summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2015-10-06 17:05:36 +0200
committerIngo Molnar <mingo@kernel.org>2015-10-06 17:05:36 +0200
commitfe19159225d8516f3f57a5fe8f735c01684f0ddd (patch)
tree1a41faa5ef5139485f4afabd6bb9d3977c0a115b /kernel/sched
parentc6e1e7b5b7f031910850ddaf7bfa65ba3b4843ea (diff)
parent95913d97914f44db2b81271c2e2ebd4d2ac2df83 (diff)
Merge branch 'sched/urgent' into sched/core, to pick up fixes before applying new changes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/core.c39
-rw-r--r--kernel/sched/sched.h5
-rw-r--r--kernel/sched/wait.c7
3 files changed, 33 insertions, 18 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a91df6171f48..88a425443ff4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2511,11 +2511,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
* If a task dies, then it sets TASK_DEAD in tsk->state and calls
* schedule one last time. The schedule call will never return, and
* the scheduled task must drop that reference.
- * The test for TASK_DEAD must occur while the runqueue locks are
- * still held, otherwise prev could be scheduled on another cpu, die
- * there before we look at prev->state, and then the reference would
- * be dropped twice.
- * Manfred Spraul <manfred@colorfullife.com>
+ *
+ * We must observe prev->state before clearing prev->on_cpu (in
+ * finish_lock_switch), otherwise a concurrent wakeup can get prev
+ * running on another CPU and we could rave with its RUNNING -> DEAD
+ * transition, resulting in a double drop.
*/
prev_state = prev->state;
vtime_task_switch(prev);
@@ -2663,13 +2663,20 @@ unsigned long nr_running(void)
/*
* Check if only the current task is running on the cpu.
+ *
+ * Caution: this function does not check that the caller has disabled
+ * preemption, thus the result might have a time-of-check-to-time-of-use
+ * race. The caller is responsible to use it correctly, for example:
+ *
+ * - from a non-preemptable section (of course)
+ *
+ * - from a thread that is bound to a single CPU
+ *
+ * - in a loop with very short iterations (e.g. a polling loop)
*/
bool single_task_running(void)
{
- if (cpu_rq(smp_processor_id())->nr_running == 1)
- return true;
- else
- return false;
+ return raw_rq()->nr_running == 1;
}
EXPORT_SYMBOL(single_task_running);
@@ -4918,7 +4925,15 @@ void init_idle(struct task_struct *idle, int cpu)
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
- do_set_cpus_allowed(idle, cpumask_of(cpu));
+#ifdef CONFIG_SMP
+ /*
+ * Its possible that init_idle() gets called multiple times on a task,
+ * in that case do_set_cpus_allowed() will not do the right thing.
+ *
+ * And since this is boot we can forgo the serialization.
+ */
+ set_cpus_allowed_common(idle, cpumask_of(cpu));
+#endif
/*
* We're having a chicken and egg problem, even though we are
* holding rq->lock, the cpu isn't yet set to this cpu so the
@@ -4935,7 +4950,7 @@ void init_idle(struct task_struct *idle, int cpu)
rq->curr = rq->idle = idle;
idle->on_rq = TASK_ON_RQ_QUEUED;
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
idle->on_cpu = 1;
#endif
raw_spin_unlock(&rq->lock);
@@ -4950,7 +4965,7 @@ void init_idle(struct task_struct *idle, int cpu)
idle->sched_class = &idle_sched_class;
ftrace_graph_init_idle_task(idle, cpu);
vtime_init_idle(idle, cpu);
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
#endif
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index af6f252e7e34..046242feff3a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1072,9 +1072,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
* After ->on_cpu is cleared, the task can be moved to a different CPU.
* We must ensure this doesn't happen until the switch is completely
* finished.
+ *
+ * Pairs with the control dependency and rmb in try_to_wake_up().
*/
- smp_wmb();
- prev->on_cpu = 0;
+ smp_store_release(&prev->on_cpu, 0);
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
/* this is a valid case when another task releases the spinlock */
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 272d9322bc5d..052e02672d12 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -106,10 +106,9 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
}
EXPORT_SYMBOL_GPL(__wake_up_locked);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
- void *key)
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
{
- __wake_up_common(q, mode, nr, 0, key);
+ __wake_up_common(q, mode, 1, 0, key);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_key);
@@ -284,7 +283,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
if (!list_empty(&wait->task_list))
list_del_init(&wait->task_list);
else if (waitqueue_active(q))
- __wake_up_locked_key(q, mode, 1, key);
+ __wake_up_locked_key(q, mode, key);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(abort_exclusive_wait);