change_end(struct task_struct *tsk) * * 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. + * change ->group_leader/pid. 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. + * de_thread() does threadgroup_change_{begin|end}() when a non-leader + * sub-thread becomes a new leader. */ 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); } @@ -2499,7 +2490,6 @@ static inline void threadgroup_lock(struct task_struct *tsk) 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) {} -- cgit v1.2.3