Merge branch 'for-3.5' of git://git.kernel.org/pub/scm/linux/kernel/g…

…it/tj/wq

Pull workqueue changes from Tejun Heo:
 "Nothing exciting.  Most are updates to debug stuff and related fixes.
  Two not-too-critical bugs are fixed - WARN_ON() triggering spurious
  during cpu offlining and unlikely lockdep related oops."

* 'for-3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  lockdep: fix oops in processing workqueue
  workqueue: skip nr_running sanity check in worker_enter_idle() if trustee is active
  workqueue: Catch more locking problems with flush_work()
  workqueue: change BUG_ON() to WARN_ON()
  trace: Remove unused workqueue tracer

include/linux/lockdep.h

@@ -157,6 +157,24 @@ struct lockdep_map {
 #endif
 };
 
+static inline void lockdep_copy_map(struct lockdep_map *to,
+				    struct lockdep_map *from)
+{
+	int i;
+
+	*to = *from;
+	/*
+	 * Since the class cache can be modified concurrently we could observe
+	 * half pointers (64bit arch using 32bit copy insns). Therefore clear
+	 * the caches and take the performance hit.
+	 *
+	 * XXX it doesn't work well with lockdep_set_class_and_subclass(), since
+	 *     that relies on cache abuse.
+	 */
+	for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
+		to->class_cache[i] = NULL;
+}
+
 /*
  * Every lock has a list of other locks that were taken after it.
  * We only grow the list, never remove from it:

kernel/timer.c

@@ -1108,7 +1108,9 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
 	 * warnings as well as problems when looking into
 	 * timer->lockdep_map, make a copy and use that here.
 	 */
-	struct lockdep_map lockdep_map = timer->lockdep_map;
+	struct lockdep_map lockdep_map;
+
+	lockdep_copy_map(&lockdep_map, &timer->lockdep_map);
 #endif
 	/*
 	 * Couple the lock chain with the lock chain at

kernel/trace/Makefile

@@ -41,7 +41,6 @@ obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
 ifeq ($(CONFIG_BLOCK),y)
 obj-$(CONFIG_EVENT_TRACING) += blktrace.o

kernel/workqueue.c

@@ -1032,7 +1032,10 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 	cwq = get_cwq(gcwq->cpu, wq);
 	trace_workqueue_queue_work(cpu, cwq, work);
 
-	BUG_ON(!list_empty(&work->entry));
+	if (WARN_ON(!list_empty(&work->entry))) {
+		spin_unlock_irqrestore(&gcwq->lock, flags);
+		return;
+	}
 
 	cwq->nr_in_flight[cwq->work_color]++;
 	work_flags = work_color_to_flags(cwq->work_color);
@@ -1210,8 +1213,13 @@ static void worker_enter_idle(struct worker *worker)
 	} else
 		wake_up_all(&gcwq->trustee_wait);
 
-	/* sanity check nr_running */
-	WARN_ON_ONCE(gcwq->nr_workers == gcwq->nr_idle &&
+	/*
+	 * Sanity check nr_running.  Because trustee releases gcwq->lock
+	 * between setting %WORKER_ROGUE and zapping nr_running, the
+	 * warning may trigger spuriously.  Check iff trustee is idle.
+	 */
+	WARN_ON_ONCE(gcwq->trustee_state == TRUSTEE_DONE &&
+		     gcwq->nr_workers == gcwq->nr_idle &&
 		     atomic_read(get_gcwq_nr_running(gcwq->cpu)));
 }
 
@@ -1810,7 +1818,9 @@ __acquires(&gcwq->lock)
 	 * lock freed" warnings as well as problems when looking into
 	 * work->lockdep_map, make a copy and use that here.
 	 */
-	struct lockdep_map lockdep_map = work->lockdep_map;
+	struct lockdep_map lockdep_map;
+
+	lockdep_copy_map(&lockdep_map, &work->lockdep_map);
 #endif
 	/*
 	 * A single work shouldn't be executed concurrently by
@@ -2506,6 +2516,9 @@ bool flush_work(struct work_struct *work)
 {
 	struct wq_barrier barr;
 
+	lock_map_acquire(&work->lockdep_map);
+	lock_map_release(&work->lockdep_map);
+
 	if (start_flush_work(work, &barr, true)) {
 		wait_for_completion(&barr.done);
 		destroy_work_on_stack(&barr.work);