Add a facility to the workqueue subsystem whereby an atomic_t can be
registered by a work function such that the work function dispatcher will
decrement the atomic after the work function has returned and then call
wake_up_atomic() on it if it reached 0.
This is analogous to complete_and_exit() for kernel threads and is used to
avoid a race between notifying that a work item is about to finish and the
.text segment from a module being discarded.
The way this is used is that the work function calls:
dec_after_work(atomic_t *counter);
to register the counter and then process_one_work() calls it, potentially
wakes it and clears the registration.
The reason I've used an atomic_t rather than a completion is that (1) it
takes up less space and (2) it can monitor multiple objects.
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Tejun Heo <tj@xxxxxxxxxx>
cc: Lai Jiangshan <jiangshanlai@xxxxxxxxx>
---
include/linux/workqueue.h | 1 +
kernel/workqueue.c | 25 +++++++++++++++++++++++++
kernel/workqueue_internal.h | 1 +
3 files changed, 27 insertions(+)
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index db6dc9dc0482..ceaed1387e9b 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -451,6 +451,7 @@ extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
extern void flush_workqueue(struct workqueue_struct *wq);
extern void drain_workqueue(struct workqueue_struct *wq);
+extern void dec_after_work(atomic_t *counter);
extern int schedule_on_each_cpu(work_func_t func);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ca937b0c3a96..2936ad0ab293 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2112,6 +2112,12 @@ __acquires(&pool->lock)
dump_stack();
}
+ if (worker->dec_after) {
+ if (atomic_dec_and_test(worker->dec_after))
+ wake_up_atomic_t(worker->dec_after);
+ worker->dec_after = NULL;
+ }
+
/*
* The following prevents a kworker from hogging CPU on !PREEMPT
* kernels, where a requeueing work item waiting for something to
@@ -3087,6 +3093,25 @@ int schedule_on_each_cpu(work_func_t func)
}
/**
+ * dec_after_work - Register counter to dec and wake after work func returns
+ * @counter: The counter to decrement and wake
+ *
+ * Register an atomic counter to be decremented after a work function returns
+ * to the core. The counter is 'woken' if it is decremented to 0. This allows
+ * synchronisation to be effected by one or more work functions in a module
+ * without leaving a window in which the work function code can be unloaded.
+ */
+void dec_after_work(atomic_t *counter)
+{
+ struct worker *worker = current_wq_worker();
+
+ BUG_ON(!worker);
+ BUG_ON(worker->dec_after);
+ worker->dec_after = counter;
+}
+EXPORT_SYMBOL(dec_after_work);
+
+/**
* execute_in_process_context - reliably execute the routine with user context
* @fn: the function to execute
* @ew: guaranteed storage for the execute work structure (must
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 8635417c587b..94ea1ca9b01f 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -28,6 +28,7 @@ struct worker {
struct work_struct *current_work; /* L: work being processed */
work_func_t current_func; /* L: current_work's fn */
+ atomic_t *dec_after; /* Decrement after func returns */
struct pool_workqueue *current_pwq; /* L: current_work's pwq */
bool desc_valid; /* ->desc is valid */
struct list_head scheduled; /* L: scheduled works */
