#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
/*
* The per-CPU workqueue (if single thread, we always use the first
struct workqueue_struct *wq;
struct task_struct *thread;
-
- int run_depth; /* Detect run_workqueue() recursion depth */
} ____cacheline_aligned;
/*
#endif
};
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+
+static struct debug_obj_descr work_debug_descr;
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int work_fixup_init(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ cancel_work_sync(work);
+ debug_object_init(work, &work_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int work_fixup_activate(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+
+ case ODEBUG_STATE_NOTAVAILABLE:
+ /*
+ * This is not really a fixup. The work struct was
+ * statically initialized. We just make sure that it
+ * is tracked in the object tracker.
+ */
+ if (test_bit(WORK_STRUCT_STATIC, work_data_bits(work))) {
+ debug_object_init(work, &work_debug_descr);
+ debug_object_activate(work, &work_debug_descr);
+ return 0;
+ }
+ WARN_ON_ONCE(1);
+ return 0;
+
+ case ODEBUG_STATE_ACTIVE:
+ WARN_ON(1);
+
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int work_fixup_free(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ cancel_work_sync(work);
+ debug_object_free(work, &work_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+static struct debug_obj_descr work_debug_descr = {
+ .name = "work_struct",
+ .fixup_init = work_fixup_init,
+ .fixup_activate = work_fixup_activate,
+ .fixup_free = work_fixup_free,
+};
+
+static inline void debug_work_activate(struct work_struct *work)
+{
+ debug_object_activate(work, &work_debug_descr);
+}
+
+static inline void debug_work_deactivate(struct work_struct *work)
+{
+ debug_object_deactivate(work, &work_debug_descr);
+}
+
+void __init_work(struct work_struct *work, int onstack)
+{
+ if (onstack)
+ debug_object_init_on_stack(work, &work_debug_descr);
+ else
+ debug_object_init(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(__init_work);
+
+void destroy_work_on_stack(struct work_struct *work)
+{
+ debug_object_free(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_work_on_stack);
+
+#else
+static inline void debug_work_activate(struct work_struct *work) { }
+static inline void debug_work_deactivate(struct work_struct *work) { }
+#endif
+
/* Serializes the accesses to the list of workqueues. */
static DEFINE_SPINLOCK(workqueue_lock);
static LIST_HEAD(workqueues);
static int singlethread_cpu __read_mostly;
-static cpumask_t cpu_singlethread_map __read_mostly;
+static const struct cpumask *cpu_singlethread_map __read_mostly;
/*
* _cpu_down() first removes CPU from cpu_online_map, then CPU_DEAD
* flushes cwq->worklist. This means that flush_workqueue/wait_on_work
* use cpu_possible_map, the cpumask below is more a documentation
* than optimization.
*/
-static cpumask_t cpu_populated_map __read_mostly;
+static cpumask_var_t cpu_populated_map __read_mostly;
/* If it's single threaded, it isn't in the list of workqueues. */
-static inline int is_single_threaded(struct workqueue_struct *wq)
+static inline int is_wq_single_threaded(struct workqueue_struct *wq)
{
return wq->singlethread;
}
-static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq)
+static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
{
- return is_single_threaded(wq)
- ? &cpu_singlethread_map : &cpu_populated_map;
+ return is_wq_single_threaded(wq)
+ ? cpu_singlethread_map : cpu_populated_map;
}
static
struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
{
- if (unlikely(is_single_threaded(wq)))
+ if (unlikely(is_wq_single_threaded(wq)))
cpu = singlethread_cpu;
return per_cpu_ptr(wq->cpu_wq, cpu);
}
static void insert_work(struct cpu_workqueue_struct *cwq,
struct work_struct *work, struct list_head *head)
{
+ trace_workqueue_insertion(cwq->thread, work);
+
set_wq_data(work, cwq);
/*
* Ensure that we get the right work->data if we see the
{
unsigned long flags;
+ debug_work_activate(work);
spin_lock_irqsave(&cwq->lock, flags);
insert_work(cwq, work, &cwq->worklist);
spin_unlock_irqrestore(&cwq->lock, flags);
static void run_workqueue(struct cpu_workqueue_struct *cwq)
{
spin_lock_irq(&cwq->lock);
- cwq->run_depth++;
- if (cwq->run_depth > 3) {
- /* morton gets to eat his hat */
- printk("%s: recursion depth exceeded: %d\n",
- __func__, cwq->run_depth);
- dump_stack();
- }
while (!list_empty(&cwq->worklist)) {
struct work_struct *work = list_entry(cwq->worklist.next,
struct work_struct, entry);
*/
struct lockdep_map lockdep_map = work->lockdep_map;
#endif
-
+ trace_workqueue_execution(cwq->thread, work);
+ debug_work_deactivate(work);
cwq->current_work = work;
list_del_init(cwq->worklist.next);
spin_unlock_irq(&cwq->lock);
spin_lock_irq(&cwq->lock);
cwq->current_work = NULL;
}
- cwq->run_depth--;
spin_unlock_irq(&cwq->lock);
}
if (cwq->wq->freezeable)
set_freezable();
- set_user_nice(current, -5);
-
for (;;) {
prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE);
if (!freezing(current) &&
static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
struct wq_barrier *barr, struct list_head *head)
{
- INIT_WORK(&barr->work, wq_barrier_func);
+ /*
+ * debugobject calls are safe here even with cwq->lock locked
+ * as we know for sure that this will not trigger any of the
+ * checks and call back into the fixup functions where we
+ * might deadlock.
