Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 45 insertions, 21 deletions

diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index e9a77f621c3..d51852bba01 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -298,6 +298,10 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg,
 	    new_num_classes == q->max_agg_classes - 1) /* agg no more full */
 		hlist_add_head(&agg->nonfull_next, &q->nonfull_aggs);
 
+	/* The next assignment may let
+	 * agg->initial_budget > agg->budgetmax
+	 * hold, we will take it into account in charge_actual_service().
+	 */
 	agg->budgetmax = new_num_classes * agg->lmax;
 	new_agg_weight = agg->class_weight * new_num_classes;
 	agg->inv_w = ONE_FP/new_agg_weight;
@@ -817,7 +821,7 @@ static void qfq_make_eligible(struct qfq_sched *q)
 	unsigned long old_vslot = q->oldV >> q->min_slot_shift;
 
 	if (vslot != old_vslot) {
-		unsigned long mask = (1UL << fls(vslot ^ old_vslot)) - 1;
+		unsigned long mask = (1ULL << fls(vslot ^ old_vslot)) - 1;
 		qfq_move_groups(q, mask, IR, ER);
 		qfq_move_groups(q, mask, IB, EB);
 	}
@@ -988,12 +992,23 @@ static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
 /* Update F according to the actual service received by the aggregate. */
 static inline void charge_actual_service(struct qfq_aggregate *agg)
 {
-	/* compute the service received by the aggregate */
-	u32 service_received = agg->initial_budget - agg->budget;
+	/* Compute the service received by the aggregate, taking into
+	 * account that, after decreasing the number of classes in
+	 * agg, it may happen that
+	 * agg->initial_budget - agg->budget > agg->bugdetmax
+	 */
+	u32 service_received = min(agg->budgetmax,
+				   agg->initial_budget - agg->budget);
 
 	agg->F = agg->S + (u64)service_received * agg->inv_w;
 }
 
+static inline void qfq_update_agg_ts(struct qfq_sched *q,
+				     struct qfq_aggregate *agg,
+				     enum update_reason reason);
+
+static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg);
+
 static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
@@ -1021,7 +1036,7 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 		in_serv_agg->initial_budget = in_serv_agg->budget =
 			in_serv_agg->budgetmax;
 
-		if (!list_empty(&in_serv_agg->active))
+		if (!list_empty(&in_serv_agg->active)) {
 			/*
 			 * Still active: reschedule for
 			 * service. Possible optimization: if no other
@@ -1032,8 +1047,9 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 			 * handle it, we would need to maintain an
 			 * extra num_active_aggs field.
 			*/
-			qfq_activate_agg(q, in_serv_agg, requeue);
-		else if (sch->q.qlen == 0) { /* no aggregate to serve */
+			qfq_update_agg_ts(q, in_serv_agg, requeue);
+			qfq_schedule_agg(q, in_serv_agg);
+		} else if (sch->q.qlen == 0) { /* no aggregate to serve */
 			q->in_serv_agg = NULL;
 			return NULL;
 		}
@@ -1052,7 +1068,15 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 	qdisc_bstats_update(sch, skb);
 
 	agg_dequeue(in_serv_agg, cl, len);
-	in_serv_agg->budget -= len;
+	/* If lmax is lowered, through qfq_change_class, for a class
+	 * owning pending packets with larger size than the new value
+	 * of lmax, then the following condition may hold.
+	 */
+	if (unlikely(in_serv_agg->budget < len))
+		in_serv_agg->budget = 0;
+	else
+		in_serv_agg->budget -= len;
+
 	q->V += (u64)len * IWSUM;
 	pr_debug("qfq dequeue: len %u F %lld now %lld\n",
 		 len, (unsigned long long) in_serv_agg->F,
@@ -1217,17 +1241,11 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	cl->deficit = agg->lmax;
 	list_add_tail(&cl->alist, &agg->active);
 
-	if (list_first_entry(&agg->active, struct qfq_class, alist) != cl)
-		return err; /* aggregate was not empty, nothing else to do */
+	if (list_first_entry(&agg->active, struct qfq_class, alist) != cl ||
+	    q->in_serv_agg == agg)
+		return err; /* non-empty or in service, nothing else to do */
 
-	/* recharge budget */
-	agg->initial_budget = agg->budget = agg->budgetmax;
-
-	qfq_update_agg_ts(q, agg, enqueue);
-	if (q->in_serv_agg == NULL)
-		q->in_serv_agg = agg;
-	else if (agg != q->in_serv_agg)
-		qfq_schedule_agg(q, agg);
+	qfq_activate_agg(q, agg, enqueue);
 
 	return err;
 }
@@ -1261,7 +1279,8 @@ static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
 		/* group was surely ineligible, remove */
 		__clear_bit(grp->index, &q->bitmaps[IR]);
 		__clear_bit(grp->index, &q->bitmaps[IB]);
-	} else if (!q->bitmaps[ER] && qfq_gt(roundedS, q->V))
+	} else if (!q->bitmaps[ER] && qfq_gt(roundedS, q->V) &&
+		   q->in_serv_agg == NULL)
 		q->V = roundedS;
 
 	grp->S = roundedS;
@@ -1284,8 +1303,15 @@ skip_update:
 static void qfq_activate_agg(struct qfq_sched *q, struct qfq_aggregate *agg,
 			     enum update_reason reason)
 {
+	agg->initial_budget = agg->budget = agg->budgetmax; /* recharge budg. */
+
 	qfq_update_agg_ts(q, agg, reason);
-	qfq_schedule_agg(q, agg);
+	if (q->in_serv_agg == NULL) { /* no aggr. in service or scheduled */
+		q->in_serv_agg = agg; /* start serving this aggregate */
+		 /* update V: to be in service, agg must be eligible */
+		q->oldV = q->V = agg->S;
+	} else if (agg != q->in_serv_agg)
+		qfq_schedule_agg(q, agg);
 }
 
 static void qfq_slot_remove(struct qfq_sched *q, struct qfq_group *grp,
@@ -1357,8 +1383,6 @@ static void qfq_deactivate_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
 			__set_bit(grp->index, &q->bitmaps[s]);
 		}
 	}
-
-	qfq_update_eligible(q);
 }
 
 static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg)