Merge ssh://master.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

6 files changed, 61 insertions, 111 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 9923a15a999..e0a5412b7e6 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -45,11 +45,11 @@
 #include <linux/config.h>
 #include <linux/kref.h>
 #include <linux/if_infiniband.h>
+#include <linux/mutex.h>
 
 #include <net/neighbour.h>
 
 #include <asm/atomic.h>
-#include <asm/semaphore.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
@@ -123,8 +123,8 @@ struct ipoib_dev_priv {
 
 	unsigned long flags;
 
-	struct semaphore mcast_mutex;
-	struct semaphore vlan_mutex;
+	struct mutex mcast_mutex;
+	struct mutex vlan_mutex;
 
 	struct rb_root  path_tree;
 	struct list_head path_list;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 23885801b6d..86bcdd72a10 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -52,7 +52,7 @@ MODULE_PARM_DESC(data_debug_level,
 
 #define	IPOIB_OP_RECV	(1ul << 31)
 
-static DECLARE_MUTEX(pkey_sem);
+static DEFINE_MUTEX(pkey_mutex);
 
 struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
 				 struct ib_pd *pd, struct ib_ah_attr *attr)
@@ -445,25 +445,16 @@ int ipoib_ib_dev_down(struct net_device *dev)
 
 	/* Shutdown the P_Key thread if still active */
 	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
-		down(&pkey_sem);
+		mutex_lock(&pkey_mutex);
 		set_bit(IPOIB_PKEY_STOP, &priv->flags);
 		cancel_delayed_work(&priv->pkey_task);
-		up(&pkey_sem);
+		mutex_unlock(&pkey_mutex);
 		flush_workqueue(ipoib_workqueue);
 	}
 
 	ipoib_mcast_stop_thread(dev, 1);
-
-	/*
-	 * Flush the multicast groups first so we stop any multicast joins. The
-	 * completion thread may have already died and we may deadlock waiting
-	 * for the completion thread to finish some multicast joins.
-	 */
 	ipoib_mcast_dev_flush(dev);
 
-	/* Delete broadcast and local addresses since they will be recreated */
-	ipoib_mcast_dev_down(dev);
-
 	ipoib_flush_paths(dev);
 
 	return 0;
@@ -608,13 +599,13 @@ void ipoib_ib_dev_flush(void *_dev)
 	if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
 		ipoib_ib_dev_up(dev);
 
-	down(&priv->vlan_mutex);
+	mutex_lock(&priv->vlan_mutex);
 
 	/* Flush any child interfaces too */
 	list_for_each_entry(cpriv, &priv->child_intfs, list)
 		ipoib_ib_dev_flush(&cpriv->dev);
 
-	up(&priv->vlan_mutex);
+	mutex_unlock(&priv->vlan_mutex);
 }
 
 void ipoib_ib_dev_cleanup(struct net_device *dev)
@@ -624,9 +615,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev)
 	ipoib_dbg(priv, "cleaning up ib_dev\n");
 
 	ipoib_mcast_stop_thread(dev, 1);
-
-	/* Delete the broadcast address and the local address */
-	ipoib_mcast_dev_down(dev);
+	ipoib_mcast_dev_flush(dev);
 
 	ipoib_transport_dev_cleanup(dev);
 }
@@ -662,12 +651,12 @@ void ipoib_pkey_poll(void *dev_ptr)
 	if (test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
 		ipoib_open(dev);
 	else {
-		down(&pkey_sem);
+		mutex_lock(&pkey_mutex);
 		if (!test_bit(IPOIB_PKEY_STOP, &priv->flags))
 			queue_delayed_work(ipoib_workqueue,
 					   &priv->pkey_task,
 					   HZ);
-		up(&pkey_sem);
+		mutex_unlock(&pkey_mutex);
 	}
 }
 
@@ -681,12 +670,12 @@ int ipoib_pkey_dev_delay_open(struct net_device *dev)
 
 	/* P_Key value not assigned yet - start polling */
 	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
-		down(&pkey_sem);
+		mutex_lock(&pkey_mutex);
 		clear_bit(IPOIB_PKEY_STOP, &priv->flags);
 		queue_delayed_work(ipoib_workqueue,
 				   &priv->pkey_task,
 				   HZ);
-		up(&pkey_sem);
+		mutex_unlock(&pkey_mutex);
 		return 1;
 	}
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 780009c7eaa..fd3f5c862a5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -105,7 +105,7 @@ int ipoib_open(struct net_device *dev)
 		struct ipoib_dev_priv *cpriv;
 