+ */
+ INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
init_completion(&barr->done);
+ debug_work_activate(&barr->work);
insert_work(cwq, &barr->work, head);
}
static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
{
- int active;
+ int active = 0;
+ struct wq_barrier barr;
- if (cwq->thread == current) {
- /*
- * Probably keventd trying to flush its own queue. So simply run
- * it by hand rather than deadlocking.
- */
- run_workqueue(cwq);
- active = 1;
- } else {
- struct wq_barrier barr;
+ WARN_ON(cwq->thread == current);
- active = 0;
- spin_lock_irq(&cwq->lock);
- if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
- insert_wq_barrier(cwq, &barr, &cwq->worklist);
- active = 1;
- }
- spin_unlock_irq(&cwq->lock);
+ spin_lock_irq(&cwq->lock);
+ if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
+ insert_wq_barrier(cwq, &barr, &cwq->worklist);
+ active = 1;
+ }
+ spin_unlock_irq(&cwq->lock);
- if (active)
- wait_for_completion(&barr.done);
+ if (active) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
}
return active;
*/
void flush_workqueue(struct workqueue_struct *wq)
{
- const cpumask_t *cpu_map = wq_cpu_map(wq);
+ const struct cpumask *cpu_map = wq_cpu_map(wq);
int cpu;
might_sleep();
lock_map_acquire(&wq->lockdep_map);
lock_map_release(&wq->lockdep_map);
- for_each_cpu_mask_nr(cpu, *cpu_map)
+ for_each_cpu(cpu, cpu_map)
flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
}
EXPORT_SYMBOL_GPL(flush_workqueue);
return 0;
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
return 1;
}
EXPORT_SYMBOL_GPL(flush_work);
*/
smp_rmb();
if (cwq == get_wq_data(work)) {
+ debug_work_deactivate(work);
list_del_init(&work->entry);
ret = 1;
}
}
spin_unlock_irq(&cwq->lock);
- if (unlikely(running))
+ if (unlikely(running)) {
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
}
static void wait_on_work(struct work_struct *work)
{
struct cpu_workqueue_struct *cwq;
struct workqueue_struct *wq;
- const cpumask_t *cpu_map;
+ const struct cpumask *cpu_map;
int cpu;
might_sleep();
wq = cwq->wq;
cpu_map = wq_cpu_map(wq);
- for_each_cpu_mask_nr(cpu, *cpu_map)
+ for_each_cpu(cpu, cpu_map)
wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
}
* schedule_work - put work task in global workqueue
* @work: job to be done
*
- * This puts a job in the kernel-global workqueue.
+ * Returns zero if @work was already on the kernel-global workqueue and
+ * non-zero otherwise.
+ *
+ * This puts a job in the kernel-global workqueue if it was not already
+ * queued and leaves it in the same position on the kernel-global
+ * workqueue otherwise.
*/
int schedule_work(struct work_struct *work)
{
EXPORT_SYMBOL(schedule_delayed_work);
/**
+ * flush_delayed_work - block until a dwork_struct's callback has terminated
+ * @dwork: the delayed work which is to be flushed
+ *
+ * Any timeout is cancelled, and any pending work is run immediately.
