pkt_sched: Fix queue quiescence testing in dev_deactivate().

Based upon discussions with Jarek P. and Herbert Xu.

First, we're testing the wrong qdisc.  We just reset the device
queue qdiscs to &noop_qdisc and checking it's state is completely
pointless here.

We want to wait until the previous qdisc that was sitting at
the ->qdisc pointer is not busy any more.  And that would be
->qdisc_sleeping.

Because of how we propagate the samples qdisc pointer down into
qdisc_run and friends via per-cpu ->output_queue and netif_schedule,
we have to wait also for the __QDISC_STATE_SCHED bit to clear as
well.

Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7cf83b37459d0f08926baf49c07ce1ad9882b433..468574682caab154eba2d8f35b09de3f8272522e 100644 (file)
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -647,7 +647,7 @@ static void dev_deactivate_queue(struct net_device *dev,
        }
 }
 
-static bool some_qdisc_is_running(struct net_device *dev, int lock)
+static bool some_qdisc_is_busy(struct net_device *dev, int lock)
 {
        unsigned int i;
 
@@ -658,13 +658,14 @@ static bool some_qdisc_is_running(struct net_device *dev, int lock)
                int val;
 
                dev_queue = netdev_get_tx_queue(dev, i);
-               q = dev_queue->qdisc;
+               q = dev_queue->qdisc_sleeping;
                root_lock = qdisc_lock(q);
 
                if (lock)
                        spin_lock_bh(root_lock);
 
-               val = test_bit(__QDISC_STATE_RUNNING, &q->state);
+               val = (test_bit(__QDISC_STATE_RUNNING, &q->state) ||
+                      test_bit(__QDISC_STATE_SCHED, &q->state));
 
                if (lock)
                        spin_unlock_bh(root_lock);
@@ -689,14 +690,14 @@ void dev_deactivate(struct net_device *dev)
 
        /* Wait for outstanding qdisc_run calls. */
        do {
-               while (some_qdisc_is_running(dev, 0))
+               while (some_qdisc_is_busy(dev, 0))
                        yield();
 
                /*
                 * Double-check inside queue lock to ensure that all effects
                 * of the queue run are visible when we return.
                 */
-               running = some_qdisc_is_running(dev, 1);
+               running = some_qdisc_is_busy(dev, 1);
 
                /*
                 * The running flag should never be set at this point because