 		/* Bring up any child interfaces too */
-		down(&priv->vlan_mutex);
+		mutex_lock(&priv->vlan_mutex);
 		list_for_each_entry(cpriv, &priv->child_intfs, list) {
 			int flags;
 
@@ -115,7 +115,7 @@ int ipoib_open(struct net_device *dev)
 
 			dev_change_flags(cpriv->dev, flags | IFF_UP);
 		}
-		up(&priv->vlan_mutex);
+		mutex_unlock(&priv->vlan_mutex);
 	}
 
 	netif_start_queue(dev);
@@ -140,7 +140,7 @@ static int ipoib_stop(struct net_device *dev)
 		struct ipoib_dev_priv *cpriv;
 
 		/* Bring down any child interfaces too */
-		down(&priv->vlan_mutex);
+		mutex_lock(&priv->vlan_mutex);
 		list_for_each_entry(cpriv, &priv->child_intfs, list) {
 			int flags;
 
@@ -150,7 +150,7 @@ static int ipoib_stop(struct net_device *dev)
 
 			dev_change_flags(cpriv->dev, flags & ~IFF_UP);
 		}
-		up(&priv->vlan_mutex);
+		mutex_unlock(&priv->vlan_mutex);
 	}
 
 	return 0;
@@ -892,8 +892,8 @@ static void ipoib_setup(struct net_device *dev)
 	spin_lock_init(&priv->lock);
 	spin_lock_init(&priv->tx_lock);
 
-	init_MUTEX(&priv->mcast_mutex);
-	init_MUTEX(&priv->vlan_mutex);
+	mutex_init(&priv->mcast_mutex);
+	mutex_init(&priv->vlan_mutex);
 
 	INIT_LIST_HEAD(&priv->path_list);
 	INIT_LIST_HEAD(&priv->child_intfs);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index ed0c2ead8bc..98039da0caf 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -55,7 +55,7 @@ MODULE_PARM_DESC(mcast_debug_level,
 		 "Enable multicast debug tracing if > 0");
 #endif
 
-static DECLARE_MUTEX(mcast_mutex);
+static DEFINE_MUTEX(mcast_mutex);
 
 /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
 struct ipoib_mcast {
@@ -97,8 +97,6 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast)
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_neigh *neigh, *tmp;
 	unsigned long flags;
-	LIST_HEAD(ah_list);
-	struct ipoib_ah *ah, *tah;
 
 	ipoib_dbg_mcast(netdev_priv(dev),
 			"deleting multicast group " IPOIB_GID_FMT "\n",
@@ -107,8 +105,14 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast)
 	spin_lock_irqsave(&priv->lock, flags);
 
 	list_for_each_entry_safe(neigh, tmp, &mcast->neigh_list, list) {
+		/*
+		 * It's safe to call ipoib_put_ah() inside priv->lock
+		 * here, because we know that mcast->ah will always
+		 * hold one more reference, so ipoib_put_ah() will
+		 * never do more than decrement the ref count.
+		 */
 		if (neigh->ah)
-			list_add_tail(&neigh->ah->list, &ah_list);
+			ipoib_put_ah(neigh->ah);
 		*to_ipoib_neigh(neigh->neighbour) = NULL;
 		neigh->neighbour->ops->destructor = NULL;
 		kfree(neigh);
@@ -116,9 +120,6 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast)
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	list_for_each_entry_safe(ah, tah, &ah_list, list)
-		ipoib_put_ah(ah);
-
 	if (mcast->ah)
 		ipoib_put_ah(mcast->ah);
 
@@ -384,10 +385,10 @@ static void ipoib_mcast_join_complete(int status,
 
 	if (!status && !ipoib_mcast_join_finish(mcast, mcmember)) {
 		mcast->backoff = 1;
-		down(&mcast_mutex);
+		mutex_lock(&mcast_mutex);
 		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
 			queue_work(ipoib_workqueue, &priv->mcast_task);
-		up(&mcast_mutex);
+		mutex_unlock(&mcast_mutex);
 		complete(&mcast->done);
 		return;
 	}
@@ -417,7 +418,7 @@ static void ipoib_mcast_join_complete(int status,
 
 	mcast->query = NULL;
 
