1 files changed, 67 insertions, 27 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0b72e816b8d0..29b79852a845 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -16,9 +16,10 @@
  *
  * This is the generic async execution mechanism.  Work items as are
  * executed in process context.  The worker pool is shared and
- * automatically managed.  There is one worker pool for each CPU and
- * one extra for works which are better served by workers which are
- * not bound to any specific CPU.
+ * automatically managed.  There are two worker pools for each CPU (one for
+ * normal work items and the other for high priority ones) and some extra
+ * pools for workqueues which are not bound to any specific CPU - the
+ * number of these backing pools is dynamic.
  *
  * Please read Documentation/workqueue.txt for details.
  */
@@ -2033,8 +2034,11 @@ static bool maybe_destroy_workers(struct worker_pool *pool)
  * multiple times.  Does GFP_KERNEL allocations.
  *
  * RETURNS:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
- * multiple times.  Does GFP_KERNEL allocations.
+ * %false if the pool don't need management and the caller can safely start
+ * processing works, %true indicates that the function released pool->lock
+ * and reacquired it to perform some management function and that the
+ * conditions that the caller verified while holding the lock before
+ * calling the function might no longer be true.
  */
 static bool manage_workers(struct worker *worker)
 {
@@ -2201,6 +2205,15 @@ __acquires(&pool->lock)
                 dump_stack();
         }
 
+        /*
+         * The following prevents a kworker from hogging CPU on !PREEMPT
+         * kernels, where a requeueing work item waiting for something to
+         * happen could deadlock with stop_machine as such work item could
+         * indefinitely requeue itself while all other CPUs are trapped in
+         * stop_machine.
+         */
+        cond_resched();
+
         spin_lock_irq(&pool->lock);
 
         /* clear cpu intensive status */
@@ -2817,6 +2830,19 @@ already_gone:
         return false;
 }
 
+static bool __flush_work(struct work_struct *work)
+{
+        struct wq_barrier barr;
+
+        if (start_flush_work(work, &barr)) {
+                wait_for_completion(&barr.done);
+                destroy_work_on_stack(&barr.work);
+                return true;
+        } else {
+                return false;
+        }
+}
+
 /**
  * flush_work - wait for a work to finish executing the last queueing instance
  * @work: the work to flush
@@ -2830,18 +2856,10 @@ already_gone:
  */
 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)) {
-                wait_for_completion(&barr.done);
-                destroy_work_on_stack(&barr.work);
-                return true;
-        } else {
-                return false;
-        }
+        return __flush_work(work);
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
@@ -3081,25 +3099,26 @@ static struct workqueue_struct *dev_to_wq(struct device *dev)
         return wq_dev->wq;
 }
 
-static ssize_t wq_per_cpu_show(struct device *dev,
-                               struct device_attribute *attr, char *buf)
+static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr,
+                            char *buf)
 {
         struct workqueue_struct *wq = dev_to_wq(dev);
 
         return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND));
 }
+static DEVICE_ATTR_RO(per_cpu);
 
-static ssize_t wq_max_active_show(struct device *dev,
-                                  struct device_attribute *attr, char *buf)
+static ssize_t max_active_show(struct device *dev,
+                               struct device_attribute *attr, char *buf)
 {
         struct workqueue_struct *wq = dev_to_wq(dev);
 
         return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active);
 }
 
-static ssize_t wq_max_active_store(struct device *dev,
-                                   struct device_attribute *attr,
-                                   const char *buf, size_t count)
+static ssize_t max_active_store(struct device *dev,
+                                struct device_attribute *attr, const char *buf,
+                                size_t count)
 {
         struct workqueue_struct *wq = dev_to_wq(dev);
         int val;
@@ -3110,12 +3129,14 @@ static ssize_t wq_max_active_store(struct device *dev,
         workqueue_set_max_active(wq, val);
         return count;
 }
+static DEVICE_ATTR_RW(max_active);
 
-static struct device_attribute wq_sysfs_attrs[] = {
-        __ATTR(per_cpu, 0444, wq_per_cpu_show, NULL),
-        __ATTR(max_active, 0644, wq_max_active_show, wq_max_active_store),
-        __ATTR_NULL,
+static struct attribute *wq_sysfs_attrs[] = {
+        &dev_attr_per_cpu.attr,
+        &dev_attr_max_active.attr,
+        NULL,
 };
+ATTRIBUTE_GROUPS(wq_sysfs);
 
 static ssize_t wq_pool_ids_show(struct device *dev,
                                 struct device_attribute *attr, char *buf)
@@ -3265,7 +3286,7 @@ static struct device_attribute wq_sysfs_unbound_attrs[] = {
 
 static struct bus_type wq_subsys = {
         .name                           = "workqueue",
-        .dev_attrs                      = wq_sysfs_attrs,
+        .dev_groups                     = wq_sysfs_groups,
 };
 
 static int __init wq_sysfs_init(void)
@@ -3411,6 +3432,12 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to,
 {
         to->nice = from->nice;
         cpumask_copy(to->cpumask, from->cpumask);
+        /*
+         * Unlike hash and equality test, this function doesn't ignore
+         * ->no_numa as it is used for both pool and wq attrs.  Instead,
+         * get_unbound_pool() explicitly clears ->no_numa after copying.
+         */
+        to->no_numa = from->no_numa;
 }
 
 /* hash value of the content of @attr */
@@ -3578,6 +3605,12 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
         lockdep_set_subclass(&pool->lock, 1);   /* see put_pwq() */
         copy_workqueue_attrs(pool->attrs, attrs);
 
+        /*
+         * no_numa isn't a worker_pool attribute, always clear it.  See
+         * 'struct workqueue_attrs' comments for detail.
+         */
+        pool->attrs->no_numa = false;
+
         /* if cpumask is contained inside a NUMA node, we belong to that node */
         if (wq_numa_enabled) {
                 for_each_node(node) {
@@ -4756,7 +4789,14 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 
         INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
         schedule_work_on(cpu, &wfc.work);
-        flush_work(&wfc.work);
+
+        /*
+         * The work item is on-stack and can't lead to deadlock through
+         * flushing.  Use __flush_work() to avoid spurious lockdep warnings
+         * when work_on_cpu()s are nested.
+         */
+        __flush_work(&wfc.work);
+
         return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);