From: Xunlei Pang A crash happened while I was playing with deadline PI rtmutex. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [] rt_mutex_get_top_task+0x1f/0x30 PGD 232a75067 PUD 230947067 PMD 0 Oops: 0000 [#1] SMP CPU: 1 PID: 10994 Comm: a.out Not tainted Call Trace: [] enqueue_task+0x2c/0x80 [] activate_task+0x23/0x30 [] pull_dl_task+0x1d5/0x260 [] pre_schedule_dl+0x16/0x20 [] __schedule+0xd3/0x900 [] schedule+0x29/0x70 [] __rt_mutex_slowlock+0x4b/0xc0 [] rt_mutex_slowlock+0xd1/0x190 [] rt_mutex_timed_lock+0x53/0x60 [] futex_lock_pi.isra.18+0x28c/0x390 [] do_futex+0x190/0x5b0 [] SyS_futex+0x80/0x180 This is because rt_mutex_enqueue_pi() and rt_mutex_dequeue_pi() are only protected by pi_lock when operating pi waiters, while rt_mutex_get_top_task(), will access them with rq lock held but not holding pi_lock. In order to tackle it, we introduce new "pi_top_task" pointer cached in task_struct, and add new rt_mutex_update_top_task() to update its value, it can be called by rt_mutex_setprio() which held both owner's pi_lock and rq lock. Thus "pi_top_task" can be safely accessed by enqueue_task_dl() under rq lock. Originally-From: Peter Zijlstra Cc: Ingo Molnar Cc: Juri Lelli Acked-by: Steven Rostedt Reviewed-by: Thomas Gleixner Signed-off-by: Xunlei Pang Signed-off-by: Peter Zijlstra (Intel) --- include/linux/init_task.h | 1 + include/linux/sched.h | 2 ++ include/linux/sched/rt.h | 1 + kernel/fork.c | 1 + kernel/locking/rtmutex.c | 29 +++++++++++++++++++++-------- kernel/sched/core.c | 2 ++ 6 files changed, 28 insertions(+), 8 deletions(-) --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -181,6 +181,7 @@ extern struct cred init_cred; #ifdef CONFIG_RT_MUTEXES # define INIT_RT_MUTEXES(tsk) \ .pi_waiters = RB_ROOT, \ + .pi_top_task = NULL, \ .pi_waiters_leftmost = NULL, #else # define INIT_RT_MUTEXES(tsk) --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -775,6 +775,8 @@ struct task_struct { /* PI waiters blocked on a rt_mutex held by this task: */ struct rb_root pi_waiters; struct rb_node *pi_waiters_leftmost; + /* Updated under owner's pi_lock and rq lock */ + struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ struct rt_mutex_waiter *pi_blocked_on; #endif --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -21,6 +21,7 @@ static inline int rt_task(struct task_st extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio); +extern void rt_mutex_update_top_task(struct task_struct *p); extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task); extern void rt_mutex_adjust_pi(struct task_struct *p); static inline bool tsk_is_pi_blocked(struct task_struct *tsk) --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1438,6 +1438,7 @@ static void rt_mutex_init_task(struct ta #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT; p->pi_waiters_leftmost = NULL; + p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -323,6 +323,19 @@ rt_mutex_dequeue_pi(struct task_struct * } /* + * Must hold both p->pi_lock and task_rq(p)->lock. + */ +void rt_mutex_update_top_task(struct task_struct *p) +{ + if (!task_has_pi_waiters(p)) { + p->pi_top_task = NULL; + return; + } + + p->pi_top_task = task_top_pi_waiter(p)->task; +} + +/* * Calculate task priority from the waiter tree priority * * Return task->normal_prio when the waiter tree is empty or when @@ -337,12 +350,12 @@ int rt_mutex_getprio(struct task_struct task->normal_prio); } +/* + * Must hold either p->pi_lock or task_rq(p)->lock. + */ struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { - if (likely(!task_has_pi_waiters(task))) - return NULL; - - return task_top_pi_waiter(task)->task; + return task->pi_top_task; } /* @@ -351,12 +364,12 @@ struct task_struct *rt_mutex_get_top_tas */ int rt_mutex_get_effective_prio(struct task_struct *task, int newprio) { - if (!task_has_pi_waiters(task)) + struct task_struct *top_task = rt_mutex_get_top_task(task); + + if (!top_task) return newprio; - if (task_top_pi_waiter(task)->task->prio <= newprio) - return task_top_pi_waiter(task)->task->prio; - return newprio; + return min(top_task->prio, newprio); } /* --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3716,6 +3716,8 @@ void rt_mutex_setprio(struct task_struct goto out_unlock; } + rt_mutex_update_top_task(p); + trace_sched_pi_setprio(p, prio); oldprio = p->prio;