Clarify and tighten try_invoke_on_locked_down_task().
Basically the function calls @func under task_rq_lock(), except it
avoids taking rq->lock when possible.
This makes calling @func unconditional (the function will get renamed
in a later patch to remove the try).
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
kernel/sched/core.c | 63 ++++++++++++++++++++++++++++++++--------------------
1 file changed, 39 insertions(+), 24 deletions(-)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4111,41 +4111,56 @@ try_to_wake_up(struct task_struct *p, un
* @func: Function to invoke.
* @arg: Argument to function.
*
- * If the specified task can be quickly locked into a definite state
- * (either sleeping or on a given runqueue), arrange to keep it in that
- * state while invoking @func(@arg). This function can use ->on_rq and
- * task_curr() to work out what the state is, if required. Given that
- * @func can be invoked with a runqueue lock held, it had better be quite
- * lightweight.
+ * Fix the task in it's current state by avoiding wakeups and or rq operations
+ * and call @func(@arg) on it. This function can use ->on_rq and task_curr()
+ * to work out what the state is, if required. Given that @func can be invoked
+ * with a runqueue lock held, it had better be quite lightweight.
*
* Returns:
- * @false if the task slipped out from under the locks.
- * @true if the task was locked onto a runqueue or is sleeping.
- * However, @func can override this by returning @false.
+ * Whatever @func returns
*/
bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg)
{
+ struct rq *rq = NULL;
+ unsigned int state;
struct rq_flags rf;
bool ret = false;
- struct rq *rq;
raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
- if (p->on_rq) {
+
+ state = READ_ONCE(p->__state);
+
+ /*
+ * Ensure we load p->on_rq after p->__state, otherwise it would be
+ * possible to, falsely, observe p->on_rq == 0.
+ *
+ * See try_to_wake_up() for a longer comment.
+ */
+ smp_rmb();
+
+ /*
+ * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
+ * the task is blocked. Make sure to check @state since ttwu() can drop
+ * locks at the end, see ttwu_queue_wakelist().
+ */
+ if (state == TASK_RUNNING || state == TASK_WAKING || p->on_rq)
rq = __task_rq_lock(p, &rf);
- if (task_rq(p) == rq)
- ret = func(p, arg);
+
+ /*
+ * At this point the task is pinned; either:
+ * - blocked and we're holding off wakeups (pi->lock)
+ * - woken, and we're holding off enqueue (rq->lock)
+ * - queued, and we're holding off schedule (rq->lock)
+ * - running, and we're holding off de-schedule (rq->lock)
+ *
+ * The called function (@func) can use: task_curr(), p->on_rq and
+ * p->__state to differentiate between these states.
+ */
+ ret = func(p, arg);
+
+ if (rq)
rq_unlock(rq, &rf);
- } else {
- switch (READ_ONCE(p->__state)) {
- case TASK_RUNNING:
- case TASK_WAKING:
- break;
- default:
- smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
- if (!p->on_rq)
- ret = func(p, arg);
- }
- }
+
raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
return ret;
}