-	down(&mcast_mutex);
+	mutex_lock(&mcast_mutex);
 	if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) {
 		if (status == -ETIMEDOUT)
 			queue_work(ipoib_workqueue, &priv->mcast_task);
@@ -426,7 +427,7 @@ static void ipoib_mcast_join_complete(int status,
 					   mcast->backoff * HZ);
 	} else
 		complete(&mcast->done);
-	up(&mcast_mutex);
+	mutex_unlock(&mcast_mutex);
 
 	return;
 }
@@ -481,12 +482,12 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
 		if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
 			mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
 
-		down(&mcast_mutex);
+		mutex_lock(&mcast_mutex);
 		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
 			queue_delayed_work(ipoib_workqueue,
 					   &priv->mcast_task,
 					   mcast->backoff * HZ);
-		up(&mcast_mutex);
+		mutex_unlock(&mcast_mutex);
 	} else
 		mcast->query_id = ret;
 }
@@ -519,11 +520,11 @@ void ipoib_mcast_join_task(void *dev_ptr)
 		priv->broadcast = ipoib_mcast_alloc(dev, 1);
 		if (!priv->broadcast) {
 			ipoib_warn(priv, "failed to allocate broadcast group\n");
-			down(&mcast_mutex);
+			mutex_lock(&mcast_mutex);
 			if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
 				queue_delayed_work(ipoib_workqueue,
 						   &priv->mcast_task, HZ);
-			up(&mcast_mutex);
+			mutex_unlock(&mcast_mutex);
 			return;
 		}
 
@@ -579,10 +580,10 @@ int ipoib_mcast_start_thread(struct net_device *dev)
 
 	ipoib_dbg_mcast(priv, "starting multicast thread\n");
 
-	down(&mcast_mutex);
+	mutex_lock(&mcast_mutex);
 	if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags))
 		queue_work(ipoib_workqueue, &priv->mcast_task);
-	up(&mcast_mutex);
+	mutex_unlock(&mcast_mutex);
 
 	return 0;
 }
@@ -594,10 +595,10 @@ int ipoib_mcast_stop_thread(struct net_device *dev, int flush)
 
 	ipoib_dbg_mcast(priv, "stopping multicast thread\n");
 
-	down(&mcast_mutex);
+	mutex_lock(&mcast_mutex);
 	clear_bit(IPOIB_MCAST_RUN, &priv->flags);
 	cancel_delayed_work(&priv->mcast_task);
-	up(&mcast_mutex);
+	mutex_unlock(&mcast_mutex);
 
 	if (flush)
 		flush_workqueue(ipoib_workqueue);
@@ -741,48 +742,23 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	LIST_HEAD(remove_list);
-	struct ipoib_mcast *mcast, *tmcast, *nmcast;
+	struct ipoib_mcast *mcast, *tmcast;
 	unsigned long flags;
 
 	ipoib_dbg_mcast(priv, "flushing multicast list\n");
 
 	spin_lock_irqsave(&priv->lock, flags);
-	list_for_each_entry_safe(mcast, tmcast, &priv->multicast_list, list) {
-		nmcast = ipoib_mcast_alloc(dev, 0);
-		if (nmcast) {
-			nmcast->flags =
-				mcast->flags & (1 << IPOIB_MCAST_FLAG_SENDONLY);
 
-			nmcast->mcmember.mgid = mcast->mcmember.mgid;
-
-			/* Add the new group in before the to-be-destroyed group */
-			list_add_tail(&nmcast->list, &mcast->list);
-			list_del_init(&mcast->list);
-
-			rb_replace_node(&mcast->rb_node, &nmcast->rb_node,
-					&priv->multicast_tree);
-
-			list_add_tail(&mcast->list, &remove_list);
-		} else {
-			ipoib_warn(priv, "could not reallocate multicast group "
-				   IPOIB_GID_FMT "\n",
-				   IPOIB_GID_ARG(mcast->mcmember.mgid));
-		}
+	list_for_each_entry_safe(mcast, tmcast, &priv->multicast_list, list) {
+		list_del(&mcast->list);
+		rb_erase(&mcast->rb_node, &priv->multicast_tree);
+		list_add_tail(&mcast->list, &remove_list);
 	}
 
 	if (priv->broadcast) {
-		nmcast = ipoib_mcast_alloc(dev, 0);
-		if (nmcast) {
-			nmcast->mcmember.mgid = priv->broadcast->mcmember.mgid;
-
-			rb_replace_node(&priv->broadcast->rb_node,
-					&nmcast->rb_node,
-					&priv->multicast_tree);
-
-			list_add_tail(&priv->broadcast->list, &remove_list);
-		}
-
-		priv->broadcast = nmcast;
+ 		rb_erase(&priv->broadcast->rb_node, &priv->multicast_tree);
+		list_add_tail(&priv->broadcast->list, &remove_list);
+		priv->broadcast = NULL;
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
@@ -793,24 +769,6 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
 	}
 }
 
