From: Sebastian Andrzej Siewior Date: Thu, 29 Aug 2013 18:21:04 +0200 Subject: [PATCH 153/342] ptrace: fix ptrace vs tasklist_lock race Origin: https://git.kernel.org/cgit/linux/kernel/git/rt/linux-stable-rt.git/commit?id=cb675ae1b0511d73895bd276d65c88740717b40b As explained by Alexander Fyodorov : |read_lock(&tasklist_lock) in ptrace_stop() is converted to mutex on RT kernel, |and it can remove __TASK_TRACED from task->state (by moving it to |task->saved_state). If parent does wait() on child followed by a sys_ptrace |call, the following race can happen: | |- child sets __TASK_TRACED in ptrace_stop() |- parent does wait() which eventually calls wait_task_stopped() and returns | child's pid |- child blocks on read_lock(&tasklist_lock) in ptrace_stop() and moves | __TASK_TRACED flag to saved_state |- parent calls sys_ptrace, which calls ptrace_check_attach() and wait_task_inactive() The patch is based on his initial patch where an additional check is added in case the __TASK_TRACED moved to ->saved_state. The pi_lock is taken in case the caller is interrupted between looking into ->state and ->saved_state. Signed-off-by: Sebastian Andrzej Siewior --- include/linux/sched.h | 49 +++++++++++++++++++++++++++++++++++++++---- kernel/ptrace.c | 9 +++++++- kernel/sched/core.c | 17 +++++++++++++-- 3 files changed, 68 insertions(+), 7 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index e4e206a1e7dd..5374ade34b87 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -101,12 +101,8 @@ struct task_group; __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) -#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) - #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) -#define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) - #define task_contributes_to_load(task) ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ (task->flags & PF_FROZEN) == 0 && \ (task->state & TASK_NOLOAD) == 0) @@ -1717,6 +1713,51 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } +static inline bool __task_is_stopped_or_traced(struct task_struct *task) +{ + if (task->state & (__TASK_STOPPED | __TASK_TRACED)) + return true; +#ifdef CONFIG_PREEMPT_RT_FULL + if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) + return true; +#endif + return false; +} + +static inline bool task_is_stopped_or_traced(struct task_struct *task) +{ + bool traced_stopped; + +#ifdef CONFIG_PREEMPT_RT_FULL + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + traced_stopped = __task_is_stopped_or_traced(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); +#else + traced_stopped = __task_is_stopped_or_traced(task); +#endif + return traced_stopped; +} + +static inline bool task_is_traced(struct task_struct *task) +{ + bool traced = false; + + if (task->state & __TASK_TRACED) + return true; +#ifdef CONFIG_PREEMPT_RT_FULL + /* in case the task is sleeping on tasklist_lock */ + raw_spin_lock_irq(&task->pi_lock); + if (task->state & __TASK_TRACED) + traced = true; + else if (task->saved_state & __TASK_TRACED) + traced = true; + raw_spin_unlock_irq(&task->pi_lock); +#endif + return traced; +} + /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return diff --git a/kernel/ptrace.c b/kernel/ptrace.c index bf8360e86f62..9078fdefc6e0 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -190,7 +190,14 @@ static bool ptrace_freeze_traced(struct task_struct *task) spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { - task->state = __TASK_TRACED; + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + if (task->state & __TASK_TRACED) + task->state = __TASK_TRACED; + else + task->saved_state = __TASK_TRACED; + raw_spin_unlock_irqrestore(&task->pi_lock, flags); ret = true; } spin_unlock_irq(&task->sighand->siglock); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1f450a7649f0..9494e2007118 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1349,6 +1349,18 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, } #endif /* CONFIG_NUMA_BALANCING */ +static bool check_task_state(struct task_struct *p, long match_state) +{ + bool match = false; + + raw_spin_lock_irq(&p->pi_lock); + if (p->state == match_state || p->saved_state == match_state) + match = true; + raw_spin_unlock_irq(&p->pi_lock); + + return match; +} + /* * wait_task_inactive - wait for a thread to unschedule. * @@ -1393,7 +1405,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * is actually now running somewhere else! */ while (task_running(rq, p)) { - if (match_state && unlikely(p->state != match_state)) + if (match_state && !check_task_state(p, match_state)) return 0; cpu_relax(); } @@ -1408,7 +1420,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) running = task_running(rq, p); queued = task_on_rq_queued(p); ncsw = 0; - if (!match_state || p->state == match_state) + if (!match_state || p->state == match_state || + p->saved_state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ task_rq_unlock(rq, p, &rf);