summaryrefslogtreecommitdiff
path: root/drivers/infiniband
diff options
context:
space:
mode:
authorRoland Dreier <roland@purestorage.com>2012-12-19 09:16:43 -0800
committerRoland Dreier <roland@purestorage.com>2012-12-19 09:16:43 -0800
commitb13912bbb4a2d445c35db24586eb6ecf4707d52d (patch)
tree1cd9be4af43845b21861384e66d93e9d71f690b2 /drivers/infiniband
parent5bd665f28db2b04a8d6fe277342479906fc60b62 (diff)
IPoIB: Call skb_dst_drop() once skb is enqueued for sending
Currently, IPoIB delays collecting send completions for TX packets in order to batch work more efficiently. It does skb_orphan() right after queuing the packets so that destructors run early, to avoid problems like holding socket send buffers for too long (since we might not collect a send completion until a long time after the packet is actually sent). However, IPoIB clears IFF_XMIT_DST_RELEASE because it actually looks at skb_dst() to update the PMTU when it gets a too-long packet. This means that the packets sitting in the TX ring with uncollected send completions are holding a reference on the dst. We've seen this lead to pathological behavior with respect to route and neighbour GC. The easy fix for this is to call skb_dst_drop() when we call skb_orphan(). Also, give packets sent via connected mode (CM) the same skb_orphan() / skb_dst_drop() treatment that packets sent via datagram mode get. Signed-off-by: Roland Dreier <roland@purestorage.com>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_cm.c3
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_ib.c3
2 files changed, 5 insertions, 1 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 72ae63f0072d..03103d2bd641 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -752,6 +752,9 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
dev->trans_start = jiffies;
++tx->tx_head;
+ skb_orphan(skb);
+ skb_dst_drop(skb);
+
if (++priv->tx_outstanding == ipoib_sendq_size) {
ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n",
tx->qp->qp_num);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index f10221f40803..a1bca70e20aa 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -615,8 +615,9 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
address->last_send = priv->tx_head;
++priv->tx_head;
- skb_orphan(skb);
+ skb_orphan(skb);
+ skb_dst_drop(skb);
}
if (unlikely(priv->tx_outstanding > MAX_SEND_CQE))