-void ipoib_mcast_dev_down(struct net_device *dev)
-{
-	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	unsigned long flags;
-
-	/* Delete broadcast since it will be recreated */
-	if (priv->broadcast) {
-		ipoib_dbg_mcast(priv, "deleting broadcast group\n");
-
-		spin_lock_irqsave(&priv->lock, flags);
-		rb_erase(&priv->broadcast->rb_node, &priv->multicast_tree);
-		spin_unlock_irqrestore(&priv->lock, flags);
-		ipoib_mcast_leave(dev, priv->broadcast);
-		ipoib_mcast_free(priv->broadcast);
-		priv->broadcast = NULL;
-	}
-}
-
 void ipoib_mcast_restart_task(void *dev_ptr)
 {
 	struct net_device *dev = dev_ptr;
@@ -824,7 +782,8 @@ void ipoib_mcast_restart_task(void *dev_ptr)
 
 	ipoib_mcast_stop_thread(dev, 0);
 
-	spin_lock_irqsave(&priv->lock, flags);
+	spin_lock_irqsave(&dev->xmit_lock, flags);
+	spin_lock(&priv->lock);
 
 	/*
 	 * Unfortunately, the networking core only gives us a list of all of
@@ -896,7 +855,9 @@ void ipoib_mcast_restart_task(void *dev_ptr)
 			list_add_tail(&mcast->list, &remove_list);
 		}
 	}
-	spin_unlock_irqrestore(&priv->lock, flags);
+
+	spin_unlock(&priv->lock);
+	spin_unlock_irqrestore(&dev->xmit_lock, flags);
 
 	/* We have to cancel outside of the spinlock */
 	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index e829e10400e..faaf10e5fc7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -65,9 +65,9 @@ int ipoib_mcast_attach(struct net_device *dev, u16 mlid, union ib_gid *mgid)
 	}
 
 	/* attach QP to multicast group */
-	down(&priv->mcast_mutex);
+	mutex_lock(&priv->mcast_mutex);
 	ret = ib_attach_mcast(priv->qp, mgid, mlid);
-	up(&priv->mcast_mutex);
+	mutex_unlock(&priv->mcast_mutex);
 	if (ret)
 		ipoib_warn(priv, "failed to attach to multicast group, ret = %d\n", ret);
 
@@ -81,9 +81,9 @@ int ipoib_mcast_detach(struct net_device *dev, u16 mlid, union ib_gid *mgid)
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret;
 
-	down(&priv->mcast_mutex);
+	mutex_lock(&priv->mcast_mutex);
 	ret = ib_detach_mcast(priv->qp, mgid, mlid);
-	up(&priv->mcast_mutex);
+	mutex_unlock(&priv->mcast_mutex);
 	if (ret)
 		ipoib_warn(priv, "ib_detach_mcast failed (result = %d)\n", ret);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index d280b341a37..4ca175553f9 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -63,7 +63,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 
 	ppriv = netdev_priv(pdev);
 
-	down(&ppriv->vlan_mutex);
+	mutex_lock(&ppriv->vlan_mutex);
 
 	/*
 	 * First ensure this isn't a duplicate. We check the parent device and
@@ -124,7 +124,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 
 	list_add_tail(&priv->list, &ppriv->child_intfs);
 
-	up(&ppriv->vlan_mutex);
+	mutex_unlock(&ppriv->vlan_mutex);
 
 	return 0;
 
@@ -139,7 +139,7 @@ device_init_failed:
 	free_netdev(priv->dev);
 
 err:
-	up(&ppriv->vlan_mutex);
+	mutex_unlock(&ppriv->vlan_mutex);
 	return result;
 }
 
@@ -153,7 +153,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 
 	ppriv = netdev_priv(pdev);
 
-	down(&ppriv->vlan_mutex);
+	mutex_lock(&ppriv->vlan_mutex);
 	list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
 		if (priv->pkey == pkey) {
 			unregister_netdev(priv->dev);
@@ -167,7 +167,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 			break;
 		}
 	}
-	up(&ppriv->vlan_mutex);
+	mutex_unlock(&ppriv->vlan_mutex);
 
 	return ret;
 }