+ */
+void flush_delayed_work(struct delayed_work *dwork)
+{
+ if (del_timer_sync(&dwork->timer)) {
+ struct cpu_workqueue_struct *cwq;
+ cwq = wq_per_cpu(keventd_wq, get_cpu());
+ __queue_work(cwq, &dwork->work);
+ put_cpu();
+ }
+ flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
int schedule_on_each_cpu(work_func_t func)
{
int cpu;
+ int orig = -1;
struct work_struct *works;
works = alloc_percpu(struct work_struct);
return -ENOMEM;
get_online_cpus();
+
+ /*
+ * When running in keventd don't schedule a work item on
+ * itself. Can just call directly because the work queue is
+ * already bound. This also is faster.
+ */
+ if (current_is_keventd())
+ orig = raw_smp_processor_id();
+
for_each_online_cpu(cpu) {
struct work_struct *work = per_cpu_ptr(works, cpu);
INIT_WORK(work, func);
- schedule_work_on(cpu, work);
+ if (cpu != orig)
+ schedule_work_on(cpu, work);
}
+ if (orig >= 0)
+ func(per_cpu_ptr(works, orig));
+
for_each_online_cpu(cpu)
flush_work(per_cpu_ptr(works, cpu));
+
put_online_cpus();
free_percpu(works);
return 0;
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
struct workqueue_struct *wq = cwq->wq;
- const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d";
+ const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d";
struct task_struct *p;
p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu);
sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m);
cwq->thread = p;
+ trace_workqueue_creation(cwq->thread, cpu);
+
return 0;
}
* checks list_empty(), and a "normal" queue_work() can't use
* a dead CPU.
*/
+ trace_workqueue_destruction(cwq->thread);
kthread_stop(cwq->thread);
cwq->thread = NULL;
}
*/
void destroy_workqueue(struct workqueue_struct *wq)
{
- const cpumask_t *cpu_map = wq_cpu_map(wq);
+ const struct cpumask *cpu_map = wq_cpu_map(wq);
int cpu;
cpu_maps_update_begin();
list_del(&wq->list);
spin_unlock(&workqueue_lock);
- for_each_cpu_mask_nr(cpu, *cpu_map)
+ for_each_cpu(cpu, cpu_map)
cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
cpu_maps_update_done();
switch (action) {
case CPU_UP_PREPARE:
- cpu_set(cpu, cpu_populated_map);
+ cpumask_set_cpu(cpu, cpu_populated_map);
}
undo:
list_for_each_entry(wq, &workqueues, list) {
switch (action) {
case CPU_UP_CANCELED:
case CPU_POST_DEAD:
- cpu_clear(cpu, cpu_populated_map);
+ cpumask_clear_cpu(cpu, cpu_populated_map);
}
return ret;
}
+#ifdef CONFIG_SMP
+
+struct work_for_cpu {
+ struct completion completion;
+ long (*fn)(void *);
+ void *arg;
+ long ret;
+};
+
+static int do_work_for_cpu(void *_wfc)
+{
+ struct work_for_cpu *wfc = _wfc;
+ wfc->ret = wfc->fn(wfc->arg);
+ complete(&wfc->completion);
+ return 0;
+}
+
+/**
+ * work_on_cpu - run a function in user context on a particular cpu
+ * @cpu: the cpu to run on
+ * @fn: the function to run
+ * @arg: the function arg
+ *
+ * This will return the value @fn returns.
+ * It is up to the caller to ensure that the cpu doesn't go offline.
+ * The caller must not hold any locks which would prevent @fn from completing.
+ */
+long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+{
+ struct task_struct *sub_thread;
+ struct work_for_cpu wfc = {
+ .completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
+ .fn = fn,
+ .arg = arg,
+ };
+
+ sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
+ if (IS_ERR(sub_thread))
+ return PTR_ERR(sub_thread);
+ kthread_bind(sub_thread, cpu);
+ wake_up_process(sub_thread);
+ wait_for_completion(&wfc.completion);
+ return wfc.ret;
+}
+EXPORT_SYMBOL_GPL(work_on_cpu);
+#endif /* CONFIG_SMP */
+
void __init init_workqueues(void)
{
- cpu_populated_map = cpu_online_map;
- singlethread_cpu = first_cpu(cpu_possible_map);
- cpu_singlethread_map = cpumask_of_cpu(singlethread_cpu);
+ alloc_cpumask_var(&cpu_populated_map, GFP_KERNEL);
+
+ cpumask_copy(cpu_populated_map, cpu_online_mask);
+ singlethread_cpu = cpumask_first(cpu_possible_mask);
+ cpu_singlethread_map = cpumask_of(singlethread_cpu);
hotcpu_notifier(workqueue_cpu_callback, 0);
keventd_wq = create_workqueue("events");
BUG_ON(!keventd_wq);