Index: linux-stable/kernel/sched/core.c =================================================================== --- linux-stable.orig/kernel/sched/core.c +++ linux-stable/kernel/sched/core.c @@ -1376,12 +1376,6 @@ out: } } - /* - * Clear PF_NO_SETAFFINITY, otherwise we wreckage - * migrate_disable/enable. See optimization for - * PF_NO_SETAFFINITY tasks there. - */ - p->flags &= ~PF_NO_SETAFFINITY; return dest_cpu; } @@ -2917,9 +2911,8 @@ need_resched: static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state || tsk_is_pi_blocked(tsk)) + if (!tsk->state) return; - /* * If a worker went to sleep, notify and ask workqueue whether * it wants to wake up a task to maintain concurrency. @@ -2927,6 +2920,10 @@ static inline void sched_submit_work(str if (tsk->flags & PF_WQ_WORKER) wq_worker_sleeping(tsk); + + if (tsk_is_pi_blocked(tsk)) + return; + /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. Index: linux-stable/kernel/workqueue.c =================================================================== --- linux-stable.orig/kernel/workqueue.c +++ linux-stable/kernel/workqueue.c @@ -126,6 +126,11 @@ enum { * cpu or grabbing pool->lock is enough for read access. If * POOL_DISASSOCIATED is set, it's identical to L. * + * On RT we need the extra protection via rt_lock_idle_list() for + * the list manipulations against read access from + * wq_worker_sleeping(). All other places are nicely serialized via + * pool->lock. + * * MG: pool->manager_mutex and pool->lock protected. Writes require both * locks. Reads can happen under either lock. * @@ -409,6 +414,31 @@ static void copy_workqueue_attrs(struct if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ else +#ifdef CONFIG_PREEMPT_RT_BASE +static inline void rt_lock_idle_list(struct worker_pool *pool) +{ + preempt_disable(); +} +static inline void rt_unlock_idle_list(struct worker_pool *pool) +{ + preempt_enable(); +} +static inline void sched_lock_idle_list(struct worker_pool *pool) { } +static inline void sched_unlock_idle_list(struct worker_pool *pool) { } +#else +static inline void rt_lock_idle_list(struct worker_pool *pool) { } +static inline void rt_unlock_idle_list(struct worker_pool *pool) { } +static inline void sched_lock_idle_list(struct worker_pool *pool) +{ + spin_lock_irq(&pool->lock); +} +static inline void sched_unlock_idle_list(struct worker_pool *pool) +{ + spin_unlock_irq(&pool->lock); +} +#endif + + #ifdef CONFIG_DEBUG_OBJECTS_WORK static struct debug_obj_descr work_debug_descr; @@ -808,10 +838,16 @@ static struct worker *first_worker(struc */ static void wake_up_worker(struct worker_pool *pool) { - struct worker *worker = first_worker(pool); + struct worker *worker; + + rt_lock_idle_list(pool); + + worker = first_worker(pool); if (likely(worker)) wake_up_process(worker->task); + + rt_unlock_idle_list(pool); } /** @@ -839,7 +875,7 @@ void wq_worker_running(struct task_struc */ void wq_worker_sleeping(struct task_struct *task) { - struct worker *next, *worker = kthread_data(task); + struct worker *worker = kthread_data(task); struct worker_pool *pool; /* @@ -856,25 +892,18 @@ void wq_worker_sleeping(struct task_stru return; worker->sleeping = 1; - spin_lock_irq(&pool->lock); + /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). * Please read comment there. - * - * NOT_RUNNING is clear. This means that we're bound to and - * running on the local cpu w/ rq lock held and preemption - * disabled, which in turn means that none else could be - * manipulating idle_list, so dereferencing idle_list without pool - * lock is safe. */ if (atomic_dec_and_test(&pool->nr_running) && !list_empty(&pool->worklist)) { - next = first_worker(pool); - if (next) - wake_up_process(next->task); + sched_lock_idle_list(pool); + wake_up_worker(pool); + sched_unlock_idle_list(pool); } - spin_unlock_irq(&pool->lock); } /** @@ -1578,7 +1607,9 @@ static void worker_enter_idle(struct wor worker->last_active = jiffies; /* idle_list is LIFO */ + rt_lock_idle_list(pool); list_add(&worker->entry, &pool->idle_list); + rt_unlock_idle_list(pool); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); @@ -1611,7 +1642,9 @@ static void worker_leave_idle(struct wor return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; + rt_lock_idle_list(pool); list_del_init(&worker->entry); + rt_unlock_idle_list(pool); } /** @@ -1857,7 +1890,9 @@ static void destroy_worker(struct worker */ get_task_struct(worker->task); + rt_lock_idle_list(pool); list_del_init(&worker->entry); + rt_unlock_idle_list(pool); worker->flags |= WORKER_DIE; idr_remove(&pool->worker_idr, worker->id); Index: linux-stable/localversion-rt =================================================================== --- linux-stable.orig/localversion-rt +++ linux-stable/localversion-rt @@ -1 +1 @@ --rt6 +-rt7